Compare commits

..

37 Commits

Author SHA1 Message Date
d10d79399b fix(docker): trust bind-mounted repos via git safe.directory
The container runs as root over uid-1000-owned host repos; git's dubious-
ownership guard made every project read as not-a-repo, hiding the git diff
panel's Git tab and nulling the branch indicator. Bakes safe.directory='*'
into the runtime image. Applied live to the running container too.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-03 08:29:33 +00:00
aeb2777ad4 docs: changelog for v2.7.14-backlog-hardening + v2.7.15-git-diff-panel
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-03 03:42:40 +00:00
2c58f2b3d3 Merge epic-backlog-and-gitdiff: v2.7.14 backlog hardening + v2.7.15 git diff panel
Two plans delivered via paseo-epic in an isolated worktree, audited green:
- v2.7.14: post-review backlog (external task-cancel + finalization, tool-call
  parser prune + pino logging, BooChat stall-timeout, view_session_history MCP
  tool, retire the :9502 fallback SPA).
- v2.7.15: git diff panel (Files/Git tab in the file browser with stage/commit/
  discard, server-side argv-safe git, sessionEvent-driven refresh).
2026-06-03 03:41:12 +00:00
d8bb2dabfe feat: git diff panel (Files/Git tab in the file browser)
Adds a Git tab to the right-side file panel that shows the project
repository's diff and lets the user stage, unstage, commit, and discard
whole files in-session. Two comparison modes (Uncommitted vs HEAD, and the
branch vs its base — upstream tracking branch else default branch), auto-
selected by repo state on first open and pinned after explicit choice;
per-file expand/collapse with lazy syntax-highlighted diffs, +/- stats, and
binary/large-file placeholders. All git read and write logic lives in
apps/server via a new git_diff service: argv-safe execFile only (never a
shell), per-file paths validated repo-relative through pathGuard with a
realpath symlink-escape check, server-derived commit identity (the request
carries no author fields), and the write endpoints are deliberately absent
from the assistant tool registry. Reads are bounded (30s deadline, 10MB);
an index lock or an in-progress merge/rebase/cherry-pick/bisect surfaces as
"repository busy" and disables writes. The panel stays current via a client
git_diff_refresh session event (no new wire contract) coalesced across tab
open, mutations, turn completion, and pending-change apply. Discard is an
irrecoverable hard-delete behind a plain confirm that distinguishes
reverting a tracked file from deleting an untracked one.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-03 03:18:41 +00:00
ca028a4024 docs: add git-diff-panel implementation planning artifacts
Implementation decision log, iteration history, synthesis input, the
implementation plan, and discovery notes for the git-diff-panel feature.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 02:26:04 +00:00
3e7115afad docs: record @boocode/contracts SSOT + schema-migration learnings in CLAUDE.md
Add the packages/contracts package to the monorepo list, a consolidated
@boocode/contracts conventions bullet (subpaths, build-first, web-local strict
WsFrame union, built-dist consumption), and the `SELECT *` view / DROP COLUMN
(2BP01) schema gotcha that crash-looped boocoder.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 02:25:59 +00:00
f32fd928b3 feat: post-review backlog hardening (cancel/parser/stall/history/9502)
Five independent items from the post-review backlog. F1: Stop on an external
agent task now aborts the running child via a per-task AbortController registry
reachable from the cancel route, and finalizes the assistant message as
cancelled (fixing two latent bugs — catch blocks left the message streaming,
and warm success-paths wrote complete on an aborted turn); warm pools/worktrees
are preserved and the native path is unchanged. F2/F3: prune the tool-call
parser to its two load-bearing exports (unexport eight zero-caller symbols, add
a gate test for the <invoke>-as-text fallback) and route placeholder-rejection
logging through pino. F6: a 90s per-chunk stall-timeout wraps native inference's
fullStream via AbortSignal.any so a hung stream finalizes the message instead of
hanging — no retry (a pure classifyStreamError helper is added). F7: a read-only
view_session_history MCP tool (newest-N, chronological). F9: retire the unused
apps/coder/web :9502 fallback SPA, keeping every API/WS/health/MCP route.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-03 02:23:11 +00:00
9a139633b8 fix(coder): drop human_inbox view before dropping tasks columns
The audit-cleanup migration dropped tasks.feature_values/worktree_path, but
human_inbox is `SELECT * FROM tasks` and pins every column, so the DROP COLUMN
failed (2BP01) on any existing DB and crash-looped boocoder on boot. Drop the
view, drop the columns, then recreate it — idempotent on fresh and existing DBs.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-03 00:29:28 +00:00
2c4ff2063d fix: reconcile audit-cleanup refactor with @boocode/contracts SSOT (worktree-risk type, frame-emitter import)
worktree-risk.ts now returns the package's WorktreeRiskReport (local RiskReport interface removed); frame-emitter.ts imports WsFrame from @boocode/contracts/ws-frames (the deleted @boocode/server/ws-frames subpath).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 23:25:50 +00:00
ae3f10b19d Merge remote-tracking branch 'origin/main' 2026-06-02 21:30:28 +00:00
cc4bd04aa4 Merge contracts-ssot-pkg: v2.7.13 single-source cross-app wire contracts in @boocode/contracts 2026-06-02 21:24:14 +00:00
649ce71eff feat: single-source cross-app wire contracts in @boocode/contracts (v2.7.13)
Move all hand-synced cross-app wire contracts into one built workspace
package, @boocode/contracts, consumed by server/web/coder/coder-web via
workspace:* + a per-subpath exports map. The ws-frames and provider-config
Zod schemas are schema-first (z.infer); MessageMetadata, ErrorReason,
AgentSessionConfig, the provider snapshot types, and WorktreeRiskReport are
each single-sourced. Deletes the byte-identical copies and their parity
tests, fixes a live AgentSessionConfig drift (coder dead copy removed,
unified to the web required/nullable shape), removes the dead pending_change
WS arms in the fallback SPA, and inverts the build order (contracts builds
first) across root build, Dockerfile, and the coder deploy docs. Reverses
the shared-package decision declined in v2.5.12.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 21:24:08 +00:00
2a05d2f9fe docs: archive shipped openspec batches; add feature/plan/research notes
Move 13 shipped openspec change docs under openspec/changes/archived/.
Add docs/features/git-diff-panel, docs/plans/post-review-backlog, and
docs/research/cross-app-contract-ssot.md (the research behind the
@boocode/contracts SSOT work). Update BOOCHAT.md, BOOCODER.md, and
boocode_roadmap.md.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 21:20:33 +00:00
8c200216eb refactor: codebase audit cleanup — dead code, dedup, module splits
Multi-agent audit + aggressive cleanup across server/web/coder/booterm,
delivered behind a DEFER discipline so none of the in-flight files were
touched. Removes dead code/deps/columns, dedups server + coder helpers,
and splits the oversized modules (tools.ts, opencode-server.ts,
sentinel-summaries, turn.ts, TerminalPane.tsx) behind stable contracts.
Adds 78 parity/unit tests (server 587, coder 323); fixes two latent bugs
(ChatPane queue keys, FileViewerOverlay blank-line parity).

Intended tag: v2.7.12-audit-cleanup.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 21:12:29 +00:00
e5ce01ae72 fix(coder): include model in WS snapshot SELECT so the attribution chip survives refresh
CoderPane hydrates from the HTTP listMessages fetch (SELECT has model) AND the WS snapshot frame, and the snapshot handler setMessages-overwrites the HTTP load. The snapshot query in apps/coder/src/routes/ws.ts had its own column list that omitted model, so on coder refresh the chip's model was lost (it showed live via the message_complete frame). One-column fix: add model to that SELECT. CLAUDE.md mapper-chain note updated to list the WS snapshot SELECT.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 18:03:10 +00:00
81470f5a77 Merge composer-chips: v2.7.10 composer attach-file button + slash-commands chip (icon-only on mobile)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 17:27:59 +00:00
35dba828e1 feat: composer attach-file button + slash-commands chip (icon-only on mobile)
Move the slash-commands menu out of the full-width AgentCommandsHint disclosure into a compact chip in the composer's bottom controls row, and add an attach-file button that reuses the existing drag-drop pipeline (5MB/binary gate, 10-attachment cap, chips + preview). On mobile both collapse to icon-only (count hidden). Shared ChatInput, so it applies to both BooChat and BooCoder; typed-/ autocomplete is unchanged. Removes the now-unused AgentCommandsHint component.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 17:26:27 +00:00
ce621bc003 Merge mcp-env-keys-batch: v2.7.9 MCP {env:VAR} key substitution + coder model/tool-result fixes + docs refactor 2026-06-02 17:01:11 +00:00
afaca9e426 feat: MCP {env:VAR} key substitution + coder model/tool-result fixes + docs refactor (v2.7.9)
- MCP secrets: substituteEnvVars recursively resolves {env:NAME} in mcp.json string values from process.env before Zod (opencode-compatible); unset -> '' + boot warning, and invalid-config log names the unset vars (an empty {env:VAR} in a strict url/command field invalidates the whole config)
- data/mcp.json now untracked (.gitignore flips !data/mcp.json -> !data/mcp.example.json); tracked template data/mcp.example.json carries "{env:CONTEXT7_API_KEY}"; .env.example documents the key (9 mcp-config tests)
- Coder fix: message_complete frame model widened string -> string|null (server+web ws-frames parity); dispatcher publishes model: task.model at all 4 external completion points — a null model otherwise fail-closed in publishFrame and dropped the whole frame incl. status:'complete' (regression test)
- Coder fix: claude-sdk mapUserToolResults maps user-message tool_result blocks -> terminal tool_update events (completed/failed w/ output) so tool snapshots resolve instead of spinning forever
- Composer: AgentComposerBar drops §9b resumed/history/new chip + token readout, loses flex-wrap so the row stays one line; CoderPane gains a per-chat localStorage agent-config cache (restores last model on reopen) + threads model into the timeline/chip
- Docs: root CLAUDE.md slimmed (~190 lines), per-app refs split to apps/{coder,server,web}/CLAUDE.md; new docs/coder-backends.md, docs/project-discovery.md, docs/coding-standards/ (cross-app-contract-parity); ARCHITECTURE.md links the backends doc

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-02 17:01:03 +00:00
7ca4a6b344 chore: prune unused brand PNGs (keep banner-mascot + banner-wordmark)
Removes boo-badge / boocode-icon / boocode-wordmark / boocode-wordmark-tight —
copied from the design bundle but unreferenced; only the two banner badges are
imported (ProjectSidebar).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 23:10:12 +00:00
27f3a6c463 Merge boocode-ui-ember-coder-model: v2.7.8 Ember theme + brand banner + coder tabs + model-attribution chips 2026-06-01 22:30:58 +00:00
3a646fd6df feat: BooCode 2.0 UI — Ember theme, brand banner, coder tabs, model-attribution chips
- Ember theme (Obsidian charcoal + #ff7a18 orange), now DEFAULT_THEME_ID; server theme_id whitelist gains 'ember'
- Brand banner: transparent Westie mascot + >_BooCode wordmark, big/edge-to-edge (flood-filled to transparency + cropped)
- Coder panes are multi-tab: + opens a BooCode tab, split opens a pane (shared ChatTabBar via tabKind + createCoderTab; closeOtherTabs/tab-numbering extended to coder)
- Model-attribution: new messages.model column stamped at finalizeCompletion (BooChat/native coder) + dispatcher assistant-row creation (external coder); surfaced via view + wire types + live frame; rendered as a subtle shortened-name chip (shortenModelName)
- Composer Web toggle moved into a boxed focus-ringed input; glowing accent dot on tool rows
- Claude SDK follow-ups (1M context, follow-up-message fix, collapsed thinking/tool chips) + CLAUDE_SDK_BACKEND=1

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 22:30:47 +00:00
7098014261 Merge pane-header-shared: v2.7.7 shared pane-header cluster + chat-resolve WorkspaceState fix 2026-06-01 14:29:00 +00:00
c56d169ef9 feat: shared PaneHeaderActions + chat-resolve WorkspaceState fix (v2.7.7)
In-flight workspace UX work.

- Extract a shared PaneHeaderActions cluster (+/Split/Reopen/History/Close)
  used by ChatTabBar + the Workspace coder/terminal pane headers, replacing the
  divergent per-header copies; SessionLandingPage history + useWorkspacePanes
  tweaks.
- Fix coder-side correctness bug: resolveChatId read sessions.workspace_panes as
  a bare WorkspacePane[] but v2.6.5 widened it to a WorkspaceState envelope, so
  it mis-read panes and clobbered tabNumbers/nextTabNumber/closedPaneStack on
  every pane-chat write. New normalizeWorkspaceState handles either shape and
  preserves the envelope (+ regression test).
- CLAUDE.md doc-sync (coder vitest suite, deploy-by-surface, dual-remote push,
  in-flight-web-WIP staging, release-branch naming).

Web tsc + coder build + coder tests green. Builds on v2.7.6.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 14:28:49 +00:00
b7fb254e5d Merge agent-status-dot: v2.7.6 normalized external-agent status (scoped #10) 2026-06-01 14:04:26 +00:00
59cf082e06 feat: normalized external-agent status (#10 scoped) (v2.7.6)
Scoped half of boocode_code_review_v2 §1 #10 — publish the agent status
BooCoder already observes (the config-injection notify-hook is the documented
follow-on, clean-room from superset ELv2).

- agent_status_updated WS frame (working|blocked|idle|error), server+web parity.
- Published from the dispatcher's turn boundaries (warm-acp/opencode/sdk/pty:
  working at start, idle/error at end) + the permission flow (blocked/working).
  Best-effort, never breaks a turn.
- Clean-room normalizeAgentEvent helper (superset's vendor-event -> Start/blocked
  /Stop collapse, event names as facts) + 25 tests — reused by the follow-on.
- AgentComposerBar status dot (distinct from the WS-liveness dot), tracked per
  (chat,agent) by a useAgentStatus map in CoderPane.

Built by 2 parallel agents vs a pinned frame contract. Server 545 + coder 294
tests passing (25 new); web tsc + builds clean; ws-frames parity green. Clears
the actionable review backlog (#1/#3/#4/#6-#12). Builds on v2.7.5.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 14:04:04 +00:00
6fc3175730 Merge claude-sdk-backend: v2.7.5 Claude SDK backend + clean-room PostgresSessionStore 2026-06-01 13:38:05 +00:00
f3a0197d6a feat: Claude Agent SDK backend + clean-room PostgresSessionStore (v2.7.5)
Lands the lean-SDK direction (boocode_code_review_v2 §1 #9) behind a flag.
Adds @anthropic-ai/claude-agent-sdk@0.3.159 (Commercial Terms, runtime dep).

- PostgresSessionStore: clean-room impl of the SDK's real SessionStore type
  over a new claude_session_entries table. Typechecks against the SDK type;
  8 DB-integration tests.
- ClaudeSdkBackend (implements AgentBackend): one warm query() per (chat,claude)
  in streaming-input mode via a pushable async-iterable pump, sessionStore +
  resume continuity, pure mapSdkMessage->AgentEvent, session_id from init,
  usage/cost onto agent_sessions (backend CHECK gains 'claude_sdk').
- Routing env-gated by CLAUDE_SDK_BACKEND (default off) -> PTY path UNCHANGED.
- Built against real SDK 0.3.159 types (install paid off: partial=stream_event
  needing includePartialMessages, MessageParam, result error arm).
- Fix latent test-infra deadlock: serialize DB suites (fileParallelism:false).

Coder 269 passing default / 290 with DB; tsc clean vs SDK types; builds clean.
LIVE pump + resume + actual claude turn need a host smoke (CLAUDE_SDK_BACKEND=1
+ claude binary + auth). zod peer-dep wants ^4 (workspace 3.25). Builds on v2.7.4.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 13:37:57 +00:00
7e0ecde83d Merge mistake-tracker-ledger: v2.7.4 heterogeneous-failure recovery + file-read ledger 2026-06-01 13:05:19 +00:00
bcc89d8adc feat: MistakeTracker + file-provenance ledger (v2.7.4)
Two native-inference hardening features from boocode_code_review_v2 §1 #12.

MistakeTracker: new pure mistake-tracker.ts tracks consecutive heterogeneous
tool failures (kinds surfaced per tool from tool-phase.ts). On 3 in a row the
turn loop soft-nudges (model-facing recovery guidance + mistake_recovery
sentinel + reset), then escalates to stopping the turn (cap-hit-style, Continue
affordance) on a re-trip. Complements doom-loop (identical repeats) + cap-hit.

File-provenance ledger: compaction.ts derives a deterministic ## Files Read list
from the head messages' read-tool calls and injects it into the rolling-summary
prompt so provenance survives compaction (no new table; read-only).

mistake_recovery sentinel: MessageMetadata arm (server + web) + MessageBubble
render branch. Built by 2 parallel agents. Server 545 tests passing (23 new);
build + web tsc clean. Native-inference only. Builds on v2.7.3.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 13:05:03 +00:00
f53d6a8afd Merge sampling-knobs-streamjson: v2.7.3 sampling knobs + live PTY stream-json + token UI 2026-06-01 12:47:31 +00:00
a584dd16b0 feat: sampling knobs + live PTY stream-json + token UI (v2.7.3)
Three small wins from boocode_code_review_v2 §1 #11/#7/#8.

#11 sampling knobs: top_n_sigma + dry_* family as first-class Agent fields,
threaded into the request body via providerOptions.openaiCompatible. Fixes a
latent bug — top_k (rejected by the AI-SDK provider) and min_p (never passed to
streamText) were dead on the wire; both now route through the same channel.
--reasoning-budget documented in data/AGENTS.md.

#7 live PTY stream-json: new stream-json-parser.ts line-buffers qwen/claude
NDJSON and emits text/reasoning/tool frames live + persists, with a fallback to
the old opaque slice. claude gets --output-format stream-json --verbose.

#8 token UI: agent_sessions input/output_tokens/cost now flow through the route
+ type and render beside the AgentComposerBar session chip.

Built by 3 parallel agents. Server 523 + coder 245 tests passing; builds + web
tsc clean. Builds on v2.7.2. openspec sampling-streamjson-tokens.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 12:47:17 +00:00
5651f56039 Merge checkpoint-idor-fix: v2.7.2 close 2 checkpoint IDOR holes 2026-06-01 12:16:08 +00:00
9c7d80e2d8 fix(security): scope checkpoint routes to session — close 2 IDORs (v2.7.2)
Flagged by the automated push security review on v2.7.1.

- GET /checkpoints?chat_id= : the chat_id branch filtered by chat_id alone
  (any session's chat_id read its checkpoints). Now joins chats and gates on
  chats.session_id.
- restoreCheckpoint scope guard was fail-open: `cp.session_id && cp.session_id
  !== sessionId` fell through on a null denormalized session_id, allowing a
  cross-session restore (worktree reset + transcript trim). Now resolves the
  owning session via the checkpoint's chat and denies on missing/mismatch.
- Adds a DB-integration regression for the null-session_id cross-session case.

Both scope authoritatively through chats.session_id (checkpoints.session_id is
a nullable hint). Coder suite 234 passing; 7/7 checkpoint tests (incl. the
regression) against live postgres+git; typecheck clean. Hotfix on v2.7.1.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 12:15:54 +00:00
a41a02a62b Merge fuzzy-checkpoints: v2.7.1 write/edit robustness (fuzzy applier + worktree checkpoints) 2026-06-01 12:02:06 +00:00
59f07e8cb8 feat: write/edit robustness — fuzzy patch applier + worktree checkpoints (v2.7.1)
#3 Fuzzy patch applier: new pure fuzzy-match.ts (locateMatch, exact→trim→
unicode-canon→Levenshtein≥0.66, refuse-on-ambiguous) wired into pending_changes
applyOne/rewindOne so local-model whitespace/unicode drift in old_string no
longer loses the edit.

#4 Worktree checkpoint + conversation-trim: checkpoints table + checkpoints.ts
(shadow-commit of tracked+untracked into refs/boocode/checkpoints, hooked into
the 3 external-agent dispatcher paths) + POST restore route (reset --hard +
clean -fd -> transcript trim -> backend-session reset) + "Restore to here" UI.

Built by 3 parallel agents; DB-integration testing caught a created_at
self-deletion bug. Coder suite 234 passing; server+coder build + web tsc clean.
Builds on v2.7.0-mit. openspec write-edit-robustness.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-01 12:01:57 +00:00
1108d07fb2 Merge relicense-agpl-to-mit: v2.7.0 AGPL-3.0 → MIT relicense 2026-06-01 08:16:25 +00:00
303 changed files with 21003 additions and 9599 deletions

View File

@@ -11,6 +11,10 @@ POSTGRES_PASSWORD=CHANGE_ME
# point BooCode at a different SearXNG instance.
SEARXNG_URL=http://100.114.205.53:8888
# Context7 MCP key. Referenced from data/mcp.json as "{env:CONTEXT7_API_KEY}"
# ({env:VAR} substitution, opencode-compatible). Leave unset to send no key.
# CONTEXT7_API_KEY=ctx7sk-...
# Task model: lightweight model for auto-naming, search rewrite, etc.
# Direct llama-server instance (NOT llama-swap). Falls back to LLAMA_SWAP_URL
# with FAST_MODEL when unset.

2
.gitignore vendored
View File

@@ -15,6 +15,6 @@ secrets/
data/*
!data/AGENTS.md
!data/skills/
!data/mcp.json
!data/mcp.example.json
!data/coder-providers.example.json
codecontext/fork.tar.gz

View File

@@ -28,6 +28,11 @@
- Prefer codecontext (`search_symbols`, `get_symbol_info`, `get_dependencies`) over `grep` for symbol-level questions. Fall back to `grep` / `view_file` when codecontext returns degraded or empty results — that signals an unsupported language or parse failure.
- Verify before reporting work complete: run the relevant test/build/smoke command and confirm output matches the claim. Evidence first, assertion second.
## Recovery and context (v2.7)
- **Heed the recovery nudge.** Native inference tracks consecutive tool **failures** (`mistake-tracker.ts`): after 3 in a row with no successful step between, a `mistake_recovery` sentinel is injected telling you to re-read tool schemas, verify a path exists before acting, and try a *different* approach — not retry variations of the same failing call. Ignoring it (a second failure run with the nudge still outstanding) **escalates and stops the turn** to protect the step budget. This complements the doom-loop guard, which only catches *identical* repeats.
- **Files-read provenance survives compaction.** Paths you read via `view_file` / `grep` / `find_files` / `list_dir` are accumulated and merged into a cumulative `## Files Read` ledger in the rolling summary, so a file read long ago stays in context across compactions. You don't manage this — but it means you usually don't need to re-read a file just because the raw turn scrolled out of the window.
## Output format
- Stay in Markdown by default for every reply, short or long.

View File

@@ -23,6 +23,8 @@ You are BooCoder, a write-capable coding agent. You can read AND modify files wi
Every file modification queues in `pending_changes` before touching disk. The user sees a diff preview and approves/rejects each change. Never bypass this queue — it is the safety boundary between inference and the filesystem.
`edit_file`'s `old_string` match is **fuzzy** (`fuzzy-match.ts`, v2.7.1): an exact → per-line-whitespace → unicode-canonicalization (curly quotes/dashes/nbsp) → Levenshtein-≥0.66 ladder, so minor whitespace/indentation/unicode drift in `old_string` still lands on the right span. Two consequences: a near-miss `old_string` may still apply (verify the queued diff is what you intended), and an `old_string` matching **more than one** place is rejected as **ambiguous** rather than editing the first — add surrounding context to disambiguate. A genuine non-match returns a clear failure, not a thrown error.
## Behavior
- Show diffs clearly. Explain what you're changing and why.
@@ -102,7 +104,7 @@ Either way, **adding to config does NOT install the binary.** Until the CLI is o
### Deploy + smoke
Two deploy targets:
- **Routes (host service):** `pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`
- **Routes (host service):** `pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`
- **Web UI (container):** `docker compose up --build -d boocode`
Green gate (verified across phases 15): `pnpm -C apps/coder test` (134 passing) `&& pnpm -C apps/coder build`.
@@ -115,3 +117,35 @@ curl http://100.114.205.53:9500/api/coder/providers/config # raw config, throu
# Settings → Providers: disable goose → it leaves the composer picker, stays in the tab
# POST refresh → models repopulate; Add a catalog entry → it appears after refresh (unavailable until its CLI is installed)
```
## Persistent agent sessions (v2.6)
When you `dispatch_external_agent` to a chat-tab provider, BooCoder keeps that agent **warm and resumable** instead of spawning a fresh process per turn. This is mostly transparent — but the model below explains why turn 2 is fast, why an external agent remembers earlier turns, and how edits flow.
### Backends and keying
- One live backend per **`(chat_id, agent)`** pair, owned by the `agent-pool` (`agent-pool.ts`). State lives in `agent_sessions` (the resumable session id) and `worktrees` (the per-chat working copy).
- **opencode** runs a long-lived `opencode serve` (`backends/opencode-server.ts`) with per-session SSE; turns after the first reuse the same session (memory intact, ~9× faster).
- **goose / qwen** run a warm ACP connection (`backends/warm-acp.ts`) — `initialize` + `session/new` once per `(chat,agent)`, then `session/prompt` per turn. Interrupt cancels the prompt (`session/cancel`), never the child.
- **claude** runs the Claude Agent SDK backend (`backends/claude-sdk.ts`) over a clean-room Postgres session store.
- Arena, MCP `new_task`, and one-shot dispatches still use the cold `runExternalAgent` path — warm reuse needs both a `session_id` and a `chat_id`.
### Worktrees
- External agents write **directly into a persistent per-chat worktree** (`/tmp/booworktrees/sess-<id>`), not into the project root via `pending_changes`. The worktree is created once, base commit captured, and **reused across turns and across agents in the same chat** — so opencode and goose in one chat share one worktree.
- Each turn's worktree diff supersedes the prior `pending_changes` row for that `(chat,agent)` (latest-wins) and is badged with the authoring agent in the DiffPanel.
- **Staging boundary:** a provider only sees another agent's edits once they are **applied**. Unapplied worktree edits from a different agent are invisible to you — the DiffPanel shows a muted hint when that's the case.
### Lifecycle (v2.6.10v2.6.11)
- **Idle eviction:** a backend idle past `AGENT_POOL_IDLE_TTL_MS` (default 30 min) is disposed; an LRU cap of `AGENT_POOL_MAX_LIVE` (default 10) bounds live backends. A busy backend is never evicted, and the next turn transparently re-attaches or re-creates from `agent_sessions`/`worktrees`.
- **Crash recovery:** a health monitor restarts a crashed server (opencode → fresh sessions; ACP → re-`session/new`) and reclaims its port.
- **Close cleanup:** closing/deleting a chat or session evicts its backends, archives the `worktrees` row, and removes the worktree. An hourly reaper sweeps orphaned worktrees (dirty/unpushed preflight before removal).
### Checkpoints (v2.7.1)
Because external agents write the worktree directly (outside `pending_changes`), a worktree **checkpoint** is shadow-committed before each external-agent turn (tracked + untracked, into `refs/boocode/checkpoints/<id>`), anchored to that turn's assistant message. The per-message **"Restore to here"** affordance resets the worktree (`reset --hard` + `clean -fd`), trims the transcript past that message, and resets the `(chat,agent)` backend session — so files, transcript, and agent context land consistent at the restore point. `rewind` still only reverses BooCoder's own applied `pending_changes`; checkpoints are what cover external-agent worktree edits.
### Normalized status (v2.6 / v2.7.6)
Turn boundaries publish a normalized per-`(chat,agent)` status — `working | blocked | idle | error` — to the UI (`agent_status_updated` frame), so blocked-on-permission and crash/idle are visible, not just WS liveness.

View File

@@ -2,6 +2,70 @@
All notable changes per release tag. Most recent on top, ordered by tag creation date (which matches the git history). Tag names follow `vMAJOR.MINOR.PATCH-slug` — the slug describes what shipped, so the tag name alone is enough to recall the batch.
## v2.7.16-container-git-safedir — 2026-06-03
Hotfix that makes the `v2.7.15-git-diff-panel` work in production. The `boocode` container runs as root but bind-mounts host project repos owned by uid 1000, so git rejected them with "detected dubious ownership" and the diff route reported every project as not-a-repo — which hid the Git tab entirely (and had been silently nulling the existing branch indicator too). Adds `git config --system --add safe.directory '*'` to the Dockerfile runtime stage so the container's git trusts the mounted repos; applied live to the running container and baked into the image for future rebuilds. Surfaced by a live smoke immediately after the v2.7.14/v2.7.15 deploy.
## v2.7.15-git-diff-panel — 2026-06-03
A Files / Git tab in the right-side file panel (the file-browser sidebar) that shows the project repository's git diff and lets the user stage, unstage, commit, and discard whole files in-session — modeled on Paseo's diff view, scoped and planned through the `plan-a-feature``plan-implementation` skills, then built and audited via `paseo-epic` in an isolated worktree. Two comparison modes (Uncommitted vs HEAD, and the current branch vs its base — the upstream tracking branch else `origin/HEAD`), auto-selected by repo dirty-state on first open and pinned after an explicit choice; per-file expand/collapse with lazy Shiki `lang:'diff'` highlighting, +/- stats, and binary/too-large placeholders. All git read and write logic lives in `apps/server` (new `git_diff.ts` + routes on `projects.ts`) — the read-only-server posture governs the assistant's tools, not the user's own actions, and the container already mounts `/opt` read-write while `project_bootstrap` already commits via `execFile`. Every write uses the safe `execFile` argv pattern (never a shell string) with `--` operand separators, per-file `pathGuard` + realpath symlink-escape validation, server-derived `-c` commit identity (the request body is `.strict()` and carries no author fields), and the write endpoints are deliberately absent from the assistant tool registry. Reads are bounded (30s deadline, 10MB); an index lock or an in-progress merge/rebase/cherry-pick/bisect surfaces as "repository busy" and disables writes. The panel stays current via a client `git_diff_refresh` sessionEvent (no new wire contract) coalesced across tab-open, mutations, turn completion, and pending-change apply; discard is an irrecoverable hard-delete behind a plain confirm distinguishing a tracked revert from an untracked delete. New `git_diff` pure-helper + temp-repo integration tests (59 cases); server 630 tests green, web tsc clean. Pairs with `v2.7.14-backlog-hardening` (shipped together).
## v2.7.14-backlog-hardening — 2026-06-03
Five independent items from the second external-code-review backlog (`boocode_code_review_v2.md`), each built and audited as its own phase via `paseo-epic`. **External task-cancel** now actually works: Stop on an opencode/goose/qwen/claude task aborts the running child via a per-task `AbortController` registry reachable from the cancel route and finalizes the assistant message as `cancelled` — fixing two latent bugs (catch blocks left the message `streaming`; warm success-paths wrote `complete` on an aborted turn); warm pools/worktrees are preserved (abort the prompt only, never the pooled process) and the native boocode path is unchanged. **Parser prune**: the tool-call parser drops to its two load-bearing exports (eight zero-caller symbols unexported, a gate test added for the `<invoke>`-as-text fallback) with no live-path behavior change, and placeholder-rejection logging moves to pino. **BooChat stall-timeout**: a 90s per-chunk deadline wraps native inference's `fullStream` via `AbortSignal.any` so a hung local stream finalizes the message instead of hanging — no retry, since re-running re-emits already-streamed deltas (a pure `classifyStreamError` helper is added). **view_session_history**: a read-only MCP tool returning the newest-N transcript (role≠system) in chronological order. **Retire :9502**: the unused `apps/coder/web` fallback SPA is removed (package, static-serve block, build step, Dockerfile copy, `@fastify/static`), keeping every API/WS/health/MCP route. F1 added an optional `status` field to the shared `message_complete` contracts frame (so a deploy rebuilds `@boocode/contracts` first, as the sequence already does). Server 630 / coder 360 tests green.
## v2.7.13-contracts-ssot — 2026-06-02
Creates `@boocode/contracts` (`packages/contracts`), a new workspace package that becomes the single source of truth for every cross-app wire contract — reversing the decision recorded in `v2.5.12-provider-lifecycle-phase4` that declined a shared types package as not worth the Docker/build-order risk at solo scale; a live `AgentSessionConfig` drift that had since appeared between `apps/coder` and `apps/web` justified the investment. Six contracts are now defined exactly once: the `WsFrameSchema` Zod runtime schema, the provider snapshot types (`ProviderSnapshotEntry` and family), the Zod provider-config schemas, `MessageMetadata` + `ErrorReason`, `AgentSessionConfig`, and `WorktreeRiskReport`; both Zod-backed contracts use `z.infer` so validator and type derive from the same definition and cannot drift independently. All four consumers — `apps/server`, `apps/web`, `apps/coder`, and the fallback SPA `apps/coder/web` — import via `workspace:*` through a per-subpath exports map consuming built dist only (no tsconfig project references); the hand-synced copies and their parity tests (`provider-types-parity.test.ts`; the ws-frames byte-parity assertion) are deleted while the KNOWN_FRAME_TYPES drift test and broker fail-closed tests are preserved. Build order is inverted in the root build script, Dockerfile, and coder deploy docs; `apps/coder/web`'s migration also removed dead `pending_change_*` reducer arms (no frame publisher exists for these — pending changes are HTTP-delivered), closing a latent missing-default-arm crash, and reconciled field-type conflicts with the canonical `WsFrame`; zod is pinned to a single version across the workspace. Server 543 / coder 293 / contracts 11 tests passing; human smoke verified on the live stack 2026-06-02.
## v2.7.12-audit-cleanup — 2026-06-02
A repo-wide audit and aggressive cleanup pass, run as a multi-agent orchestration (five read-only Opus auditors over server/web/coder/booterm + cross-cutting deps/build/parity + a structural-architecture lens) followed by phased, behavior-preserving implementation — every change gated on the per-app test suites and delivered behind a strict DEFER discipline that never touched the files in flight for `v2.7.9``v2.7.11` (`mcp-config`, the `ws-frames` pair, `dispatcher`, `claude-sdk-map`, `AgentComposerBar`/`CoderMessageList`/`CoderPane`), so the branch rebased onto current main with zero conflicts. **Dead code/deps/schema**: removed ~9 dead files and a swathe of dead exports/write-only state across all four apps, dropped dead deps (`next-themes`, `@xterm/addon-webgl`, booterm `tslib`; `shadcn`→devDep), and idempotently dropped dead schema columns/tables (`sessions.tags`, `tasks.worktree_path`/`feature_values`, `available_agents.supports_mcp_client`, the superseded `session_worktrees` table, the always-empty `list_worktrees` MCP tool) — chat/session/message DATA untouched, only never-read columns. **Server dedup + reshapes**: collapsed the dead `budget.ts` tier system (surfacing a latent `READ_ONLY_TOOL_NAMES` drift, then deleted), extracted shared `MESSAGE_COLUMNS`/`selectProject`/`stripQuotes`/`SENTINEL_KINDS`/`samplerOptsFromAgent`/`createContentFlusher`/`insertSentinel`/a `makeCodecontextTool` factory/a pending-tool-call resolver, split `tools.ts` (799→46 barrel + `tools/{types,fs-tools,misc-tools,registry,tiers}`, register-through registry preserved so coder's import contract stays byte-stable), and decomposed the inference pipeline (`sentinel-summaries``runWrapUpSummary`, `turn.ts``turn-config`+`step-decision`, a pure `stream-phase-adapter`, shared finalize atoms — stopping short of fusing synthesis to preserve frame timing). **Coder reshapes**: split the 1062-line `opencode-server.ts` god-class into supervisor / sse-loop / pure event-map / port-utils + extracted `buildAcpClient`/`makeFrameEmitter`/`worktree-risk`, plus happy-path-safe concurrency hardening (reconnect backoff, double-spawn guard; a defensive busy-assert + ensureSession coalescing flagged for review). **Web**: `React.memo` on `MessageBubble`/`MarkdownRenderer` + module-hoisted markdown components (the streaming re-parse was the biggest perf cost), shared `linkifyPaths`/artifact/tab dedup, two latent bug fixes (`ChatPane` index-keys → stable ids; `FileViewerOverlay` blank-line line-number desync), and decomposed the 1298-line `TerminalPane.tsx` into fit/socket/selection hooks + presentational pieces (verbatim move, all ~30 listeners/timers inventoried; the label-dep fix stops a live terminal tearing down on pane renumber). +78 parity/unit tests (server 597, coder 328 green; `apps/web` has no harness, so its changes are typecheck + manual/device QA). Net ≈ 4,600 LOC. Deferred (designed; blueprints in the audit reports): the `tasks` dual-CREATE / `project_id` FK (a cross-service deploy-ordering decision, not a data migration), web structural decomposition of `useWorkspacePanes`/`MessageBubble` (needs a web test harness first), a `@boocode/contracts` shared package, and the `dispatcher.ts` split — the last two now unblocked since their in-flight files shipped in `v2.7.9``v2.7.11`. Rebased clean onto `v2.7.11-coder-model-snapshot`.
## v2.7.11-coder-model-snapshot — 2026-06-02
Hotfix for the coder model-attribution chip vanishing on refresh. The chip showed during a live turn (the `message_complete` frame carries `model`) but disappeared when a BooCoder session was reloaded — only in the coder, not BooChat. Root cause: `CoderPane`'s `useCoderMessages` hydrates from two sources on load — the HTTP `listMessages` fetch (whose SELECT includes `model`, added `v2.7.8`) AND the WS `snapshot` frame — and the WS snapshot's query in `apps/coder/src/routes/ws.ts` had its own column list that omitted `model`. The client's `snapshot` handler `setMessages`-overwrites the HTTP load, so the model-less rows won, and with no later `message_complete` for historical messages the chip stayed gone. Fix is one column: add `model` to the WS snapshot SELECT so both hydration paths agree. The `apps/coder/CLAUDE.md` "update every mapper" note now lists the WS snapshot SELECT explicitly (it was the one place not enumerated). apps/server + apps/coder builds green; deployed via `systemctl restart boocoder` (host service — the earlier `v2.7.10` docker deploy rebuilt only the container, never this route). Fixes the chip shipped in `v2.7.8-ember-coder-tabs-model-chips` / completed in `v2.7.9-mcp-keys-docs-coder-fixes`.
## v2.7.10-composer-chips — 2026-06-02
A composer control-row refresh shared by BooChat and BooCoder via `ChatInput`. The slash-commands menu moves out of the full-width `AgentCommandsHint` disclosure (now removed) into a compact chip in the message box's bottom controls row — clicking it opens the existing `SlashCommandPicker` anchored to the chip and selecting inserts `/<name> `, while the typed-`/` autocomplete is unchanged. A new attach-file button sits beside it, opening a native multi-file picker that funnels picks through the same drag-drop pipeline (5 MB / binary gate, 10-attachment cap, chips + preview, `source:'drop'`). On mobile both collapse to icon-only — the slash count is `max-md:hidden` and the paperclip is icon-only — so the row stays on one line per the no-scroll toolbar rule. Web tsc + build green; deployed (docker). Builds on the BooCode 2.0 composer work in `v2.7.8-ember-coder-tabs-model-chips`.
## v2.7.9-mcp-keys-docs-coder-fixes — 2026-06-02
The MCP-key hygiene feature plus accumulated in-flight coder fixes and a docs refactor. **MCP `{env:VAR}` substitution** (`mcp-config.ts:substituteEnvVars`, opencode-compatible) recursively resolves `{env:NAME}` references in any string value of `data/mcp.json` from `process.env` *before* Zod validation, so real keys live in `.env` (`env_file`) instead of the gitignored config — an unset var resolves to `''` with a boot-log warning, and on a validation failure the loader names the unset vars alongside the field errors (an empty `{env:VAR}` in a strict url/command field invalidates the whole config, an otherwise-disconnected warning). `data/mcp.json` is now untracked (`.gitignore` flips `!data/mcp.json``!data/mcp.example.json`); the tracked template `data/mcp.example.json` carries `"CONTEXT7_API_KEY": "{env:CONTEXT7_API_KEY}"` and `.env.example` documents the key (9 mcp-config tests). **Two coder bug fixes** ride along: the `message_complete` frame's `model` is widened `string``string | null` in both ws-frames copies (server + web parity) and the dispatcher now publishes `model: task.model` at all four external assistant-completion points — without the nullable widen a null model would fail-closed in `publishFrame` and drop the entire frame including the `status:'complete'` transition (regression test added); and Claude-SDK `mapUserToolResults` now maps `user`-message `tool_result` blocks → terminal `tool_update` events (completed/failed with output) so external-agent tool snapshots resolve instead of spinning forever (the SDK feeds tool output back as a user message, previously unmapped). On the view side the `AgentComposerBar` drops the §9b resumed/history/new-session chip and token-usage readout and loses `flex-wrap` so the control row stays on one line, while `CoderPane` gains a per-chat `localStorage` agent-config cache (provider/model/mode/thinking keyed by chat id, restoring the last model on reopen) and threads the new `model` field into the timeline + attribution chip. **Docs refactor**: the root `CLAUDE.md` is slimmed (~190 lines) with per-app deep references split into `apps/{coder,server,web}/CLAUDE.md` (auto-loaded in-subtree), plus a new 372-line `docs/coder-backends.md` dispatch reference, a `docs/project-discovery.md` stack inventory, and a `docs/coding-standards/` set (the `cross-app-contract-parity` standard, fronted by `.claude/rules` path-scoped indexes) — `ARCHITECTURE.md` links the backends doc. Server 555 + coder 299 tests passing (incl. new mcp-config, ws-frames, and claude-sdk-map suites), web tsc + server + coder builds green. Builds on `v2.7.8-ember-coder-tabs-model-chips`.
## v2.7.8-ember-coder-tabs-model-chips — 2026-06-01
The BooCode 2.0 visual identity plus two workflow features. **Ember theme** (`styles/themes/ember.css`, now `DEFAULT_THEME_ID`) is the signature orange-on-near-black look — rebuilt on Obsidian's flat charcoal structure (`#0c0c0e`/`#15151a`/`#1f1f23`) with `#ff7a18` swapped in for the purple, after a Reinvented-direction detour (neon borders + a scanline/glow texture overlay) was dialed back to taste; the server `theme_id` whitelist gains `ember` so it can actually be selected. The **brand banner** (`ProjectSidebar`) shows the eye-patch Westie mascot + the `>_BooCode` wordmark big and edge-to-edge on transparent backgrounds — the source PNGs shipped with baked-white canvases, so they were flood-filled to transparency from the corners (preserving the white dog, which a naive white-key would have destroyed) and cropped to bounds. **Coder panes are now multi-tab**: `+` opens a new BooCode tab (a fresh chat = a new agent context sharing the session worktree) while the split button still opens a pane — coder panes reuse the shared `ChatTabBar` via a kind-aware `tabKind`, backed by a new `createCoderTab` action with `closeOtherTabs`/tab-numbering extended to coder kind. **Model-attribution chips**: a new `messages.model` column (both apps share the table) stamped at `finalizeCompletion` (BooChat + native coder) and at the dispatcher's assistant-row creation (external coder), surfaced through the `messages_with_parts` view + wire types + the live `message_complete` frame (the Zod already allowed `model`; nothing consumed it), and rendered as a subtle accent chip with a shortened label (`shortenModelName``Sonnet 4.6`, `Qwen3.6 35B`) beside the message stats — so swapping models mid-coder-session stays legible. Also the composer moved its Web toggle into a boxed, focus-ringed input, tool rows lead with a glowing accent dot, and the Claude-SDK-backend follow-ups validated live this session (1M context window, follow-up-message fix, collapsed thinking/tool chips) land with `CLAUDE_SDK_BACKEND=1` flipped on. One snag fixed mid-deploy: the view's new `m.model` was first inserted mid-list and `CREATE OR REPLACE VIEW` can't reorder columns (42P16) — appended at the end. Web tsc + server + coder builds green; deployed (docker + boocoder, tools:34). Builds on `v2.7.7-pane-header-actions`.
## v2.7.7-pane-header-actions — 2026-06-01
In-flight workspace UX work, committed alongside the v2.7 review batches. Extracts a shared `PaneHeaderActions` cluster (the +/Split/Reopen-closed-pane/Session-history/Close controls) used across the `ChatTabBar` and the desktop coder + terminal pane headers in `Workspace`, replacing the divergent per-header copies, with `SessionLandingPage` history enhancements and `useWorkspacePanes` tweaks. Also fixes a coder-side correctness bug: `resolveChatId` (`apps/coder/src/routes/chat-resolve.ts`) still read `sessions.workspace_panes` as a bare `WorkspacePane[]`, but `v2.6.5-panes-tabs-composer` widened it to a `WorkspaceState` envelope — so it mis-read the panes and, worse, clobbered `tabNumbers`/`nextTabNumber`/`closedPaneStack` back to a bare array on every pane-chat write; a new `normalizeWorkspaceState` accepts either shape and preserves the envelope (with a regression test). Plus a CLAUDE.md doc-sync (apps/coder vitest suite, deploy-by-surface, dual-remote push, in-flight-web-WIP staging, release-branch naming). Web tsc + coder build + coder tests green. Builds on `v2.7.6-agent-status-normalize`.
## v2.7.6-agent-status-normalize — 2026-06-01
The scoped half of `boocode_code_review_v2.md` §1 #10 — normalized external-agent status, surfaced from BooCoder's own dispatch observation (the heavier config-injection notify-hook, clean-room from superset's ELv2 `agent-setup`, is documented as the follow-on). The review's premise ("PTY agents have no status") had partly aged out — warm-ACP/opencode/SDK already carry working/done — so the real gap was that BooCoder never *published* a normalized per-`(chat,agent)` status (blocked-on-permission was invisible; crash/idle weren't pushed). Adds an `agent_status_updated` WS frame (`working|blocked|idle|error`, server+web parity) published from the dispatcher's turn boundaries across all four external paths (warm-acp/opencode/sdk/pty — `working` at start, `idle`/`error` at end) and the permission flow (`blocked` on request, `working` on resolve), best-effort so it never breaks a turn. A clean-room `normalizeAgentEvent` helper (superset's ~30-vendor-event → Start/blocked/Stop collapse, reimplemented with the event names as facts) ships now with 25 tests so the deferred notify-hook injection reuses it verbatim. The `AgentComposerBar` gains a normalized status dot (working=spinner, blocked=amber, idle=gray, error=red) distinct from the WS-liveness dot, fed by a `useAgentStatus` map `CoderPane` tracks per `(chat,agent)`. Built by two parallel agents (data plane + view plane) against a pinned frame contract; server 545 + coder 294 tests passing (25 new), web tsc + builds clean, ws-frames parity green. Clears the actionable review backlog (#1/#3/#4/#6#12). Builds on `v2.7.5-claude-sdk-sessionstore`; openspec `agent-status-normalize`.
## v2.7.5-claude-sdk-sessionstore — 2026-06-01
Lands the Claude Agent SDK direction (`boocode_code_review_v2.md` §1 #9, §6.2 "lean SDK") behind a flag. Adds `@anthropic-ai/claude-agent-sdk@0.3.159` (Commercial Terms — runtime dep, code reference-only) and builds a warm, resumable claude backend to supersede one-shot PTY dispatch — env-gated (`CLAUDE_SDK_BACKEND`, default off) so production claude stays on the unchanged PTY path until a host smoke. **Clean-room `PostgresSessionStore`** implements the SDK's real `SessionStore` type (`append`/`load`/`listSessions`/`delete`/`listSubkeys`) over a new `claude_session_entries` table — typechecked against the installed SDK type, 8 DB-integration tests. **`ClaudeSdkBackend`** (`implements AgentBackend`, mirroring warm-acp/opencode-server) drives one persistent `query()` per `(chat,'claude')` in streaming-input mode via a pushable async-iterable pump, with `sessionStore` + `resume` for cross-turn/cross-restart continuity, a pure `mapSdkMessage``AgentEvent` mapper, `session_id` captured from the `init` message, and `result.usage`/`total_cost_usd` accumulated onto `agent_sessions` (backend CHECK gains `'claude_sdk'`). Built against the REAL SDK 0.3.159 types after installing it — surfacing shapes a blind build would have missed (`SDKPartialAssistantMessage` is `type:'stream_event'` needing `includePartialMessages`; `SDKUserMessage.message` is `MessageParam`; the `SDKResultMessage` error arm). Also fixes a latent test-infra deadlock — three DB-integration suites applying the full schema in parallel under `DATABASE_URL` deadlocked, now serialized via `fileParallelism:false`. ~32 new tests (8 store + 10 mapper + 8 pushable + 6 routing); coder suite 269 passing default / 290 with DB; tsc clean against the SDK types; builds clean. **The live streaming pump + resume + an actual claude turn need a host smoke (`CLAUDE_SDK_BACKEND=1` + claude binary + ANTHROPIC auth) — cannot run from the dev container.** The zod peer-dep wants `^4` (workspace `3.25`) — watch at runtime. Builds on `v2.7.4-mistake-tracker-ledger`; openspec `claude-sdk-sessionstore`.
## v2.7.4-mistake-tracker-ledger — 2026-06-01
Two native-inference hardening features from `boocode_code_review_v2.md` §1 #12 (cline, algorithm-reimplemented). **MistakeTracker:** complements the doom-loop guard (identical repeats) and cap-hit (budget) by catching a run of consecutive tool *failures*. A new pure `mistake-tracker.ts` tracks heterogeneous failure kinds (`zod_reject`/`tool_not_found`/`exec_error`/`api_error`/`permission_denied`, surfaced per tool from `tool-phase.ts`); after 3 consecutive failures the `turn.ts` loop does a **soft nudge** — injects model-facing recovery guidance into the next step + drops a `mistake_recovery` UI sentinel + resets — then **escalates** to stopping the turn (cap-hit-style, with a Continue affordance) if it re-trips without an intervening success, so heterogeneous failures can't burn the whole step budget. **File-provenance ledger:** `compaction.ts` now derives a deterministic, sorted `## Files Read` list from the head messages' read-tool calls (`view_file`/`grep`/`find_files`/`list_dir`) and injects it into the rolling-summary prompt so file provenance survives compaction (no new table; prompt-driven merge, read-only since BooChat has no write tools). The `mistake_recovery` sentinel adds an arm to `MessageMetadata` in both server + web type copies plus a `MessageBubble` render branch. Built by two parallel agents (backend + frontend sentinel) over disjoint apps; server 545 tests passing (23 new: 12 mistake-tracker + 11 compaction), build + web tsc clean. Native-inference only (external agents run their own loops). Builds on `v2.7.3-sampling-streamjson-tokens`; openspec `mistake-tracker-file-ledger`.
## v2.7.3-sampling-streamjson-tokens — 2026-06-01
Three small BooCode wins from `boocode_code_review_v2.md` §1 #11/#7/#8. **Sampling knobs:** per-agent `top_n_sigma` + the `dry_*` repetition family (`dry_multiplier`/`dry_base`/`dry_allowed_length`/`dry_penalty_last_n`) are now first-class Agent frontmatter fields, parsed in `agents.ts` and threaded into the llama-swap chat-completion body via `providerOptions.openaiCompatible` (the `@ai-sdk/openai-compatible` extra-body channel). This surfaced and fixed a **latent bug**: `top_k` (rejected by the AI-SDK provider as unsupported) and `min_p` (never passed to `streamText` at all) had been dead on the wire — no agent's `top_k`/`min_p` ever affected sampling; both now route through the same channel, so agents that set them will start using them. `--reasoning-budget` is documented in `data/AGENTS.md` (already works via `llama_extra_args`, permitted by the deny-list validator). **Live PTY stream-json:** qwen/claude PTY dispatch sliced stdout opaque; a new `stream-json-parser.ts` line-buffers the Claude-Code-compatible NDJSON and emits text/reasoning/tool frames live as they arrive (mirroring the ACP/opencode paths) + persists the structured parts, with a clean fallback to the old opaque slice when output isn't NDJSON (claude now runs `--output-format stream-json --verbose`). **Token UI:** the per-`(chat,agent)` `agent_sessions.input_tokens`/`output_tokens`/`cost` columns (accumulated since `v2.6.8` but dropped by the read route + wire type) now flow through and render condensed beside the AgentComposerBar session chip. Built by three parallel agents over disjoint subsystems; server 523 + coder 245 tests passing (incl. 11 new stream-json-parser + new agent-parse tests), all builds + web tsc clean. Builds on `v2.7.2-checkpoint-idor`; openspec `sampling-streamjson-tokens`. The qwen-vs-claude `usage` field names in #7 are best-guess pending a live smoke.
## v2.7.2-checkpoint-idor — 2026-06-01
Closes two IDOR authorization holes in the `v2.7.1-write-edit-robustness` checkpoint routes, flagged by the automated push security review. The `GET /api/sessions/:id/checkpoints?chat_id=` list route scoped its `chat_id` branch by `chat_id` alone — any session's `chat_id` would read its checkpoints; it now joins through `chats` and gates on `chats.session_id` (authoritative; `checkpoints.session_id` is a nullable denormalized hint). The `restoreCheckpoint` scope guard was fail-open — `cp.session_id && cp.session_id !== sessionId` fell through whenever the checkpoint's denormalized `session_id` was null, allowing a cross-session restore (worktree reset + transcript trim) — it now resolves the owning session via the checkpoint's chat and denies on any missing-or-mismatched row. A DB-integration regression covers the exact null-`session_id` cross-session case. Real-world blast radius is small (BooCoder is single-user behind Authelia on loopback), but both are genuine authorization bugs. Coder suite 234 passing (7/7 checkpoint tests incl. the regression against live postgres+git), typecheck clean. Hotfix on `v2.7.1-write-edit-robustness`.
## v2.7.1-write-edit-robustness — 2026-06-01
Two BooCoder hardening features for local quantized models, algorithm-reimplemented (not vendored) from the cline findings in `boocode_code_review_v2.md` §1 #3/#4. **Fuzzy patch applier:** `edit_file`'s apply path was exact-`.includes`-or-throw + first-occurrence `.replace` (`pending_changes.ts`), so a qwen3.6 whitespace/indentation/unicode drift in `old_string` lost the edit; a new pure `fuzzy-match.ts` (`locateMatch`) now runs an exact → per-line-trim → unicode-canon (curly quotes/dashes/nbsp) → Levenshtein-≥0.66 ladder and returns the real file span, refusing multi-exact matches as ambiguous rather than silently editing the first. `applyOne`/`rewindOne` both use it. **Worktree checkpoints + conversation-trim:** `rewind` only reversed BooCode's own `pending_changes`, blind to what external agents (opencode/goose/qwen/claude) write directly into the session worktree — so a new `checkpoints` table + `checkpoints.ts` shadow-commit (tracked **and** untracked, captured via a temp-index `read-tree`/`add`/`write-tree`/`commit-tree` into a GC-safe `refs/boocode/checkpoints/<id>`) snapshots the worktree before each external-agent turn (hooked into all three dispatcher paths), anchored to the turn's assistant message. A new `POST /api/sessions/:id/checkpoints/:cid/restore` resets the worktree (`reset --hard` + `clean -fd`), trims the transcript past that message, and resets the `(chat,agent)` backend session so files, transcript, and agent context land consistent at the restore point; a per-message "Restore to here" affordance in `CoderMessageList` drives it. Built by three parallel agents over disjoint files; DB-integration testing caught a microsecond-`created_at` self-deletion bug in the later-checkpoint cleanup. Full coder suite 234 passing (incl. 17 fuzzy-match + 6 checkpoint tests), server+coder build + web tsc clean. Builds on `v2.7.0-mit`; openspec `write-edit-robustness`. Live host smoke (dispatcher hook + restore UI end-to-end) still to run.
## v2.7.0-mit — 2026-06-01
Relicenses BooCode from AGPL-3.0 back to MIT by clearing the three Unsloth-Studio-derived files the `v2.4.0`/`v2.4.1` lifts pulled in — the root `LICENSE` and all five `package.json` had been `AGPL-3.0-only`, making the network-served work AGPL §13-encumbered. The enabling finding decoupled the relicense from the long-planned native-llama-server-parsing retirement: `tool-call-parser.ts`'s Unsloth-ported algorithm (`parseToolCallsFromText`/`scanBalancedBraces` + unused nudge constants) was **dead code** with no production import, so it was simply deleted while the load-bearing `extractToolCallBlocks`/`stripToolMarkup` (BooCode-authored streaming helpers) were kept byte-identical — no behavior change to the live tool-call path. `html-to-md.ts` was swapped to the MIT `node-html-markdown` library (`parse5` dropped; the only behavior delta is column-aligned tables, GFM hard-break `<br>`, and `<ol start>` renumbering, all feeding the LLM via `web_fetch`), and `llama-args-validator.ts` was clean-room rewritten with the managed-flag denylist re-derived from the public llama-server flag list (facts, not copyrightable). The license flip set `LICENSE` to MIT (`Copyright (c) 2026 indifferentketchup`), the five `package.json` to `MIT`, removed every AGPL SPDX header, added a README License section, and added a `license-mit` guard test that fails if AGPL provenance returns. Built by three parallel agents over the disjoint files; full server suite 519 passing (incl. 9 new guard tests), server build + coder typecheck clean. Resolves `boocode_code_review_v2.md` §1 #1 / §5k and the roadmap's `License-debt` batch (openspec `license-debt-mit`); supersedes that batch's original staged plan, which had entangled the flip with a live qwen3.6 validation window.

201
CLAUDE.md
View File

@@ -2,11 +2,11 @@
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
**Cursor agents:** start with `docs/ARCHITECTURE.md` (diagram). This file is the deep engineering reference. (Note: the root navigation `AGENTS.md` was removed in v1.12; `data/AGENTS.md` is the agent *registry*, not navigation.)
**Cursor agents:** start with `docs/ARCHITECTURE.md` (diagram); this file is the deep engineering reference. `data/AGENTS.md` is the agent *registry*, not navigation (the root navigation `AGENTS.md` was removed).
## What is BooCode
Self-hosted single-user developer chat app. AI assistant with read-only file tools (view_file, list_dir, grep, find_files) running against a local llama-swap inference server. Sessions organized by project, with a multi-pane workspace (chat + file browser side by side).
Self-hosted single-user developer chat app. AI assistant with read-only file tools (view_file, list_dir, grep, find_files) against a local llama-swap inference server. Sessions organized by project, multi-pane workspace (chat + file browser side by side).
Plus `apps/booterm` (second container, port 9501, bookworm-slim+glibc): Fastify + node-pty + tmux. Browser terminal panes WS to `/ws/term/sessions/:sid/panes/:pid`; per-session tmux session `bc-<sid>`, per-pane window `term-<pid>`. Shells drop privs to samkintop via `gosu` in `tmux.conf` default-command.
@@ -23,97 +23,33 @@ pnpm -C apps/server build # server only (tsc + copy schema.sql)
pnpm -C apps/web build # web only (vite)
# Type checking (no emit)
npx tsc --noEmit # project references (root)
npx tsc -p apps/web/tsconfig.app.json --noEmit # web app specifically
# IMPORTANT: root tsc --noEmit uses project references and can miss errors
# that the per-app tsconfig catches. Always verify with the per-app command
# when editing web code. The server build (pnpm -C apps/server build) is
# authoritative for server code.
# Per-app is authoritative. There is NO root tsconfig.json (only tsconfig.base.json),
# so a bare `npx tsc --noEmit` at root compiles nothing.
npx tsc -p apps/web/tsconfig.app.json --noEmit # web (authoritative)
pnpm -C apps/server build # server typecheck (tsc + copy schema)
pnpm -C apps/coder build # coder typecheck
pnpm -C apps/booterm typecheck # booterm typecheck
# Production
docker compose build --no-cache boocode && docker compose up -d
```
Tests: `pnpm -C apps/server test` runs the vitest suite. No test harness on `apps/web` (adding it requires installing vitest as a new devDep). Vitest pinned to `^3` because Vite 5 / vitest 4 are incompatible. No linters configured. Vitest include glob is `src/**/__tests__/**/*.test.ts` (see `apps/server/vitest.config.ts`) — tests outside `src/**/__tests__/` silently won't run; match the per-domain convention (`apps/server/src/services/__tests__/foo.test.ts`).
Tests: `pnpm -C apps/server test` (vitest); `apps/coder` has its own suite — `pnpm -C apps/coder test` (`globals:false`, so import `describe`/`it`/`expect` from `vitest`). No `apps/web` test harness, no linters. Vitest pinned to `^3` (Vite 5 / vitest 4 incompatible). Include glob is `src/**/__tests__/**/*.test.ts` — tests outside it silently won't run. Extract pure helpers to unit-test (`backends/turn-guard.ts`, `lifecycle-decisions.ts` are the pattern).
## Architecture
**Monorepo**: pnpm workspaces with `apps/server` (Fastify + postgres), `apps/web` (React + Vite), and `apps/booterm` (Fastify + node-pty + tmux).
**Monorepo**: pnpm workspaces with `apps/server` (Fastify + postgres), `apps/web` (React + Vite), `apps/booterm` (Fastify + node-pty + tmux), `apps/coder` (BooCoder, host service), `packages/contracts` (`@boocode/contracts`, cross-app wire-contract SSOT — builds FIRST).
### Server (`apps/server/src/`)
### Per-app deep references
- **Fastify** with `@fastify/websocket` and `@fastify/static` (serves built frontend)
- **postgres** (porsager/postgres) with tagged-template SQL — no ORM. Schema in `schema.sql`, applied on startup. LSP may false-positive on `sql<Type[]>\`...\`` generics; CLI `tsc` / `pnpm build` is authoritative.
- **Zod** for request validation and config parsing.
Detailed engineering notes live in per-app `CLAUDE.md` files, **auto-loaded when you read/edit files in that subtree** (and worth opening before non-trivial work there):
Key services:
- **`services/inference/`** — Public surface re-exported via `inference/index.ts`; callers import from `./services/inference/index.js` explicitly (NodeNext doesn't honor directory-index resolution). Layout: `turn.ts` (runAssistantTurn / runInference / createInferenceRunner; exports `InferenceFrame`, `InferenceContext`, `TurnArgs`, `StreamResult`, `MAX_STEPS`), `stream-phase.ts` (streamCompletion as a v1.13.1-A AI SDK adapter + executeStreamPhase), `provider.ts` (`upstreamModel(baseURL, modelId)` wrapping `createOpenAICompatible` against llama-swap), `tool-phase.ts` (executeToolPhase → returns `ToolPhaseResult`; no longer recurses into runAssistantTurn — v1.14.0 converted the recursion to an explicit while loop in turn.ts), `sentinel-summaries.ts` (runCapHitSummary + runDoomLoopSummary + runStepCapSummary + their sentinel inserters), `error-handler.ts` (handleAbortOrError, finalizeCompletion), `payload.ts` (buildMessagesPayload, loadContext, maybeFlagForCompaction, `OpenAiMessage`), `sentinels.ts` (`detectDoomLoop`, `DOOM_LOOP_THRESHOLD`, sentinel predicates), `budget.ts` (resolveToolBudget), `xml-parser.ts` (qwen3.6 XML tool-call fallback — KEEP, AI SDK doesn't handle inline-XML tool calls), `parts.ts` (parts-table write helpers: `partsFromAssistantMessage`, `partsFromToolMessage`, `insertParts` — v1.13.20 made parts the sole source of truth), `prune.ts` (v1.13.4 two-tier compaction; `selectPruneTargets` is the pure decision helper), `types.ts` (`StreamPhaseState`, `DB_FLUSH_INTERVAL_MS`). **`TurnArgs`** is the per-turn state envelope populated from loop locals each iteration; reset in `runInference` at user-message boundary. The outer loop in `runAssistantTurn` (v1.14.0) runs `while (stepNumber < effectiveCap)` where `effectiveCap = Math.min(agent.steps ?? Infinity, MAX_STEPS=200)`. Per-agent `steps:` field in AGENTS.md frontmatter. `steps: 0` means text-only (no tool execution). Step-cap hit writes a `cap_hit` sentinel so `CapHitSentinel.tsx` renders it.
- **AI SDK v6 streamCompletion adapter** (v1.13.1-A; `services/inference/stream-phase.ts`). `streamText` is the underlying call; the BooCode layer above (executeStreamPhase, finalize, dual-write) is shape-preserved via an adapter. Five gotchas the LSP/test suite won't catch:
- **Abort signals are swallowed.** `streamText`'s `fullStream` iterator exits cleanly when `abortSignal` fires — no throw. Post-iteration `if (signal?.aborted) throw <AbortError>` is required; without it the row finalizes as `complete` instead of `cancelled`. Comment in stream-phase.ts pins this; don't refactor it away.
- **Usage lands only at stream end** via `await result.usage` (`inputTokens` / `outputTokens` v6 names → mapped to `promptTokens` / `completionTokens` for the existing onUsage callback). Mid-stream live tok/s is gone vs v1.12.2; ChatThroughput shows a single value at stream end.
- **Tools have NO `execute` field.** BooCode dispatches tools in tool-phase.ts, not the AI SDK loop. Only `description` + `inputSchema: jsonSchema(parameters)` — surfacing tool-call parts via `fullStream` and stopping is what we want.
- **`includeUsage: true` MUST be set on `createOpenAICompatible`** in `services/inference/provider.ts`. The adapter defaults it false, omitting `stream_options.include_usage` from the request body; llama-swap then never emits the usage block and `result.usage.inputTokens/outputTokens` resolve to `undefined`. Latent regression from v1.13.1-A through v1.13.7 — every assistant row in that window has `tokens_used`/`ctx_used` NULL. Don't remove this flag during refactor.
- **Tool-call-only turns may emit a leading `\n` text-delta** as the assistant content. `MessageList.flatten`'s `hasText` and `MessageBubble`'s `hasContent` both `.trim()` before the length check — otherwise whitespace-only content renders an empty bubble + ActionRow between every tool call (v1.13.7 fix). `payload.ts:buildMessagesPayload` also skips `status='failed'` AND complete-but-empty (no content, no tool_calls) assistant rows to avoid "Cannot have 2 or more assistant messages at the end of the list" upstream rejections after cap-hit + Continue.
- **AI SDK ModelMessage conversion** (`toModelMessages` in stream-phase.ts). Tool messages need a `toolName` for `ToolResultPart` — BooCode's OpenAI-shape history doesn't carry it, so a forward-scan builds a `tool_call_id → toolName` map from prior assistant `tool_calls`. Tool outputs wrapped as `{ type: 'json' | 'text', value }` matching the v6 `ToolResultOutput` union. Assistant messages with reasoning emit a `ReasoningPart` first in the content array (v1.13.1-C).
- **`experimental_repairToolCall`** (v1.13.3) wired into `streamText` to keep the stream alive when qwen3.6 emits malformed tool args. Pass-through implementation — logs the bad call and returns it unmodified; `executeToolPhase`'s existing zod-reject error path routes it to the model on the next turn.
- **`chat_status` frame shape** (published via `broker.publishUser`) — `status: 'streaming' | 'tool_running' | 'waiting_for_input' | 'idle' | 'error'` (widened from `working|idle|error` in v1.12.1). Frontend `useChatStatus` derives `idle_warm` (<30s since idle) vs `idle_cold`. `ChatThroughput` renders inline beside `StatusDot` only when streaming or tool_running, fed by 500ms-throttled `'usage'` WS frames (`completion_tokens` + `ctx_used` + `ctx_max`). The `POST /api/chats/:id/discard_stale` endpoint exists to mark a stuck-streaming row as `failed` when the frontend's 60s no-token-activity timer (`ChatPane` content-length watcher) gives up.
- **Boot-time stale-streaming sweep** in `apps/server/src/index.ts` after `applySchema()`: any `messages.status='streaming'` older than 5 minutes flips to `'failed'`. Logs only on non-zero count. Recovers from container restart while inference was mid-stream (v1.12.1).
- **Periodic 60s sweeper** in `apps/server/src/index.ts` (v1.13.3 + v1.13.5). Same `setInterval` runs `sweepStaleStreaming` (marks `messages.status='streaming'` older than 5 min as `failed`, publishes `chat_status='idle'` so the UI dot drops) and `cleanupTruncations` (TTL + orphan reap of tmpfs truncation files). `app.addHook('onClose')` clears the timer. No-op when nothing to reap.
- **`services/broker.ts`** — In-memory pub/sub with two channel types: per-session (message streaming) and per-user (sidebar updates). No persistence; clients reconnect on restart. v1.13.11: every WS publish goes through `broker.publishFrame(sessionId, frame)` or `broker.publishUserFrame(user, frame)` — both Zod-validate against `WsFrameSchema` (`types/ws-frames.ts`) and fail-closed (log + drop). `ctx.publish` / `ctx.publishUser` in inference + auto_name route through the index.ts adapter that calls publishFrame internally. The schema is duplicated byte-identical at `apps/web/src/api/ws-frames.ts`; a `ws-frames.test.ts` case enforces parity. Don't add new raw `broker.publish()` / `publishUser()` calls.
- **`services/tools.ts`** — Tool registry (`ALL_TOOLS`, `READ_ONLY_TOOL_NAMES`, `TOOLS_BY_NAME`). Filesystem tools (view_file/list_dir/grep/find_files) go through three guard layers: `path_guard.ts` (workspace scope), `secret_guard.ts` (filename deny list), `url_guard.ts` (SSRF/private-IP block for web_fetch). v1.11.8+ web tools (`web_search`, `web_fetch`) are opt-in per chat via `session.web_search_enabled` (resolved with `project.default_web_search_enabled` fallback) and filtered out of the LLM's tool schema when false. v1.13.5 truncation: when a tool slice cuts content, `services/truncate.ts` stashes the full text on tmpfs at `BOOCODE_TRUNCATION_DIR` (default `/tmp/boocode-truncations`, 0o700) keyed by an opaque `tr_<12 base32 chars>` id, and the `view_truncated_output(id)` tool retrieves it. 5MB cap (matches `view_file`'s `MAX_FILE_BYTES`), 7-day TTL, reaped by the periodic sweeper. Tmpfs path means container restart loses retrieval — acceptable, the model usually has moved on.
- **`services/compaction.ts`** + **`services/model-context.ts`** — v1.11.0 anchored rolling summary (single `summary=true` assistant row per chat, supersedes itself on each compaction). Triggered when `chats.needs_compaction` is set after an inference turn exceeds `usable(ctx_max) = floor(0.85 × ctx_max)` (v1.13.9 opencode-pattern early trigger; was `ctx_max - 20k` pre-v1.13.9, which gave only 7.6% headroom at 262k and 0 budget for ≤20k contexts). **`ctx_max` comes from `model-context.getModelContext()` which fetches `${LLAMA_SWAP_URL}/upstream/<model>/props`** — NOT from `parsed.timings.n_ctx` (the stream completion's `timings` doesn't carry n_ctx; that read was dead code until v1.11.3 ripped it out). First inferences after a boocode boot may have `ctx_max=NULL` if llama-swap hasn't loaded the model yet; negative cache TTL is 60s, recovers on next turn. v1.13.6: `buildHeadPayload` embeds `reasoning_parts` as a `<reasoning>...</reasoning>` prose prefix on the assistant `content` (OpenAI wire shape has no structured reasoning field; the summarizer reads text). Standalone tag when content is empty (tool-call-only turn). `buildHeadPayload` + `OpenAiMessage` exported for test access — keep them exported.
- **`services/system-prompt.ts`** — `buildSystemPrompt` is the string-returning shim; `buildSystemPromptWithFingerprint` is the canonical impl returning `{prompt, fingerprint, drift}`. v1.13.8 instrumentation: SHA-256 of the assembled prefix is logged per `buildMessagesPayload` call (msg `prefix-fingerprint`, level=info); a `Map<sessionId, lastHash>` observer fires `prefix-drift` (level=warn) on hash change with a field-level `changed_inputs` diff. Smoke proved the prefix is byte-stable across turns in steady-state — the originally-planned `system_prompt_cache` DB table was dropped as redundant against the v1.12.0 input-layer mtime caches (BOOCHAT.md here + AGENTS.md global+per-project in `agents.ts:safeStat`).
- **`services/inference/budget.ts`** — tool-call budgets: `BUDGET_READ_ONLY = 30`, `BUDGET_NON_READ_ONLY = 10` (forward-looking; no write tools yet), `BUDGET_NO_AGENT = 30` (v1.13.7; was 15 — every tool in `ALL_TOOLS` is read-only today, so no-agent mode shares the read-only-agent cap). Per-agent `max_tool_calls` from AGENTS.md frontmatter overrides.
- **`messages_with_parts` view** (v1.13.1-B; `schema.sql`). Read sites that need `tool_calls` / `tool_results` / `reasoning_parts` SELECT from this view, NOT `messages` directly. v1.13.20 dropped the legacy `messages.tool_calls` / `messages.tool_results` JSON columns; the view now reads parts-only subselects. Writes target `message_parts` exclusively via `insertParts` (or via the helpers `partsFromAssistantMessage` / `partsFromToolMessage`). The `Message` wire type still carries `tool_calls?` / `tool_results?` because the view synthesizes them from parts — frontend reads are unchanged. Shapes: `tool_calls jsonb[]`, `tool_results jsonb` single object, `reasoning_parts jsonb[]` of `{text}`. If you ever need to UPDATE a message and return its full Message shape, do a two-step UPDATE returning `id` followed by SELECT from the view — RETURNING off the bare `messages` table no longer carries the tool fields.
- **`services/file_ops.ts`** — Shared file operation implementations used by both inference tools and HTTP routes.
- **`services/auto_name.ts`** — Non-streaming LLM call to generate 4-word session titles after first assistant reply.
- **`apps/coder/src/services/provider-registry.ts`** (BooCoder, NOT apps/server) — Static registry of provider metadata (label, transport, model source). `PROVIDERS` array, `PROVIDERS_BY_NAME` map. 5 providers: boocode (native), opencode (acp), goose (pty), claude (pty), qwen (pty).
- **`apps/coder/src/services/agent-probe.ts`** (BooCoder) — Startup probe using direct `exec()` (not SSH). Discovers installed agents on host, their versions, ACP support, and models. Qwen models read from `~/.qwen/settings.json`. Claude models are static from the registry. Results persisted to `available_agents` table.
- **`apps/coder/src/routes/providers.ts`** (BooCoder) — `GET /api/providers` returns installed providers with models. Transport field reflects actual capability (checks `supports_acp` from DB, not just registry preference). The apps/server side of this flow is the "Provider picker dispatch" bullet below.
- **Provider picker dispatch**: when `provider !== 'boocode'`, the message route creates a `tasks` row (with `session_id` set) instead of calling `inference.enqueue`. The dispatcher picks it up and dispatches via ACP or PTY using the agent's `install_path`.
- **`apps/server/CLAUDE.md`** — inference pipeline, AI-SDK adapter gotchas, tools, compaction, broker, the `messages_with_parts` view, sidecar routing, secret guard, the `data/AGENTS.md` registry.
- **`apps/coder/CLAUDE.md`** — BooCoder dispatch, provider registry/probe/snapshot, opencode/ACP/PTY/Claude-SDK backends, `agent_sessions` resume.
- **`apps/web/CLAUDE.md`** — React app, hooks/event buses, font & CSS pipeline, multi-pane workspace, all UI conventions.
- **`docs/project-discovery.md`** — full stack / tooling / command inventory across all packages (read-on-demand).
Route registration: all routes registered in `index.ts` via `register*Routes(app, sql, ...)` functions. Routes are in `routes/*.ts`.
### BooCoder (`apps/coder/src/`)
- Write-capable coding agent. Runs as a **systemd service on the host** (`boocoder.service`), NOT in Docker. Fastify server at port 9502, connects to postgres at `127.0.0.1:5500`.
- **Workspace dependency on `@boocode/server`**: imports `createInferenceRunner`, `createBroker`, `ALL_TOOLS`, `appendMcpTools` from the server's compiled `dist/`. apps/server's `package.json` has an `exports` map with `types` conditions for NodeNext resolution. apps/server must build FIRST.
- Build + deploy: `pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Env file at `apps/coder/.env.host`. Service file at `/etc/systemd/system/boocoder.service`.
- After `pnpm -C apps/coder build` the host `boocoder.service` keeps running the OLD process until `sudo systemctl restart boocoder` — a stale process shows **new routes 404 with `{error:'not found'}` while old routes still 200** (the `/api` not-found handler returns that shape). Restart, don't re-debug.
- Agent dispatch spawns binaries directly using `install_path` from `available_agents` — no `spawn('sh', ['-c', ...])` (fails under systemd). Follows Paseo's pattern: `spawn(fullBinaryPath, argsArray, { cwd })`.
- systemd hardening: only `NoNewPrivileges=true` is safe. `ProtectSystem`, `ProtectHome`, `PrivateTmp` all break agent dispatch (agents need full filesystem access to read configs, write to worktrees).
- `apps/server/tsconfig.json` has `declaration: true` so `.d.ts` files exist for workspace consumers.
- Write tools (`edit_file`, `create_file`, `delete_file`, `apply_pending`, `rewind`) queue in `pending_changes` table. Nothing hits disk until `apply_pending` is called. `write_guard.ts` validates paths (resolve + prefix-check, no realpath since files may not exist for creates).
- Frontend: NOT a separate SPA. BooCoder is a `'coder'` pane type within BooChat's SPA (`apps/web/`). `CoderPane.tsx` in `apps/web/src/components/panes/`. API requests go through `/api/coder/*` proxy (Vite dev + Fastify production) which rewrites to the boocoder host service (`BOOCODER_URL` env var, default `http://100.114.205.53:9502`). WS connects directly to `:9502`.
- `apps/coder/web/` is a STANDALONE fallback SPA served at `:9502` directly. The PRIMARY BooCoder frontend is the `CoderPane` in BooChat's SPA (`apps/web/src/components/panes/CoderPane.tsx`), accessible via the "Coder" pane in the workspace at `code.indifferentketchup.com`. Both exist; the pane is what Sam uses.
- **Provider snapshot lifecycle** (`apps/coder/src/services/`): `provider-config.ts` (Zod config, never-throws on bad input) → `provider-config-registry.ts` (`buildResolvedRegistry`, singleton) → `provider-snapshot.ts` (two-tier probe: tier-1 fast presence, tier-2 cold ACP probe skipped unless force / stale `PROVIDER_PROBE_TTL_MS` 24h / dbEmpty; cached). Verify live: `curl http://100.114.205.53:9502/api/providers/snapshot` — returns providers + models + commands, the exact shape `AgentComposerBar` renders.
- `PATCH /api/providers/config` replaces a provider id's override object **wholesale** (per-id shallow merge) — to flip one field send `{...existing, enabled}`, or a custom ACP entry's `command`/`label` is wiped and it drops out of the resolved registry. `data/coder-providers.json` is **gitignored** (it's live runtime config — the coder reads AND writes it on UI toggles); the tracked reference is `data/coder-providers.example.json`. The loader falls back to `{providers:{}}` (built-ins only) when the live file is absent, so a fresh checkout needs no copy.
- **opencode** runs as a warm HTTP server (v2.6 Phase 1, `services/backends/opencode-server.ts``opencode serve` per BooCoder process, one opencode session per BooCode session, resumed via `agent_sessions`). goose/qwen/claude still dispatch **one-shot** ACP/PTY with no ctx/token usage; only native `boocode` (llama-swap engine) tracks ctx. Paseo's per-provider native clients (design §12) deliberately not ported.
- **opencode SSE** (`opencode-server.ts`): live streaming arrives as `session.next.text.delta` / `session.next.reasoning.delta` / `session.next.tool.{called,success,failed}` — NOT `message.part.*` (those are terminal/post-hoc). `client.event.subscribe({ directory })` MUST pass the session's worktree directory; omit it and opencode scopes events to the server's `process.cwd()` → zero session events (empty turns, 180s watchdog timeout). Per-session SSE (P1.5-a): each live session owns its own `event.subscribe({directory})` loop + AbortController, so concurrent sessions in different worktrees stream independently; a `sessionID` demux guard drops cross-session events when two share a dir. Turn completes on `session.idle`; `promptAsync` is fire-and-forget (204).
- **opencode model strings** must be provider-prefixed (`llama-swap/<model>`) AND exist in `~/.config/opencode/opencode.json` `provider.llama-swap.models` — not merely loadable by llama-swap. `parseModel` infers `llama-swap/` for a bare id; the dispatcher coalesces empty→DEFAULT_MODEL then prefixes. `agent-probe` populates opencode's `available_agents.models` via `mergeLlamaSwap` (fetches `/v1/models`); empty model list → frontend sends `''` → no inference (`input:0`, empty turn).
- **agent_sessions resume**: `config_hash = sha256('opencode_server|<model>')` — must NOT include the server port (random per boot; including it breaks cross-restart resume). P1.5-b: `agent_sessions` is keyed `(chat_id, agent)` — the tab/chat is the context unit (two opencode tabs in one session = two contexts sharing one worktree). `chat_id` CASCADEs from `chats`; `session_id`/`worktree_id` are informational `SET NULL`. The `worktrees` table (one-per-session, `session_id` SET NULL so it survives session delete) supersedes the defanged `session_worktrees`. `tasks.chat_id` threads the tab id to the dispatcher; `runOpenCodeServerTask` falls back to resolve-or-create a chat when it's null (arena/MCP/new_task). The `@opencode-ai/sdk` v2 client takes flattened params (`{sessionID, directory, parts, model:{providerID,modelID}}`), imports `createOpencodeClient` from `@opencode-ai/sdk/v2/client`.
### Frontend (`apps/web/src/`)
- **React 18** + React Router v6 + **Tailwind v4** + shadcn/radix-ui primitives.
- **Shiki** for syntax highlighting (async `codeToHtml` in `CodeBlock.tsx` and `FileViewer` in `FileBrowserPane.tsx`).
- Path alias: `@/` maps to `src/`.
- **Mobile interaction primitives** (post-v1.6): `useViewport` (matchMedia, breakpoints mobile <768 / tablet 7681023 / desktop ≥1024), `useSidebarDrawer` / `useRightRailDrawer` (Context + auto-close on `useLocation().pathname` change), `useLongPress` (500ms timer, dispatches synthetic `contextmenu` on `[data-tab-id]`), `usePullToRefresh` (80px threshold, 600ms hold), `SwipeablePaneTab` (60px close, 30px vertical bail). Tap-target convention: `max-md:min-h-[44px] max-md:min-w-[44px]`. Mobile headers: `border-b px-3 sm:px-4 py-2` + `style={{ paddingTop: 'max(0.5rem, env(safe-area-inset-top))' }}`. Hamburger left, FolderTree right.
Key patterns:
- **`hooks/sessionEvents.ts`** — Module-singleton event bus (Set of listeners). Used for cross-component communication: session renames, file-open events, attachment dispatch. 9 event types in the discriminated union. When adding a new event type to the `SessionEvent` union, you must also add a case to the `applyEvent` switch in `useSidebar.ts` (even if it's a no-op `return prev`).
- **`hooks/useSessionStream.ts`** — WebSocket per session, `applyFrame` reducer builds message list from streaming frames.
- **`hooks/useUserEvents.ts`** — Single app-level WS to `/api/ws/user` with exponential backoff reconnect. Forwards frames onto the sessionEvents bus.
- **`hooks/useSidebar.ts`** — Module-singleton with Set<setState> subscriber pattern; one bus subscription guarded by `globalThis.__boocode_sidebar_subscribed` for HMR safety. Every new `SessionEvent` type needs a `case` in the `applyEvent` switch (no-op `return prev` is fine).
- **`api/client.ts`** — Centralized typed fetch wrapper. All endpoints under `api.*` namespace.
Font / CSS pipeline (apps/web):
- Tailwind v4's `@import "tailwindcss"` directive strips font URLs from subsequent CSS `@import`s — `@fontsource*` packages must be imported as JS side-effect modules in `apps/web/src/main.tsx`, not via `@import` in `globals.css`. Otherwise the woff2 files never make it to `dist/`.
- Lightning CSS (inside `@tailwindcss/postcss` v4) collapses contiguous unicode-ranges to wildcard shorthand (`U+0000-FFFF``U+????`), which iOS Safari/Vivaldi mishandles (silently drops the font from those codepoints). Use explicit non-wildcard-collapsible subranges (e.g. `U+2500-259F` not `U+2500-25FF`). The `apps/web` build script greps `dist/assets/*.css` for `U+2500-259F` and fails the build if missing — preserve that guard.
- `@font-face` blocks must live AFTER all `@import` statements (CSS spec). Earlier placement silently breaks every subsequent `@import` (this broke the 18 theme palette imports in globals.css for one session).
- JetBrainsMono Nerd Font self-hosted in `apps/web/src/fonts/` (TTF from ryanoasis/nerd-fonts release) — needed because `@fontsource-variable/jetbrains-mono` ships subsetted woff2s that don't cover `U+2500-259F` (box drawing + block elements, used by opencode's banner). "NL" = No Ligatures (matches `font-feature-settings: "liga" 0`); "Mono" = single-cell icon width so TUI layouts don't desync.
- xterm-addon-webgl rasterizes glyphs via Canvas2D into a GPU texture atlas. Canvas2D does NOT honor `font-display: block` — it uses whatever font is currently registered. Gate xterm initialization on `document.fonts.load(<font-name>)` resolving before calling `term.open()` (see `fontsReady` useState in `TerminalPane.tsx`). iOS Safari/Vivaldi also reclaims WebGL contexts from backgrounded tabs: keep `webgl.onContextLoss(() => webgl.dispose())` + recreate via visibilitychange. Do NOT manually dispose+recreate the addon after font load — iOS silently fails the second GL context creation and the terminal drops to DOM renderer with stale metrics.
Cross-app contracts (WS-frame & provider-type parity, sentinels) and everything below stay here.
### Data flow for chat
@@ -124,90 +60,67 @@ Font / CSS pipeline (apps/web):
5. Tool calls: inference executes tools server-side, publishes tool_call/tool_result frames, loops back to LLM
6. Terminal states (complete/error): DB updated with final content + token counts, `session_updated` frame published on user channel
### Multi-pane workspace
Sessions hold 15 panes (chat / empty / placeholder terminal+agent). v1.12.1 moved pane state from per-device localStorage to `sessions.workspace_panes jsonb` for cross-device sync. `PATCH /api/sessions/:id/workspace` persists; `session_workspace_updated` user-channel frame broadcasts to every device watching the session. `useWorkspacePanes` debounces saves 300ms and dedups echoes by JSON string. Legacy localStorage key `boocode.workspace.panes.<sessionId>` is read once on first hydrate (one-time seed-and-delete migration when server is empty but localStorage has data); no longer written. The deprecated `session_panes` table was dropped. `validatePanes(validChatIds)` prunes panes referencing chat IDs that no longer exist (called by `useSessionChats` after the chat list fetch lands). Each chat lives in at most one pane; tab strip is per-pane and tracks `chatIds[]` + `activeChatIdx`. Tab reorder via native HTML5 drag events. v2.6.5: `workspace_panes` is now a `WorkspaceState` envelope `{panes, tabNumbers (chatId→stable session-scoped tab number, assigned on chat-pane open, retired on close, never reused), nextTabNumber, closedPaneStack (reopen LIFO, max 10, persisted so it survives reload)}` — not a bare `WorkspacePane[]`. Hydrate (`toWorkspaceState`) and the server PATCH validator (`z.union([array, envelope])` in `routes/sessions.ts`) both accept the legacy array and normalize to the envelope on read/write. Closing a chat pane relocates its tabs to the oldest chat/empty pane; `reopenPane` strips the restored chatIds from all live panes first (no duplication). `read_tab_by_number` resolves a number→chatId through `tabNumbers`.
## Database
PostgreSQL 16. Database name: `boochat` (renamed from `boocode` in v2.0.0-alpha; Docker service name stays `boocode_db`). Tables: `projects`, `sessions`, `chats`, `messages`, `settings`, `message_parts` (v1.13.0), `pending_changes` (v2.0.0), `tasks` (v2.0.0), `available_agents` (v2.0.0). Views: `messages_with_parts` (v1.13.1-B parts-merge read path), `tool_cost_stats` (v1.13.10 per-tool 100-call rolling window), `human_inbox` (v2.0.0 — tasks WHERE state IN blocked/failed). (`session_panes` was dropped in v1.12.1; workspace pane state lives in `sessions.workspace_panes jsonb`.) Schema applied idempotently on startup via `applySchema()`. Use `clock_timestamp()` (not `NOW()`) inside transactions. CHECK constraints in place: `projects_status_chk` ('open'|'archived'), `sessions_status_chk` (same), `chats_status_chk` (same), `messages_role_chk`, `messages_status_chk` — keep in sync with the `*_STATUSES` const arrays in `apps/server/src/types/api.ts`. The older anonymous `messages_status_check` (without 'cancelled') and `messages_role_check` (without 'system') were dropped in v1.12.1; only the `_chk` variants remain. **Two schema files, one DB:** `apps/server/src/schema.sql` owns `sessions`/`chats`/`messages`/`message_parts`; `apps/coder/src/schema.sql` (applied by the boocoder host service) owns `agent_sessions`, `worktrees`, `pending_changes`, `available_agents` and extends `tasks`. Both apply idempotently to the one `boochat` DB — so e.g. an `agent_sessions` FK change goes in the **coder** schema, not the server one. Idempotent FK-action flips (e.g. `ON DELETE CASCADE``SET NULL`) guard on `pg_constraint.confdeltype` so a re-run/fresh-deploy is a no-op (see the `session_worktrees`/`agent_sessions` defang blocks).
PostgreSQL 16. DB name: `boochat` (Docker service stays `boocode_db`). Tables: `projects`, `sessions`, `chats`, `messages`, `settings`, `message_parts`, `pending_changes`, `tasks`, `available_agents`. Views: `messages_with_parts` (parts-merge read path), `tool_cost_stats` (per-tool 100-call rolling window), `human_inbox` (tasks WHERE state IN blocked/failed). Schema applied idempotently on startup via `applySchema()`. Use `clock_timestamp()` (not `NOW()`) inside transactions. CHECK constraints: `projects_status_chk`/`sessions_status_chk`/`chats_status_chk` ('open'|'archived'), `messages_role_chk`, `messages_status_chk` — keep in sync with the `*_STATUSES` const arrays in `apps/server/src/types/api.ts`. **Two schema files, one DB:** `apps/server/src/schema.sql` owns `sessions`/`chats`/`messages`/`message_parts`; `apps/coder/src/schema.sql` (applied by the boocoder host service) owns `agent_sessions`, `worktrees`, `pending_changes`, `available_agents` and extends `tasks` — so e.g. an `agent_sessions` FK change goes in the **coder** schema. Idempotent FK-action flips (e.g. `ON DELETE CASCADE``SET NULL`) guard on `pg_constraint.confdeltype` so re-runs are no-ops.
Schema CHECK migration order when renaming allowed values: (1) `ALTER TABLE ... DROP CONSTRAINT IF EXISTS <system_name>` (inline `CREATE TABLE` checks get `<table>_<column>_check`), (2) `UPDATE` rows to new values, (3) wrap new constraint ADD in `DO $$ ... pg_constraint` guard — that block is the only way to get `ADD CONSTRAINT IF NOT EXISTS`.
Schema CHECK migration order when renaming allowed values: (1) `ALTER TABLE ... DROP CONSTRAINT IF EXISTS <system_name>` (inline `CREATE TABLE` checks get `<table>_<column>_check`), (2) `UPDATE` rows to new values, (3) wrap the new constraint ADD in a `DO $$ ... pg_constraint` guard — the only way to get `ADD CONSTRAINT IF NOT EXISTS`.
**`CREATE OR REPLACE VIEW` can't reorder/rename columns** (Postgres `42P16`): append a new `messages_with_parts` column at the END of the SELECT — a mid-list insert shifts an existing column → crash-loops boot. Add it to each explicit read SELECT too (`routes/messages.ts`/`chats.ts`/`ws.ts`).
**A `SELECT *` view pins every column** (`2BP01`): `DROP COLUMN` on the table fails while such a view exists. `human_inbox` is `SELECT * FROM tasks` — to drop a `tasks` column, `DROP VIEW IF EXISTS human_inbox` first, drop the column(s), then recreate the view (idempotent). Bites existing DBs only; a fresh DB never had the column, so fresh-DB testing misses it.
## Environment
Required: `DATABASE_URL`, `LLAMA_SWAP_URL`. Optional: `PORT` (3000), `HOST` (0.0.0.0), `PROJECT_ROOT_WHITELIST` (/opt, read-only scope for add-existing path resolution), `BOOTSTRAP_ROOT` (/opt/projects, writable scope for create-new-project bootstrap mkdir target — host must `mkdir -p /opt/projects` before container start), `DEFAULT_MODEL`, `LOG_LEVEL`, `SEARXNG_URL` (default `http://100.114.205.53:8888` — internal Tailscale Fathom; the public `search.indifferentketchup.com` is behind Authelia and unusable from server context), `BOOCODE_TOOLS` (`core` | `standard` | `all`, default `all`; v1.13.15-tools tier filter — ceiling, never expands an agent's whitelist), `MCP_CONFIG_PATH` (optional; default `/data/mcp.json` — JSON config for MCP servers matching opencode's `mcpServers` shape; file missing = no MCP).
Required: `DATABASE_URL`, `LLAMA_SWAP_URL`. Optional: `PORT` (3000), `HOST` (0.0.0.0), `PROJECT_ROOT_WHITELIST` (/opt, read-only add-existing scope), `BOOTSTRAP_ROOT` (/opt/projects, writable bootstrap mkdir target — host must `mkdir -p` it before container start), `DEFAULT_MODEL`, `LOG_LEVEL`, `SEARXNG_URL` (default `http://100.114.205.53:8888` — internal Tailscale; the public host is behind Authelia, unusable from server context), `BOOCODE_TOOLS` (`core`|`standard`|`all`, default `all`; a ceiling, never expands an agent's whitelist), `MCP_CONFIG_PATH` (default `/data/mcp.json`, opencode `mcpServers` shape; missing = no MCP), `CONTEXT7_API_KEY` (the Context7 MCP key, referenced from `data/mcp.json` as `"{env:CONTEXT7_API_KEY}"`). `data/mcp.json` is **gitignored** but no longer holds secrets — string values support opencode-style `{env:VAR}` substitution (`mcp-config.ts:substituteEnvVars`, applied before Zod validation; unset var → `''` + warn), so real keys live in `.env`; template `data/mcp.example.json`. A config-only edit there needs only `docker compose restart boocode` (data/ is bind-mounted); changing a referenced secret edits `.env`. MCP loads at server startup with per-server graceful degradation; the coder does NOT load MCP (BooChat only).
BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `boocoder.service` on the host (not Docker). Deploy: `pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Health reports tool count: `{"ok":true,"db":true,"tools":33}`.
BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `boocoder.service` on the host (not Docker). Deploy: `pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Health reports tool count: `{"ok":true,"db":true,"tools":33}`.
- `FAST_MODEL` (optional) — cheaper model for titles, summaries, labeling (auto_name.ts, tool-summaries.ts). Falls back to session model or DEFAULT_MODEL when unset. Set to a small model on llama-swap (e.g. `nemotron-nano-4b`) to avoid loading the 35B for 20-token calls.
- Qwen Code dispatch: `OPENAI_BASE_URL=http://100.101.41.16:8401/v1 OPENAI_API_KEY=dummy qwen -p "<task>" --output-format stream-json`. Install: `npm install -g @qwen-code/qwen-code@latest`. Node ≥22 required on host (container stays Node 20; BooCoder dispatches via direct spawn on host). No `--yolo` flag — non-interactive mode (`-p`) runs autonomously without approval prompts. ACP bridge is HTTP daemon (not stdio); use PTY dispatch.
- Arena (v2.0.5): `POST /api/arena {project_id, input, contestants: [{agent?, model?}]}` dispatches the same task to N models/agents in parallel. Each contestant gets its own task + worktree. `GET /api/arena/:id` for results. `POST /api/arena/:id/select/:task_id` picks winner.
- `FAST_MODEL` (optional) — cheaper model for titles, summaries, labeling (auto_name.ts, tool-summaries.ts). Falls back to session model or DEFAULT_MODEL. Set to a small llama-swap model (e.g. `nemotron-nano-4b`) to avoid loading the 35B for 20-token calls.
- Qwen Code dispatch: `OPENAI_BASE_URL=http://100.101.41.16:8401/v1 OPENAI_API_KEY=dummy qwen -p "<task>" --output-format stream-json`. Install: `npm install -g @qwen-code/qwen-code@latest`. Node ≥22 on host (container stays Node 20; BooCoder dispatches via direct spawn on host). No `--yolo` flag — `-p` runs autonomously without prompts. ACP bridge is an HTTP daemon (not stdio); use PTY dispatch.
- Arena: `POST /api/arena {project_id, input, contestants: [{agent?, model?}]}` dispatches the same task to N models/agents in parallel; each contestant gets its own task + worktree. `GET /api/arena/:id` for results; `POST /api/arena/:id/select/:task_id` picks a winner.
## Workflow
- Sam reviews all diffs and commits manually. Do not commit unless explicitly asked.
- Per-batch docs live under `openspec/changes/<slug>/{proposal,tasks,design}.md`. Already-shipped batches are snapshots in `openspec/changes/archived/`. New batches follow the proposal+tasks shape; see `openspec/README.md` for the convention.
- Tag naming: `vMAJOR.MINOR.PATCH-slug` (e.g. `v1.13.13-ws-publish`). Monotonic per minor — the slug describes the batch's content so the tag name alone is enough to recall what shipped. No letter suffixes (`-a`/`-b`), no pseudo-ranges (`v1.11.x`), no slug-only sub-versions sharing a number (`v1.13.15-tools` + `-openspec` + `-agentlint` — split into sequential patches instead).
- `CHANGELOG.md` is the per-tag release log, most-recent on top. When a new tag is created, add a `## <tag> — <YYYY-MM-DD>` section with a 36 sentence paragraph summarizing what shipped, drawn from the commit body. Cross-reference other tags by name when the batch builds on, fixes, or pairs with prior work (e.g. "pairs with `v1.13.12-ws-schemas`", "fixed in `v1.13.5-stability-bundle`"). No nested bullets — one paragraph.
- Deploy: `cd /opt/boocode && docker compose up --build -d` (or `docker compose build --no-cache boocode && docker compose up -d` if you suspect a layer-cache issue).
- The `boocode` container is `build: .` — it builds web+server from the **working tree**, so uncommitted changes deploy. Web edits are live on the Vite dev server (HMR) but NOT on production (`:9500` / code.indifferentketchup.com) until `docker compose up --build -d boocode`.
- Git push to Gitea: `GIT_SSH_COMMAND="ssh -i /opt/boocode/secrets/boocode_gitea -o IdentitiesOnly=yes" git push origin <branch>`. The default agent identity is rejected; the in-repo deploy key (`secrets/`, gitignored) is the working one. Transient `Connection reset by peer` retries cleanly after `sleep 5`.
- Sam often has uncommitted `apps/web` work in flight — stage your own commits **explicitly by path** (never `git add -A`); `docker compose up --build -d boocode` builds the working tree, so a container rebuild also ships his uncommitted web changes.
- **Deploy by surface:** an `apps/coder` change → `sudo systemctl restart boocoder`; an `apps/web` or `apps/server` change → `docker compose up --build -d boocode` (rebuilds web+server from the working tree). The `boocode` container is `build: .`, so uncommitted changes deploy; web edits are live on the Vite dev server (HMR) but NOT on production (`:9500` / code.indifferentketchup.com) until a rebuild. Use `docker compose build --no-cache boocode && docker compose up -d` if you suspect a layer-cache issue.
- Cutting a release: name the feature branch DIFFERENTLY from the tag (branch `f1-interrupt-guard`, tag `v2.6.7-interrupt-guard`) — identical names trigger `warning: refname ... is ambiguous`.
- Per-batch docs live under `openspec/changes/<slug>/{proposal,tasks,design}.md`; shipped batches are snapshots in `openspec/changes/archived/`. New batches follow the proposal+tasks shape (see `openspec/README.md`).
- Tag naming: `vMAJOR.MINOR.PATCH-slug` (e.g. `v1.13.13-ws-publish`), monotonic per minor — the slug alone recalls what shipped. No letter suffixes, no pseudo-ranges, no slug-only sub-versions sharing a number (split into sequential patches).
- `CHANGELOG.md` is the per-tag release log, newest on top. New tag → add a `## <tag> — <YYYY-MM-DD>` section, one 36 sentence paragraph (no nested bullets) from the commit body; cross-reference related tags by name when the batch builds on / fixes / pairs with prior work.
- Git push to Gitea: `GIT_SSH_COMMAND="ssh -i /opt/boocode/secrets/boocode_gitea -o IdentitiesOnly=yes" git push origin <branch>`. The default agent identity is rejected; the in-repo deploy key (`secrets/`, gitignored) is the working one. Transient `Connection reset by peer` retries cleanly after `sleep 5`. Keep both remotes synced: push `main` + the release tag to `origin` (Gitea, deploy key above) AND `backup` (`git@github.com:indifferentketchup/boocode.git`, default key).
- Don't accumulate `.bak-*` files. Clean them up in the same batch or immediately after merge.
- DB-integration tests opt-in via env var: `DATABASE_URL='postgres://boocode:devpass@localhost:5500/boochat' pnpm -C apps/server test`. Host port is 5500 (mapped from `boocode_db:5432`); password is `${POSTGRES_PASSWORD}` from `.env` (`devpass`), NOT the literal in `.env`'s `DATABASE_URL=postgres://boocode:Ketchup1479@boocode_db:5432/...` line. `psql` is not on the host PATH — for an interactive query use `docker exec boocode_db psql -U boocode -d boochat -c "..."`. Pattern: `describe.runIf(!!process.env.DATABASE_URL)(...)` with a `beforeAll` that applies the schema via `sql.unsafe(readFileSync(schemaPath))`. Tests skip cleanly when var is unset. `tool_cost_stats.test.ts` is the reference.
- Host-side smoke endpoint: `curl http://100.114.205.53:9500/api/...`. The boocode container's port mapping binds to the Tailscale IP, not `0.0.0.0`, so `localhost:9500` doesn't work from the host shell. Same for booterm at `:9501`.
- Frontend blank-screen / runtime crash: get the stack-trace column offset from the browser console, then `cut -c <start>-<end> apps/web/dist/assets/index-*.js | sed -n '<line>p'` to read the exact minified expression that threw. Faster than bisecting source. Watch for `=== null`/`!== null` on optional fields fed an `as unknown as` cast — those bypass tsc.
- Fastify global JSON parser tolerates empty bodies (overridden in `index.ts`); bodyless POSTs (archive, unarchive, stop) work without setting `Content-Type` tricks on the client.
- DB-integration tests opt-in via env var: `DATABASE_URL='postgres://boocode:devpass@localhost:5500/boochat' pnpm -C apps/server test`. Host port 5500; password is `${POSTGRES_PASSWORD}` from `.env` (`devpass`), NOT the literal in `.env`'s `DATABASE_URL` line. `psql` isn't on host PATH — use `docker exec boocode_db psql -U boocode -d boochat -c "..."`. Pattern: `describe.runIf(!!process.env.DATABASE_URL)(...)` + `beforeAll` applying schema via `sql.unsafe(readFileSync(schemaPath))`. `tool_cost_stats.test.ts` is the reference.
- Host-side smoke endpoint: `curl http://100.114.205.53:9500/api/...`. The container's port mapping binds to the Tailscale IP, not `0.0.0.0`, so `localhost:9500` doesn't work from the host shell. Same for booterm at `:9501`.
- Frontend blank-screen / runtime crash: get the stack-trace column offset from the browser console, then `cut -c <start>-<end> apps/web/dist/assets/index-*.js | sed -n '<line>p'` to read the exact minified expression that threw. Watch for `=== null`/`!== null` on optional fields fed an `as unknown as` cast — those bypass tsc.
- Fastify global JSON parser tolerates empty bodies (overridden in `index.ts`); bodyless POSTs (archive, unarchive, stop) work without `Content-Type` tricks on the client.
- Event dedup discipline: for any mutation the server publishes via `broker.publishUser`, do NOT add a local `sessionEvents.emit(...)` after the API call — `useUserEvents` forwards the WS frame onto the bus. Frontend mutation handlers must be idempotent (dedup by id, no-op on already-present).
- `node:20-*` base images ship a `node` user at uid/gid 1000 — delete it (`userdel`/`groupdel` on debian, `deluser`/`delgroup` on alpine) before adding samkintop at 1000.
- node-pty's compiled `.node` is libc-specific: proddeps and runtime Dockerfile stages must share libc (alpine↔musl or bookworm-slim↔glibc); the TS-only builder stage can stay alpine for speed.
- pnpm 10 `--frozen-lockfile` skips node-pty's postinstall — the Docker proddeps stage runs `cd node_modules/node-pty && npm run install` to force the native compile.
- A local PreToolUse hook (`security_reminder_hook.py`) regex-flags Node's older `child_process` spawn helpers as unsafe (false positive even on the File-suffixed variant). Use `spawn` — it's accepted.
- `/opt/boolab` hosts a working sibling BooCode terminal at `boocode.indifferentketchup.com`. Useful for visual side-by-side comparison on the same iPhone when debugging booterm rendering. Boolab uses Tailwind v3 (`@tailwind base`); boocode uses v4 — many subtle build differences. Don't assume parity.
- booterm SSHs to the host as `samkintop@100.114.205.53` (the Tailscale IP). The hostname `ubuntu-homelab` (shown in the bash prompt after login) does NOT resolve from inside the container — only the host's `/etc/hosts` knows it. Override via `BOOTERM_SSH_HOST` / `BOOTERM_SSH_USER` env vars in docker-compose if you ever move the shell to a different machine.
- codecontext sidecar lives at `/opt/boocode/codecontext/`. Sidecar HTTP API at `http://codecontext:8080/v1/<tool_name>` over the `boocode_net` bridge (no host port). BooCode wrappers in `apps/server/src/services/tools/codecontext/`. The `.codecontextignore` at project root is honored when `--respect-gitignore` is passed (enabled in the shim).
- codecontext fork at `/opt/forks/codecontext/` — separate git repo (branch `boocode-ts`), pushed via the same boocode_gitea SSH key to `indifferentketchup/codecontext`. Build: `go build ./...`. Test: `go test ./...`. Docker rebuild requires staging the fork source first: `tar -czf codecontext/fork.tar.gz -C /opt/forks/codecontext --exclude=.git --exclude=bin .` then `docker compose build --no-cache codecontext`. The Dockerfile COPYs `fork.tar.gz` into the builder stage (Gitea is behind Authelia, no HTTP clone). `fork.tar.gz` is gitignored.
- Go binary: `/snap/go/current/bin/go` (not on PATH by default). Use `export PATH=$PATH:/snap/go/current/bin` or full path for Go commands.
- `os/exec` child supervisors must explicitly call `child.Wait()` in a goroutine and `os.Exit` on child death. `Signal(0)` returns nil on zombies and is NOT a liveness check. Without `Wait()`, docker's `restart: unless-stopped` policy never fires because the parent stays alive. The `codecontext/shim.go` implementation is the reference pattern.
- `/opt/boolab` hosts a sibling BooCode at `boocode.indifferentketchup.com` — useful for side-by-side iPhone comparison when debugging booterm rendering. It uses Tailwind v3, boocode uses v4 — don't assume build parity.
- booterm SSHs to the host as `samkintop@100.114.205.53` (the Tailscale IP). The hostname `ubuntu-homelab` (in the bash prompt) does NOT resolve inside the container. Override via `BOOTERM_SSH_HOST` / `BOOTERM_SSH_USER` env vars in docker-compose if the shell moves to a different machine.
- codecontext sidecar lives at `/opt/boocode/codecontext/`. HTTP API at `http://codecontext:8080/v1/<tool_name>` over the `boocode_net` bridge (no host port). BooCode wrappers in `apps/server/src/services/tools/codecontext/`. The `.codecontextignore` at project root is honored when `--respect-gitignore` is passed (enabled in the shim).
- codecontext fork at `/opt/forks/codecontext/` — separate git repo (branch `boocode-ts`), pushed via the boocode_gitea SSH key to `indifferentketchup/codecontext`. Build `go build ./...`; test `go test ./...`. Docker rebuild requires staging the fork first: `tar -czf codecontext/fork.tar.gz -C /opt/forks/codecontext --exclude=.git --exclude=bin .` then `docker compose build --no-cache codecontext` (the Dockerfile COPYs `fork.tar.gz` into the builder stage; Gitea is behind Authelia, no HTTP clone). `fork.tar.gz` is gitignored.
- Go binary: `/snap/go/current/bin/go` (not on PATH). Use `export PATH=$PATH:/snap/go/current/bin` or the full path.
- `os/exec` child supervisors must call `child.Wait()` in a goroutine and `os.Exit` on child death. `Signal(0)` returns nil on zombies and is NOT a liveness check. Without `Wait()`, docker's `restart: unless-stopped` never fires because the parent stays alive. `codecontext/shim.go` is the reference.
## Conventions
- `overflowWrap` not `wordWrap` — TypeScript's CSSStyleDeclaration marks `wordWrap` as deprecated (error 6385).
Cross-cutting only. Per-app conventions live in the matching `apps/*/CLAUDE.md`.
- No app-layer auth. Authelia handles auth at the reverse proxy. All `broker.publishUser`/`subscribeUser` calls use `'default'` as the user key.
- TypeScript strict mode. Both apps share `tsconfig.base.json`.
- Server uses NodeNext module resolution (`.js` extensions in imports).
- TypeScript strict mode. Both apps share `tsconfig.base.json`. Server + coder use NodeNext module resolution (`.js` extensions in imports).
- Discriminated unions for type narrowing: `Pane` (by `kind`), `SessionEvent` (by `type`), `InferenceFrame` (by `type`).
- **Adding a new WS frame type** requires updating BOTH the server's `InferenceFrame` (loose `type:` union + optional fields in `services/inference/turn.ts`) AND the web `WsFrame` (strict discriminated union in `apps/web/src/api/types.ts`). Server publish is permissive; the frontend type is the wire-format gate. The `'usage'` frame added in v1.12.2 needed both sides; missing the web side silently drops the frame at JSON-parse.
- shadcn primitives live in `components/ui/`. Don't modify them unless adding a new primitive.
- `ui/` primitives present: button, card, context-menu, dialog, dropdown-menu, input, label, radio-group, sonner, textarea. No switch/sheet/drawer/badge/checkbox — use a `<button role="switch" aria-checked>` toggle (a hand-rolled `Switch` already lives in `SettingsPane.tsx`) and a Dialog-based panel for "drawers".
- `inferLanguage()` from `lib/attachments.ts` is the canonical file-extension-to-language map. `CodeBlock.tsx` keeps its own `LANG_MAP` because it also resolves markdown fence names.
- Two UI event buses: `hooks/sessionEvents.ts` for DB-state events (chat_created, session_updated); `lib/events.ts` for ephemeral UI (`sendToTerminal`, `terminalsRegistry`). Don't merge — different subscriber lifecycles.
- `vite.config.ts` proxy entries are order-sensitive: more-specific prefixes (`/api/term`, `/ws/term`) must come BEFORE `/api`.
- Mobile pane URL sync (`Session.tsx`): the `?pane=<id>` effect resets `activePaneIdx` whenever `panes` changes. New-pane creation on mobile must push `?pane=` atomically — `addPaneAndSwitch` is the wrapper that does this. `addSplitPane` returns the new pane id for callers.
- A scrollable list inside a Dialog on mobile: cap `DialogContent` (`max-h-[85vh]` + `grid-rows-[auto_minmax(0,1fr)_auto]`) and make the list the single scroll region with `overscroll-contain` — otherwise touch-scroll drags the whole fixed modal / chains to the page.
- xterm.js v5 uses canvas rendering — browser doesn't see xterm's selection; the native right-click menu has no working Copy for terminal text. App keybindings (`Cmd/Ctrl-C`, `Cmd/Ctrl-Shift-C`) are the path.
- **New tools** live in their own `services/<name>.ts` file (see `web_search.ts`, `web_fetch.ts`) — exports a pure `executeFoo(input, ...deps)` for direct test access plus a `ToolDef` wrapper that `loadConfig()`s its real dependencies. Register the ToolDef in `tools.ts` `ALL_TOOLS` (and `READ_ONLY_TOOL_NAMES` if applicable). Inject `fetcher: typeof fetch = fetch` rather than `vi.spyOn(globalThis, 'fetch')` — cleanup is simpler and the production call site stays unchanged.
- **DB/session-aware tools** take an optional 4th `ToolExecCtx { sql, sessionId }` arg on `ToolDef.execute`, plumbed `executeToolPhase``executeToolCall``execute`. It's optional so the filesystem tools and the `apps/coder` `ALL_TOOLS` consumer stay compatible; filesystem tools ignore it. `read_tab_by_number` (reads `sessions.workspace_panes` + the chat's messages via `sql`) is the reference.
- **Sentinels** are `role='system'` rows with structured `metadata.kind` (`cap_hit`, `doom_loop`). UI-only — `buildMessagesPayload` strips them via `isAnySentinel` so the LLM never sees them. A new kind requires arms in `MessageMetadata` in BOTH `apps/server/src/types/api.ts` AND `apps/web/src/api/types.ts`, plus a render branch in `apps/web/src/components/MessageBubble.tsx`.
- **ReadableStream test stubs** use `pull()` (not `start()`) so chunks are produced lazily — `start()` enqueues everything and calls `controller.close()` before the consumer reads, so a subsequent `reader.cancel()` finds the stream already closed and the `cancel()` callback never fires. Also provide MORE chunks than the test will consume so the source stays in 'readable' state when cancel runs (e.g. cap test reads ~6 chunks, stub provides 10).
- React **StrictMode is on** (`main.tsx`): an updater passed to one `setState` that itself calls another `setState` (e.g. `setClosedPaneStack` inside a `setPanes` updater) is double-invoked in dev. Make such nested updates idempotent — `useWorkspacePanes`'s `appendClosed` dedupes a value-identical top entry for exactly this reason.
- Tool-name whitelists must derive from `ALL_TOOLS` in `services/tools.ts`, never hardcoded. `services/agents.ts` `ALL_TOOL_NAMES` had this drift class until v1.12 — same pattern applies to any future tool-aware code.
- Agent registry lives at `data/AGENTS.md` (global, bind-mounted at `/data/AGENTS.md`). No per-project `AGENTS.md` in this repo — removed in v1.12 to eliminate the two-files-must-stay-in-sync drift. The `getAgentsForProject` per-project override mechanism remains for *other* projects.
- `data/AGENTS.md` is PARSED (`agents.ts` `splitSections`/`parseAgentSection`): each `## <Name>` is one agent and must be followed by a `---` frontmatter fence or the block throws; content before the first `## ` is discarded. Do NOT add free-form `## ` rule sections — they break the registry. Cross-cutting agent rules go in CLAUDE.md or a parser-ignored preamble.
- Skills live in `data/skills/<vendor>/`; Sam's own namespace is `boocode/` (`committing-changes`, `using-worktrees`, `improving-boocode-guidance`) — `SKILL.md` + optional `eval.yaml` (gerund names; eval = `skill:` + `tasks:` of `prompt`+`grader`, incl. a negative-trigger task). `data/skills/` is canonical; a divergent mirror at `/opt/skills/` exists.
- MCP stdio transport uses newline-delimited JSON (NDJSON), NOT LSP-style `Content-Length` headers. The `codecontext/shim.go` framing implementation is the reference; per the MCP spec (modelcontextprotocol.io/specification/server/transports).
- **Workspace dependency pattern** (`apps/coder``@boocode/server`): the consuming package adds `"@boocode/server": "workspace:*"` in `package.json`. The provider's `package.json` needs `exports` with `types` + `default` conditions per subpath: `"./inference": { "types": "./dist/.../index.d.ts", "default": "./dist/.../index.js" }`. Without the `types` condition, NodeNext resolution can't find `.d.ts` files and tsc fails with "Cannot find module" in the consumer.
- **JSONB columns**: use `sql.json(value as never)` — NOT `${JSON.stringify(value)}::jsonb` which double-serializes (stores a JSON string instead of a JSON object/array). Pattern established in `parts.ts`, `settings.ts`.
- **`payload.ts:loadContext` SELECT**: must include every `Session` field that downstream code reads. The tool phase reads `session.allowed_read_paths`; if the SELECT omits it, cross-repo read grants silently fail. The `Session` TypeScript type doesn't catch this because `sql<Session[]>` doesn't enforce column coverage.
- **Sidecar routing** (`services/inference/provider.ts`): `upstreamModel(config, modelId, agent)` routes to `LLAMA_SIDECAR_URL` when agent has `llama_extra_args`, otherwise `LLAMA_SWAP_URL`. `resolveRoute(agent)` returns `{route: 'swap'|'sidecar', flags}`. Sidecar provider created fresh per call (not cached) because `X-Agent-Flags` header varies per agent. Boot-time guard in `index.ts` refuses to start if any agent has `llama_extra_args` but `LLAMA_SIDECAR_URL` is unset.
- **Secret guard safe patterns** (`services/secret_guard.ts`): `.env.example`, `.env.sample`, `.env.template`, `.env.defaults` are allowlisted via `SAFE_PATTERNS` set. Do NOT add `.env.production`/`.env.development`/`.env.test` — those can hold real secrets.
- **CoderPane uses ChatInput** (`components/panes/CoderPane.tsx`): shares the same `ChatInput` component as BooChat for full parity — attachments, paste-to-chip, auto-grow textarea, queued messages during send. CoderPane's `sendOneMessage` is the send callback; queued messages drain via `useEffect` when `sending` goes false.
- **Adding a new `SessionEvent` type**: add the interface, add it to the `SessionEvent` union, add a `case` in `useSidebar.ts` `applyEvent` switch (no-op `return prev` is fine), and subscribe in any hook that needs it (e.g. `useSessionStream` for `refetch_messages`).
- **BooCoder provider registry** (`apps/coder/src/services/provider-registry.ts`): static list of provider defs (boocode, opencode, goose, claude, qwen). `PROBED_AGENT_NAMES` derives from it. Adding/removing providers means editing this file, not the frontend.
- **AgentComposerBar filters `e.installed`**: provider snapshot entries with `installed:false` (loading/unavailable) are dropped from the dropdown. `getProviderSnapshot` must await the full build — returning synchronous `loading` placeholders makes every provider vanish (the v2.5.7 "no providers showing up" regression); surfacing loading states needs a client poll.
- **Coder↔web provider-type parity** (`apps/coder/src/services/provider-types.ts``apps/web/src/api/types.ts`): enforced by runtime `provider-types-parity.test.ts` (compile-time cross-import is blocked by TS6307 on web's composite tsconfig). Mirror of the ws-frames parity pattern — edit both copies together or the test fails.
- **ACP command discovery is async**: `acp-probe.ts` must poll after `newSession` for `available_commands_update` (commands arrive in a later notification; reading synchronously captures 0). PTY providers (claude) instead discover from disk via `claude-command-discovery.ts` (`~/.claude/commands` + `enabledPlugins` `skills/`+`commands/`, bare names, deduped). `AgentCommand.kind` tags `'command'` vs `'skill'`; `CoderPane`'s `slashGroups` splits them into icon'd groups. `SlashCommandPicker`'s `groups?` prop is opt-in — BooChat passes flat `items` (unchanged).
- **Pane header architecture (mobile vs desktop)**: Desktop coder pane header (BooCode label + [+] [×]) lives in `Workspace.tsx` gated by `isCoder && !isMobile`. Mobile coder controls (● ×) live in `Session.tsx` header row next to `MobileTabSwitcher`/`NewPaneMenu`. `AgentComposerBar` (provider/mode/model pickers) renders inside `CoderPane.tsx` on both. The ● status dot is passed via `connected` prop from CoderPane to AgentComposerBar.
- **MessageBubble shared between BooChat and BooCoder** (`components/MessageBubble.tsx`): accepts optional `actions?: MessageActions` callbacks (onRegenerate, onResend, onFork, onDelete) and `hideActions?: ('fork'|'delete'|'openInPane')[]`. Defaults use BooChat API; CoderPane overrides via `CoderMessageList` props. `CoderTextBubble` was removed. **`CoderMessageList` passes `CoderMessageWire as unknown as Message`** — the coder wire shape lacks `metadata`/`kind`/`summary`, so those fields are `undefined` (not `null`) on coder messages. Null-guards on any `Message` field MUST use loose `!= null`, not strict `!== null` (`undefined !== null` is `true``.kind` throws → blank-screen crash). The `as unknown as` cast hides this from tsc; build + typecheck pass while runtime crashes.
- **llama-sidecar** (`/opt/forks/llama-sidecar/`): Go daemon for per-agent llama-server process pool. Cross-compile: `GOOS=windows GOARCH=amd64 /snap/go/current/bin/go build -o bin/llama-sidecar.exe ./cmd/llama-sidecar`. Gitea: `indifferentketchup/llama-sidecar`. Windows child process gotchas: use `context.Background()` for child lifetime (not request ctx), `os.Open(os.DevNull)` for stdin, `os.Pipe()` for stdout with drain goroutine, `DETACHED_PROCESS | CREATE_NEW_PROCESS_GROUP` creation flags. SSH to sam-desktop: `ssh samki@100.101.41.16`; use `schtasks` for persistent process spawning (SSH `start /B` doesn't survive session close).
- **Adding a new WS frame type** (cross-app): add it to `WsFrameSchema` in `packages/contracts/src/ws-frames.ts` (single source of truth; rebuild with `pnpm -C packages/contracts build`). The server's `InferenceFrame` loose union (`services/inference/turn.ts`) and the web's strict `WsFrame` discriminated union (`apps/web/src/api/types.ts`) still exist separately and also need updating. Server publish is permissive; the frontend type is the wire-format gate missing the web side silently drops the frame at JSON-parse.
- **Sentinels** (cross-app) are `role='system'` rows with structured `metadata.kind` (`cap_hit`, `doom_loop`). UI-only — `buildMessagesPayload` strips them via `isAnySentinel` so the LLM never sees them. `MessageMetadata` is single-sourced in `@boocode/contracts` (`packages/contracts/src/message-metadata.ts`). A new kind requires updating that file and rebuilding the package, plus a render branch in `apps/web/src/components/MessageBubble.tsx`.
- **Provider snapshot types** (`ProviderSnapshotEntry`, `ProviderModel`, `ProviderMode`, `ThinkingOption`, `AgentCommand`, `ProviderSnapshotStatus`) are single-sourced in `@boocode/contracts` (`packages/contracts/src/provider-snapshot.ts`); `apps/coder/src/services/provider-types.ts` re-exports them. Edit the package source; there is no hand-synced web copy to update.
- **`@boocode/contracts`** single-sources cross-app wire contracts via per-subpath built-dist exports, consumed by all four apps (incl. `apps/coder/web`): `./ws-frames`, `./provider-snapshot`, `./provider-config` (Zod schemas), `./message-metadata` (`MessageMetadata`/`ErrorReason`/`AgentSessionConfig`), `./worktree-risk`. It builds BEFORE every consumer (root build, Dockerfile, coder deploy). Its `WsFrame` is the loose `z.infer` of `WsFrameSchema` (payloads `unknown`); the web's richer strict `WsFrame` union is **deliberately web-local** (`apps/web/src/api/types.ts`), bridged to the validated frame by a cast — don't move it into the package. Consume built `dist` via the exports map; never add the package to a tsconfig `references` array.
- **JSONB columns**: use `sql.json(value as never)` — NOT `${JSON.stringify(value)}::jsonb` which double-serializes (stores a JSON string instead of an object/array). Pattern in `parts.ts`, `settings.ts`.
- Skills live in `data/skills/<vendor>/`; Sam's own namespace is `boocode/` (`committing-changes`, `using-worktrees`, `improving-boocode-guidance`, `systematic-debugging`) — `SKILL.md` + optional `eval.yaml` (gerund names; eval = `skill:` + `tasks:` of `prompt`+`grader`, incl. a negative-trigger task). `data/skills/` is canonical; a divergent mirror at `/opt/skills/` exists.
### Coding standards
Coding standards live in `docs/coding-standards/` (canonical, human-readable). They are exposed to Claude Code through per-file-type/subsystem index files under `.claude/rules/coding-standards/`. Each index is a path-scoped rule that lists the standards relevant to its `paths:` glob with a one-line description of each. When Claude reads a file matching an index's `paths:`, it loads only that small index and then decides which (if any) standards to open with Read — the full text of a standard is never loaded automatically, and standards do not appear in the skills picker. Browse `docs/coding-standards/` for the readable form.

View File

@@ -1,10 +1,9 @@
# Current focus
Last updated: 2026-05-26
Last updated: 2026-06-02
- **Batch:** v2.3-provider-lifecycle (openspec drafted; not started)
- **Branch:** `main`
- **Blockers:** none
- **Last shipped:** `v2.2.2-xml-placeholder-reject`
- **Last shipped:** `v2.7.8-ember-coder-tabs-model-chips` (2026-06-01)
- **Branch:** `codebase-audit-cleanup` (audit + cleanup epic, off main HEAD)
- **In progress:** Phase 3 — stale comments + docs refresh
Update this file when starting or finishing a batch. Agents: read this first for session intent; if stale vs `CHANGELOG.md`, trust CHANGELOG for shipped state.
See `CHANGELOG.md` for the full shipped history. That file is always authoritative; this file is a quick orientation pointer only.

View File

@@ -5,11 +5,15 @@ RUN corepack enable
WORKDIR /build
COPY package.json pnpm-workspace.yaml pnpm-lock.yaml tsconfig.base.json ./
COPY packages/contracts/package.json ./packages/contracts/
COPY apps/server/package.json ./apps/server/
COPY apps/web/package.json ./apps/web/
RUN pnpm install --frozen-lockfile
# @boocode/contracts must be present before `pnpm build`, which builds it FIRST
# (root build script) so apps/web can resolve its compiled dist via the exports map.
COPY packages/contracts ./packages/contracts
COPY apps/server ./apps/server
COPY apps/web ./apps/web
@@ -20,6 +24,9 @@ RUN pnpm deploy --filter=@boocode/server --prod --legacy /out/server
FROM node:20-alpine AS runtime
RUN apk add --no-cache ripgrep git openssh-client
# The container runs as root but bind-mounts host project repos owned by uid 1000;
# trust them so git read/write tools (git_status, the git diff panel) work over the mount.
RUN git config --system --add safe.directory '*'
RUN mkdir -p /root/.ssh && ssh-keyscan -p 2222 -H 100.114.205.53 git.indifferentketchup.com >> /root/.ssh/known_hosts && chmod 700 /root/.ssh && chmod 600 /root/.ssh/known_hosts
WORKDIR /app

View File

@@ -58,7 +58,7 @@ upstream and inject `Remote-User`. Postgres binds loopback only.
BooCoder runs as a **host systemd service** (`boocoder.service`, port `:9502`), not in Docker:
```bash
pnpm -C apps/server build && pnpm -C apps/coder build
pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build
sudo systemctl restart boocoder
curl http://100.114.205.53:9502/api/health
```

View File

@@ -15,7 +15,6 @@
"fastify": "^4.28.1",
"node-pty": "^1.0.0",
"pg": "^8.13.0",
"tslib": "^2.6.3",
"zod": "^3.23.8"
},
"devDependencies": {

View File

@@ -9,7 +9,7 @@ const ConfigSchema = z.object({
TMUX_CONF_PATH: z.string().default('/etc/booterm/tmux.conf'),
});
export type Config = z.infer<typeof ConfigSchema>;
type Config = z.infer<typeof ConfigSchema>;
let cached: Config | null = null;

View File

@@ -10,7 +10,7 @@ export function getPool(databaseUrl: string): pg.Pool {
return pool;
}
export interface SessionInfo {
interface SessionInfo {
id: string;
project_id: string;
project_path: string;

View File

@@ -1,7 +1,7 @@
import * as pty from 'node-pty';
import type { IPty } from 'node-pty';
export interface AttachPtyOptions {
interface AttachPtyOptions {
sessionName: string;
projectRoot: string;
cols: number;

View File

@@ -14,3 +14,4 @@ GITEA_SSH_HOST=100.114.205.53:2222
MCP_CONFIG_PATH=/data/mcp.json
SKILLS_ROOT=/opt/boocode/data/skills
CODER_PROVIDERS_PATH=/opt/boocode/data/coder-providers.json
CLAUDE_SDK_BACKEND=1

34
apps/coder/CLAUDE.md Normal file
View File

@@ -0,0 +1,34 @@
# apps/coder — BooCoder (deep reference)
> Per-app engineering notes for `apps/coder/src/`. BooCoder runs as a **systemd service on the host** (`boocoder.service`), NOT in Docker — Fastify at port 9502, postgres at `127.0.0.1:5500`. Cross-cutting commands, database, environment, workflow, and cross-app contracts live in the **root `CLAUDE.md`**. This file auto-loads when you read/edit files under `apps/coder/`.
## Probe & provider discovery
- **`services/provider-registry.ts`** — Static registry of provider metadata (label, transport, model source). `PROVIDERS` array, `PROVIDERS_BY_NAME` map. 5 providers: boocode (native), opencode (acp), goose (pty), claude (pty), qwen (pty). `PROBED_AGENT_NAMES` derives from it — adding/removing providers means editing this file, not the frontend.
- **`services/agent-probe.ts`** — Startup probe via direct `exec()` (not SSH): discovers installed agents, versions, ACP support, models. Qwen models from `~/.qwen/settings.json`; Claude models static from the registry. Persisted to `available_agents`.
- **`routes/providers.ts`** — `GET /api/providers` returns installed providers with models. Transport reflects actual capability (checks `supports_acp` from DB, not just registry preference). The apps/server side is "Provider picker dispatch" (see `apps/server/CLAUDE.md`).
- **Provider snapshot lifecycle** (`services/`): `provider-config.ts` (Zod config, never-throws) → `provider-config-registry.ts` (`buildResolvedRegistry`, singleton) → `provider-snapshot.ts` (two-tier probe: tier-1 fast presence, tier-2 cold ACP probe skipped unless force / stale `PROVIDER_PROBE_TTL_MS` 24h / dbEmpty; cached). Verify live: `curl http://100.114.205.53:9502/api/providers/snapshot` — returns providers + models + commands, the exact shape `AgentComposerBar` renders.
- `PATCH /api/providers/config` replaces a provider id's override object **wholesale** (per-id shallow merge) — to flip one field send `{...existing, enabled}`, or a custom ACP entry's `command`/`label` is wiped and it drops out of the resolved registry. `data/coder-providers.json` is **gitignored** (live runtime config — the coder reads AND writes it on UI toggles); tracked reference is `data/coder-providers.example.json`. The loader falls back to `{providers:{}}` (built-ins only) when absent, so a fresh checkout needs no copy.
## Build, deploy, dispatch
- **Workspace dependency on `@boocode/server`**: imports `createInferenceRunner`, `createBroker`, `ALL_TOOLS`, `appendMcpTools` from the server's compiled `dist/`. apps/server's `package.json` has an `exports` map with `types` conditions for NodeNext resolution. **apps/server must build FIRST.**
- Build + deploy: `pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Env file at `apps/coder/.env.host`. Service file at `/etc/systemd/system/boocoder.service`.
- After `pnpm -C apps/coder build` the host service keeps running the OLD process until `sudo systemctl restart boocoder` — a stale process shows **new routes 404 with `{error:'not found'}` while old routes still 200** (the `/api` not-found handler shape). Restart, don't re-debug.
- `:9502/api/health` is down ~1520s after a boocoder restart while the startup agent-probe scan runs — retry; an early connection-refused is not a failed deploy.
- Agent dispatch spawns binaries directly using `install_path` from `available_agents` — no `spawn('sh', ['-c', ...])` (fails under systemd). Paseo's pattern: `spawn(fullBinaryPath, argsArray, { cwd })`.
- systemd hardening: only `NoNewPrivileges=true` is safe. `ProtectSystem`, `ProtectHome`, `PrivateTmp` all break agent dispatch (agents need full filesystem access to read configs, write to worktrees).
- `apps/server/tsconfig.json` has `declaration: true` so `.d.ts` files exist for workspace consumers. The provider's `package.json` needs `exports` with `types` + `default` conditions per subpath (`"./inference": { "types": "./dist/.../index.d.ts", "default": "./dist/.../index.js" }`) — without the `types` condition, NodeNext can't find `.d.ts` files and tsc fails "Cannot find module" here.
- Write tools (`edit_file`, `create_file`, `delete_file`, `apply_pending`, `rewind`) queue in `pending_changes`. Nothing hits disk until `apply_pending`. `write_guard.ts` validates paths (resolve + prefix-check, no realpath since files may not exist for creates).
## Backends
> Behavioral overview + flows + data model: see [/docs/coder-backends.md](/docs/coder-backends.md). The notes below are the deep per-fact reference.
- **opencode** runs as a warm HTTP server (`services/backends/opencode-server.ts``opencode serve` per BooCoder process, one opencode session per BooCode session, resumed via `agent_sessions`). goose/qwen/claude dispatch **one-shot** ACP/PTY with no ctx/token usage; only native `boocode` (llama-swap) tracks ctx.
- **opencode SSE** (`opencode-server.ts`): live streaming is `session.next.text.delta` / `.reasoning.delta` / `.tool.{called,success,failed}` — NOT `message.part.*` (terminal/post-hoc). `client.event.subscribe({ directory })` MUST pass the session's worktree dir; omit it and opencode scopes events to the server `process.cwd()` → zero session events (empty turns, 180s timeout). Each live session owns its own subscribe loop + AbortController (a `sessionID` demux guard drops cross-session events when two share a dir). Turn completes on `session.idle`; `promptAsync` is fire-and-forget (204).
- **opencode model strings** must be provider-prefixed (`llama-swap/<model>`) AND exist in `~/.config/opencode/opencode.json` `provider.llama-swap.models` — not merely loadable by llama-swap. `parseModel` infers `llama-swap/` for a bare id; the dispatcher coalesces empty→DEFAULT_MODEL then prefixes. `agent-probe` populates opencode's `available_agents.models` via `mergeLlamaSwap` (fetches `/v1/models`); empty model list → frontend sends `''` → no inference (empty turn).
- **agent_sessions resume**: `config_hash = sha256('opencode_server|<model>')` — must NOT include the server port (random per boot; breaks cross-restart resume). Keyed `(chat_id, agent)` — the tab/chat is the context unit (two opencode tabs = two contexts sharing one worktree). `chat_id` CASCADEs from `chats`; `session_id`/`worktree_id` are informational `SET NULL`. The `worktrees` table (one-per-session, survives session delete) supersedes the defanged `session_worktrees`. `tasks.chat_id` threads the tab id to the dispatcher; `runOpenCodeServerTask` resolves-or-creates a chat when null. The `@opencode-ai/sdk` v2 client takes flattened params (`{sessionID, directory, parts, model:{providerID,modelID}}`), `createOpencodeClient` from `@opencode-ai/sdk/v2/client`.
- **Claude SDK backend tool RESULTS arrive as `type:'user'` SDK messages** (tool_result content blocks): `mapSdkMessage` (`claude-sdk-map.ts`) MUST map the `user` case → a terminal `tool_update` (completed/failed + output), else the tool_call persists `status:'running'` and the UI spinner never stops. The dispatcher's `tool_update` path then publishes + persists it.
- **ACP command discovery is async**: `acp-probe.ts` must poll after `newSession` for `available_commands_update` (commands arrive in a later notification; reading synchronously captures 0). PTY providers (claude) discover from disk via `claude-command-discovery.ts` (`~/.claude/commands` + `enabledPlugins`, bare names, deduped). `AgentCommand.kind` tags `'command'` vs `'skill'`; `CoderPane`'s `slashGroups` splits them into icon'd groups. `SlashCommandPicker`'s `groups?` prop is opt-in.
- **A new per-message coder field silently drops unless you update every mapper**: the HTTP read SELECT + `mapCoderMessageRow` (`apps/coder/src/routes/messages.ts`), **the WS `snapshot` SELECT (`apps/coder/src/routes/ws.ts`)** — it has its OWN column list and the client's `snapshot` handler `setMessages`-overwrites the HTTP load, so a field present in the HTTP route but absent here shows live yet vanishes on refresh — `CoderPane.tsx` (`RawCoderMessage`/`CoderMessage`/`mapCoderTimelineRow` + the live `message_complete` WS reducer), `CoderMessageWire` (`CoderMessageList.tsx`), and `api/types.ts`. The client `mapCoderTimelineRow` whitelists fields — easiest to forget. This bit `model` twice: the client chain (`v2.7.9`) and then the WS snapshot SELECT (`v2.7.11`) — the chip showed live but vanished on coder refresh until both were fixed.

View File

@@ -7,7 +7,6 @@ WORKDIR /build
COPY package.json pnpm-workspace.yaml pnpm-lock.yaml tsconfig.base.json ./
COPY apps/server/package.json ./apps/server/
COPY apps/coder/package.json ./apps/coder/
COPY apps/coder/web/package.json ./apps/coder/web/
RUN pnpm install --frozen-lockfile
@@ -16,7 +15,6 @@ COPY apps/server ./apps/server
RUN pnpm -C apps/server build
COPY apps/coder ./apps/coder
RUN pnpm -C apps/coder/web build
RUN pnpm -C apps/coder build
RUN pnpm deploy --filter=@boocode/coder --prod --legacy /out/coder
@@ -27,7 +25,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends ripgrep git ope
WORKDIR /app
COPY --from=builder /out/coder ./
COPY --from=builder /build/apps/coder/web/dist ./web
ENV NODE_ENV=production
EXPOSE 3000

View File

@@ -13,12 +13,13 @@
"test": "vitest run"
},
"dependencies": {
"@boocode/contracts": "workspace:*",
"@agentclientprotocol/sdk": "^0.22.1",
"@anthropic-ai/claude-agent-sdk": "^0.3.159",
"@boocode/server": "workspace:*",
"@fastify/static": "^7.0.4",
"@opencode-ai/sdk": "~1.15.0",
"@fastify/websocket": "^10.0.1",
"@modelcontextprotocol/sdk": "^1.29.0",
"@opencode-ai/sdk": "~1.15.0",
"fastify": "^4.28.1",
"postgres": "^3.4.4",
"ws": "^8.18.0",

View File

@@ -1,12 +1,5 @@
import { resolve, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { existsSync } from 'node:fs';
import Fastify from 'fastify';
import fastifyWebsocket from '@fastify/websocket';
import fastifyStatic from '@fastify/static';
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
import { loadConfig } from './config.js';
import { getSql, applySchema, pingDb, closeDb } from './db.js';
import { startMcpServer } from './services/mcp-server.js';
@@ -16,7 +9,7 @@ import { createInferenceRunner } from '@boocode/server/inference';
import { createBroker } from '@boocode/server/broker';
import { appendMcpTools, ALL_TOOLS } from '@boocode/server/tools';
import type { Config as ServerConfig } from '@boocode/server/config';
import type { WsFrame } from '@boocode/server/ws-frames';
import type { WsFrame } from '@boocode/contracts/ws-frames';
// v2.0.0 Phase 2C: write tools + adapter for BooChat ToolDef compatibility.
import { WRITE_TOOLS } from './services/tools/index.js';
import { adaptWriteTool } from './services/tools/adapter.js';
@@ -25,6 +18,7 @@ import { setInferenceContext, clearInferenceContext } from './services/tools/inf
import { registerMessageRoutes } from './routes/messages.js';
import { registerSkillRoutes } from './routes/skills.js';
import { registerPendingRoutes } from './routes/pending.js';
import { registerCheckpointRoutes } from './routes/checkpoints.js';
import { registerAgentSessionRoutes } from './routes/agent-sessions.js';
import { registerTaskRoutes } from './routes/tasks.js';
import { registerInboxRoutes } from './routes/inbox.js';
@@ -41,6 +35,7 @@ import { createOrphanWorktreeReaper } from './services/orphan-worktree-reaper.js
import { probeAgents } from './services/agent-probe.js';
import { getProviderSnapshot, persistProbedModels } from './services/provider-snapshot.js';
import { setPermissionHooks } from './services/permission-waiter.js';
import { publishAgentStatus } from './services/agent-status-publish.js';
import { homedir } from 'node:os';
async function main() {
@@ -81,6 +76,21 @@ async function main() {
// Broker: in-memory pub/sub for session + user channel streaming.
const broker = createBroker(app.log);
// agent-status-normalize (#10): the permission hooks carry only taskId +
// sessionId, but the tasks row holds the (chat_id, agent) pair the status frame
// is keyed on. Resolve it best-effort so a blocked/working status accompanies
// every permission_requested/permission_resolved. Returns null when the task
// lacks a chat_id or agent (sessionless creators) — we simply skip the status.
const resolveChatAgent = async (
taskId: string,
): Promise<{ chatId: string; agent: string } | null> => {
const [row] = await sql<{ chat_id: string | null; agent: string | null }[]>`
SELECT chat_id, agent FROM tasks WHERE id = ${taskId}
`;
if (!row?.chat_id || !row.agent) return null;
return { chatId: row.chat_id, agent: row.agent };
};
setPermissionHooks({
onPrompt: async (prompt) => {
await sql`
@@ -95,6 +105,18 @@ async function main() {
...(prompt.input ? { input: prompt.input } : {}),
options: prompt.options.map((o) => ({ option_id: o.optionId, label: o.label })),
} as WsFrame);
// #10: agent is blocked on a human decision.
const ca = await resolveChatAgent(prompt.taskId).catch(() => null);
if (ca) {
publishAgentStatus(
broker.publishFrame,
prompt.sessionId,
ca.chatId,
ca.agent,
'blocked',
'permission_request',
);
}
},
onResolved: async (taskId, sessionId) => {
await sql`
@@ -105,6 +127,18 @@ async function main() {
task_id: taskId,
session_id: sessionId,
} as WsFrame);
// #10: human responded — agent resumes work.
const ca = await resolveChatAgent(taskId).catch(() => null);
if (ca) {
publishAgentStatus(
broker.publishFrame,
sessionId,
ca.chatId,
ca.agent,
'working',
'permission_resolved',
);
}
},
});
@@ -214,8 +248,9 @@ async function main() {
registerMessageRoutes(app, sql, broker, inferenceApi);
registerSkillRoutes(app, sql, broker, inferenceApi);
registerPendingRoutes(app, sql);
registerCheckpointRoutes(app, sql);
registerAgentSessionRoutes(app, sql);
registerTaskRoutes(app, sql, inferenceApi);
registerTaskRoutes(app, sql, inferenceApi, dispatcher.cancelExternalTask);
registerInboxRoutes(app, sql);
registerStatsRoutes(app, sql);
registerArenaRoutes(app, sql);
@@ -224,28 +259,6 @@ async function main() {
registerLifecycleRoutes(app, sql);
registerWebSocket(app, sql, broker);
// Serve static frontend (built web app). In production, the dist/ is
// copied to ../web relative to the dist/ directory at /app/web. In dev,
// check adjacent to the source.
const webRoot = resolve(__dirname, '../web');
if (existsSync(webRoot)) {
await app.register(fastifyStatic, {
root: webRoot,
prefix: '/',
// Don't intercept /api routes — static only serves files that exist.
wildcard: false,
});
// SPA fallback: serve index.html for non-API routes that don't match a file.
app.setNotFoundHandler(async (req, reply) => {
if (req.url.startsWith('/api')) {
reply.code(404);
return { error: 'not found' };
}
return reply.sendFile('index.html');
});
app.log.info(`serving frontend from ${webRoot}`);
}
// Graceful shutdown
const shutdown = async () => {
app.log.info('shutting down');

View File

@@ -0,0 +1,110 @@
import { describe, it, expect } from 'vitest';
import { resolveChatId } from '../chat-resolve.js';
import type { Sql } from '../../db.js';
// Mock the porsager/postgres surface that chat-resolve.ts uses: a tagged-template
// `tx` (dispatched by query substring), `tx.json`, and `sql.begin(fn)` which just
// runs fn(tx). Captures the value written back to workspace_panes so we can assert
// the WorkspaceState envelope survives the UPDATE.
interface MockState {
stored: unknown; // initial sessions.workspace_panes value
existingChatOpen: boolean; // whether `SELECT id FROM chats ...` finds the active chat
newChatId: string;
written?: unknown; // captured tx.json(...) payload from `UPDATE sessions`
inserted: boolean; // whether INSERT INTO chats ran
}
interface MockTx {
(strings: TemplateStringsArray): Promise<unknown>;
json: (v: unknown) => unknown;
}
function mockSql(state: MockState): Sql {
const tx = ((strings: TemplateStringsArray) => {
const q = strings.join('');
if (q.includes('SELECT workspace_panes FROM sessions')) {
return Promise.resolve([{ workspace_panes: state.stored }]);
}
if (q.includes('FROM chats')) {
return Promise.resolve(state.existingChatOpen ? [{ id: 'placeholder' }] : []);
}
if (q.includes('INSERT INTO chats')) {
state.inserted = true;
return Promise.resolve([{ id: state.newChatId }]);
}
if (q.includes('UPDATE sessions')) {
return Promise.resolve([]);
}
return Promise.resolve([]);
}) as unknown as MockTx;
tx.json = (v: unknown) => {
state.written = v;
return v;
};
const sql = {
begin: (fn: (t: Sql) => Promise<unknown>) => fn(tx as unknown as Sql),
};
return sql as unknown as Sql;
}
const ENVELOPE = () => ({
panes: [{ id: 'pane-1', kind: 'coder', chatIds: [] as string[], activeChatIdx: 0 }],
tabNumbers: { 'chat-x': 3 },
nextTabNumber: 7,
closedPaneStack: [{ kind: 'coder', chatIds: ['old'], activeChatIdx: 0 }],
});
describe('resolveChatId — v2.6.5 WorkspaceState envelope', () => {
it('reads panes from the envelope without crashing (regression: panes.findIndex is not a function)', async () => {
const state: MockState = {
stored: ENVELOPE(),
existingChatOpen: false,
newChatId: 'new-chat-1',
inserted: false,
};
const chatId = await resolveChatId(mockSql(state), 'session-1', 'pane-1');
expect(chatId).toBe('new-chat-1');
expect(state.inserted).toBe(true);
});
it('preserves the envelope (tabNumbers/nextTabNumber/closedPaneStack) on write-back', async () => {
const state: MockState = {
stored: ENVELOPE(),
existingChatOpen: false,
newChatId: 'new-chat-1',
inserted: false,
};
await resolveChatId(mockSql(state), 'session-1', 'pane-1');
const w = state.written as Record<string, unknown>;
expect(Array.isArray(w.panes)).toBe(true); // envelope, not a bare array
expect(w.tabNumbers).toEqual({ 'chat-x': 3 });
expect(w.nextTabNumber).toBe(7);
expect(w.closedPaneStack).toEqual([{ kind: 'coder', chatIds: ['old'], activeChatIdx: 0 }]);
});
it('returns the existing open chat when the pane already has one', async () => {
const env = ENVELOPE();
env.panes[0]!.chatIds = ['existing-1'];
const state: MockState = {
stored: env,
existingChatOpen: true,
newChatId: 'should-not-be-used',
inserted: false,
};
const chatId = await resolveChatId(mockSql(state), 'session-1', 'pane-1');
expect(chatId).toBe('existing-1');
expect(state.inserted).toBe(false);
});
it('still accepts a legacy bare WorkspacePane[] array', async () => {
const state: MockState = {
stored: [{ id: 'pane-1', kind: 'coder', chatId: 'legacy-1', chatIds: ['legacy-1'], activeChatIdx: 0 }],
existingChatOpen: true,
newChatId: 'should-not-be-used',
inserted: false,
};
const chatId = await resolveChatId(mockSql(state), 'session-1', 'pane-1');
expect(chatId).toBe('legacy-1');
expect(state.inserted).toBe(false);
});
});

View File

@@ -0,0 +1,138 @@
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import { readFileSync } from 'node:fs';
import { resolve } from 'node:path';
import Fastify, { type FastifyInstance } from 'fastify';
import postgres from 'postgres';
import { registerTaskRoutes } from '../tasks.js';
/**
* F1 — POST /api/tasks/:id/cancel route wiring.
*
* The route's job: reach the in-flight external run via `cancelExternal(taskId)`
* (the new abort hook), keep cancelling native inference for open chats unchanged,
* and land the task row in 'cancelled'. The streaming assistant message is
* finalized by the dispatcher's run-function, not here — that path is covered by
* finalize-message.test.ts. This suite pins the route's behavior against a real DB.
*/
describe.runIf(!!process.env.DATABASE_URL)('POST /api/tasks/:id/cancel (route, F1)', () => {
let sql: ReturnType<typeof postgres>;
let app: FastifyInstance;
let projectId: string;
let sessionId: string;
let chatId: string;
const externalCancelCalls: string[] = [];
const inferenceCancelCalls: Array<[string, string]> = [];
let externalReturns = true;
beforeAll(async () => {
sql = postgres(process.env.DATABASE_URL!, { max: 3 });
const serverSchema = resolve(__dirname, '../../../../server/src/schema.sql');
const coderSchema = resolve(__dirname, '../../schema.sql');
await sql.unsafe(readFileSync(serverSchema, 'utf8'));
await sql.unsafe(readFileSync(coderSchema, 'utf8'));
const [p] = await sql<{ id: string }[]>`
INSERT INTO projects (name, path, status) VALUES ('f1-cancel-route', '/tmp/f1-cancel-route', 'open') RETURNING id
`;
projectId = p!.id;
const [s] = await sql<{ id: string }[]>`
INSERT INTO sessions (project_id, name, model, status) VALUES (${projectId}, 'f1', 'm', 'open') RETURNING id
`;
sessionId = s!.id;
const [c] = await sql<{ id: string }[]>`
INSERT INTO chats (session_id, name, status) VALUES (${sessionId}, 'tab', 'open') RETURNING id
`;
chatId = c!.id;
app = Fastify();
registerTaskRoutes(
app,
sql,
{
cancel: async (sid: string, cid: string) => {
inferenceCancelCalls.push([sid, cid]);
return false;
},
},
(taskId: string) => {
externalCancelCalls.push(taskId);
return externalReturns;
},
);
await app.ready();
});
afterAll(async () => {
if (app) await app.close();
if (!sql) return;
await sql`DELETE FROM messages WHERE session_id = ${sessionId}`.catch(() => {});
await sql`DELETE FROM tasks WHERE project_id = ${projectId}`.catch(() => {});
await sql`DELETE FROM chats WHERE id = ${chatId}`.catch(() => {});
await sql`DELETE FROM sessions WHERE id = ${sessionId}`.catch(() => {});
await sql`DELETE FROM projects WHERE id = ${projectId}`.catch(() => {});
await sql.end({ timeout: 5 });
});
async function insertTask(agent: string | null, state: string): Promise<string> {
const [t] = await sql<{ id: string }[]>`
INSERT INTO tasks (project_id, input, agent, session_id, state, started_at)
VALUES (${projectId}, 'do a thing', ${agent}, ${sessionId}, ${state}, clock_timestamp())
RETURNING id
`;
return t!.id;
}
it('reaches cancelExternal and lands the task cancelled for a running external task', async () => {
externalReturns = true;
externalCancelCalls.length = 0;
const taskId = await insertTask('opencode', 'running');
const res = await app.inject({ method: 'POST', url: `/api/tasks/${taskId}/cancel` });
expect(res.statusCode).toBe(200);
expect(res.json()).toEqual({ cancelled: true });
expect(externalCancelCalls).toContain(taskId);
const [row] = await sql<{ state: string; ended_at: Date | null }[]>`
SELECT state, ended_at FROM tasks WHERE id = ${taskId}
`;
expect(row!.state).toBe('cancelled');
expect(row!.ended_at).not.toBeNull();
});
it('still cancels a native boocode task (cancelExternal returns false → inference.cancel path unchanged)', async () => {
externalReturns = false; // native task: no controller registered
externalCancelCalls.length = 0;
inferenceCancelCalls.length = 0;
const taskId = await insertTask(null, 'running');
const res = await app.inject({ method: 'POST', url: `/api/tasks/${taskId}/cancel` });
expect(res.statusCode).toBe(200);
// The route calls cancelExternal unconditionally (cheap, returns false here)...
expect(externalCancelCalls).toContain(taskId);
// ...and the native inference.cancel path still fires for the open chat.
expect(inferenceCancelCalls).toContainEqual([sessionId, chatId]);
const [row] = await sql<{ state: string }[]>`SELECT state FROM tasks WHERE id = ${taskId}`;
expect(row!.state).toBe('cancelled');
});
it('rejects cancelling an already-terminal task with 409 and never touches the abort hook', async () => {
externalCancelCalls.length = 0;
const taskId = await insertTask('opencode', 'completed');
const res = await app.inject({ method: 'POST', url: `/api/tasks/${taskId}/cancel` });
expect(res.statusCode).toBe(409);
expect(externalCancelCalls).not.toContain(taskId);
});
it('returns 404 for an unknown task', async () => {
const res = await app.inject({
method: 'POST',
url: `/api/tasks/00000000-0000-0000-0000-000000000000/cancel`,
});
expect(res.statusCode).toBe(404);
});
});

View File

@@ -16,6 +16,11 @@ export interface AgentSessionRow {
status: string;
has_session: boolean;
last_active_at: string | null;
// v2.6.8 per-(chat,agent) running token/cost totals (sampling-streamjson-tokens
// #8). BIGINT columns arrive as strings over the wire; the frontend coerces.
input_tokens: number;
output_tokens: number;
cost: number;
}
export function registerAgentSessionRoutes(app: FastifyInstance, sql: Sql): void {
@@ -39,7 +44,10 @@ export function registerAgentSessionRoutes(app: FastifyInstance, sql: Sql): void
a.agent AS agent,
a.status AS status,
(a.agent_session_id IS NOT NULL) AS has_session,
a.last_active_at AS last_active_at
a.last_active_at AS last_active_at,
a.input_tokens AS input_tokens,
a.output_tokens AS output_tokens,
a.cost AS cost
FROM agent_sessions a
JOIN chats c ON c.id = a.chat_id
WHERE c.session_id = ${sessionId}

View File

@@ -8,6 +8,36 @@ interface WorkspacePaneRow {
activeChatIdx?: number;
}
// v2.6.5: sessions.workspace_panes widened from a bare WorkspacePane[] to a
// WorkspaceState envelope { panes, tabNumbers, nextTabNumber, closedPaneStack }.
// (See the union validator in apps/server routes/sessions.ts + normalizeWorkspaceState
// in apps/server read_tab_by_number.ts — this is the coder-side mirror.)
interface WorkspaceStateRow {
panes: WorkspacePaneRow[];
tabNumbers: Record<string, number>;
nextTabNumber: number;
closedPaneStack: unknown[];
}
// MIGRATION: the stored value may be the legacy bare array OR the envelope.
// Normalize to a full envelope so callers always read `.panes` as an array and
// write the envelope back intact (preserving tabNumbers/nextTabNumber/closedPaneStack).
export function normalizeWorkspaceState(v: unknown): WorkspaceStateRow {
if (Array.isArray(v)) {
return { panes: v as WorkspacePaneRow[], tabNumbers: {}, nextTabNumber: 1, closedPaneStack: [] };
}
if (v && typeof v === 'object' && Array.isArray((v as { panes?: unknown }).panes)) {
const env = v as Partial<WorkspaceStateRow>;
return {
panes: env.panes ?? [],
tabNumbers: env.tabNumbers ?? {},
nextTabNumber: env.nextTabNumber ?? 1,
closedPaneStack: env.closedPaneStack ?? [],
};
}
return { panes: [], tabNumbers: {}, nextTabNumber: 1, closedPaneStack: [] };
}
function chatNameForKind(kind: string): string {
if (kind === 'coder' || kind === 'agent') return 'BooCoder';
if (kind === 'terminal') return 'Terminal';
@@ -28,12 +58,13 @@ export async function resolveChatId(
paneId: string,
): Promise<string | null> {
return sql.begin(async (tx) => {
const sessionRows = await tx<{ workspace_panes: WorkspacePaneRow[] }[]>`
const sessionRows = await tx<{ workspace_panes: unknown }[]>`
SELECT workspace_panes FROM sessions WHERE id = ${sessionId} FOR UPDATE
`;
if (sessionRows.length === 0) return null;
const panes = sessionRows[0]!.workspace_panes ?? [];
const state = normalizeWorkspaceState(sessionRows[0]!.workspace_panes);
const panes = state.panes;
const paneIdx = panes.findIndex((p) => p.id === paneId);
if (paneIdx < 0) return null;
@@ -69,9 +100,10 @@ export async function resolveChatId(
: p,
);
const nextState: WorkspaceStateRow = { ...state, panes: nextPanes };
await tx`
UPDATE sessions
SET workspace_panes = ${tx.json(nextPanes as never)},
SET workspace_panes = ${tx.json(nextState as never)},
updated_at = clock_timestamp()
WHERE id = ${sessionId}
`;

View File

@@ -0,0 +1,73 @@
/**
* write-edit-robustness #4 — checkpoint restore + list routes (coder side).
*
* Proxied through the apps/server `/api/coder/*` blanket forwarder (no server-side
* change needed for new routes). Restore rewinds the session worktree to the
* checkpoint's shadow commit, trims the transcript from the anchor message forward,
* and resets the agent backend — see services/checkpoints.ts.
*/
import type { FastifyInstance } from 'fastify';
import type { Sql } from '../db.js';
import { restoreCheckpoint, CheckpointNotFoundError } from '../services/checkpoints.js';
export function registerCheckpointRoutes(app: FastifyInstance, sql: Sql): void {
// GET /api/sessions/:sessionId/checkpoints?chat_id= — list a chat's checkpoints
// so the frontend can mark which messages have a restore point. When chat_id is
// omitted, returns every checkpoint for the session's chats.
app.get<{ Params: { sessionId: string }; Querystring: { chat_id?: string } }>(
'/api/sessions/:sessionId/checkpoints',
async (req, reply) => {
const sessionId = req.params.sessionId;
const chatId = req.query.chat_id;
const session = await sql<{ id: string }[]>`SELECT id FROM sessions WHERE id = ${sessionId}`;
if (session.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
// Scope authoritatively through chats.session_id (always set) — NOT the
// denormalized checkpoints.session_id (nullable). The chat_id branch must
// still be session-gated or it's an IDOR (any session's chat_id reads its
// checkpoints).
const rows = chatId
? await sql<{ id: string; chat_id: string; message_id: string | null; label: string | null; created_at: Date }[]>`
SELECT cp.id, cp.chat_id, cp.message_id, cp.label, cp.created_at
FROM checkpoints cp
JOIN chats c ON c.id = cp.chat_id
WHERE cp.chat_id = ${chatId} AND c.session_id = ${sessionId}
ORDER BY cp.created_at
`
: await sql<{ id: string; chat_id: string; message_id: string | null; label: string | null; created_at: Date }[]>`
SELECT cp.id, cp.chat_id, cp.message_id, cp.label, cp.created_at
FROM checkpoints cp
JOIN chats c ON c.id = cp.chat_id
WHERE c.session_id = ${sessionId}
ORDER BY cp.created_at
`;
return rows;
},
);
// POST /api/sessions/:sessionId/checkpoints/:checkpointId/restore — restore.
app.post<{ Params: { sessionId: string; checkpointId: string } }>(
'/api/sessions/:sessionId/checkpoints/:checkpointId/restore',
async (req, reply) => {
const { sessionId, checkpointId } = req.params;
try {
const result = await restoreCheckpoint(sql, checkpointId, {
sessionId,
log: app.log,
});
return result;
} catch (err) {
if (err instanceof CheckpointNotFoundError) {
reply.code(404);
return { error: err.message };
}
throw err;
}
},
);
}

View File

@@ -2,7 +2,7 @@ import type { FastifyInstance } from 'fastify';
import { z } from 'zod';
import type { Sql } from '../db.js';
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/server/ws-frames';
import type { WsFrame } from '@boocode/contracts/ws-frames';
import { resolveChatId } from './chat-resolve.js';
const AnswerUserInputBody = z.object({
@@ -53,6 +53,9 @@ interface MessageRow {
role: string;
content: string | null;
status: string | null;
model: string | null;
ctx_used: number | null;
ctx_max: number | null;
tool_calls: Array<{ id: string; name: string; args?: Record<string, unknown> }> | null;
tool_results: {
tool_call_id: string;
@@ -88,6 +91,9 @@ function mapCoderMessageRow(row: MessageRow) {
role: row.role as 'user' | 'assistant' | 'system',
content: row.content ?? '',
status: (row.status ?? 'complete') as 'streaming' | 'complete' | 'failed',
...(row.model ? { model: row.model } : {}),
...(row.ctx_used != null ? { ctx_used: row.ctx_used } : {}),
...(row.ctx_max != null ? { ctx_max: row.ctx_max } : {}),
...(reasoningText ? { reasoning_text: reasoningText } : {}),
...(tool_calls?.length ? { tool_calls } : {}),
};
@@ -126,13 +132,13 @@ export function registerMessageRoutes(
const rows = chatId
? await sql<MessageRow[]>`
SELECT id, role, content, status, tool_calls, tool_results, reasoning_parts
SELECT id, role, content, status, model, ctx_used, ctx_max, tool_calls, tool_results, reasoning_parts
FROM messages_with_parts
WHERE session_id = ${sessionId} AND chat_id = ${chatId}
ORDER BY created_at ASC, id ASC
`
: await sql<MessageRow[]>`
SELECT id, role, content, status, tool_calls, tool_results, reasoning_parts
SELECT id, role, content, status, model, ctx_used, ctx_max, tool_calls, tool_results, reasoning_parts
FROM messages_with_parts
WHERE session_id = ${sessionId}
ORDER BY created_at ASC, id ASC

View File

@@ -2,7 +2,7 @@ import type { FastifyInstance } from 'fastify';
import { z } from 'zod';
import type { Sql } from '../db.js';
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/server/ws-frames';
import type { WsFrame } from '@boocode/contracts/ws-frames';
import { getSkillBody } from '@boocode/server/skills';
import {
buildSkillInvokeSyntheticFrames,

View File

@@ -8,6 +8,12 @@ interface InferenceApi {
cancel: (sessionId: string, chatId: string) => Promise<boolean>;
}
// F1: the dispatcher's reach into an in-flight external-agent run. Narrow by
// design (not the whole dispatcher) — the route only needs to fire the abort.
// Returns true when a controller was registered for the task (an external run was
// in flight), false otherwise (native boocode task, or already finished).
export type ExternalCancelFn = (taskId: string) => boolean;
const CreateBody = z.object({
project_id: z.string().uuid(),
input: z.string().min(1).max(64_000),
@@ -27,7 +33,12 @@ const ListQuery = z.object({
project_id: z.string().uuid().optional(),
});
export function registerTaskRoutes(app: FastifyInstance, sql: Sql, inference: InferenceApi): void {
export function registerTaskRoutes(
app: FastifyInstance,
sql: Sql,
inference: InferenceApi,
cancelExternal: ExternalCancelFn,
): void {
// POST /api/tasks — create a new task
app.post('/api/tasks', async (req, reply) => {
const parsed = CreateBody.safeParse(req.body);
@@ -95,7 +106,7 @@ export function registerTaskRoutes(app: FastifyInstance, sql: Sql, inference: In
// GET /api/tasks/:id — single task detail
app.get<{ Params: { id: string } }>('/api/tasks/:id', async (req, reply) => {
const rows = await sql`
SELECT id, project_id, parent_task_id, state, input, output_summary, agent, model, execution_path, worktree_path, session_id, cost_tokens, started_at, ended_at, created_at
SELECT id, project_id, parent_task_id, state, input, output_summary, agent, model, execution_path, session_id, cost_tokens, started_at, ended_at, created_at
FROM tasks
WHERE id = ${req.params.id}
`;
@@ -127,7 +138,14 @@ export function registerTaskRoutes(app: FastifyInstance, sql: Sql, inference: In
cancelPendingPermission(taskId);
// If running, try to cancel inference
// F1: abort the in-flight external-agent run (opencode / goose / qwen / claude).
// Idempotent — a double-Stop re-aborts harmlessly; a native boocode task is not
// registered, so this returns false and the inference.cancel path below handles
// it unchanged. The dispatcher's run-function finalizes the streaming assistant
// message as 'cancelled' once the backend honors the signal.
cancelExternal(taskId);
// If running, try to cancel inference (native boocode path — unchanged).
if ((task.state === 'running' || task.state === 'blocked') && task.session_id) {
// Find active chat in the task's session
const chats = await sql<{ id: string }[]>`

View File

@@ -9,7 +9,7 @@
*/
import type { FastifyInstance } from 'fastify';
import type { Sql } from '../db.js';
import { checkWorktreeWorkAtRisk, stashWorktree } from '../services/worktrees.js';
import { checkWorktreeWorkAtRisk, stashWorktree } from '../services/worktree-risk.js';
export function registerWorktreeSafetyRoutes(app: FastifyInstance, sql: Sql): void {
// GET risk for a session's worktree(s). One row per session today (PK on

View File

@@ -25,7 +25,7 @@ export function registerWebSocket(
// Send snapshot of existing messages so client can hydrate
const messages = await sql<Record<string, unknown>[]>`
SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, reasoning_parts, status, last_seq,
SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, reasoning_parts, status, model, last_seq,
tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
summary, tail_start_id, compacted_at
FROM messages_with_parts

View File

@@ -25,7 +25,6 @@ CREATE TABLE IF NOT EXISTS tasks (
agent TEXT,
model TEXT,
execution_path TEXT,
worktree_path TEXT,
cost_tokens INTEGER,
started_at TIMESTAMPTZ,
ended_at TIMESTAMPTZ,
@@ -39,9 +38,9 @@ CREATE TABLE IF NOT EXISTS available_agents (
install_path TEXT,
version TEXT,
supports_acp BOOLEAN NOT NULL DEFAULT false,
supports_mcp_client BOOLEAN NOT NULL DEFAULT false,
last_probed_at TIMESTAMPTZ
);
ALTER TABLE available_agents DROP COLUMN IF EXISTS supports_mcp_client;
-- v2.0.0 Phase 4: link tasks to their inference sessions.
ALTER TABLE tasks ADD COLUMN IF NOT EXISTS session_id UUID REFERENCES sessions(id);
@@ -74,31 +73,16 @@ ALTER TABLE available_agents ADD COLUMN IF NOT EXISTS commands JSONB DEFAULT '[]
-- v2.2.0: Paseo-style session config on tasks.
ALTER TABLE tasks ADD COLUMN IF NOT EXISTS mode_id TEXT;
ALTER TABLE tasks ADD COLUMN IF NOT EXISTS thinking_option_id TEXT;
ALTER TABLE tasks ADD COLUMN IF NOT EXISTS feature_values JSONB;
-- v2.6: one shared worktree per session (all agents/panes in the session operate in it).
CREATE TABLE IF NOT EXISTS session_worktrees (
session_id UUID PRIMARY KEY REFERENCES sessions(id) ON DELETE CASCADE,
worktree_path TEXT NOT NULL,
base_commit TEXT,
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
);
-- P1.5-b: DEFANG the CASCADE — a session delete must no longer wipe its worktree
-- row. This table is SUPERSEDED by `worktrees` below; all readers are repointed
-- this phase, so the row just persists (dead) on session delete until a later
-- cleanup drops the table. session_id is this table's PRIMARY KEY, so it cannot be
-- nullable → SET NULL is invalid and NO ACTION/RESTRICT would block deletes; the
-- only valid defang is to drop the FK with no replacement. Idempotent: only fires
-- while the FK is still ON DELETE CASCADE ('c').
DO $$ BEGIN
IF EXISTS (
SELECT 1 FROM pg_constraint
WHERE conname = 'session_worktrees_session_id_fkey'
AND confdeltype = 'c'
) THEN
ALTER TABLE session_worktrees DROP CONSTRAINT session_worktrees_session_id_fkey;
END IF;
END $$;
-- tasks.feature_values and tasks.worktree_path were never read or written by any
-- code path; drop them from existing DBs (fresh DBs never had them in the CREATE).
-- human_inbox is `SELECT *` over tasks, so it pins every task column — dropping a
-- column while the view exists fails (2BP01). Drop the view, drop the columns, then
-- recreate it with the current column set (idempotent on fresh + existing DBs).
DROP VIEW IF EXISTS human_inbox;
ALTER TABLE tasks DROP COLUMN IF EXISTS feature_values;
ALTER TABLE tasks DROP COLUMN IF EXISTS worktree_path;
CREATE OR REPLACE VIEW human_inbox AS
SELECT * FROM tasks WHERE state IN ('blocked', 'failed');
-- v2.6: one backend session per (session, agent); resumed on switch-back.
CREATE TABLE IF NOT EXISTS agent_sessions (
@@ -168,12 +152,9 @@ CREATE TABLE IF NOT EXISTS worktrees (
);
CREATE UNIQUE INDEX IF NOT EXISTS worktrees_active_path_uidx ON worktrees(path) WHERE status='active';
-- Migrate any surviving session_worktrees rows → worktrees (idempotent; 0 rows
-- after the test-session delete, kept for generality / fresh-DB safety).
INSERT INTO worktrees (session_id, path, branch, base_commit, status)
SELECT sw.session_id, sw.worktree_path, 'session-' || sw.session_id, sw.base_commit, 'active'
FROM session_worktrees sw
WHERE NOT EXISTS (SELECT 1 FROM worktrees w WHERE w.session_id = sw.session_id AND w.status='active');
-- session_worktrees was superseded by worktrees (v2.6/P1.5-b); all rows migrated
-- before P2 cleanup. Drop the dead table; no-op on fresh DBs that never had it.
DROP TABLE IF EXISTS session_worktrees;
-- Dispatch hint: which chat (tab) a task belongs to. The coder message route and
-- skills route set it from the frontend tab; session-less creators (arena, MCP,
@@ -240,6 +221,55 @@ END $$;
-- v2.6: attribution for DiffPanel badges (Phase 1 UX reads this).
ALTER TABLE pending_changes ADD COLUMN IF NOT EXISTS agent TEXT;
-- write-edit-robustness #4: worktree checkpoints. A pre-turn shadow-commit of the
-- session worktree (tracked + untracked, captured without disturbing the real
-- index/working tree) stored in a private GC-safe ref refs/boocode/checkpoints/<id>.
-- Created best-effort before each external-agent turn (opencode / warm-ACP / one-shot
-- ACP+PTY); restore resets the worktree to commit_sha, trims the transcript from
-- message_id forward, and resets the backend session. chat_id CASCADEs from chats
-- (like agent_sessions); worktree_id SET NULL so a checkpoint outlives a reaped
-- worktree row. session_id / message_id are informational (no FK — message rows are
-- trimmed by a checkpoint restore and we must not block that on a dangling ref).
CREATE TABLE IF NOT EXISTS checkpoints (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
chat_id UUID NOT NULL REFERENCES chats(id) ON DELETE CASCADE,
session_id UUID,
worktree_id UUID REFERENCES worktrees(id) ON DELETE SET NULL,
message_id UUID, -- anchor: the assistant turn row this checkpoint precedes
commit_sha TEXT NOT NULL, -- shadow-commit capturing the pre-turn worktree tree
label TEXT,
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
);
CREATE INDEX IF NOT EXISTS checkpoints_chat_created_idx ON checkpoints(chat_id, created_at);
-- claude-sdk-sessionstore #9 (Part 1): append-only mirror of Claude Agent SDK
-- session transcripts. The SDK's SessionStore adapter writes one JSONL line per
-- entry; PostgresSessionStore (services/backends/claude-session-store.ts) inserts
-- one row per entry and replays them ORDER BY id on resume. The store is generic
-- per the SDK's SessionKey (project_key, session_id, subpath) — chat↔session
-- ownership lives in agent_sessions, not here. subpath '' is the main transcript
-- (the SDK's undefined subpath maps to '' in the column).
CREATE TABLE IF NOT EXISTS claude_session_entries (
id BIGSERIAL PRIMARY KEY,
project_key TEXT NOT NULL,
session_id TEXT NOT NULL,
subpath TEXT NOT NULL DEFAULT '', -- '' = main transcript (SDK's undefined subpath maps here)
entry JSONB NOT NULL,
created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
);
CREATE INDEX IF NOT EXISTS claude_session_entries_key_idx ON claude_session_entries (project_key, session_id, subpath, id);
-- claude-sdk-sessionstore #9 (Part 2): the warm Claude-SDK backend persists its
-- agent_sessions rows with backend='claude_sdk'. Widen the named CHECK to accept
-- it. Idempotent: DROP the named constraint (the inline CREATE TABLE check above
-- carries this explicit name, so DROP IF EXISTS targets it) + re-ADD the widened
-- list. Re-runs/fresh deploys land on the same final constraint (the table-level
-- CREATE already includes only the old two values on a fresh DB; this block then
-- replaces it with the three-value list).
ALTER TABLE agent_sessions DROP CONSTRAINT IF EXISTS agent_sessions_backend_chk;
ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_backend_chk
CHECK (backend IN ('opencode_server', 'acp_warm', 'claude_sdk'));
-- LISTEN/NOTIFY fast path: every tasks INSERT (from any call site — routes,
-- new_task tool, arena, MCP server) fires pg_notify('tasks_new') in the same
-- transaction, so the dispatcher reacts immediately instead of waiting for the

View File

@@ -0,0 +1,74 @@
import { describe, it, expect, vi } from 'vitest';
import type { RequestPermissionRequest, CreateElicitationRequest, SessionNotification } from '@agentclientprotocol/sdk';
import { buildAcpClient, type AcpTurnContext } from '../acp-client.js';
/**
* buildAcpClient (v2.7 audit reshape): the shared ACP `Client` closures. These
* tests cover the pure routing decisions that don't require the permission-waiter
* broker machinery — the auto-select/decline fallbacks and the between-turns drop.
*/
describe('buildAcpClient — sessionUpdate', () => {
it('drops the update when no turn is active (resolveTurn → null)', async () => {
const client = buildAcpClient('/wt', () => null);
// Must resolve without throwing and without an onSessionUpdate to call.
await expect(client.sessionUpdate({ sessionId: 's', update: {} } as unknown as SessionNotification)).resolves.toBeUndefined();
});
it('forwards the update to the active turn', async () => {
const onSessionUpdate = vi.fn();
const turn: AcpTurnContext = { taskId: 't', sessionId: 's', modeId: undefined, agent: 'goose', onSessionUpdate };
const client = buildAcpClient('/wt', () => turn);
const note = { sessionId: 's', update: {} } as unknown as SessionNotification;
await client.sessionUpdate(note);
expect(onSessionUpdate).toHaveBeenCalledWith(note);
});
});
describe('buildAcpClient — requestPermission fallback (no UI routing)', () => {
function req(options: Array<{ optionId: string }>): RequestPermissionRequest {
return { options } as unknown as RequestPermissionRequest;
}
it('auto-selects the first option when there is no turn', async () => {
const client = buildAcpClient('/wt', () => null);
const res = await client.requestPermission(req([{ optionId: 'allow' }, { optionId: 'deny' }]));
expect(res).toEqual({ outcome: { outcome: 'selected', optionId: 'allow' } });
});
it('cancels when there is no turn and no options', async () => {
const client = buildAcpClient('/wt', () => null);
const res = await client.requestPermission(req([]));
expect(res).toEqual({ outcome: { outcome: 'cancelled' } });
});
it('auto-selects when the turn has no taskId (UI routing gated off)', async () => {
const turn: AcpTurnContext = { taskId: undefined, sessionId: 's', modeId: undefined, agent: 'goose', onSessionUpdate: () => {} };
const client = buildAcpClient('/wt', () => turn);
const res = await client.requestPermission(req([{ optionId: 'ok' }]));
expect(res).toEqual({ outcome: { outcome: 'selected', optionId: 'ok' } });
});
});
describe('buildAcpClient — elicitation fallback', () => {
it('declines when there is no turn', async () => {
const client = buildAcpClient('/wt', () => null);
const res = await client.unstable_createElicitation!({} as CreateElicitationRequest);
expect(res).toEqual({ action: 'decline' });
});
it('declines when the turn has no taskId', async () => {
const turn: AcpTurnContext = { taskId: undefined, sessionId: 's', modeId: undefined, agent: 'goose', onSessionUpdate: () => {} };
const client = buildAcpClient('/wt', () => turn);
const res = await client.unstable_createElicitation!({} as CreateElicitationRequest);
expect(res).toEqual({ action: 'decline' });
});
});
describe('buildAcpClient — createTerminal', () => {
it('returns the noop terminal id', async () => {
const client = buildAcpClient('/wt', () => null);
const res = await client.createTerminal!({} as never);
expect(res).toEqual({ terminalId: 'noop' });
});
});

View File

@@ -0,0 +1,51 @@
import { describe, it, expect } from 'vitest';
import { createCancelRegistry } from '../cancel-registry.js';
/**
* F1 — per-task abort wiring. The registry is the missing link between the Stop
* route and the in-flight external run: register an AbortController per task id,
* cancel(taskId) aborts its signal, the run's .finally deletes it. Pure (no DB /
* child / IO) so the abort + idempotency contract is unit-testable in isolation.
*/
describe('CancelRegistry (F1 abort wiring)', () => {
it('register hands back a fresh controller; cancel aborts its signal', () => {
const reg = createCancelRegistry();
const ac = reg.register('t1');
expect(ac.signal.aborted).toBe(false);
expect(reg.has('t1')).toBe(true);
expect(reg.cancel('t1')).toBe(true);
expect(ac.signal.aborted).toBe(true);
});
it('cancel on an unknown task returns false (native task / cancel-before-register)', () => {
const reg = createCancelRegistry();
expect(reg.has('nope')).toBe(false);
expect(reg.cancel('nope')).toBe(false);
});
it('double-Stop is idempotent: a second cancel never throws and the signal stays aborted', () => {
const reg = createCancelRegistry();
const ac = reg.register('t1');
expect(reg.cancel('t1')).toBe(true);
// The run-function has not hit its .finally yet, so the entry is still
// present — a rapid second Stop re-aborts (abort() no-ops) without throwing.
expect(() => reg.cancel('t1')).not.toThrow();
expect(reg.cancel('t1')).toBe(true);
expect(ac.signal.aborted).toBe(true);
});
it('cancel after delete returns false (cancel-after-natural-exit is safe)', () => {
const reg = createCancelRegistry();
reg.register('t1');
reg.delete('t1');
expect(reg.has('t1')).toBe(false);
expect(reg.cancel('t1')).toBe(false);
});
it('delete of an unknown id is a no-op (never throws)', () => {
const reg = createCancelRegistry();
expect(() => reg.delete('ghost')).not.toThrow();
});
});

View File

@@ -0,0 +1,252 @@
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import { readFileSync } from 'node:fs';
import { rm, mkdir } from 'node:fs/promises';
import { resolve } from 'node:path';
import postgres from 'postgres';
import {
buildShadowCommitCommand,
createCheckpoint,
restoreCheckpoint,
CheckpointNotFoundError,
} from '../checkpoints.js';
import { ensureSessionWorktree } from '../worktrees.js';
import { hostExec } from '../host-exec.js';
/**
* write-edit-robustness #4 — worktree checkpoint tests.
*
* Pure-helper coverage (no DB / no host) for the shadow-commit command builder,
* plus a DB+git integration block (DB-opt-in via DATABASE_URL, skips cleanly
* otherwise; mirrors reconnect_integration.test.ts) that exercises the real
* create → restore round trip against a worktree on the host fs.
*/
describe('buildShadowCommitCommand (pure)', () => {
it('parks the commit under refs/boocode/checkpoints/<id> and prints only the SHA', () => {
const cmd = buildShadowCommitCommand('/tmp/booworktrees/sess-abc', 'cp-id-123');
// Uses a temp index so the real working tree/index is untouched.
expect(cmd).toContain('TMP=$(mktemp)');
expect(cmd).toContain('GIT_INDEX_FILE="$TMP" git read-tree HEAD');
expect(cmd).toContain('GIT_INDEX_FILE="$TMP" git add -A');
expect(cmd).toContain('git write-tree');
expect(cmd).toContain("git commit-tree \"$TREE\" -p HEAD -m \"boocode checkpoint\"");
// Ref name matches the row id, and stdout is ONLY the SHA (printf, no newline).
expect(cmd).toContain("update-ref 'refs/boocode/checkpoints/cp-id-123'");
expect(cmd).toContain("printf '%s' \"$SHA\"");
expect(cmd).not.toContain('echo "$SHA"');
});
it('shell-escapes the worktree path and the id', () => {
const cmd = buildShadowCommitCommand("/tmp/it's a path", "id'; rm -rf /");
// Single quotes inside the path/id are escaped via the '\'' wrapping idiom — no
// bare interpolation that could break out of the quoting.
expect(cmd).toContain("cd '/tmp/it'\\''s a path'");
expect(cmd).toContain("refs/boocode/checkpoints/id'\\''; rm -rf /");
});
});
describe.runIf(!!process.env.DATABASE_URL)('checkpoint create + restore (DB + git)', () => {
let sql: ReturnType<typeof postgres>;
const stamp = Date.now();
const projectDir = `/tmp/boocode-checkpoint-proj-${stamp}`;
let projectId: string;
let sessionId: string;
let chatId: string;
let worktreePath: string;
beforeAll(async () => {
sql = postgres(process.env.DATABASE_URL!, { max: 3 });
// Server schema first (FK targets), then coder schema (worktrees + checkpoints).
const serverSchema = resolve(__dirname, '../../../../server/src/schema.sql');
const coderSchema = resolve(__dirname, '../../schema.sql');
await sql.unsafe(readFileSync(serverSchema, 'utf8'));
await sql.unsafe(readFileSync(coderSchema, 'utf8'));
await mkdir(projectDir, { recursive: true });
await hostExec(
`cd ${projectDir} && git init -q && git config user.email t@t && git config user.name t ` +
`&& echo hello > README.md && git add -A && git commit -qm init`,
{ timeoutMs: 20_000 },
);
const [project] = await sql<{ id: string }[]>`
INSERT INTO projects (name, path, status) VALUES ('checkpoint-test', ${projectDir}, 'open') RETURNING id
`;
projectId = project!.id;
const [session] = await sql<{ id: string }[]>`
INSERT INTO sessions (project_id, name, model, status)
VALUES (${projectId}, 'cp', 'm', 'open') RETURNING id
`;
sessionId = session!.id;
const [chat] = await sql<{ id: string }[]>`
INSERT INTO chats (session_id, name, status) VALUES (${sessionId}, 'tab', 'open') RETURNING id
`;
chatId = chat!.id;
const wt = await ensureSessionWorktree(sql, projectDir, sessionId);
worktreePath = wt.worktreePath;
});
afterAll(async () => {
if (sql) {
const rows = await sql<{ path: string }[]>`SELECT path FROM worktrees WHERE session_id = ${sessionId}`.catch(() => []);
for (const r of rows) {
await hostExec(`git -C ${projectDir} worktree remove ${r.path} --force`, { timeoutMs: 10_000 }).catch(() => {});
}
await sql`DELETE FROM checkpoints WHERE chat_id = ${chatId}`.catch(() => {});
await sql`DELETE FROM agent_sessions WHERE chat_id = ${chatId}`.catch(() => {});
await sql`DELETE FROM worktrees WHERE session_id = ${sessionId}`.catch(() => {});
await sql`DELETE FROM chats WHERE id = ${chatId}`.catch(() => {});
await sql`DELETE FROM sessions WHERE id = ${sessionId}`.catch(() => {});
await sql`DELETE FROM projects WHERE id = ${projectId}`.catch(() => {});
await sql.end({ timeout: 5 });
}
await rm(projectDir, { recursive: true, force: true });
});
it('createCheckpoint inserts a row + a private ref capturing tracked + untracked', async () => {
const [wt] = await sql<{ id: string }[]>`SELECT id FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'`;
const worktreeId = wt!.id;
// Pre-turn untracked + tracked-edit state the agent will start from.
await hostExec(`cd ${worktreePath} && echo edited >> README.md && echo new > extra.txt`, { timeoutMs: 10_000 });
const [assistantMsg] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming') RETURNING id
`;
const messageId = assistantMsg!.id;
const cp = await createCheckpoint(sql, {
chatId,
sessionId,
worktreeId,
worktreePath,
messageId,
});
expect(cp).not.toBeNull();
expect(cp!.commit_sha).toMatch(/^[0-9a-f]{40}$/);
const [row] = await sql<{ commit_sha: string; worktree_id: string; message_id: string }[]>`
SELECT commit_sha, worktree_id, message_id FROM checkpoints WHERE id = ${cp!.id}
`;
expect(row!.commit_sha).toBe(cp!.commit_sha);
expect(row!.worktree_id).toBe(worktreeId);
expect(row!.message_id).toBe(messageId);
// The ref exists and the captured tree carries the untracked file (proves the
// temp-index `git add -A` snapshotted untracked content).
const refLs = await hostExec(
`git -C ${worktreePath} ls-tree -r --name-only ${cp!.commit_sha}`,
{ timeoutMs: 10_000 },
);
expect(refLs.exitCode).toBe(0);
expect(refLs.stdout).toContain('extra.txt');
// The shadow commit did NOT disturb the real working tree: extra.txt is still
// present + still untracked (status shows it).
const status = await hostExec(`git -C ${worktreePath} status --porcelain`, { timeoutMs: 10_000 });
expect(status.stdout).toContain('extra.txt');
});
it('restoreCheckpoint resets the worktree, trims the transcript, and drops later checkpoints', async () => {
// Clean slate for this test: reset the worktree to HEAD, clear prior rows.
await hostExec(`git -C ${worktreePath} reset --hard HEAD && git -C ${worktreePath} clean -fd`, { timeoutMs: 10_000 });
await sql`DELETE FROM checkpoints WHERE chat_id = ${chatId}`;
await sql`DELETE FROM messages WHERE chat_id = ${chatId}`;
const [wt] = await sql<{ id: string }[]>`SELECT id FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'`;
const worktreeId = wt!.id;
// Turn 1: a user msg, then the assistant turn the checkpoint anchors. The
// worktree is pristine (matches HEAD) when this checkpoint is captured.
await sql`INSERT INTO messages (session_id, chat_id, role, content, status) VALUES (${sessionId}, ${chatId}, 'user', 'do it', 'complete')`;
const [a1] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status)
VALUES (${sessionId}, ${chatId}, 'assistant', 'turn 1', 'complete') RETURNING id
`;
const cp1 = await createCheckpoint(sql, { chatId, sessionId, worktreeId, worktreePath, messageId: a1!.id });
expect(cp1).not.toBeNull();
// The agent (turn 1) writes a file into the worktree.
await hostExec(`cd ${worktreePath} && echo agent-wrote > agent.txt`, { timeoutMs: 10_000 });
// Turn 2: another user msg + assistant turn, AND a second (later) checkpoint.
await sql`INSERT INTO messages (session_id, chat_id, role, content, status) VALUES (${sessionId}, ${chatId}, 'user', 'more', 'complete')`;
const [a2] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status)
VALUES (${sessionId}, ${chatId}, 'assistant', 'turn 2', 'complete') RETURNING id
`;
const cp2 = await createCheckpoint(sql, { chatId, sessionId, worktreeId, worktreePath, messageId: a2!.id });
expect(cp2).not.toBeNull();
// An agent_sessions row that restore should mark 'crashed'.
await sql`
INSERT INTO agent_sessions (chat_id, session_id, worktree_id, agent, backend, agent_session_id, status, last_active_at)
VALUES (${chatId}, ${sessionId}, ${worktreeId}, 'goose', 'acp_warm', 'sess-1', 'active', clock_timestamp())
ON CONFLICT (chat_id, agent) DO UPDATE SET status = 'active'
`;
const before = await sql<{ id: string }[]>`SELECT id FROM messages WHERE chat_id = ${chatId} ORDER BY created_at`;
expect(before.length).toBe(4); // user, a1, user, a2
// Restore to cp1 (before turn 1's assistant message).
const result = await restoreCheckpoint(sql, cp1!.id, { sessionId });
expect(result.checkpoint_id).toBe(cp1!.id);
expect(result.worktree_reset).toBe(true);
expect(result.backend_reset).toBe(true);
// a1, user(turn2), a2 deleted (created_at >= a1) → 3 trimmed.
expect(result.messages_deleted).toBe(3);
// Transcript trimmed to just the first user message.
const after = await sql<{ role: string; content: string }[]>`SELECT role, content FROM messages WHERE chat_id = ${chatId} ORDER BY created_at`;
expect(after.length).toBe(1);
expect(after[0]!.role).toBe('user');
// Worktree reset: the agent's file is gone (it was written after cp1).
const ls = await hostExec(`ls ${worktreePath}/agent.txt`, { timeoutMs: 10_000 });
expect(ls.exitCode).not.toBe(0);
// The agent_sessions row was reset to 'crashed'.
const [as] = await sql<{ status: string }[]>`SELECT status FROM agent_sessions WHERE chat_id = ${chatId} AND agent = 'goose'`;
expect(as!.status).toBe('crashed');
// cp1 survives (re-restorable); cp2 (later) was dropped.
const cps = await sql<{ id: string }[]>`SELECT id FROM checkpoints WHERE chat_id = ${chatId}`;
expect(cps.map((c) => c.id)).toEqual([cp1!.id]);
});
it('restoreCheckpoint throws CheckpointNotFoundError for an unknown id', async () => {
await expect(
restoreCheckpoint(sql, '00000000-0000-0000-0000-000000000000', { sessionId }),
).rejects.toBeInstanceOf(CheckpointNotFoundError);
});
it('restoreCheckpoint throws when the checkpoint is not in the requested session', async () => {
// A checkpoint whose session_id differs from the route's sessionId.
const [wt] = await sql<{ id: string }[]>`SELECT id FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'`;
const cp = await createCheckpoint(sql, { chatId, sessionId, worktreeId: wt!.id, worktreePath, messageId: null });
expect(cp).not.toBeNull();
await expect(
restoreCheckpoint(sql, cp!.id, { sessionId: '11111111-1111-1111-1111-111111111111' }),
).rejects.toBeInstanceOf(CheckpointNotFoundError);
await sql`DELETE FROM checkpoints WHERE id = ${cp!.id}`;
});
it('restoreCheckpoint denies a NULL-session_id checkpoint from another session (no fail-open IDOR)', async () => {
// Regression for the fail-open authorization bug: a checkpoint row whose
// denormalized session_id is NULL must STILL be scoped via its chat's owning
// session (chats.session_id), not skipped. The old guard `cp.session_id &&
// cp.session_id !== sessionId` fell through on NULL → cross-session restore.
const [row] = await sql<{ id: string }[]>`
INSERT INTO checkpoints (chat_id, session_id, message_id, commit_sha)
VALUES (${chatId}, NULL, NULL, 'deadbeef')
RETURNING id
`;
await expect(
restoreCheckpoint(sql, row!.id, { sessionId: '22222222-2222-2222-2222-222222222222' }),
).rejects.toBeInstanceOf(CheckpointNotFoundError);
await sql`DELETE FROM checkpoints WHERE id = ${row!.id}`;
});
});

View File

@@ -0,0 +1,163 @@
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import { readFileSync } from 'node:fs';
import { resolve } from 'node:path';
import postgres from 'postgres';
import type { WsFrame } from '@boocode/contracts/ws-frames';
import { classifyTerminalStatus, finalizeStreamingMessage } from '../finalize-message.js';
/**
* F1 (D-7 / OCE-001 / OCE-002) — finalizing a Stop'd or errored external turn.
*
* `classifyTerminalStatus` is the pure D-7 decision (user Stop / AbortError →
* cancelled, genuine error → failed). `finalizeStreamingMessage` writes that
* terminal state onto the streaming assistant row and publishes the matching
* message_complete frame — idempotently, guarded by `WHERE status='streaming'`,
* so a double-Stop or an abort-then-catch settles the message exactly once and
* never clobbers a row that already finished cleanly.
*/
describe('classifyTerminalStatus (pure, D-7)', () => {
it('maps a fired abort signal to cancelled (user Stop)', () => {
expect(classifyTerminalStatus({ aborted: true })).toBe('cancelled');
});
it('maps a thrown AbortError to cancelled', () => {
const e = new Error('the operation was aborted');
e.name = 'AbortError';
expect(classifyTerminalStatus({ aborted: false, error: e })).toBe('cancelled');
});
it('maps a genuine thrown error to failed', () => {
expect(classifyTerminalStatus({ aborted: false, error: new Error('boom') })).toBe('failed');
});
it('defaults a no-abort / no-error catch to failed', () => {
expect(classifyTerminalStatus({ aborted: false })).toBe('failed');
});
});
describe.runIf(!!process.env.DATABASE_URL)('finalizeStreamingMessage (DB)', () => {
let sql: ReturnType<typeof postgres>;
let projectId: string;
let sessionId: string;
let chatId: string;
beforeAll(async () => {
sql = postgres(process.env.DATABASE_URL!, { max: 3 });
// Server schema owns messages/sessions/chats (FK targets); coder schema after.
const serverSchema = resolve(__dirname, '../../../../server/src/schema.sql');
const coderSchema = resolve(__dirname, '../../schema.sql');
await sql.unsafe(readFileSync(serverSchema, 'utf8'));
await sql.unsafe(readFileSync(coderSchema, 'utf8'));
const [p] = await sql<{ id: string }[]>`
INSERT INTO projects (name, path, status) VALUES ('f1-finalize', '/tmp/f1-finalize', 'open') RETURNING id
`;
projectId = p!.id;
const [s] = await sql<{ id: string }[]>`
INSERT INTO sessions (project_id, name, model, status) VALUES (${projectId}, 'f1', 'm', 'open') RETURNING id
`;
sessionId = s!.id;
const [c] = await sql<{ id: string }[]>`
INSERT INTO chats (session_id, name, status) VALUES (${sessionId}, 'tab', 'open') RETURNING id
`;
chatId = c!.id;
});
afterAll(async () => {
if (!sql) return;
await sql`DELETE FROM messages WHERE session_id = ${sessionId}`.catch(() => {});
await sql`DELETE FROM chats WHERE id = ${chatId}`.catch(() => {});
await sql`DELETE FROM sessions WHERE id = ${sessionId}`.catch(() => {});
await sql`DELETE FROM projects WHERE id = ${projectId}`.catch(() => {});
await sql.end({ timeout: 5 });
});
async function insertStreaming(): Promise<string> {
const [m] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming') RETURNING id
`;
return m!.id;
}
it('finalizes a streaming row to cancelled, persists partial content, publishes one frame', async () => {
const id = await insertStreaming();
const frames: WsFrame[] = [];
const did = await finalizeStreamingMessage(sql, (_s, f) => frames.push(f), {
sessionId,
chatId,
assistantId: id,
status: 'cancelled',
model: 'qwen',
content: 'partial answer',
});
expect(did).toBe(true);
const [row] = await sql<{ status: string; content: string; finished_at: Date | null }[]>`
SELECT status, content, finished_at FROM messages WHERE id = ${id}
`;
expect(row!.status).toBe('cancelled');
expect(row!.content).toBe('partial answer');
expect(row!.finished_at).not.toBeNull();
expect(frames).toHaveLength(1);
expect(frames[0]!.type).toBe('message_complete');
expect((frames[0] as { status?: string }).status).toBe('cancelled');
});
it('is idempotent for a double-Stop: second call updates nothing and re-publishes nothing', async () => {
const id = await insertStreaming();
const frames: WsFrame[] = [];
const push = (_s: string, f: WsFrame): void => {
frames.push(f);
};
expect(
await finalizeStreamingMessage(sql, push, { sessionId, chatId, assistantId: id, status: 'cancelled', model: null }),
).toBe(true);
expect(
await finalizeStreamingMessage(sql, push, { sessionId, chatId, assistantId: id, status: 'cancelled', model: null }),
).toBe(false);
expect(frames).toHaveLength(1);
const [row] = await sql<{ status: string }[]>`SELECT status FROM messages WHERE id = ${id}`;
expect(row!.status).toBe('cancelled');
});
it('never clobbers a row that already finished cleanly (abort raced a clean finish)', async () => {
const [m] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status)
VALUES (${sessionId}, ${chatId}, 'assistant', 'done', 'complete') RETURNING id
`;
const id = m!.id;
const frames: WsFrame[] = [];
const did = await finalizeStreamingMessage(sql, (_s, f) => frames.push(f), {
sessionId,
chatId,
assistantId: id,
status: 'cancelled',
model: null,
});
expect(did).toBe(false);
expect(frames).toHaveLength(0);
const [row] = await sql<{ status: string; content: string }[]>`
SELECT status, content FROM messages WHERE id = ${id}
`;
expect(row!.status).toBe('complete');
expect(row!.content).toBe('done');
});
it('no-ops on an empty assistantId (throw happened before the row was created)', async () => {
const frames: WsFrame[] = [];
const did = await finalizeStreamingMessage(sql, (_s, f) => frames.push(f), {
sessionId,
chatId,
assistantId: '',
status: 'failed',
model: null,
});
expect(did).toBe(false);
expect(frames).toHaveLength(0);
});
});

View File

@@ -0,0 +1,102 @@
import { describe, it, expect } from 'vitest';
import type { Broker } from '@boocode/server/broker';
import { makeFrameEmitter } from '../frame-emitter.js';
import { makeDcpStreamStripper } from '../dcp-strip.js';
import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
/**
* makeFrameEmitter (v2.7 audit reshape): the AgentEvent → WS-frame mapping + turn
* accumulators extracted from AcpStreamContext. Pure-ish over an injected broker.
*/
function fakeBroker(): { broker: Broker; frames: Array<{ sid: string; frame: Record<string, unknown> }> } {
const frames: Array<{ sid: string; frame: Record<string, unknown> }> = [];
const broker = {
publishFrame: (sid: string, frame: unknown) => {
frames.push({ sid, frame: frame as Record<string, unknown> });
},
} as unknown as Broker;
return { broker, frames };
}
const toolSnap: AcpToolSnapshot = { toolCallId: 'c1', title: 'grep', status: 'completed', rawOutput: 'x' };
describe('makeFrameEmitter — streaming frames', () => {
it('maps text/reasoning/tool events to delta/reasoning_delta/tool_call frames', () => {
const { broker, frames } = fakeBroker();
const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
em.onEvent({ type: 'text', text: 'hello ' });
em.onEvent({ type: 'reasoning', text: 'mulling' });
em.onEvent({ type: 'tool_call', toolCall: toolSnap });
expect(frames.map((f) => f.frame.type)).toEqual(['delta', 'reasoning_delta', 'tool_call']);
expect(frames[0]!.frame).toMatchObject({ message_id: 'm1', chat_id: 'ch1', content: 'hello ' });
expect(frames[2]!.frame).toMatchObject({ message_id: 'm1', chat_id: 'ch1' });
expect(em.output).toBe('hello ');
expect(em.reasoningText).toBe('mulling');
expect(em.snapshots).toHaveLength(1);
});
it('publishes a tool_call frame for BOTH tool_call and tool_update events', () => {
const { broker, frames } = fakeBroker();
const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
em.onEvent({ type: 'tool_update', toolCall: toolSnap });
expect(frames).toHaveLength(1);
expect(frames[0]!.frame.type).toBe('tool_call');
});
it('publishes an agent_commands frame and merges the command cache', () => {
const { broker, frames } = fakeBroker();
const taskId = `task-fe-${Math.floor(performance.now())}-${frames.length}`;
const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1', taskId });
em.onEvent({ type: 'commands', commands: [{ name: 'plan' }] });
expect(frames).toHaveLength(1);
expect(frames[0]!.frame).toMatchObject({ type: 'agent_commands', task_id: taskId, session_id: 's1' });
});
it('does not publish a commands frame without a taskId', () => {
const { broker, frames } = fakeBroker();
const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
em.onEvent({ type: 'commands', commands: [{ name: 'plan' }] });
expect(frames).toHaveLength(0);
});
});
describe('makeFrameEmitter — no broker (one-shot accumulation)', () => {
it('accumulates output/reasoning/snapshots but publishes nothing', () => {
const em = makeFrameEmitter({ sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
em.onEvent({ type: 'text', text: 'abc' });
em.onEvent({ type: 'reasoning', text: 'r' });
em.onEvent({ type: 'tool_call', toolCall: toolSnap });
expect(em.output).toBe('abc');
expect(em.reasoningText).toBe('r');
expect(em.snapshots).toHaveLength(1);
});
});
describe('makeFrameEmitter — dcp stripping (opencode path contract)', () => {
it('strips a split dcp tag across deltas and flushes the tail on finalize', () => {
const { broker, frames } = fakeBroker();
const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1', dcp: makeDcpStreamStripper() });
for (const chunk of ['Answer.', '<dcp', '-message', '-id>m1</dcp', '-message-id>', ' tail']) {
em.onEvent({ type: 'text', text: chunk });
}
em.finalize();
expect(em.output).toBe('Answer. tail');
const published = frames.filter((f) => f.frame.type === 'delta').map((f) => f.frame.content).join('');
expect(published).toBe('Answer. tail');
});
it('finalize is a no-op without a dcp stripper', () => {
const { broker, frames } = fakeBroker();
const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
em.onEvent({ type: 'text', text: 'raw <dcp-message-id>m</dcp-message-id>' });
em.finalize();
// No stripping without a stripper — verbatim text (prior ACP-path behavior).
expect(em.output).toBe('raw <dcp-message-id>m</dcp-message-id>');
expect(frames).toHaveLength(1);
});
});

View File

@@ -0,0 +1,173 @@
import { describe, it, expect } from 'vitest';
import { locateMatch, SIMILARITY_THRESHOLD } from '../fuzzy-match.js';
// Helper: assert a resolved span and slice it back out of the content so the
// test pins the EXACT file text the caller would replace.
function span(result: ReturnType<typeof locateMatch>): { start: number; end: number } {
if (result.kind !== 'exact' && result.kind !== 'fuzzy') {
throw new Error(`expected a located span, got ${result.kind}`);
}
return { start: result.start, end: result.end };
}
describe('locateMatch — strategy 1: exact', () => {
it('returns an exact unique span', () => {
const content = 'alpha\nbeta\ngamma\n';
const result = locateMatch(content, 'beta');
expect(result.kind).toBe('exact');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe('beta');
});
it('returns the right offsets for a multi-line exact needle', () => {
const content = 'one\ntwo\nthree\nfour\n';
const needle = 'two\nthree';
const result = locateMatch(content, needle);
expect(result.kind).toBe('exact');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe(needle);
});
it('refuses when the exact needle occurs more than once', () => {
const content = 'foo\nbar\nfoo\nbar\nfoo\n';
const result = locateMatch(content, 'foo');
expect(result).toEqual({ kind: 'ambiguous', count: 3 });
});
});
describe('locateMatch — strategy 2: per-line whitespace', () => {
it('matches across trailing-whitespace drift at the real span', () => {
// File has trailing spaces the model dropped from a TWO-line copy. A
// single-line needle would be located by exact indexOf (it's a substring),
// so use two lines where line 1's trailing ws breaks an exact substring run.
const content = 'function f() {\n setup(); \n return 1;\n}\n';
const needle = ' setup();\n return 1;'; // line 1 missing trailing spaces
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
// The returned span covers the ORIGINAL lines including the trailing spaces.
expect(content.slice(start, end)).toBe(' setup(); \n return 1;');
});
it('matches across indentation drift (multi-line block)', () => {
// File indents with 4 spaces; model emitted 2-space indentation. trimEnd
// alone does not normalize LEADING whitespace, so this exercises... actually
// leading-indent drift is a Levenshtein-tier fallback. Here we keep the
// leading indent identical and drift only trailing whitespace per line.
const content = ['if (x) {', ' doThing(); ', ' doOther();', '}'].join('\n');
const needle = [' doThing();', ' doOther();'].join('\n');
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe(' doThing(); \n doOther();');
});
it('ignores leading/trailing blank needle lines', () => {
const content = 'header\nbody line\nfooter\n';
const needle = '\n\nbody line\n\n';
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe('body line');
});
it('reports ambiguous when a whitespace-window matches twice', () => {
// Both line 1 and line 4 differ from the needle only by trailing whitespace,
// so exact indexOf fails (no exact substring) and the whitespace tier finds
// two equivalent windows → ambiguous.
const content = 'x = 1; \ny = 2;\nz = 3;\nx = 1;\t\n';
const needle = 'x = 1;'; // no trailing ws → not an exact substring of either line
const result = locateMatch(content, needle);
expect(result).toEqual({ kind: 'ambiguous', count: 2 });
});
});
describe('locateMatch — strategy 3: unicode canonicalization', () => {
it('matches across curly quotes', () => {
const content = "const s = 'hello';\n";
const needle = 'const s = hello;'; // hello
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
// Span maps back to ORIGINAL (straight-quote) text.
expect(content.slice(start, end)).toBe("const s = 'hello';");
});
it('matches across curly double-quotes', () => {
const content = 'log("done");\n';
const needle = 'log(“done”);'; // “done”
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe('log("done");');
});
it('matches across an em-dash drift', () => {
const content = 'range 1-10 inclusive\n';
const needle = 'range 1—10 inclusive'; // em-dash
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe('range 1-10 inclusive');
});
it('matches across a non-breaking space drift', () => {
const content = 'a b c\n'; // plain spaces
const needle = 'a b c'; // nbsp between words
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe('a b c');
});
});
describe('locateMatch — strategy 4: Levenshtein', () => {
it('matches a >= threshold near-miss (small typo drift)', () => {
// Needle has a one-char typo ('totals' vs 'total') so it is NOT an exact
// substring and the whitespace/canonical tiers (which require equality) both
// miss; Levenshtein similarity stays well above the 0.66 floor.
const content = 'const total = sum + tax;\n';
const needle = 'const totals = sum + tax;';
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
// Span maps to the real (correctly-spelled) file line.
expect(content.slice(start, end)).toBe('const total = sum + tax;');
});
it('matches a multi-line block with indentation drift via Levenshtein', () => {
const content = ['function g() {', ' return compute(a, b);', '}'].join('\n');
// 6-space indent vs file's 2-space; trimEnd does not fix leading indent, so
// this lands on the Levenshtein tier (joined-trim makes it identical → ~1.0).
const needle = [' return compute(a, b);'].join('\n');
const result = locateMatch(content, needle);
expect(result.kind).toBe('fuzzy');
const { start, end } = span(result);
expect(content.slice(start, end)).toBe(' return compute(a, b);');
});
it('returns not_found for a below-threshold miss', () => {
const content = 'the quick brown fox jumps over the lazy dog\n';
const needle = 'completely unrelated string of text here xyz';
const result = locateMatch(content, needle);
expect(result).toEqual({ kind: 'not_found' });
});
it('returns not_found for a genuinely-absent needle', () => {
const content = 'alpha\nbeta\ngamma\n';
const needle = 'this content does not exist anywhere at all';
const result = locateMatch(content, needle);
expect(result).toEqual({ kind: 'not_found' });
});
});
describe('locateMatch — edge cases', () => {
it('returns not_found for an empty needle', () => {
expect(locateMatch('anything', '')).toEqual({ kind: 'not_found' });
});
it('exposes a sane similarity threshold', () => {
expect(SIMILARITY_THRESHOLD).toBeGreaterThan(0);
expect(SIMILARITY_THRESHOLD).toBeLessThanOrEqual(1);
});
});

View File

@@ -1,64 +0,0 @@
import { describe, it, expect } from 'vitest';
import { readFileSync } from 'node:fs';
import { resolve, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
/**
* Parity guard between the two copies of the provider snapshot types:
* apps/coder/src/services/provider-types.ts (backend source of truth)
* apps/web/src/api/types.ts (web wire copy)
*
* APPROACH: text-identity of each shared type block (mirrors the repo's existing
* ws-frames.test.ts byte-parity convention). A compile-time bidirectional-
* assignability check was attempted first (a web-side file importing coder's
* import-free provider-types.ts), but apps/web/tsconfig.app.json is a composite
* project and rejects out-of-include files with TS6307 — so cross-project type
* import is structurally blocked. This runtime guard FAILS on any field
* add/remove/rename/loosen in either copy, including the nested model/mode/
* command types that ProviderSnapshotEntry references. Single-source-of-truth
* (shared workspace package) is deferred as a Tier-2 follow-up.
*/
const here = dirname(fileURLToPath(import.meta.url));
const coderSrc = readFileSync(resolve(here, '../provider-types.ts'), 'utf8');
const webSrc = readFileSync(resolve(here, '../../../../web/src/api/types.ts'), 'utf8');
function extractBlock(src: string, name: string): string {
const iface = src.match(new RegExp(`export interface ${name} \\{[\\s\\S]*?\\n\\}`));
const alias = src.match(new RegExp(`export type ${name} =[^;]*;`));
const block = iface?.[0] ?? alias?.[0];
if (!block) throw new Error(`type block '${name}' not found`);
// Normalize to type structure: drop blank + comment lines (//, /* */, *),
// trim each line. Field add/remove/rename/loosen still changes a field line.
return block
.split('\n')
.map((l) => l.trim())
.filter(
(l) =>
l.length > 0 &&
!l.startsWith('//') &&
!l.startsWith('/*') &&
!l.startsWith('*'),
)
.join('\n');
}
describe('provider snapshot type parity (coder ↔ web)', () => {
// Includes the nested types ProviderSnapshotEntry references, so structural
// drift anywhere in the snapshot surface is caught.
const names = [
'ProviderSnapshotStatus',
'ProviderSnapshotEntry',
'ProviderModel',
'ProviderMode',
'ThinkingOption',
'AgentCommand',
];
for (const name of names) {
it(`${name} is identical in both copies`, () => {
expect(
extractBlock(webSrc, name),
`${name} drifted between apps/coder/src/services/provider-types.ts and apps/web/src/api/types.ts`,
).toBe(extractBlock(coderSrc, name));
});
}
});

View File

@@ -0,0 +1,189 @@
import { describe, it, expect } from 'vitest';
import {
makeStreamJsonParser,
makeStreamJsonState,
parseStreamJsonLine,
type AgentEventList,
} from '../stream-json-parser.js';
import type { AgentEvent } from '../agent-backend.js';
import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
// Helpers to JSON-encode the representative Claude-Code stream-json lines.
const sys = (sessionId: string) =>
JSON.stringify({ type: 'system', subtype: 'init', session_id: sessionId, tools: ['read', 'edit'] });
const streamEvent = (event: unknown) => JSON.stringify({ type: 'stream_event', event });
const textDelta = (index: number, text: string) =>
streamEvent({ type: 'content_block_delta', index, delta: { type: 'text_delta', text } });
const thinkingDelta = (index: number, thinking: string) =>
streamEvent({ type: 'content_block_delta', index, delta: { type: 'thinking_delta', thinking } });
const toolStart = (index: number, id: string, name: string) =>
streamEvent({ type: 'content_block_start', index, content_block: { type: 'tool_use', id, name } });
const inputJsonDelta = (index: number, partial: string) =>
streamEvent({ type: 'content_block_delta', index, delta: { type: 'input_json_delta', partial_json: partial } });
const blockStop = (index: number) => streamEvent({ type: 'content_block_stop', index });
const resultLine = (input: number, output: number, sessionId?: string) =>
JSON.stringify({ type: 'result', subtype: 'success', session_id: sessionId, usage: { input_tokens: input, output_tokens: output } });
describe('parseStreamJsonLine (pure per-line mapping)', () => {
it('captures session_id from the system init line and emits no events', () => {
const state = makeStreamJsonState();
const events = parseStreamJsonLine(sys('sess-abc'), state);
expect(events).toEqual([]);
expect(state.sessionId).toBe('sess-abc');
});
it('maps a text_delta stream_event → a text event', () => {
const state = makeStreamJsonState();
expect(parseStreamJsonLine(textDelta(0, 'Hello'), state)).toEqual([{ type: 'text', text: 'Hello' }]);
});
it('maps a thinking_delta stream_event → a reasoning event', () => {
const state = makeStreamJsonState();
expect(parseStreamJsonLine(thinkingDelta(0, 'pondering'), state)).toEqual([
{ type: 'reasoning', text: 'pondering' },
]);
});
it('tolerates a garbage / non-JSON line (returns [], no throw)', () => {
const state = makeStreamJsonState();
expect(parseStreamJsonLine('not json at all {{{', state)).toEqual([]);
expect(parseStreamJsonLine('', state)).toEqual([]);
expect(parseStreamJsonLine(' ', state)).toEqual([]);
// A truncated/partial JSON object also yields [] rather than throwing.
expect(parseStreamJsonLine('{"type":"stream_event","eve', state)).toEqual([]);
});
it('ignores unknown top-level line types and the user (tool-result) line', () => {
const state = makeStreamJsonState();
expect(parseStreamJsonLine(JSON.stringify({ type: 'user', message: {} }), state)).toEqual([]);
expect(parseStreamJsonLine(JSON.stringify({ type: 'whatever' }), state)).toEqual([]);
});
it('assembles a tool call across input_json_delta chunks (split across lines)', () => {
const state = makeStreamJsonState();
// start → tool_call (running, empty args)
const start = parseStreamJsonLine(toolStart(1, 'toolu_1', 'edit_file'), state);
expect(start).toHaveLength(1);
expect(start[0]!.type).toBe('tool_call');
const startSnap = (start[0] as { type: 'tool_call'; toolCall: AcpToolSnapshot }).toolCall;
expect(startSnap.toolCallId).toBe('toolu_1');
expect(startSnap.title).toBe('edit_file');
expect(startSnap.status).toBe('in_progress');
expect(startSnap.rawInput).toEqual({});
// args streamed in fragments — no events until stop
expect(parseStreamJsonLine(inputJsonDelta(1, '{"path":"a'), state)).toEqual([]);
expect(parseStreamJsonLine(inputJsonDelta(1, '.ts","content":'), state)).toEqual([]);
expect(parseStreamJsonLine(inputJsonDelta(1, '"hi"}'), state)).toEqual([]);
// stop → tool_update with the parsed, fully-assembled input
const stop = parseStreamJsonLine(blockStop(1), state);
expect(stop).toHaveLength(1);
expect(stop[0]!.type).toBe('tool_update');
const stopSnap = (stop[0] as { type: 'tool_update'; toolCall: AcpToolSnapshot }).toolCall;
expect(stopSnap.toolCallId).toBe('toolu_1');
expect(stopSnap.status).toBe('completed');
expect(stopSnap.rawInput).toEqual({ path: 'a.ts', content: 'hi' });
});
it('falls back to {_raw} when accumulated tool args are not valid JSON', () => {
const state = makeStreamJsonState();
parseStreamJsonLine(toolStart(0, 'toolu_x', 'run'), state);
parseStreamJsonLine(inputJsonDelta(0, '{"broken'), state);
const stop = parseStreamJsonLine(blockStop(0), state);
const snap = (stop[0] as { type: 'tool_update'; toolCall: AcpToolSnapshot }).toolCall;
expect(snap.rawInput).toEqual({ _raw: '{"broken' });
});
it('captures usage from message_delta and result lines', () => {
const state = makeStreamJsonState();
parseStreamJsonLine(streamEvent({ type: 'message_delta', usage: { output_tokens: 42 } }), state);
expect(state.usage.outputTokens).toBe(42);
parseStreamJsonLine(resultLine(100, 250, 'sess-z'), state);
expect(state.usage.inputTokens).toBe(100);
expect(state.usage.outputTokens).toBe(250);
expect(state.sessionId).toBe('sess-z');
});
it('maps a terminal assistant message (fallback) → text + reasoning + tool events', () => {
const state = makeStreamJsonState();
const line = JSON.stringify({
type: 'assistant',
session_id: 'sess-asst',
message: {
content: [
{ type: 'thinking', thinking: 'let me think' },
{ type: 'text', text: 'Here is the answer' },
{ type: 'tool_use', id: 'toolu_9', name: 'view_file', input: { path: 'x.ts' } },
],
usage: { input_tokens: 5, output_tokens: 7 },
},
});
const events = parseStreamJsonLine(line, state);
expect(events).toEqual([
{ type: 'reasoning', text: 'let me think' },
{ type: 'text', text: 'Here is the answer' },
{
type: 'tool_update',
toolCall: { toolCallId: 'toolu_9', title: 'view_file', kind: null, status: 'completed', rawInput: { path: 'x.ts' } },
},
]);
expect(state.usage).toEqual({ inputTokens: 5, outputTokens: 7 });
expect(state.sessionId).toBe('sess-asst');
});
});
describe('makeStreamJsonParser (stateful wrapper over a full turn)', () => {
it('streams a representative turn: init → text → thinking → tool → result', () => {
const parser = makeStreamJsonParser();
const all: AgentEvent[] = [];
const feed = (line: string): AgentEventList => {
const evs = parser.push(line);
all.push(...evs);
return evs;
};
feed(sys('sess-1'));
feed(textDelta(0, 'Reading '));
feed(textDelta(0, 'the file. '));
feed(thinkingDelta(0, 'I should edit it'));
feed(toolStart(1, 'toolu_a', 'edit_file'));
feed(inputJsonDelta(1, '{"path":'));
feed(inputJsonDelta(1, '"main.ts"}'));
feed(blockStop(1));
feed(textDelta(0, 'Done.'));
feed(resultLine(120, 80, 'sess-1'));
expect(all).toEqual([
{ type: 'text', text: 'Reading ' },
{ type: 'text', text: 'the file. ' },
{ type: 'reasoning', text: 'I should edit it' },
{
type: 'tool_call',
toolCall: { toolCallId: 'toolu_a', title: 'edit_file', kind: null, status: 'in_progress', rawInput: {} },
},
{
type: 'tool_update',
toolCall: { toolCallId: 'toolu_a', title: 'edit_file', kind: null, status: 'completed', rawInput: { path: 'main.ts' } },
},
{ type: 'text', text: 'Done.' },
]);
expect(parser.usage()).toEqual({ inputTokens: 120, outputTokens: 80 });
expect(parser.sessionId()).toBe('sess-1');
});
it('a garbage line interleaved mid-turn does not derail subsequent parsing', () => {
const parser = makeStreamJsonParser();
expect(parser.push(textDelta(0, 'a'))).toEqual([{ type: 'text', text: 'a' }]);
expect(parser.push('>>> not json <<<')).toEqual([]);
expect(parser.push(textDelta(0, 'b'))).toEqual([{ type: 'text', text: 'b' }]);
});
});

View File

@@ -0,0 +1,88 @@
/**
* Shared ACP `Client` builder — the callback closures every ACP connection needs
* (worktree-scoped FS bridge + permission/elicitation routing + session updates).
*
* Extracted (v2.7 audit reshape) from the byte-identical `buildClient` closures in
* `acp-dispatch.ts` (one-shot) and `backends/warm-acp.ts` (warm). The two differed
* only in WHERE the per-turn context comes from (a fixed dispatch vs. the warm
* backend's `activeTurn`) and a trivially-equivalent permission gate — both are now
* supplied via the `resolveTurn` callback, so the FS/permission/elicitation wiring
* lives once. Behavior is preserved exactly:
* - `sessionUpdate` drops when `resolveTurn()` returns null (between turns).
* - permission/elicitation route to the UI only when BOTH a taskId AND sessionId
* are present (warm always has a sessionId, so this matches its prior
* `turn?.taskId` gate); otherwise the same auto-select-first / decline fallback.
*/
import type {
Client,
SessionNotification,
RequestPermissionRequest,
RequestPermissionResponse,
ReadTextFileRequest,
ReadTextFileResponse,
WriteTextFileRequest,
WriteTextFileResponse,
CreateTerminalRequest,
CreateTerminalResponse,
CreateElicitationRequest,
CreateElicitationResponse,
} from '@agentclientprotocol/sdk';
import { readWorktreeTextFile, writeWorktreeTextFile } from './acp-client-fs.js';
import { waitForPermissionResponse, waitForElicitationResponse } from './permission-waiter.js';
/** The per-turn context an ACP `Client` closure needs, resolved lazily per call. */
export interface AcpTurnContext {
/** Per-turn task id, for routing permission/elicitation prompts back to the UI. */
taskId: string | undefined;
/** BooCode session id (for permission-waiter's broker frames). */
sessionId: string | undefined;
/** Per-turn mode id (autonomous-mode gate in permission-waiter). */
modeId: string | undefined;
/** The agent name (for permission-waiter routing). */
agent: string;
/** Forward a session/update notification to the turn's event sink. */
onSessionUpdate: (params: SessionNotification) => void | Promise<void>;
}
/**
* Build the ACP `Client` callbacks once per connection. `resolveTurn` is called at
* the moment each callback fires and returns the live turn context (or null when no
* turn is active — `sessionUpdate` then drops, matching the warm backend's
* between-turns behavior). The FS bridge is scoped to `worktreePath`.
*/
export function buildAcpClient(worktreePath: string, resolveTurn: () => AcpTurnContext | null): Client {
return {
sessionUpdate: async (params: SessionNotification): Promise<void> => {
const turn = resolveTurn();
if (!turn) return; // between turns — drop (no orphan settles a future turn)
await turn.onSessionUpdate(params);
},
requestPermission: async (params: RequestPermissionRequest): Promise<RequestPermissionResponse> => {
const turn = resolveTurn();
if (turn && turn.taskId && turn.sessionId) {
return waitForPermissionResponse(turn.taskId, turn.sessionId, turn.agent, turn.modeId, params);
}
const firstOption = params.options[0];
if (firstOption) return { outcome: { outcome: 'selected', optionId: firstOption.optionId } };
return { outcome: { outcome: 'cancelled' } };
},
readTextFile: async (params: ReadTextFileRequest): Promise<ReadTextFileResponse> => {
const content = await readWorktreeTextFile(worktreePath, params.path, params.line, params.limit);
return { content };
},
writeTextFile: async (params: WriteTextFileRequest): Promise<WriteTextFileResponse> => {
await writeWorktreeTextFile(worktreePath, params.path, params.content);
return {};
},
createTerminal: async (_params: CreateTerminalRequest): Promise<CreateTerminalResponse> => {
return { terminalId: 'noop' };
},
unstable_createElicitation: async (params: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
const turn = resolveTurn();
if (turn && turn.taskId && turn.sessionId) {
return waitForElicitationResponse(turn.taskId, turn.sessionId, turn.agent, turn.modeId, params);
}
return { action: 'decline' };
},
};
}

View File

@@ -9,35 +9,21 @@ import {
ClientSideConnection,
type Client,
type SessionNotification,
type RequestPermissionRequest,
type RequestPermissionResponse,
type ReadTextFileRequest,
type ReadTextFileResponse,
type WriteTextFileRequest,
type WriteTextFileResponse,
type CreateTerminalRequest,
type CreateTerminalResponse,
type CreateElicitationRequest,
type CreateElicitationResponse,
type SessionConfigOption,
type ClientSideConnection as ConnectionType,
} from '@agentclientprotocol/sdk';
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/server/ws-frames';
import { spawn } from 'node:child_process';
import { findThoughtLevelConfigId } from './acp-derive.js';
import { resolveLaunchSpec } from './acp-spawn.js';
import { getResolvedRegistry, type ResolvedProviderDef } from './provider-config-registry.js';
import { createAcpNdJsonStream } from './acp-stream.js';
import { waitForPermissionResponse, waitForElicitationResponse, cancelPendingPermission } from './permission-waiter.js';
import { mergeTaskCommands, getTaskCommands } from './agent-commands-cache.js';
import { readWorktreeTextFile, writeWorktreeTextFile } from './acp-client-fs.js';
import { cancelPendingPermission } from './permission-waiter.js';
import { mapSessionUpdate } from './acp-event-map.js';
import {
type AcpToolSnapshot,
snapshotToWireToolCall,
synthesizeCanceledSnapshots,
} from './acp-tool-snapshot.js';
import { type AcpToolSnapshot, synthesizeCanceledSnapshots } from './acp-tool-snapshot.js';
import { makeFrameEmitter, type FrameEmitter } from './frame-emitter.js';
import { buildAcpClient } from './acp-client.js';
export interface AcpDispatchResult {
exitCode: number;
@@ -111,144 +97,61 @@ async function applySessionOverrides(
}
class AcpStreamContext {
readonly textChunks: string[] = [];
readonly reasoningChunks: string[] = [];
readonly toolSnapshots = new Map<string, AcpToolSnapshot>();
private aborted = false;
/** AgentEvent → WS-frame mapping + text/reasoning/tool accumulation (shared
* `makeFrameEmitter`). The one-shot path passes no `dcp` stripper, so text is
* emitted verbatim — byte-identical to the prior inline switch. */
private readonly emitter: FrameEmitter;
constructor(
private readonly opts: Pick<
AcpDispatchOpts,
'broker' | 'sessionId' | 'chatId' | 'messageId' | 'taskId'
>,
opts: Pick<AcpDispatchOpts, 'broker' | 'sessionId' | 'chatId' | 'messageId' | 'taskId'>,
private readonly worktreePath: string,
) {}
) {
this.emitter = makeFrameEmitter({
broker: opts.broker,
sessionId: opts.sessionId,
chatId: opts.chatId,
assistantId: opts.messageId,
taskId: opts.taskId,
});
}
get reasoningText(): string {
return this.reasoningChunks.join('');
return this.emitter.reasoningText;
}
get output(): string {
return this.textChunks.join('');
return this.emitter.output;
}
get snapshots(): AcpToolSnapshot[] {
return [...this.toolSnapshots.values()];
return this.emitter.snapshots;
}
markAborted(): void {
this.aborted = true;
for (const snap of synthesizeCanceledSnapshots(this.toolSnapshots.values())) {
this.toolSnapshots.set(snap.toolCallId, snap);
this.publishToolSnapshot(snap);
// Synthesize 'canceled' updates for still-running tool calls so the UI doesn't
// leave them spinning, then emit them through the same frame path (tool_update
// → the same `tool_call` wire frame the original published).
for (const snap of synthesizeCanceledSnapshots(this.emitter.toolSnapshots.values())) {
this.emitter.onEvent({ type: 'tool_update', toolCall: snap });
}
}
private canStream(): boolean {
return !!(this.opts.broker && this.opts.sessionId && this.opts.chatId && this.opts.messageId);
}
private publishToolSnapshot(snapshot: AcpToolSnapshot): void {
if (!this.canStream()) return;
const wire = snapshotToWireToolCall(snapshot);
this.opts.broker!.publishFrame(this.opts.sessionId!, {
type: 'tool_call',
message_id: this.opts.messageId!,
chat_id: this.opts.chatId!,
tool_call: wire,
} as WsFrame);
}
async handleSessionUpdate(params: SessionNotification): Promise<void> {
// v2.6 Phase 2: the case-by-case mapping now lives in the shared, pure
// `mapSessionUpdate` (reused by the warm ACP backend). This method keeps the
// identical broker-publishing side effects — it just translates the normalized
// AgentEvents back into the same frames it always emitted. `this.toolSnapshots`
// is the merge accumulator, so a later tool_call_update merges over its
// tool_call (the prior `handleToolUpdate` behavior, byte-for-byte).
for (const event of mapSessionUpdate(params, this.toolSnapshots)) {
switch (event.type) {
case 'text':
this.textChunks.push(event.text);
if (this.canStream()) {
this.opts.broker!.publishFrame(this.opts.sessionId!, {
type: 'delta',
message_id: this.opts.messageId!,
chat_id: this.opts.chatId!,
content: event.text,
} as WsFrame);
}
break;
case 'reasoning':
this.reasoningChunks.push(event.text);
if (this.canStream()) {
this.opts.broker!.publishFrame(this.opts.sessionId!, {
type: 'reasoning_delta',
message_id: this.opts.messageId!,
chat_id: this.opts.chatId!,
content: event.text,
} as WsFrame);
}
break;
case 'tool_call':
case 'tool_update':
// mapSessionUpdate already stored the merged snapshot in this.toolSnapshots.
this.publishToolSnapshot(event.toolCall);
break;
case 'commands':
if (this.opts.taskId && event.commands.length > 0) {
mergeTaskCommands(this.opts.taskId, event.commands);
if (this.canStream() && this.opts.sessionId) {
const all = getTaskCommands(this.opts.taskId) ?? event.commands;
this.opts.broker!.publishFrame(this.opts.sessionId, {
type: 'agent_commands',
task_id: this.opts.taskId,
session_id: this.opts.sessionId,
commands: all,
} as WsFrame);
}
}
break;
}
handleSessionUpdate(params: SessionNotification): void {
// The merge accumulator (`this.emitter.toolSnapshots`) is the same Map the
// emitter publishes from, so a later tool_call_update merges over its tool_call.
for (const event of mapSessionUpdate(params, this.emitter.toolSnapshots)) {
this.emitter.onEvent(event);
}
}
buildClient(agent: string, modeId: string | undefined, taskId: string | undefined, sessionId: string | undefined): Client {
return {
sessionUpdate: (params) => this.handleSessionUpdate(params),
requestPermission: async (params: RequestPermissionRequest): Promise<RequestPermissionResponse> => {
if (taskId && sessionId) {
return waitForPermissionResponse(taskId, sessionId, agent, modeId, params);
}
const firstOption = params.options[0];
if (firstOption) {
return { outcome: { outcome: 'selected', optionId: firstOption.optionId } };
}
return { outcome: { outcome: 'cancelled' } };
},
readTextFile: async (params: ReadTextFileRequest): Promise<ReadTextFileResponse> => {
const content = await readWorktreeTextFile(
this.worktreePath,
params.path,
params.line,
params.limit,
);
return { content };
},
writeTextFile: async (params: WriteTextFileRequest): Promise<WriteTextFileResponse> => {
await writeWorktreeTextFile(this.worktreePath, params.path, params.content);
return {};
},
createTerminal: async (_params: CreateTerminalRequest): Promise<CreateTerminalResponse> => {
return { terminalId: 'noop' };
},
unstable_createElicitation: async (params: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
if (taskId && sessionId) {
return waitForElicitationResponse(taskId, sessionId, agent, modeId, params);
}
return { action: 'decline' };
},
};
return buildAcpClient(this.worktreePath, () => ({
taskId,
sessionId,
modeId,
agent,
onSessionUpdate: (params) => this.handleSessionUpdate(params),
}));
}
}

View File

@@ -2,7 +2,7 @@ import { Readable, Writable } from 'node:stream';
import type { ChildProcess } from 'node:child_process';
import { ndJsonStream } from '@agentclientprotocol/sdk';
export function nodeReadableToWeb(nodeStream: NodeJS.ReadableStream): ReadableStream<Uint8Array> {
function nodeReadableToWeb(nodeStream: NodeJS.ReadableStream): ReadableStream<Uint8Array> {
return new ReadableStream<Uint8Array>({
start(controller) {
nodeStream.on('data', (chunk: Buffer) => controller.enqueue(new Uint8Array(chunk)));
@@ -17,7 +17,7 @@ export function nodeReadableToWeb(nodeStream: NodeJS.ReadableStream): ReadableSt
});
}
export function nodeWritableToWeb(nodeStream: NodeJS.WritableStream): WritableStream<Uint8Array> {
function nodeWritableToWeb(nodeStream: NodeJS.WritableStream): WritableStream<Uint8Array> {
return new WritableStream<Uint8Array>({
write(chunk) {
return new Promise<void>((resolve, reject) => {

View File

@@ -13,7 +13,7 @@ import type { AcpToolSnapshot } from './acp-tool-snapshot.js';
import type { AgentCommand } from './provider-types.js';
/** Backend transport kind. Mirrors `agent_sessions.backend` CHECK in schema.sql. */
export type AgentBackendKind = 'opencode_server' | 'acp_warm';
export type AgentBackendKind = 'opencode_server' | 'acp_warm' | 'claude_sdk';
/**
* Normalized, transport-agnostic events a backend emits during a turn (§2).
@@ -82,6 +82,12 @@ export interface PromptCtx {
export interface TurnResult {
ok: boolean;
error?: string;
// Optional context-window telemetry (claude SDK): the model's reported window
// (ctxMax, 1M-aware) and the peak request input ≈ current fill (ctxUsed). The
// dispatcher writes these onto the assistant message so the ContextBar renders a
// real fill for the turn. Omitted by backends that don't report a window.
ctxUsed?: number;
ctxMax?: number;
}
/**

View File

@@ -0,0 +1,55 @@
/**
* agent-status-publish (#10) — builds + publishes the `agent_status_updated`
* WS frame on the per-session channel (the same channel CoderPane subscribes to).
*
* Kept separate from normalize-agent-status.ts so that module stays a pure,
* broker-free helper (trivially unit-testable; reused by the config-injection
* follow-on). The frame contract is pinned in apps/server/src/types/ws-frames.ts
* (`AgentStatusUpdatedFrame`) and mirrored byte-identical in apps/web.
*/
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/contracts/ws-frames';
import type { AgentStatus } from './normalize-agent-status.js';
// The exact slice of Broker we need — accepting just the bound method keeps call
// sites flexible (pass `broker.publishFrame.bind(broker)` or, since the broker's
// publishFrame doesn't read `this`, `broker.publishFrame` directly).
type PublishFrame = Broker['publishFrame'];
/**
* Best-effort publish of a normalized agent status. The broker's publishFrame
* already fail-closes (validates + logs + drops on bad input, never throws), but
* we additionally swallow any unexpected error so a publish can NEVER break the
* turn it's reporting on.
*
* @param publishFrame the session channel publisher (broker.publishFrame)
* @param sessionId WS subscription channel (CoderPane subscribes per-session)
* @param chatId the (chat) half of the (chat, agent) status key
* @param agent the (agent) half of the key
* @param status normalized lifecycle status
* @param reason free-form discriminator (turn_start / turn_complete / …)
* @param at ISO timestamp; defaults to now
*/
export function publishAgentStatus(
publishFrame: PublishFrame,
sessionId: string,
chatId: string,
agent: string,
status: AgentStatus,
reason?: string,
at: string = new Date().toISOString(),
): void {
try {
const frame: WsFrame = {
type: 'agent_status_updated',
chat_id: chatId,
agent,
status,
...(reason ? { reason } : {}),
at,
};
publishFrame(sessionId, frame);
} catch {
// never let a status publish break the turn — best-effort only.
}
}

View File

@@ -0,0 +1,251 @@
import { describe, it, expect } from 'vitest';
import type { SDKMessage } from '@anthropic-ai/claude-agent-sdk';
import { mapSdkMessage, createClaudeSdkMapState } from '../claude-sdk-map.js';
import type { AgentEvent } from '../../agent-backend.js';
/**
* Pure mapper for Claude-SDK messages → AgentEvents (claude-sdk-sessionstore #9 Part 2).
* Verifies the partial-stream → live-delta mapping, tool assembly across blocks, and
* the final-assistant dedup, with no live `claude` binary involved.
*
* Messages are cast through `unknown` to `SDKMessage`: the real SDK shapes carry many
* fields (uuid, parent_tool_use_id, …) irrelevant to the mapper, which reads only the
* `type`/`event`/`message.content` it discriminates on. The cast keeps the fixtures
* minimal while the production code path sees the full real types (the backend's
* typecheck against the real SDK is the type-safety proof).
*/
function msg(m: unknown): SDKMessage {
return m as SDKMessage;
}
/** A partial-stream message wrapping one BetaRawMessageStreamEvent. */
function streamEvent(event: unknown): SDKMessage {
return msg({ type: 'stream_event', event, parent_tool_use_id: null, uuid: 'u', session_id: 's' });
}
describe('mapSdkMessage — partial stream deltas', () => {
it('maps a text_delta to a text event', () => {
const state = createClaudeSdkMapState();
const out = mapSdkMessage(
streamEvent({ type: 'content_block_delta', index: 0, delta: { type: 'text_delta', text: 'Hello' } }),
state,
);
expect(out).toEqual<AgentEvent[]>([{ type: 'text', text: 'Hello' }]);
});
it('maps a thinking_delta to a reasoning event', () => {
const state = createClaudeSdkMapState();
const out = mapSdkMessage(
streamEvent({
type: 'content_block_delta',
index: 0,
delta: { type: 'thinking_delta', thinking: 'pondering', estimated_tokens: null },
}),
state,
);
expect(out).toEqual<AgentEvent[]>([{ type: 'reasoning', text: 'pondering' }]);
});
it('drops empty text/thinking deltas', () => {
const state = createClaudeSdkMapState();
expect(
mapSdkMessage(streamEvent({ type: 'content_block_delta', index: 0, delta: { type: 'text_delta', text: '' } }), state),
).toEqual([]);
expect(
mapSdkMessage(
streamEvent({ type: 'content_block_delta', index: 0, delta: { type: 'thinking_delta', thinking: '', estimated_tokens: null } }),
state,
),
).toEqual([]);
});
it('ignores message framing + signature/citation deltas', () => {
const state = createClaudeSdkMapState();
expect(mapSdkMessage(streamEvent({ type: 'message_start', message: {} }), state)).toEqual([]);
expect(mapSdkMessage(streamEvent({ type: 'message_stop' }), state)).toEqual([]);
expect(
mapSdkMessage(streamEvent({ type: 'content_block_delta', index: 0, delta: { type: 'signature_delta', signature: 'x' } }), state),
).toEqual([]);
});
});
describe('mapSdkMessage — tool assembly across blocks', () => {
it('opens a tool_call on content_block_start, buffers input_json_delta, emits tool_update with parsed input on stop', () => {
const state = createClaudeSdkMapState();
const started = mapSdkMessage(
streamEvent({
type: 'content_block_start',
index: 1,
content_block: { type: 'tool_use', id: 'tool-1', name: 'view_file', input: {} },
}),
state,
);
expect(started).toEqual<AgentEvent[]>([
{ type: 'tool_call', toolCall: { toolCallId: 'tool-1', title: 'view_file', kind: null, status: 'in_progress', rawInput: {}, rawOutput: undefined } },
]);
// args stream in fragments under the same block index
expect(
mapSdkMessage(streamEvent({ type: 'content_block_delta', index: 1, delta: { type: 'input_json_delta', partial_json: '{"path":' } }), state),
).toEqual([]);
expect(
mapSdkMessage(streamEvent({ type: 'content_block_delta', index: 1, delta: { type: 'input_json_delta', partial_json: '"a.ts"}' } }), state),
).toEqual([]);
const stopped = mapSdkMessage(streamEvent({ type: 'content_block_stop', index: 1 }), state);
expect(stopped).toHaveLength(1);
const ev = stopped[0]!;
expect(ev.type).toBe('tool_update');
if (ev.type === 'tool_update') {
expect(ev.toolCall.toolCallId).toBe('tool-1');
expect(ev.toolCall.title).toBe('view_file');
expect(ev.toolCall.rawInput).toEqual({ path: 'a.ts' });
}
});
it('content_block_stop for a non-tool block (no tracked index) emits nothing', () => {
const state = createClaudeSdkMapState();
// text block was streamed at index 0 but never tracked as a tool
mapSdkMessage(streamEvent({ type: 'content_block_delta', index: 0, delta: { type: 'text_delta', text: 'hi' } }), state);
expect(mapSdkMessage(streamEvent({ type: 'content_block_stop', index: 0 }), state)).toEqual([]);
});
it('falls back to the prior input when the buffered tool JSON is invalid', () => {
const state = createClaudeSdkMapState();
mapSdkMessage(
streamEvent({ type: 'content_block_start', index: 2, content_block: { type: 'tool_use', id: 't2', name: 'grep', input: { q: 'seed' } } }),
state,
);
mapSdkMessage(streamEvent({ type: 'content_block_delta', index: 2, delta: { type: 'input_json_delta', partial_json: '{not json' } }), state);
const stopped = mapSdkMessage(streamEvent({ type: 'content_block_stop', index: 2 }), state);
const ev = stopped[0]!;
if (ev.type === 'tool_update') {
expect(ev.toolCall.rawInput).toEqual({ q: 'seed' });
} else {
throw new Error('expected tool_update');
}
});
});
describe('mapSdkMessage — final assistant message', () => {
function assistant(content: unknown[]): SDKMessage {
return msg({ type: 'assistant', message: { content }, parent_tool_use_id: null, uuid: 'u', session_id: 's' });
}
it('dedups text/thinking (already streamed) and emits a completed tool_update per tool_use block', () => {
const state = createClaudeSdkMapState();
const out = mapSdkMessage(
assistant([
{ type: 'text', text: 'final answer', citations: null },
{ type: 'thinking', thinking: 'reasoned', signature: 'sig' },
{ type: 'tool_use', id: 'tool-9', name: 'find_files', input: { glob: '**/*.ts' } },
]),
state,
);
expect(out).toEqual<AgentEvent[]>([
{
type: 'tool_update',
toolCall: { toolCallId: 'tool-9', title: 'find_files', kind: null, status: 'completed', rawInput: { glob: '**/*.ts' }, rawOutput: undefined },
},
]);
});
it('preserves a title from a prior partial tool_call snapshot', () => {
const state = createClaudeSdkMapState();
mapSdkMessage(
streamEvent({ type: 'content_block_start', index: 0, content_block: { type: 'tool_use', id: 'tool-x', name: 'view_file', input: {} } }),
state,
);
const out = mapSdkMessage(assistant([{ type: 'tool_use', id: 'tool-x', name: 'view_file', input: { path: 'z' } }]), state);
const ev = out[0]!;
if (ev.type === 'tool_update') {
expect(ev.toolCall.status).toBe('completed');
expect(ev.toolCall.title).toBe('view_file');
expect(ev.toolCall.rawInput).toEqual({ path: 'z' });
} else {
throw new Error('expected tool_update');
}
});
});
describe('mapSdkMessage — non-content messages', () => {
it('returns [] for system/init, status, result, and other variants', () => {
const state = createClaudeSdkMapState();
expect(mapSdkMessage(msg({ type: 'system', subtype: 'init', session_id: 's', uuid: 'u' }), state)).toEqual([]);
expect(mapSdkMessage(msg({ type: 'system', subtype: 'status', status: null, session_id: 's', uuid: 'u' }), state)).toEqual([]);
expect(
mapSdkMessage(msg({ type: 'result', subtype: 'success', result: 'done', session_id: 's', uuid: 'u' }), state),
).toEqual([]);
});
});
describe('mapSdkMessage — user tool results', () => {
/** A `user` message carrying tool_result blocks (the SDK feeds tool output back here). */
function userMsg(content: unknown): SDKMessage {
return msg({ type: 'user', message: { role: 'user', content }, parent_tool_use_id: null, uuid: 'u', session_id: 's' });
}
it('maps a string tool_result to a completed tool_update carrying the output', () => {
const state = createClaudeSdkMapState();
const out = mapSdkMessage(userMsg([{ type: 'tool_result', tool_use_id: 't1', content: 'done' }]), state);
expect(out).toEqual<AgentEvent[]>([
{
type: 'tool_update',
toolCall: { toolCallId: 't1', title: 't1', kind: null, status: 'completed', rawInput: undefined, rawOutput: 'done' },
},
]);
});
it('marks an is_error result failed', () => {
const state = createClaudeSdkMapState();
const out = mapSdkMessage(userMsg([{ type: 'tool_result', tool_use_id: 't1', content: 'boom', is_error: true }]), state);
const ev = out[0]!;
if (ev.type !== 'tool_update') throw new Error('expected tool_update');
expect(ev.toolCall.status).toBe('failed');
expect(ev.toolCall.rawOutput).toBe('boom');
});
it('flattens array text blocks (skipping non-text) and reuses a prior snapshot title', () => {
const state = createClaudeSdkMapState();
mapSdkMessage(
streamEvent({ type: 'content_block_start', index: 1, content_block: { type: 'tool_use', id: 't2', name: 'view_file', input: {} } }),
state,
);
const out = mapSdkMessage(
userMsg([
{
type: 'tool_result',
tool_use_id: 't2',
content: [
{ type: 'text', text: 'line1' },
{ type: 'image', source: {} },
{ type: 'text', text: 'line2' },
],
},
]),
state,
);
const ev = out[0]!;
if (ev.type !== 'tool_update') throw new Error('expected tool_update');
expect(ev.toolCall.toolCallId).toBe('t2');
expect(ev.toolCall.title).toBe('view_file');
expect(ev.toolCall.status).toBe('completed');
expect(ev.toolCall.rawOutput).toBe('line1\nline2');
});
it('surfaces a result for an unknown tool_use_id with the id as the title', () => {
const state = createClaudeSdkMapState();
const out = mapSdkMessage(userMsg([{ type: 'tool_result', tool_use_id: 'orphan-id', content: 'x' }]), state);
expect(out[0]).toMatchObject({
type: 'tool_update',
toolCall: { toolCallId: 'orphan-id', title: 'orphan-id', kind: null, status: 'completed' },
});
});
it('ignores non-tool_result blocks and non-array content', () => {
const state = createClaudeSdkMapState();
expect(mapSdkMessage(userMsg([{ type: 'text', text: 'hi' }]), state)).toEqual([]);
expect(mapSdkMessage(userMsg('plain string'), state)).toEqual([]);
});
});

View File

@@ -0,0 +1,49 @@
import { describe, it, expect } from 'vitest';
import { shouldUseClaudeSdk, claudeSdkBackendEnabled } from '../claude-sdk-routing.js';
/**
* Env-flagged routing for the warm Claude-SDK backend. With CLAUDE_SDK_BACKEND off
* (the production default) every claude task falls through to the unchanged PTY path;
* with it on, only chat-tab claude tasks (session_id + chat_id) route to the SDK.
*/
const ON = { CLAUDE_SDK_BACKEND: '1' } as NodeJS.ProcessEnv;
const OFF = {} as NodeJS.ProcessEnv;
describe('claudeSdkBackendEnabled', () => {
it('is false when unset or falsy', () => {
expect(claudeSdkBackendEnabled({} as NodeJS.ProcessEnv)).toBe(false);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: '' } as NodeJS.ProcessEnv)).toBe(false);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: '0' } as NodeJS.ProcessEnv)).toBe(false);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: 'false' } as NodeJS.ProcessEnv)).toBe(false);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: 'off' } as NodeJS.ProcessEnv)).toBe(false);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: 'no' } as NodeJS.ProcessEnv)).toBe(false);
});
it('is true for any other truthy value', () => {
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: '1' } as NodeJS.ProcessEnv)).toBe(true);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: 'true' } as NodeJS.ProcessEnv)).toBe(true);
expect(claudeSdkBackendEnabled({ CLAUDE_SDK_BACKEND: 'on' } as NodeJS.ProcessEnv)).toBe(true);
});
});
describe('shouldUseClaudeSdk', () => {
it('is always false while the env flag is off — production claude stays on PTY', () => {
expect(shouldUseClaudeSdk({ agent: 'claude', session_id: 's1', chat_id: 'c1' }, OFF)).toBe(false);
});
it('routes a chat-tab claude task to the SDK when the flag is on', () => {
expect(shouldUseClaudeSdk({ agent: 'claude', session_id: 's1', chat_id: 'c1' }, ON)).toBe(true);
});
it('only applies to the claude agent', () => {
expect(shouldUseClaudeSdk({ agent: 'qwen', session_id: 's1', chat_id: 'c1' }, ON)).toBe(false);
expect(shouldUseClaudeSdk({ agent: 'opencode', session_id: 's1', chat_id: 'c1' }, ON)).toBe(false);
expect(shouldUseClaudeSdk({ agent: null, session_id: 's1', chat_id: 'c1' }, ON)).toBe(false);
});
it('requires both session_id and chat_id (session-less creators stay one-shot)', () => {
expect(shouldUseClaudeSdk({ agent: 'claude', session_id: null, chat_id: null }, ON)).toBe(false);
expect(shouldUseClaudeSdk({ agent: 'claude', session_id: 's1', chat_id: null }, ON)).toBe(false);
expect(shouldUseClaudeSdk({ agent: 'claude', session_id: null, chat_id: 'c1' }, ON)).toBe(false);
});
});

View File

@@ -0,0 +1,135 @@
import { describe, it, expect, beforeAll, afterAll } from 'vitest';
import { readFileSync } from 'node:fs';
import { resolve } from 'node:path';
import postgres from 'postgres';
import { PostgresSessionStore } from '../claude-session-store.js';
import type { SessionStoreEntry } from '@anthropic-ai/claude-agent-sdk';
/**
* claude-sdk-sessionstore #9 (Part 1) — PostgresSessionStore tests.
*
* DB-opt-in (DATABASE_URL), mirrors checkpoints.test.ts: skips cleanly when the
* var is unset; otherwise applies the server + coder schemas and exercises the
* real append/load/listSessions/delete/listSubkeys round trips against postgres.
* Rows are namespaced under a unique project_key so concurrent suites / leftover
* data can't collide, and afterAll deletes everything written.
*/
describe.runIf(!!process.env.DATABASE_URL)('PostgresSessionStore (DB)', () => {
let sql: ReturnType<typeof postgres>;
let store: PostgresSessionStore;
const projectKey = `claude-store-test-${Date.now()}`;
const entry = (type: string, extra: Record<string, unknown> = {}): SessionStoreEntry => ({
type,
...extra,
});
beforeAll(async () => {
sql = postgres(process.env.DATABASE_URL!, { max: 3 });
const serverSchema = resolve(__dirname, '../../../../../server/src/schema.sql');
const coderSchema = resolve(__dirname, '../../../schema.sql');
await sql.unsafe(readFileSync(serverSchema, 'utf8'));
await sql.unsafe(readFileSync(coderSchema, 'utf8'));
store = new PostgresSessionStore(sql);
});
afterAll(async () => {
if (sql) {
await sql`DELETE FROM claude_session_entries WHERE project_key = ${projectKey}`.catch(() => {});
await sql.end({ timeout: 5 });
}
});
it('append → load round-trips and preserves order across two appends', async () => {
const key = { projectKey, sessionId: 'sess-order' };
await store.append(key, [entry('user', { uuid: 'u1' }), entry('assistant', { uuid: 'a1' })]);
await store.append(key, [entry('result', { uuid: 'r1' })]);
const loaded = await store.load(key);
expect(loaded).not.toBeNull();
expect(loaded!.map((e) => e.uuid)).toEqual(['u1', 'a1', 'r1']);
expect(loaded!.map((e) => e.type)).toEqual(['user', 'assistant', 'result']);
});
it('append with an empty batch is a no-op (load still null for an otherwise-unseen key)', async () => {
const key = { projectKey, sessionId: 'sess-empty' };
await store.append(key, []);
expect(await store.load(key)).toBeNull();
});
it('load of a key that was never written returns null', async () => {
expect(await store.load({ projectKey, sessionId: 'never-seen' })).toBeNull();
});
it('isolates the main transcript from a subpath (load each independently)', async () => {
const sessionId = 'sess-subpath';
const mainKey = { projectKey, sessionId };
const subKey = { projectKey, sessionId, subpath: 'subagents/x' };
await store.append(mainKey, [entry('user', { uuid: 'main-1' })]);
await store.append(subKey, [entry('assistant', { uuid: 'sub-1' })]);
const main = await store.load(mainKey);
const sub = await store.load(subKey);
expect(main!.map((e) => e.uuid)).toEqual(['main-1']);
expect(sub!.map((e) => e.uuid)).toEqual(['sub-1']);
});
it('listSessions returns the session with a numeric mtime (main transcripts only)', async () => {
const sessionId = 'sess-list';
await store.append({ projectKey, sessionId }, [entry('user', { uuid: 'l1' })]);
// A subagent-only session must NOT surface as a main-transcript session.
await store.append(
{ projectKey, sessionId: 'sess-sub-only', subpath: 'subagents/y' },
[entry('user', { uuid: 's1' })],
);
const sessions = await store.listSessions(projectKey);
const ids = sessions.map((s) => s.sessionId);
expect(ids).toContain(sessionId);
expect(ids).not.toContain('sess-sub-only');
const row = sessions.find((s) => s.sessionId === sessionId)!;
expect(typeof row.mtime).toBe('number');
expect(Number.isFinite(row.mtime)).toBe(true);
expect(row.mtime).toBeGreaterThan(0);
});
it('delete with a subpath removes only that subpath', async () => {
const sessionId = 'sess-del-subpath';
const mainKey = { projectKey, sessionId };
const subKey = { projectKey, sessionId, subpath: 'subagents/z' };
await store.append(mainKey, [entry('user', { uuid: 'keep-1' })]);
await store.append(subKey, [entry('assistant', { uuid: 'drop-1' })]);
await store.delete(subKey);
expect(await store.load(subKey)).toBeNull();
expect((await store.load(mainKey))!.map((e) => e.uuid)).toEqual(['keep-1']);
});
it('delete without a subpath removes the whole session (all subpaths)', async () => {
const sessionId = 'sess-del-all';
const mainKey = { projectKey, sessionId };
const subKey = { projectKey, sessionId, subpath: 'subagents/w' };
await store.append(mainKey, [entry('user', { uuid: 'm' })]);
await store.append(subKey, [entry('assistant', { uuid: 's' })]);
await store.delete({ projectKey, sessionId });
expect(await store.load(mainKey)).toBeNull();
expect(await store.load(subKey)).toBeNull();
expect(await store.listSubkeys({ projectKey, sessionId })).toEqual([]);
});
it('listSubkeys returns the distinct non-main subpaths', async () => {
const sessionId = 'sess-subkeys';
await store.append({ projectKey, sessionId }, [entry('user', { uuid: 'main' })]);
await store.append({ projectKey, sessionId, subpath: 'subagents/a' }, [entry('user', { uuid: 'a1' })]);
await store.append({ projectKey, sessionId, subpath: 'subagents/a' }, [entry('user', { uuid: 'a2' })]);
await store.append({ projectKey, sessionId, subpath: 'subagents/b' }, [entry('user', { uuid: 'b1' })]);
const subkeys = await store.listSubkeys({ projectKey, sessionId });
expect(subkeys.sort()).toEqual(['subagents/a', 'subagents/b']);
});
});

View File

@@ -0,0 +1,173 @@
import { describe, it, expect, vi } from 'vitest';
import type { Event, OpencodeClient } from '@opencode-ai/sdk/v2/client';
import {
reconnectDecision,
runSessionEventLoop,
DEFAULT_RECONNECT_POLICY,
type SessionState,
type SseLoopDeps,
} from '../opencode-sse.js';
import { shouldStartServer } from '../opencode-server-process.js';
/**
* v2.7 concurrency hardening (Phase 7): the pure decision cores for SSE reconnect
* backoff + the ensureServer double-spawn guard, plus a deterministic exercise of
* the loop's breaker (injected sleep, fake client). Happy path is asserted to be
* unchanged (clean stream end → reset → base-delay reconnect).
*/
function freshState(): SessionState {
return {
boocodeSessionId: 'boo1',
agentSessionId: 'oc1',
worktreePath: '/wt',
streamedPartKeys: new Set(),
partTypeById: new Map(),
activeTurn: { onEvent: () => {}, settle: () => {} },
watchdog: null,
sseAbort: null,
swallowNextTerminal: false,
};
}
const silentLog = {
warn: () => {},
info: () => {},
error: () => {},
debug: () => {},
} as unknown as SseLoopDeps['log'];
describe('reconnectDecision (pure backoff + breaker)', () => {
it('first failure uses the base delay (matches pre-hardening flat delay)', () => {
expect(reconnectDecision(1)).toEqual({ action: 'reconnect', delayMs: DEFAULT_RECONNECT_POLICY.baseMs });
});
it('grows exponentially and caps at maxMs', () => {
const policy = { baseMs: 1000, maxMs: 30_000, maxAttempts: 10 };
expect(reconnectDecision(2, policy)).toEqual({ action: 'reconnect', delayMs: 2000 });
expect(reconnectDecision(3, policy)).toEqual({ action: 'reconnect', delayMs: 4000 });
expect(reconnectDecision(6, policy)).toEqual({ action: 'reconnect', delayMs: 30_000 }); // 32000 capped
expect(reconnectDecision(9, policy)).toEqual({ action: 'reconnect', delayMs: 30_000 });
});
it('gives up once failures exceed maxAttempts', () => {
const policy = { baseMs: 1, maxMs: 8, maxAttempts: 3 };
expect(reconnectDecision(3, policy).action).toBe('reconnect');
expect(reconnectDecision(4, policy)).toEqual({ action: 'give-up' });
});
});
describe('shouldStartServer (double-spawn guard)', () => {
it('does not start when the server is live', () => {
expect(shouldStartServer({ up: true, hasClient: true, serverStarting: true, childDead: false, startInFlight: false })).toBe(false);
});
it('starts on a fresh process (no start in flight)', () => {
expect(shouldStartServer({ up: false, hasClient: false, serverStarting: false, childDead: false, startInFlight: false })).toBe(true);
});
it('re-spawns after a crash once the prior start finished', () => {
expect(shouldStartServer({ up: false, hasClient: false, serverStarting: true, childDead: true, startInFlight: false })).toBe(true);
});
it('does NOT double-spawn while a start is already in flight (the race fix)', () => {
expect(shouldStartServer({ up: false, hasClient: false, serverStarting: true, childDead: true, startInFlight: true })).toBe(false);
});
it('does NOT double-spawn when a crash nulled serverStarting mid-start', () => {
// The narrow window: a crash during the in-flight start (await freePort) nulls
// serverStarting while startInFlight is still true. The startInFlight guard must
// win over the !serverStarting branch, else a second server spawns on a new port.
expect(shouldStartServer({ up: false, hasClient: false, serverStarting: false, childDead: true, startInFlight: true })).toBe(false);
});
it('waits (no spawn) when a cached start exists and the child is still alive', () => {
expect(shouldStartServer({ up: false, hasClient: false, serverStarting: true, childDead: false, startInFlight: false })).toBe(false);
});
});
describe('runSessionEventLoop — happy path (unchanged)', () => {
it('dispatches streamed events, reconciles on clean end, reconnects at base delay', async () => {
const state = freshState();
const abort = new AbortController();
const events = [
{ type: 'session.next.text.delta', properties: { sessionID: 'oc1', delta: 'hi' } },
{ type: 'session.idle', properties: { sessionID: 'oc1' } },
] as unknown as Event[];
const client = {
event: {
subscribe: vi.fn(async () => ({
stream: (async function* () {
for (const ev of events) yield ev;
})(),
})),
},
} as unknown as OpencodeClient;
const dispatched: Event[] = [];
const sleeps: number[] = [];
let reconciles = 0;
const deps: SseLoopDeps = {
isUp: () => true,
getClient: () => client,
dispatchEvent: (ev) => dispatched.push(ev),
reconcile: async () => {
reconciles += 1;
abort.abort(); // stop the loop after the first clean cycle
return false;
},
onReconnectGiveUp: () => {
throw new Error('should not give up on the happy path');
},
log: silentLog,
sleep: async (ms) => {
sleeps.push(ms);
},
};
await runSessionEventLoop(state, abort, deps);
expect(dispatched).toHaveLength(2);
expect(reconciles).toBe(1);
expect(sleeps).toEqual([DEFAULT_RECONNECT_POLICY.baseMs]); // base delay, not backed off
});
});
describe('runSessionEventLoop — circuit breaker', () => {
it('backs off on repeated throws then gives up + fails the turn', async () => {
const state = freshState();
const abort = new AbortController();
const policy = { baseMs: 1, maxMs: 8, maxAttempts: 3 };
const subscribe = vi.fn(async () => {
throw new Error('connection refused');
});
const client = { event: { subscribe } } as unknown as OpencodeClient;
const sleeps: number[] = [];
const gaveUp = vi.fn();
const deps: SseLoopDeps = {
isUp: () => true,
getClient: () => client,
dispatchEvent: () => {},
reconcile: async () => false,
onReconnectGiveUp: gaveUp,
log: silentLog,
sleep: async (ms) => {
sleeps.push(ms);
},
policy,
};
await runSessionEventLoop(state, abort, deps);
// 3 backoff sleeps (1, 2, 4), then the 4th failure trips the breaker.
expect(sleeps).toEqual([1, 2, 4]);
expect(subscribe).toHaveBeenCalledTimes(4);
expect(gaveUp).toHaveBeenCalledTimes(1);
expect(gaveUp).toHaveBeenCalledWith(state);
});
});

View File

@@ -0,0 +1,226 @@
import { describe, it, expect } from 'vitest';
import type { Event, Part } from '@opencode-ai/sdk/v2/client';
import {
stripDcpTags,
eventSessionId,
resolvePartDedupeKey,
mapToolStatus,
toolPartToSnapshot,
toolCalledSnapshot,
toolSuccessSnapshot,
toolFailedSnapshot,
classifyPartDelta,
classifyUpdatedPart,
errToString,
errMsg,
type DedupState,
} from '../opencode-event-map.js';
/**
* Pure opencode Event → AgentEvent translation + dedup gate (v2.7 audit reshape).
* Mirrors the original `dispatchEvent` / `handleUpdatedPart` arms verbatim — no
* I/O, so it's unit-testable. The slimmed backend keeps the routing + side effects.
*/
function freshDedup(): DedupState {
return { streamedPartKeys: new Set(), partTypeById: new Map() };
}
describe('stripDcpTags', () => {
it('removes a complete dcp tag', () => {
expect(stripDcpTags('hi <dcp-message-id>m1</dcp-message-id> there')).toBe('hi there');
});
it('leaves untagged text untouched', () => {
expect(stripDcpTags('plain text <div>')).toBe('plain text <div>');
});
});
describe('eventSessionId', () => {
it('reads properties.sessionID for a normal event', () => {
const ev = { type: 'session.idle', properties: { sessionID: 's1' } } as unknown as Event;
expect(eventSessionId(ev)).toBe('s1');
});
it('reads properties.part.sessionID for message.part.updated', () => {
const ev = {
type: 'message.part.updated',
properties: { part: { sessionID: 's2' } },
} as unknown as Event;
expect(eventSessionId(ev)).toBe('s2');
});
it('returns null when there is no session', () => {
const ev = { type: 'server.connected', properties: {} } as unknown as Event;
expect(eventSessionId(ev)).toBeNull();
});
});
describe('resolvePartDedupeKey', () => {
it('prefers the part id', () => {
expect(resolvePartDedupeKey({ id: 'p1', messageID: 'm1' }, 'text')).toBe('text:p1');
});
it('falls back to the message id', () => {
expect(resolvePartDedupeKey({ id: ' ', messageID: 'm1' }, 'reasoning')).toBe('reasoning:message:m1');
});
it('returns null when neither is present', () => {
expect(resolvePartDedupeKey({ id: '', messageID: '' }, 'text')).toBeNull();
});
});
describe('mapToolStatus', () => {
it('maps the opencode tool states to ACP statuses', () => {
expect(mapToolStatus('pending')).toBe('pending');
expect(mapToolStatus('running')).toBe('in_progress');
expect(mapToolStatus('completed')).toBe('completed');
expect(mapToolStatus('error')).toBe('failed');
expect(mapToolStatus(undefined)).toBeNull();
});
});
describe('session.next.tool.* snapshot builders', () => {
it('toolCalledSnapshot → in_progress with tool title + raw input', () => {
expect(toolCalledSnapshot({ callID: 'c1', tool: 'read_file', input: { path: 'a.ts' } })).toEqual({
toolCallId: 'c1',
title: 'read_file',
kind: null,
status: 'in_progress',
rawInput: { path: 'a.ts' },
rawOutput: undefined,
});
});
it('toolSuccessSnapshot → completed with joined text content', () => {
const snap = toolSuccessSnapshot({ callID: 'c1', content: [{ text: 'foo' }, { text: 'bar' }, { other: 1 }] });
expect(snap.status).toBe('completed');
expect(snap.title).toBe('c1');
expect(snap.rawOutput).toBe('foobar');
});
it('toolSuccessSnapshot → empty output when content is missing', () => {
expect(toolSuccessSnapshot({ callID: 'c1' }).rawOutput).toBe('');
});
it('toolFailedSnapshot → failed with stringified error', () => {
const snap = toolFailedSnapshot({ callID: 'c1', error: 'boom' });
expect(snap.status).toBe('failed');
expect(snap.title).toBe('c1');
expect(snap.rawOutput).toBe('boom');
});
});
describe('toolPartToSnapshot', () => {
it('extracts input/output/title/status from the tool state', () => {
const part = {
type: 'tool',
callID: 'c1',
tool: 'grep',
state: { status: 'completed', input: { q: 'x' }, output: 'result', title: 'Grep run' },
} as unknown as Parameters<typeof toolPartToSnapshot>[0];
expect(toolPartToSnapshot(part)).toEqual({
toolCallId: 'c1',
title: 'Grep run',
kind: null,
status: 'completed',
rawInput: { q: 'x' },
rawOutput: 'result',
});
});
it('falls back to the tool name and uses error as output', () => {
const part = {
type: 'tool',
callID: 'c2',
tool: 'edit',
state: { status: 'error', error: 'nope' },
} as unknown as Parameters<typeof toolPartToSnapshot>[0];
const snap = toolPartToSnapshot(part);
expect(snap.title).toBe('edit');
expect(snap.status).toBe('failed');
expect(snap.rawOutput).toBe('nope');
});
});
describe('classifyPartDelta (message.part.delta dedup recording)', () => {
it('records a reasoning key and emits a reasoning event', () => {
const st = freshDedup();
const e = classifyPartDelta({ partID: 'p1', field: 'reasoning', delta: 'thinking' }, st);
expect(e).toEqual({ type: 'reasoning', text: 'thinking' });
expect(st.streamedPartKeys.has('reasoning:p1')).toBe(true);
});
it('records a text key, strips dcp, and emits text', () => {
const st = freshDedup();
const e = classifyPartDelta({ partID: 'p2', field: 'text', delta: 'hi <dcp-message-id>m</dcp-message-id>' }, st);
expect(e).toEqual({ type: 'text', text: 'hi ' });
expect(st.streamedPartKeys.has('text:p2')).toBe(true);
});
it('still records the text key even when the cleaned delta is empty', () => {
const st = freshDedup();
const e = classifyPartDelta({ partID: 'p3', field: 'text', delta: '<dcp-message-id>m</dcp-message-id>' }, st);
expect(e).toBeNull();
expect(st.streamedPartKeys.has('text:p3')).toBe(true);
});
it('uses the recorded part type when the field is absent', () => {
const st = freshDedup();
st.partTypeById.set('p4', 'reasoning');
const e = classifyPartDelta({ partID: 'p4', delta: 'more' }, st);
expect(e).toEqual({ type: 'reasoning', text: 'more' });
});
it('returns null for an unknown field', () => {
expect(classifyPartDelta({ partID: 'p5', field: 'other', delta: 'x' }, freshDedup())).toBeNull();
});
});
describe('classifyUpdatedPart (message.part.updated dedup gate)', () => {
function textPart(over: Partial<Part> = {}): Part {
return {
type: 'text',
id: 'p1',
messageID: 'm1',
sessionID: 's1',
text: 'final text',
time: { start: 1, end: 2 },
...over,
} as unknown as Part;
}
it('drops a terminal part already streamed via deltas', () => {
const st = freshDedup();
st.streamedPartKeys.add('text:p1');
expect(classifyUpdatedPart(textPart(), st)).toBeNull();
// the key is consumed
expect(st.streamedPartKeys.has('text:p1')).toBe(false);
});
it('emits a finished (ended) text part not seen via deltas', () => {
const st = freshDedup();
expect(classifyUpdatedPart(textPart(), st)).toEqual({ type: 'text', text: 'final text' });
expect(st.partTypeById.get('p1')).toBe('text');
});
it('does not emit a part that has not ended yet', () => {
const st = freshDedup();
expect(classifyUpdatedPart(textPart({ time: { start: 1 } as never }), st)).toBeNull();
});
it('strips dcp tags from the finished text', () => {
const st = freshDedup();
const part = textPart({ text: 'a <dcp-message-id>m</dcp-message-id>b' });
expect(classifyUpdatedPart(part, st)).toEqual({ type: 'text', text: 'a b' });
});
it('maps a running tool part to tool_call', () => {
const st = freshDedup();
const part = { type: 'tool', callID: 'c1', tool: 'grep', state: { status: 'running' } } as unknown as Part;
const e = classifyUpdatedPart(part, st);
expect(e?.type).toBe('tool_call');
});
it('maps a completed tool part to tool_update', () => {
const st = freshDedup();
const part = { type: 'tool', callID: 'c1', tool: 'grep', state: { status: 'completed', output: 'x' } } as unknown as Part;
const e = classifyUpdatedPart(part, st);
expect(e?.type).toBe('tool_update');
});
});
describe('error formatters', () => {
it('errMsg unwraps Error.message', () => {
expect(errMsg(new Error('x'))).toBe('x');
expect(errMsg('plain')).toBe('plain');
});
it('errToString handles null/string/Error/object', () => {
expect(errToString(null)).toBe('unknown error');
expect(errToString('s')).toBe('s');
expect(errToString(new Error('e'))).toBe('e');
expect(errToString({ a: 1 })).toBe('{"a":1}');
});
});

View File

@@ -0,0 +1,96 @@
import { describe, it, expect } from 'vitest';
import { createPushable } from '../pushable-iterable.js';
/**
* The pushable async-iterable that feeds the Claude SDK's streaming-input query()
* one message per turn while staying open across turns. Tests cover the ordering
* contract (push/close/async-iterate) without any SDK shape.
*/
describe('createPushable — push/iterate ordering', () => {
it('yields buffered values in FIFO order then parks', async () => {
const p = createPushable<number>();
const it = p.iterable[Symbol.asyncIterator]();
p.push(1);
p.push(2);
expect(await it.next()).toEqual({ value: 1, done: false });
expect(await it.next()).toEqual({ value: 2, done: false });
// No more buffered → next() parks; resolve it by pushing.
const parked = it.next();
p.push(3);
expect(await parked).toEqual({ value: 3, done: false });
});
it('hands a value directly to a parked consumer (push after await)', async () => {
const p = createPushable<string>();
const it = p.iterable[Symbol.asyncIterator]();
const pending = it.next(); // parks immediately (empty buffer)
p.push('hello');
expect(await pending).toEqual({ value: 'hello', done: false });
});
it('close() resolves a parked consumer as done and reports done thereafter', async () => {
const p = createPushable<number>();
const it = p.iterable[Symbol.asyncIterator]();
const pending = it.next();
p.close();
expect(await pending).toEqual({ value: undefined, done: true });
expect(await it.next()).toEqual({ value: undefined, done: true });
expect(p.closed).toBe(true);
});
it('still drains values buffered BEFORE close', async () => {
const p = createPushable<number>();
const it = p.iterable[Symbol.asyncIterator]();
p.push(10);
p.push(20);
p.close();
expect(await it.next()).toEqual({ value: 10, done: false });
expect(await it.next()).toEqual({ value: 20, done: false });
expect(await it.next()).toEqual({ value: undefined, done: true });
});
it('drops values pushed after close', async () => {
const p = createPushable<number>();
const it = p.iterable[Symbol.asyncIterator]();
p.close();
p.push(99); // no-op
expect(await it.next()).toEqual({ value: undefined, done: true });
});
it('close() is idempotent', () => {
const p = createPushable<number>();
p.close();
expect(() => p.close()).not.toThrow();
expect(p.closed).toBe(true);
});
it('works with a for-await loop driven by interleaved pushes', async () => {
const p = createPushable<number>();
const seen: number[] = [];
const consumer = (async () => {
for await (const v of p.iterable) seen.push(v);
})();
p.push(1);
await Promise.resolve();
p.push(2);
await Promise.resolve();
p.close();
await consumer;
expect(seen).toEqual([1, 2]);
});
it('return() on the iterator closes the queue (for-await break)', async () => {
const p = createPushable<number>();
const it = p.iterable[Symbol.asyncIterator]();
p.push(1);
expect(await it.next()).toEqual({ value: 1, done: false });
// Simulate a `break` in for-await: the runtime calls return().
expect(await it.return!()).toEqual({ value: undefined, done: true });
expect(p.closed).toBe(true);
p.push(2); // dropped — queue is closed
expect(await it.next()).toEqual({ value: undefined, done: true });
});
});

View File

@@ -0,0 +1,245 @@
/**
* claude-sdk-sessionstore #9 (Part 2) — PURE Claude-SDK message → AgentEvent mapper.
*
* `ClaudeSdkBackend` drives one `query()` per (chat, agent) session and feeds each
* `SDKMessage` it yields through this function, forwarding the returned
* `AgentEvent[]` to the dispatcher's `onEvent` (which maps them to WS frames +
* persists). Kept PURE (one message + a caller-owned accumulator → events) so it's
* unit-testable without a live `claude` binary — the whole point of Part 2's
* typecheck-and-unit-test gate (the live pump needs a host smoke).
*
* SDK shapes (verified against @anthropic-ai/claude-agent-sdk@0.3.159 sdk.d.ts +
* @anthropic-ai/sdk beta messages d.ts):
* - `SDKPartialAssistantMessage` (`type:'stream_event'`) carries a
* `BetaRawMessageStreamEvent` — the LIVE delta stream (only emitted when
* `options.includePartialMessages` is set, which the backend sets). We map:
* · content_block_delta + text_delta → { text }
* · content_block_delta + thinking_delta → { reasoning }
* · content_block_start + tool_use block → { tool_call } (in_progress)
* · content_block_delta + input_json_delta → buffered into the tool's args
* (no event; the assembled input rides the terminal tool_update)
* - `SDKAssistantMessage` (`type:'assistant'`) carries the FINAL `message.content`
* blocks. Text/thinking there are post-hoc repeats of what the partials already
* streamed, so we DROP them (dedup) and only emit a terminal `tool_update`
* (status completed) per `tool_use` block, with its now-complete `input`.
* - All other `SDKMessage` variants (system/init, status, result, hooks, task
* notifications, …) carry no renderable turn content → return [].
*
* Tool assembly spans messages: a tool_use block opens in a partial
* `content_block_start`, its args stream as `input_json_delta` frames keyed by the
* block `index`, and the final assistant message restates the complete block. The
* caller owns a `ClaudeSdkMapState` (snapshot map + per-index tool tracking) that
* threads this across calls, mirroring the `Map<string, AcpToolSnapshot>` the other
* backends pass into `mapSessionUpdate`. The result frames carry the SAME
* `AcpToolSnapshot` shape, so `persistExternalAgentTurn` / `snapshotToWireToolCall`
* are reused unchanged.
*/
import type { SDKMessage } from '@anthropic-ai/claude-agent-sdk';
import type { AgentEvent } from '../agent-backend.js';
import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
/**
* The underlying `@anthropic-ai/sdk` Beta message types (`BetaRawMessageStreamEvent`,
* `BetaContentBlock`) are a TRANSITIVE dep of `@anthropic-ai/claude-agent-sdk` — not
* a direct dependency of apps/coder — so a `@anthropic-ai/sdk/...` import does NOT
* resolve here under pnpm's strict node_modules. We instead DERIVE both shapes from
* the SDK's own exported message types, which is also more correct (it tracks the
* exact `event` / `content` shapes the SDK yields, not a hand-picked import path).
*/
type StreamEvent = Extract<SDKMessage, { type: 'stream_event' }>['event'];
type AssistantContent = Extract<SDKMessage, { type: 'assistant' }>['message']['content'];
type ContentBlock = AssistantContent extends readonly (infer B)[] ? B : never;
type UserContent = Extract<SDKMessage, { type: 'user' }>['message']['content'];
/**
* Caller-owned accumulator threaded across `mapSdkMessage` calls within ONE turn.
* The backend creates a fresh one per turn and clears it at turn end.
*/
export interface ClaudeSdkMapState {
/** Stable tool-call snapshots by tool_use id, merged across start/delta/stop. */
snapshots: Map<string, AcpToolSnapshot>;
/**
* Partial-stream block index → in-flight tool assembly. Anthropic's stream keys
* blocks by a numeric `index`; tool_use args arrive as `input_json_delta`s under
* that index with no id, so we map index→id to route them and buffer the raw
* JSON fragments until the block closes (or the final assistant message lands).
*/
toolByIndex: Map<number, { id: string; name: string; jsonBuf: string }>;
}
/** Construct a fresh per-turn accumulator. */
export function createClaudeSdkMapState(): ClaudeSdkMapState {
return { snapshots: new Map(), toolByIndex: new Map() };
}
/**
* Map one `SDKMessage` → zero or more `AgentEvent`s, mutating `state` for
* cross-message tool assembly + dedup. Pure w.r.t. its inputs otherwise.
*/
export function mapSdkMessage(msg: SDKMessage, state: ClaudeSdkMapState): AgentEvent[] {
switch (msg.type) {
case 'stream_event':
return mapStreamEvent(msg.event, state);
case 'assistant':
return mapFinalAssistant(msg.message.content, state);
case 'user':
// Tool RESULTS ride in as user messages (tool_result blocks): the SDK ran
// the tool and feeds its output back. Without mapping these, the tool_call
// never reaches a terminal snapshot — it persists as status:'running' with
// no output and the UI spinner never stops (the bug this fixes).
return mapUserToolResults(msg.message.content, state);
default:
// system/init, status, result, hooks, task_*, etc. — no turn content here.
// (The backend reads session_id off the init message and usage/cost off the
// result message directly; neither produces a renderable AgentEvent.)
return [];
}
}
/** Live partial-stream delta → AgentEvent(s). */
function mapStreamEvent(event: StreamEvent, state: ClaudeSdkMapState): AgentEvent[] {
switch (event.type) {
case 'content_block_start': {
const block = event.content_block;
if (block.type === 'tool_use') {
const snap: AcpToolSnapshot = {
toolCallId: block.id,
title: block.name,
kind: null,
status: 'in_progress',
rawInput: block.input ?? undefined,
rawOutput: undefined,
};
state.snapshots.set(block.id, snap);
state.toolByIndex.set(event.index, { id: block.id, name: block.name, jsonBuf: '' });
return [{ type: 'tool_call', toolCall: snap }];
}
return [];
}
case 'content_block_delta': {
const delta = event.delta;
if (delta.type === 'text_delta') {
return delta.text ? [{ type: 'text', text: delta.text }] : [];
}
if (delta.type === 'thinking_delta') {
return delta.thinking ? [{ type: 'reasoning', text: delta.thinking }] : [];
}
if (delta.type === 'input_json_delta') {
// Buffer the tool's streamed args under its block index; no event yet —
// the assembled input rides the terminal tool_update (or the final block).
const t = state.toolByIndex.get(event.index);
if (t) t.jsonBuf += delta.partial_json ?? '';
return [];
}
// signature_delta / citations_delta / compaction_delta — nothing to render.
return [];
}
case 'content_block_stop': {
// Close out a streamed tool block: parse its buffered JSON args and emit a
// tool_update carrying the assembled input. The final assistant message will
// restate the same block, but its snapshot is dedup-merged (same id) so this
// is harmless — we emit here so a tool's input renders even if the assistant
// message is delayed/dropped.
const t = state.toolByIndex.get(event.index);
if (!t) return [];
state.toolByIndex.delete(event.index);
const prev = state.snapshots.get(t.id);
const snap: AcpToolSnapshot = {
toolCallId: t.id,
title: prev?.title ?? t.name,
kind: null,
status: 'in_progress',
rawInput: parseJsonOr(t.jsonBuf, prev?.rawInput),
rawOutput: undefined,
};
state.snapshots.set(t.id, snap);
return [{ type: 'tool_update', toolCall: snap }];
}
default:
// message_start / message_delta / message_stop — turn framing, no content.
return [];
}
}
/**
* Final assistant message content blocks. Text/thinking are post-hoc repeats of
* the partial stream → dropped (dedup). Only tool_use blocks emit a terminal
* tool_update carrying the complete `input`.
*/
function mapFinalAssistant(content: ContentBlock[], state: ClaudeSdkMapState): AgentEvent[] {
const out: AgentEvent[] = [];
for (const block of content) {
if (block.type === 'tool_use') {
const prev = state.snapshots.get(block.id);
const snap: AcpToolSnapshot = {
toolCallId: block.id,
title: prev?.title ?? block.name,
kind: null,
status: 'completed',
rawInput: block.input ?? prev?.rawInput,
rawOutput: undefined,
};
state.snapshots.set(block.id, snap);
out.push({ type: 'tool_update', toolCall: snap });
}
// text / thinking / redacted_thinking blocks: already streamed via partials.
}
return out;
}
/**
* User-message tool_result blocks → terminal tool_update events. The SDK runs
* each tool and feeds the output back in a `user` message; we mark the matching
* snapshot completed (or failed, on is_error) WITH its output so the snapshot
* persists/renders as resolved instead of spinning. Unknown ids (no prior
* snapshot) are still surfaced so a stray result isn't silently lost.
*/
function mapUserToolResults(content: UserContent, state: ClaudeSdkMapState): AgentEvent[] {
if (!Array.isArray(content)) return [];
const out: AgentEvent[] = [];
for (const raw of content) {
const block = raw as { type?: string; tool_use_id?: string; content?: unknown; is_error?: boolean };
if (block.type !== 'tool_result' || !block.tool_use_id) continue;
const prev = state.snapshots.get(block.tool_use_id);
const snap: AcpToolSnapshot = {
toolCallId: block.tool_use_id,
title: prev?.title ?? block.tool_use_id,
kind: prev?.kind ?? null,
status: block.is_error ? 'failed' : 'completed',
rawInput: prev?.rawInput,
rawOutput: toolResultText(block.content),
};
state.snapshots.set(block.tool_use_id, snap);
out.push({ type: 'tool_update', toolCall: snap });
}
return out;
}
/** tool_result content is a string OR an array of content blocks (text/image).
* Flatten text blocks; fall back to the raw value so nothing is lost. */
function toolResultText(content: unknown): unknown {
if (typeof content === 'string') return content;
if (Array.isArray(content)) {
const text = content
.map((c) =>
c && typeof c === 'object' && (c as { type?: string }).type === 'text'
? String((c as { text?: unknown }).text ?? '')
: '',
)
.filter(Boolean)
.join('\n');
return text || content;
}
return content ?? '';
}
/** Parse a buffered JSON string; fall back to a prior value on empty/invalid. */
function parseJsonOr(buf: string, fallback: unknown): unknown {
const s = buf.trim();
if (!s) return fallback;
try {
return JSON.parse(s);
} catch {
return fallback;
}
}

View File

@@ -0,0 +1,38 @@
/**
* claude-sdk-sessionstore #9 (Part 2) — claude-SDK-vs-PTY routing predicate.
*
* Sibling to `shouldUseWarmBackend` (warm-acp-routing.ts). The warm Claude-SDK
* backend keys its persistent `query()` on (chat_id, agent) — exactly like the
* warm-ACP / opencode-server backends — so a task only routes to it when it carries
* BOTH a `session_id` and a `chat_id` (a real chat tab).
*
* CRUCIALLY this is ALSO gated behind the `CLAUDE_SDK_BACKEND` env flag (default
* OFF). While off — the production default — claude always falls through to the
* existing one-shot PTY `runExternalAgent` path, UNCHANGED. The live SDK streaming
* pump + cross-turn resume need a host smoke against the real `claude` binary, so
* we keep the working PTY path as the default until that lands. Flip the env var
* on a host (any truthy value) to opt a deployment into the SDK backend.
*
* Pure (env read injected) so it's unit-testable; the dispatcher consumes it.
*/
/** True iff the `CLAUDE_SDK_BACKEND` env flag is set to a truthy value. */
export function claudeSdkBackendEnabled(env: NodeJS.ProcessEnv = process.env): boolean {
const v = env.CLAUDE_SDK_BACKEND;
if (v == null) return false;
const s = v.trim().toLowerCase();
return s !== '' && s !== '0' && s !== 'false' && s !== 'off' && s !== 'no';
}
export function shouldUseClaudeSdk(
task: {
agent: string | null;
session_id: string | null;
chat_id: string | null;
},
env: NodeJS.ProcessEnv = process.env,
): boolean {
if (!claudeSdkBackendEnabled(env)) return false;
if (task.agent !== 'claude') return false;
return task.session_id != null && task.chat_id != null;
}

View File

@@ -0,0 +1,425 @@
/**
* claude-sdk-sessionstore #9 (Part 2) — ClaudeSdkBackend.
*
* A warm, resumable backend for the `claude` agent built on the Claude Agent SDK
* (`@anthropic-ai/claude-agent-sdk`), implementing the Phase-0 `AgentBackend`
* contract (same shape as `WarmAcpBackend` / `OpenCodeServerBackend`). One
* persistent `query()` per (chat, agent) session, driven in STREAMING-INPUT mode:
* the `prompt` is a pushable `AsyncIterable<SDKUserMessage>` that stays open across
* turns, so the SDK subprocess + conversation stay warm between `prompt()` calls
* until `closeSession`/`dispose`.
*
* ⚠ LIVE PUMP IS HOST-ONLY. The actual streaming turn needs the real `claude`
* binary + ANTHROPIC auth on a host — it CANNOT run in the dev container. This file
* is written against the REAL SDK types so it TYPECHECKS, and the PURE pieces (the
* `mapSdkMessage` mapper + the `createPushable` queue) are unit-tested. Routing to
* this backend is gated behind `CLAUDE_SDK_BACKEND` (default OFF) so production
* claude stays on the working PTY path until a host smoke validates the pump +
* cross-turn resume.
*
* Lifecycle (mirrors warm-acp.ts / opencode-server.ts):
* - `ensureSession`: resolve the resume id from `agent_sessions(chat_id,'claude')`
* and (re)build the single `query()` if not already live. The SDK's own
* `sessionStore` (Part 1 PostgresSessionStore) materializes the transcript on
* resume; `options.resume` carries the provider session id.
* - `prompt`: push ONE user message onto the open queue, iterate the generator,
* map each `SDKMessage` → `AgentEvent`s via `mapSdkMessage`, forward to
* `ctx.onEvent`, and resolve when the turn's `result` message lands. Capture the
* `session_id` from the `init` message and persist it to `agent_sessions`;
* accumulate `result.usage` / `total_cost_usd` onto the row (mirrors opencode U.6).
* - `closeSession` / `dispose`: close the queue + dispose the query generator.
* - A thrown error or `result.subtype==='error*'` marks `agent_sessions.status='crashed'`.
*
* Turn serialization: like warm-acp, exactly one turn is in flight at a time on a
* given backend (the dispatcher's per-session `inflight` map enforces this upstream;
* `isBusy()` reports it so the pool never evicts mid-turn).
*/
import { query, type Query, type SDKMessage, type SDKUserMessage, type Options } from '@anthropic-ai/claude-agent-sdk';
import type { FastifyBaseLogger } from 'fastify';
import type { Sql } from '../../db.js';
import { PostgresSessionStore } from './claude-session-store.js';
import { createPushable, type Pushable } from './pushable-iterable.js';
import { mapSdkMessage, createClaudeSdkMapState, type ClaudeSdkMapState } from './claude-sdk-map.js';
import type {
AgentBackend,
AgentSessionHandle,
EnsureSessionOpts,
PromptCtx,
TurnResult,
} from '../agent-backend.js';
export interface ClaudeSdkBackendDeps {
sql: Sql;
log: FastifyBaseLogger;
/** The (chat, agent) this backend serves — its pool identity + DB key. */
chatId: string;
/** Always 'claude' today; kept explicit so the pool key + DB writes stay honest. */
agent: string;
/** Resolved `claude` binary path (available_agents.install_path); null → SDK default. */
installPath: string | null;
}
export class ClaudeSdkBackend implements AgentBackend {
readonly backend = 'claude_sdk' as const;
private readonly sql: Sql;
private readonly log: FastifyBaseLogger;
private readonly chatId: string;
private readonly agent: string;
private readonly installPath: string | null;
private readonly sessionStore: PostgresSessionStore;
/** The single persistent query() generator; null until the first turn builds it. */
private query: Query | null = null;
/** The open input queue feeding the generator one SDKUserMessage per turn. */
private input: Pushable<SDKUserMessage> | null = null;
/** The provider's own session id (resume token), captured from the init message. */
private agentSessionId: string | null = null;
/** Resolved model the live query() was built with; a change forces a rebuild. */
private builtModel: string | null = null;
/** True between prompt() start and settle. */
private busy = false;
private up = false;
constructor(deps: ClaudeSdkBackendDeps) {
this.sql = deps.sql;
this.log = deps.log;
this.chatId = deps.chatId;
this.agent = deps.agent;
this.installPath = deps.installPath;
this.sessionStore = new PostgresSessionStore(deps.sql);
}
/** §2: liveness for the health endpoint + dispatcher fallback decision. */
health(): 'up' | 'down' {
return this.up ? 'up' : 'down';
}
/** Phase 3: busy iff a turn is in flight (pool never evicts a busy backend). */
isBusy(): boolean {
return this.busy;
}
// ─── ensureSession: resolve resume id + (re)build the warm query ──────────────
async ensureSession(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle> {
// Resolve the resume token from the (chat_id, agent) row. A crashed row is not
// resumed (the SDK would fail to load a dead session); we create fresh.
const [row] = await this.sql<{ agent_session_id: string | null; status: string }[]>`
SELECT agent_session_id, status FROM agent_sessions
WHERE chat_id = ${opts.chatId} AND agent = ${opts.agent}
`;
const resumeId = row && row.status !== 'crashed' ? row.agent_session_id : null;
// (Re)build the warm query if there is none, or the model changed (the SDK can
// change model mid-session via setModel, but a fresh build is simplest + matches
// opencode's config-drift → fresh-session rule). The query stays alive across
// turns; only closeSession/dispose tears it down.
if (!this.query || this.builtModel !== opts.model) {
await this.teardownQuery();
this.buildQuery(opts.worktreePath, opts.model, resumeId);
}
// Seed the in-memory resume id from the DB so a handle built before the first
// turn's init message still carries the last-known token. The init message
// overwrites it with the authoritative current id during the turn.
if (this.agentSessionId == null) this.agentSessionId = resumeId;
// Upsert the agent_sessions row (backend='claude_sdk'). agent_session_id may be
// null until the first turn captures it from the init message; prompt() updates it.
await this.sql`
INSERT INTO agent_sessions
(chat_id, session_id, worktree_id, agent, backend, agent_session_id, server_port, status, last_active_at)
VALUES
(${opts.chatId}, ${sessionId}, ${opts.worktreeId}, ${opts.agent}, 'claude_sdk', ${this.agentSessionId}, NULL, 'active', clock_timestamp())
ON CONFLICT (chat_id, agent) DO UPDATE SET
session_id = EXCLUDED.session_id,
worktree_id = EXCLUDED.worktree_id,
backend = 'claude_sdk',
agent_session_id = COALESCE(EXCLUDED.agent_session_id, agent_sessions.agent_session_id),
server_port = NULL,
status = 'active',
last_active_at = clock_timestamp()
`.catch((err) => {
this.log.warn({ err: errMsg(err), chatId: opts.chatId, agent: opts.agent }, 'claude-sdk: agent_sessions upsert failed (non-fatal)');
});
return {
sessionId,
agent: opts.agent,
backend: 'claude_sdk',
chatId: opts.chatId,
worktreeId: opts.worktreeId,
agentSessionId: this.agentSessionId,
serverPort: null,
};
}
/** Build the persistent query() in streaming-input mode. Lazy — no subprocess
* work happens until the generator is first iterated in prompt(). */
private buildQuery(worktreePath: string, model: string, resumeId: string | null): void {
const input = createPushable<SDKUserMessage>();
const options: Options = {
sessionStore: this.sessionStore,
cwd: worktreePath,
// Stream partial assistant messages so text/thinking/tool deltas arrive live
// (the mapper reads them; without this only terminal messages land).
includePartialMessages: true,
// BooCode default: enable the documented 1M-context-window beta. Active on
// models that support it (the SDK lists Sonnet 4/4.5); a non-supporting model
// simply doesn't get the larger window. The TRUE window is read back from
// `result.modelUsage[*].contextWindow` and shown in the ContextBar, so whatever
// window a model actually gets is surfaced truthfully (no guessing).
betas: ['context-1m-2025-08-07'],
...(model ? { model } : {}),
...(resumeId ? { resume: resumeId } : {}),
...(this.installPath ? { pathToClaudeCodeExecutable: this.installPath } : {}),
// ANTHROPIC auth/env must reach the child; inherit the process env (host concern).
env: process.env as Record<string, string>,
};
this.input = input;
this.query = query({ prompt: input.iterable, options });
this.builtModel = model;
this.up = true;
this.log.info({ chatId: this.chatId, agent: this.agent, model, resume: resumeId ?? null }, 'claude-sdk: warm query built');
}
// ─── prompt: push one user message + drain the generator until result ─────────
async prompt(handle: AgentSessionHandle, input: string, ctx: PromptCtx): Promise<TurnResult> {
if (!this.query || !this.input) {
// ensureSession should have built it; rebuild defensively (e.g. evicted/raced).
this.buildQuery(ctx.worktreePath, ctx.model, handle.agentSessionId);
}
const gen = this.query!;
const queue = this.input!;
if (ctx.signal.aborted) return { ok: false, error: 'aborted' };
this.busy = true;
const state: ClaudeSdkMapState = createClaudeSdkMapState();
// Peak per-request input (incl. cache) across the turn ≈ the conversation context
// held in the window. result.usage SUMS input over the turn's internal requests
// (overcounts for multi-tool turns), so the per-request peak is the accurate
// "context used" for the ContextBar (paseo's approach).
let maxInputTokens = 0;
// Per-turn abort: interrupt the in-flight query on the SAME generator (never
// tear down the warm query — that's the pool's lifetime). The generator then
// emits its terminal result and the drain loop exits.
let aborted = false;
const onAbort = () => {
if (aborted) return;
aborted = true;
void gen.interrupt().catch(() => {});
};
ctx.signal.addEventListener('abort', onAbort, { once: true });
// Push the turn's user message onto the open queue. session_id is optional on
// the wire; the SDK manages it via resume + the init message.
const userMsg: SDKUserMessage = {
type: 'user',
message: { role: 'user', content: input },
parent_tool_use_id: null,
...(handle.agentSessionId ? { session_id: handle.agentSessionId } : {}),
};
queue.push(userMsg);
try {
// Manual iteration — NOT `for await (… of gen)`. Returning out of a for-await
// loop calls gen.return(), which CLOSES the async generator; that killed the
// warm streaming-input query after a single turn, so every FOLLOW-UP message
// hit a dead generator and failed. gen.next() leaves the generator suspended
// (alive) for the next pushed user message — the warm query is only closed
// deliberately in teardownQuery()/dispose().
while (true) {
const next = await gen.next();
if (next.done) {
// Generator ended (e.g. disposed) without a result — non-fatal incomplete.
if (aborted) return { ok: false, error: 'aborted' };
return { ok: false, error: 'claude-sdk: query ended before result' };
}
const msg = next.value;
// Track the peak per-request input from message_start usage (delivered by
// includePartialMessages) — the largest single request's input is the real
// context fill, unlike the summed result.usage.
if (msg.type === 'stream_event') {
const sev = msg.event as { type?: string; message?: { usage?: Record<string, unknown> } };
if (sev?.type === 'message_start' && sev.message?.usage) {
const ru = sev.message.usage;
const reqInput =
num(ru.input_tokens) + num(ru.cache_read_input_tokens) + num(ru.cache_creation_input_tokens);
if (reqInput > maxInputTokens) maxInputTokens = reqInput;
}
}
// Capture the provider session id from the init message (authoritative).
if (msg.type === 'system' && msg.subtype === 'init' && msg.session_id) {
if (this.agentSessionId !== msg.session_id) {
this.agentSessionId = msg.session_id;
await this.persistAgentSessionId(msg.session_id);
}
}
// The result message ends THIS turn (it does not close the generator —
// streaming-input keeps it alive for the next pushed message).
if (msg.type === 'result') {
await this.accumulateUsage(msg);
const ok = msg.subtype === 'success' && !aborted;
if (!ok) {
// error_during_execution / error_max_turns / aborted → crashed row.
await this.markCrashed();
} else {
await this.markIdle();
}
if (aborted) return { ok: false, error: 'aborted' };
if (!ok) return { ok: false, error: resultErrorMessage(msg) };
// Context-window telemetry for the ContextBar (paseo's method):
// ctxMax = the model's OWN reported window (1M-aware — reflects the active
// window, so the bar shows the truth per model);
// ctxUsed = peak request input (history in the window) + this turn's output.
const ctxMax = extractMaxContextWindow((msg as { modelUsage?: unknown }).modelUsage);
const fallbackInput =
num(msg.usage?.input_tokens) +
num(msg.usage?.cache_read_input_tokens) +
num(msg.usage?.cache_creation_input_tokens);
const ctxUsed = (maxInputTokens || fallbackInput) + num(msg.usage?.output_tokens);
return {
ok: true,
...(ctxMax > 0 ? { ctxMax } : {}),
...(ctxUsed > 0 ? { ctxUsed } : {}),
};
}
// Map renderable content → AgentEvents for the dispatcher's onEvent.
for (const ev of mapSdkMessage(msg, state)) {
ctx.onEvent(ev);
}
}
} catch (err) {
if (aborted) return { ok: false, error: 'aborted' };
await this.markCrashed();
return { ok: false, error: errMsg(err) };
} finally {
ctx.signal.removeEventListener('abort', onAbort);
this.busy = false;
}
}
// ─── persistence helpers ──────────────────────────────────────────────────────
private async persistAgentSessionId(id: string): Promise<void> {
await this.sql`
UPDATE agent_sessions
SET agent_session_id = ${id}, last_active_at = clock_timestamp()
WHERE chat_id = ${this.chatId} AND agent = ${this.agent}
`.catch((err) => {
this.log.warn({ err: errMsg(err), chatId: this.chatId }, 'claude-sdk: failed to persist agent_session_id (non-fatal)');
});
}
/**
* Accumulate the turn's usage/cost onto the (chat_id, agent) row — mirrors the
* opencode U.6 running-total pattern. The SDK reports usage once per turn on the
* result message (not per step), so this fires once per prompt(). Cache read/write
* input tokens fold into `input_tokens`; usage telemetry never fails a turn.
*/
private async accumulateUsage(result: Extract<SDKMessage, { type: 'result' }>): Promise<void> {
const u = result.usage;
const input = num(u?.input_tokens) + num(u?.cache_read_input_tokens) + num(u?.cache_creation_input_tokens);
const output = num(u?.output_tokens);
const cost = numF(result.total_cost_usd);
if (input === 0 && output === 0 && cost === 0) return;
await this.sql`
UPDATE agent_sessions SET
input_tokens = input_tokens + ${input},
output_tokens = output_tokens + ${output},
cost = cost + ${cost}
WHERE chat_id = ${this.chatId} AND agent = ${this.agent}
`.catch((err) => {
this.log.warn({ err: errMsg(err), chatId: this.chatId }, 'claude-sdk: failed to persist usage (non-fatal)');
});
}
private async markIdle(): Promise<void> {
await this.sql`
UPDATE agent_sessions SET status = 'idle', last_active_at = clock_timestamp()
WHERE chat_id = ${this.chatId} AND agent = ${this.agent}
`.catch(() => {});
}
private async markCrashed(): Promise<void> {
await this.sql`
UPDATE agent_sessions SET status = 'crashed'
WHERE chat_id = ${this.chatId} AND agent = ${this.agent}
`.catch(() => {});
}
// ─── teardown ────────────────────────────────────────────────────────────────
async closeSession(handle: AgentSessionHandle): Promise<void> {
await this.teardownQuery();
await this.sql`
UPDATE agent_sessions SET status = 'closed'
WHERE chat_id = ${handle.chatId} AND agent = ${handle.agent}
`.catch(() => {});
}
async dispose(): Promise<void> {
await this.teardownQuery();
}
/** Close the input queue + dispose the generator. Idempotent. */
private async teardownQuery(): Promise<void> {
this.up = false;
this.busy = false;
const q = this.query;
const queue = this.input;
this.query = null;
this.input = null;
this.builtModel = null;
queue?.close();
if (q) {
// return() ends the AsyncGenerator and lets the SDK clean up its subprocess.
await q.return(undefined).catch(() => {});
}
}
}
// ─── helpers ──────────────────────────────────────────────────────────────────
/** Coerce to a non-negative finite integer (tokens). */
function num(v: unknown): number {
const x = typeof v === 'number' ? v : Number(v);
return Number.isFinite(x) && x > 0 ? Math.round(x) : 0;
}
/** Coerce to a non-negative finite float (cost USD). */
function numF(v: unknown): number {
const x = typeof v === 'number' ? v : Number(v);
return Number.isFinite(x) && x > 0 ? x : 0;
}
/** Largest context-window the SDK reports across `result.modelUsage` (a
* `Record<model, ModelUsage>`, each with a `contextWindow`). This is the model's
* OWN window — 1M when the 1M model/beta is active, 200K otherwise — so the
* ContextBar shows the true window without us mapping model→size ourselves. */
function extractMaxContextWindow(modelUsage: unknown): number {
if (!modelUsage || typeof modelUsage !== 'object') return 0;
let max = 0;
for (const v of Object.values(modelUsage as Record<string, unknown>)) {
if (v && typeof v === 'object') {
const cw = (v as { contextWindow?: unknown }).contextWindow;
if (typeof cw === 'number' && Number.isFinite(cw) && cw > max) max = cw;
}
}
return max;
}
/** Build a human-readable error from an SDK error-result message. */
function resultErrorMessage(result: Extract<SDKMessage, { type: 'result' }>): string {
if (result.subtype === 'success') return 'ok';
const errs = (result as { errors?: string[] }).errors;
if (Array.isArray(errs) && errs.length > 0) return `${result.subtype}: ${errs.join('; ')}`;
return result.subtype;
}
function errMsg(e: unknown): string {
return e instanceof Error ? e.message : String(e);
}

View File

@@ -0,0 +1,117 @@
import type { SessionStore, SessionKey, SessionStoreEntry } from '@anthropic-ai/claude-agent-sdk';
import type { Sql } from '../../db.js';
/**
* claude-sdk-sessionstore #9 (Part 1) — clean-room PostgresSessionStore.
*
* A Postgres-backed implementation of the Claude Agent SDK's `SessionStore`
* adapter type. The SDK mirrors each transcript line (a JSON-safe POJO with a
* `type` discriminant) to this store via `append`; on resume it calls `load`
* to materialize the full transcript back. We treat entries as opaque blobs and
* preserve append order via a BIGSERIAL `id` — `load` replays `ORDER BY id`.
*
* Storage shape: one row per entry in `claude_session_entries`, keyed by the
* SDK's `SessionKey` (project_key, session_id, subpath). The SDK uses an
* *undefined* subpath for the main transcript and disallows the empty string;
* we collapse `undefined → ''` so the main transcript and subagent files share
* one table, distinguished by the `subpath` column (`'' = main`).
*
* Clean-room: written against the SDK's published `SessionStore` type contract
* and BooCode's existing SQL conventions (porsager tagged templates, `sql.json`
* for JSONB). No SDK example/reference code was consulted.
*/
export class PostgresSessionStore implements SessionStore {
constructor(private readonly sql: Sql) {}
/**
* Mirror a batch of transcript entries. No-op on an empty batch; otherwise a
* single multi-row INSERT writes them in array order. Because `id` is a
* monotonically-increasing BIGSERIAL, the insert order is the replay order
* `load` reconstructs — entries within one call land in the order given.
*/
async append(key: SessionKey, entries: SessionStoreEntry[]): Promise<void> {
if (entries.length === 0) return;
const subpath = key.subpath ?? '';
const rows = entries.map((entry) => ({
project_key: key.projectKey,
session_id: key.sessionId,
subpath,
entry: this.sql.json(entry as never),
}));
await this.sql`
INSERT INTO claude_session_entries ${this.sql(rows, 'project_key', 'session_id', 'subpath', 'entry')}
`;
}
/**
* Load a full transcript for resume. Returns the entries in append order, or
* `null` for a (project_key, session_id, subpath) key that was never written.
*/
async load(key: SessionKey): Promise<SessionStoreEntry[] | null> {
const subpath = key.subpath ?? '';
const rows = await this.sql<{ entry: SessionStoreEntry }[]>`
SELECT entry
FROM claude_session_entries
WHERE project_key = ${key.projectKey}
AND session_id = ${key.sessionId}
AND subpath = ${subpath}
ORDER BY id
`;
if (rows.length === 0) return null;
return rows.map((r) => r.entry);
}
/**
* List the main transcripts for a project. `mtime` is the storage write time
* (latest `created_at` for the session) in Unix epoch milliseconds; the SDK
* sorts the result by mtime descending.
*/
async listSessions(projectKey: string): Promise<Array<{ sessionId: string; mtime: number }>> {
const rows = await this.sql<{ session_id: string; mtime: string }[]>`
SELECT session_id, extract(epoch FROM max(created_at)) * 1000 AS mtime
FROM claude_session_entries
WHERE project_key = ${projectKey}
AND subpath = ''
GROUP BY session_id
`;
return rows.map((r) => ({ sessionId: r.session_id, mtime: Number(r.mtime) }));
}
/**
* Delete a session. With a `subpath` set, only that subpath's rows are
* removed; with `subpath` omitted, every row for the session is removed
* (all subpaths, including the main transcript).
*/
async delete(key: SessionKey): Promise<void> {
if (key.subpath !== undefined) {
await this.sql`
DELETE FROM claude_session_entries
WHERE project_key = ${key.projectKey}
AND session_id = ${key.sessionId}
AND subpath = ${key.subpath}
`;
return;
}
await this.sql`
DELETE FROM claude_session_entries
WHERE project_key = ${key.projectKey}
AND session_id = ${key.sessionId}
`;
}
/**
* List the distinct non-main subpaths under a session (e.g. subagent files).
* Used during resume to discover and materialize subagent transcripts; the
* main transcript (`subpath = ''`) is excluded.
*/
async listSubkeys(key: { projectKey: string; sessionId: string }): Promise<string[]> {
const rows = await this.sql<{ subpath: string }[]>`
SELECT DISTINCT subpath
FROM claude_session_entries
WHERE project_key = ${key.projectKey}
AND session_id = ${key.sessionId}
AND subpath <> ''
`;
return rows.map((r) => r.subpath);
}
}

View File

@@ -0,0 +1,203 @@
/**
* Pure opencode `Event` → normalized `AgentEvent` translation.
*
* Extracted (v2.7 audit reshape) from `OpenCodeServerBackend.dispatchEvent` /
* `handleUpdatedPart` and the file-local helpers. NO I/O, no timers, no DB, no
* `byOpencodeId` — every function here is a deterministic transform over its
* arguments (the dedup state is caller-owned and mutated in place, mirroring the
* `acp-event-map.ts` `priorSnapshots` pattern). This is the unit-testable core; the
* backend keeps the routing + side effects (watchdog, usage persistence, settle).
*
* Depends only on SDK TYPES + AcpToolSnapshot — safe to import anywhere.
*/
import type { Event, Part, ToolPart, ToolState } from '@opencode-ai/sdk/v2/client';
import type { ToolCallStatus } from '@agentclientprotocol/sdk';
import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
import type { AgentEvent } from '../agent-backend.js';
/** Per-(opencode session) dedup state the part-stream classifiers read + mutate. */
export interface DedupState {
/** dedup gate: `${type}:${id}` added on delta, deleted-and-tested on updated. */
streamedPartKeys: Set<string>;
/** partID → 'text' | 'reasoning', so a delta with a non-'reasoning' field is still classed right. */
partTypeById: Map<string, string>;
}
/** Strip opencode-dcp plugin tags that render as literal text in the UI. */
export function stripDcpTags(s: string): string {
return s.replace(/<dcp-message-id>[^<]*<\/dcp-message-id>/g, '');
}
/** Extract the opencode sessionID an event belongs to, across event shapes.
* Most carry `properties.sessionID`; `message.part.updated` nests it under
* `properties.part.sessionID`. Returns null when the event has no session
* (the per-session loop then leaves it to dispatchEvent, which drops it). */
export function eventSessionId(ev: Event): string | null {
const props = (ev as { properties?: unknown }).properties;
if (!props || typeof props !== 'object') return null;
if (ev.type === 'message.part.updated') {
const part = (props as { part?: { sessionID?: string } }).part;
return part?.sessionID ?? null;
}
return (props as { sessionID?: string }).sessionID ?? null;
}
/** Ported verbatim from Paseo opencode-agent.ts: id → message-id fallback → null. */
export function resolvePartDedupeKey(part: { id: string; messageID: string }, type: string): string | null {
if (part.id.trim().length > 0) return `${type}:${part.id}`;
if (part.messageID.trim().length > 0) return `${type}:message:${part.messageID}`;
return null;
}
export function mapToolStatus(s: ToolState['status'] | undefined): ToolCallStatus | null {
switch (s) {
case 'pending':
return 'pending';
case 'running':
return 'in_progress';
case 'completed':
return 'completed';
case 'error':
return 'failed';
default:
return null;
}
}
/** opencode ToolPart → ACP-shaped snapshot (reuses the existing persist/render path). */
export function toolPartToSnapshot(part: ToolPart): AcpToolSnapshot {
const state = part.state;
let rawInput: unknown;
let rawOutput: unknown;
let title: string | undefined;
if (state) {
if ('input' in state) rawInput = (state as { input?: unknown }).input;
if ('output' in state) rawOutput = (state as { output?: unknown }).output;
else if ('error' in state) rawOutput = (state as { error?: unknown }).error;
if ('title' in state) title = (state as { title?: string }).title;
}
return {
toolCallId: part.callID,
title: title ?? part.tool,
kind: null,
status: mapToolStatus(state?.status),
rawInput,
rawOutput,
};
}
// ─── session.next.tool.* snapshot builders ───────────────────────────────────
/** `session.next.tool.called` → an in-progress tool_call snapshot. */
export function toolCalledSnapshot(p: { callID: string; tool: string; input: unknown }): AcpToolSnapshot {
return {
toolCallId: p.callID,
title: p.tool,
kind: null,
status: 'in_progress',
rawInput: p.input,
rawOutput: undefined,
};
}
/** `session.next.tool.success` → a completed tool snapshot (text content joined). */
export function toolSuccessSnapshot(p: { callID: string; content?: ReadonlyArray<unknown> | null }): AcpToolSnapshot {
const output = p.content?.map((c) => (c && typeof c === 'object' && 'text' in c ? (c as { text: string }).text : '')).join('') ?? '';
return {
toolCallId: p.callID,
title: p.callID,
kind: null,
status: 'completed',
rawInput: undefined,
rawOutput: output,
};
}
/** `session.next.tool.failed` → a failed tool snapshot (error stringified). */
export function toolFailedSnapshot(p: { callID: string; error: unknown }): AcpToolSnapshot {
return {
toolCallId: p.callID,
title: p.callID,
kind: null,
status: 'failed',
rawInput: undefined,
rawOutput: errToString(p.error),
};
}
// ─── message.part.* dedup gate ────────────────────────────────────────────────
/**
* `message.part.delta`: mark the part as streamed (so a later `message.part.updated`
* for the same part is deduped) and return the AgentEvent to emit, or null when the
* field is neither reasoning nor text, or a text delta strips down to empty. Mutates
* `st.streamedPartKeys` exactly as the original inline arm did (the key is recorded
* for text even when the cleaned delta is empty).
*/
export function classifyPartDelta(
p: { partID: string; field?: string; delta: string },
st: DedupState,
): AgentEvent | null {
const isReasoning = p.field === 'reasoning' || st.partTypeById.get(p.partID) === 'reasoning';
if (isReasoning) {
st.streamedPartKeys.add(`reasoning:${p.partID}`);
return { type: 'reasoning', text: p.delta };
}
if (p.field === 'text') {
st.streamedPartKeys.add(`text:${p.partID}`);
const cleaned = stripDcpTags(p.delta);
return cleaned ? { type: 'text', text: cleaned } : null;
}
return null;
}
/**
* `message.part.updated` terminal part: the dedup gate for text/reasoning (drop a
* part already streamed via deltas; otherwise emit the finished text) plus the
* tool-part → tool_call/tool_update mapping. Returns null when nothing should be
* emitted. Mutates `st.partTypeById` / `st.streamedPartKeys` like the original.
*/
export function classifyUpdatedPart(part: Part, st: DedupState): AgentEvent | null {
if (part.type === 'text' || part.type === 'reasoning') {
st.partTypeById.set(part.id, part.type);
const key = resolvePartDedupeKey(part, part.type);
if (key && st.streamedPartKeys.delete(key)) return null; // already streamed via delta
const raw = part.text ?? '';
const text = part.type === 'text' ? stripDcpTags(raw) : raw;
if (text && part.time?.end != null) {
return { type: part.type, text };
}
return null;
}
if (part.type === 'tool') {
const snap = toolPartToSnapshot(part);
const status = part.state?.status;
// tool_call on start (pending/running), tool_update on terminal (completed/error).
// The current ACP path merges both into one frame; the contract keeps them
// distinct because opencode's SSE distinguishes start from result.
return status === 'completed' || status === 'error'
? { type: 'tool_update', toolCall: snap }
: { type: 'tool_call', toolCall: snap };
}
// NOTE: opencode's SSE payload union carries no available-commands event, so the
// AgentEvent 'commands' arm is intentionally never emitted here.
return null;
}
// ─── shared error formatters (pure) ───────────────────────────────────────────
export function errMsg(e: unknown): string {
return e instanceof Error ? e.message : String(e);
}
export function errToString(e: unknown): string {
if (e == null) return 'unknown error';
if (typeof e === 'string') return e;
if (e instanceof Error) return e.message;
try {
return JSON.stringify(e);
} catch {
return String(e);
}
}

View File

@@ -0,0 +1,325 @@
/**
* OpenCodeServerSupervisor — the opencode `serve` child + HTTP client + port +
* health-counter lifecycle, extracted (v2.7 audit reshape) from the backend
* god-class. Owns spawn / ready / crash / proactive-health restart / dispose and
* exposes `client` / `port` / `health()` / `tickHealth()` to the backend.
*
* Session-level recovery (failing in-flight turns, marking agent_sessions crashed,
* tearing down SSE loops) is NOT a process concern — it's delegated back to the
* backend through the injected `hooks.onServerDown` callback, keeping this module
* free of the demux map / SQL / turn state.
*
* v2.7 concurrency hardening: `ensureServer` is guarded against the crash-window
* double-spawn (two concurrent callers each re-spawning on different ports) via a
* synchronous `startInFlight` flag — see `shouldStartServer`.
*/
import { spawn, type ChildProcess } from 'node:child_process';
import { createOpencodeClient, type OpencodeClient } from '@opencode-ai/sdk/v2/client';
import type { FastifyBaseLogger } from 'fastify';
import { decideRestart, DEFAULT_HEALTH_FAILURE_THRESHOLD } from './lifecycle-decisions.js';
import { reclaimPort, waitForPortRelease, freePort } from '../net/port-utils.js';
const READY_TIMEOUT_MS = 30_000;
/** Info handed to the backend when the server goes down (crash or forced restart). */
export interface ServerDownInfo {
code: number | null;
signal: NodeJS.Signals | null;
port: number;
}
export interface SupervisorHooks {
/** True iff ANY pooled session has an in-flight turn (defers a busy restart). */
isBusy: () => boolean;
/** Session-level recovery: fail in-flight turns, mark crashed, drop demux state. */
onServerDown: (info: ServerDownInfo) => void;
}
export interface OpenCodeServerSupervisorDeps {
/** Absolute path to the opencode binary (resolved from available_agents). */
opencodeBinary: string;
log: FastifyBaseLogger;
hooks: SupervisorHooks;
}
/**
* Pure decision for `ensureServer`: should we (re)spawn the server right now?
*
* - A live, ready server (`up && client`) → no.
* - A start already in flight (`startInFlight`) → no, NEVER double-spawn — join the
* running start instead. This is checked BEFORE `serverStarting` because the crash
* handler can null `serverStarting` mid-start (a crash during `await freePort()`),
* and without this guard the `!serverStarting` branch would spawn a second server
* on a different port while the first is still coming up.
* - No start cached/running → yes (fresh start or post-crash re-spawn, since the
* crash handler nulls `serverStarting`).
* - A cached start that already finished, but the child has since died and the crash
* handler hasn't reset us yet → yes.
*/
export function shouldStartServer(s: {
up: boolean;
hasClient: boolean;
serverStarting: boolean;
childDead: boolean;
startInFlight: boolean;
}): boolean {
if (s.up && s.hasClient) return false;
if (s.startInFlight) return false;
if (!s.serverStarting) return true;
if (!s.up && s.childDead) return true;
return false;
}
export class OpenCodeServerSupervisor {
private readonly opencodeBinary: string;
private readonly log: FastifyBaseLogger;
private readonly hooks: SupervisorHooks;
private childProc: ChildProcess | null = null;
private opencodeClient: OpencodeClient | null = null;
private serverPort: number | null = null;
private up = false;
private serverStarting: Promise<void> | null = null;
/** True from the synchronous head of startServer() until it settles — the
* double-spawn guard reads it so a concurrent ensureServer joins instead of
* kicking a second spawn. */
private startInFlight = false;
// Phase 3 busy-aware health monitor (openchamber lift): consecutive failed
// probes + the start of an unhealthy-while-busy window feed `decideRestart`.
private consecutiveHealthFailures = 0;
private unhealthyBusySince = 0;
private restarting: Promise<void> | null = null;
constructor(deps: OpenCodeServerSupervisorDeps) {
this.opencodeBinary = deps.opencodeBinary;
this.log = deps.log;
this.hooks = deps.hooks;
}
/** The live opencode HTTP client, or null between (re)starts. */
get client(): OpencodeClient | null {
return this.opencodeClient;
}
/** The current server port, or null before the first start. */
get port(): number | null {
return this.serverPort;
}
/** §2: liveness for the health endpoint + dispatcher fallback decision. */
health(): 'up' | 'down' {
return this.up ? 'up' : 'down';
}
isUp(): boolean {
return this.up;
}
// ─── lifecycle (spawn once + client + ready; crash-restart) ──────────────────
/**
* Lazy: start the single server on first use; re-spawn after a crash. Idempotent
* within one live server — `serverStarting` caches the in-flight start, reset to
* null by the crash handler so the NEXT ensureServer re-spawns. A dead-but-not-
* yet-reaped child (exit handler raced) is also treated as needing a restart.
* Concurrent callers in a crash window are coalesced via `startInFlight`.
*/
ensureServer(): Promise<void> {
if (this.up && this.opencodeClient) return Promise.resolve();
const childDead =
this.childProc != null && (this.childProc.exitCode !== null || this.childProc.signalCode !== null);
if (
shouldStartServer({
up: this.up,
hasClient: this.opencodeClient != null,
serverStarting: this.serverStarting != null,
childDead,
startInFlight: this.startInFlight,
})
) {
this.serverStarting = this.startServer();
}
return this.serverStarting ?? Promise.resolve();
}
private async startServer(): Promise<void> {
// Set synchronously (before the first await) so a concurrent ensureServer sees
// the in-flight start and joins `serverStarting` instead of double-spawning.
this.startInFlight = true;
try {
const port = await freePort();
// Phase 1: run unsecured on loopback (opencode's documented default — serve.ts
// only WARNS when OPENCODE_SERVER_PASSWORD is unset). The real boundary is the
// 127.0.0.1 bind.
const child = spawn(this.opencodeBinary, ['serve', '--hostname', '127.0.0.1', '--port', String(port)], {
stdio: ['ignore', 'pipe', 'pipe'],
env: { ...process.env },
});
this.childProc = child;
this.serverPort = port;
// Child lifetime is the backend's (the pool's), NOT a request's. On unexpected
// exit we recover: settle in-flight turns, mark sessions crashed (the backend's
// onServerDown), reclaim the port, and reset state so the next ensureServer
// re-spawns.
child.on('exit', (code, signal) => {
// Only react to THIS child's exit (a restart may have swapped in a new one).
if (this.childProc !== child) return;
this.handleCrash(code, signal, port);
});
await waitForReady(child, READY_TIMEOUT_MS);
this.opencodeClient = createOpencodeClient({ baseUrl: `http://127.0.0.1:${port}` });
this.up = true;
this.log.info({ port }, 'opencode-server: ready');
} finally {
this.startInFlight = false;
}
}
/**
* Server down (crash-exit or forced restart): reset process/port state, delegate
* session-level recovery to the backend, and reclaim the port. Mirrors the
* original `handleServerCrash` ordering (up=false → session cleanup → client/
* serverStarting null → reclaimPort).
*/
private handleCrash(code: number | null, signal: NodeJS.Signals | null, port: number): void {
this.up = false;
this.hooks.onServerDown({ code, signal, port });
this.opencodeClient = null;
this.serverStarting = null; // force a re-spawn on the next ensureServer
// Reclaim the port so a re-spawn on a fixed/leaked port isn't blocked. Best
// effort; the next start uses a fresh ephemeral port anyway.
reclaimPort(port);
}
/**
* Phase 3 proactive health monitor (openchamber `runHealthCheckCycle` lift,
* busy-aware). Probes /global/health; on a sustained failure of a NON-busy server,
* force a restart so the next turn isn't blocked by a wedged process. Busy servers
* are deferred via the stale-grace in `decideRestart`. No-op when never started or
* a restart is already in flight.
*/
async tickHealth(now: number = Date.now()): Promise<void> {
if (!this.childProc || this.restarting) return;
const childExited = this.childProc.exitCode !== null || this.childProc.signalCode !== null;
// An exited child is recovered lazily by ensureServer; don't double-restart it.
if (childExited) return;
const healthy = await this.probeHealth();
if (healthy) {
this.consecutiveHealthFailures = 0;
this.unhealthyBusySince = 0;
return;
}
this.consecutiveHealthFailures += 1;
const busy = this.hooks.isBusy();
const decision = decideRestart({
processExited: false,
consecutiveFailures: this.consecutiveHealthFailures,
busy,
unhealthyBusySince: this.unhealthyBusySince,
now,
failureThreshold: DEFAULT_HEALTH_FAILURE_THRESHOLD,
});
// Stamp the start of an unhealthy-while-busy window so the stale-grace can fire.
if (busy && this.unhealthyBusySince === 0) this.unhealthyBusySince = now;
if (decision.action === 'restart') {
this.log.warn(
{ failures: this.consecutiveHealthFailures, busy, reason: decision.reason },
'opencode-server: health monitor forcing restart',
);
this.consecutiveHealthFailures = 0;
this.unhealthyBusySince = 0;
await this.restartServer();
}
}
private async probeHealth(): Promise<boolean> {
if (!this.opencodeClient) return false;
try {
const res = await this.opencodeClient.global.health();
return !res.error;
} catch {
return false;
}
}
/** Force-kill the current server + reclaim its port; the next ensureServer
* re-spawns (lazy). Mirrors handleCrash's state reset but is initiated by the
* health monitor rather than the OS. */
private async restartServer(): Promise<void> {
if (this.restarting) return this.restarting;
this.restarting = (async () => {
const child = this.childProc;
const port = this.serverPort;
this.up = false;
// Fail in-flight turns + mark sessions crashed via the same path as a crash.
if (child) {
this.handleCrash(null, null, port ?? 0);
if (!child.killed) child.kill('SIGTERM');
}
if (port) {
reclaimPort(port);
await waitForPortRelease(port, 3_000);
}
this.childProc = null;
})().finally(() => {
this.restarting = null;
});
return this.restarting;
}
/** Full teardown of the child + client + port state. */
async dispose(): Promise<void> {
this.up = false;
const child = this.childProc;
this.childProc = null;
this.opencodeClient = null;
if (child && !child.killed) {
child.kill('SIGTERM');
const t = setTimeout(() => {
if (!child.killed) child.kill('SIGKILL');
}, 5_000);
t.unref();
}
}
}
/** Resolve when the child prints the ready line; reject on timeout or early exit. */
function waitForReady(child: ChildProcess, timeoutMs: number): Promise<void> {
return new Promise((resolve, reject) => {
let done = false;
let stderrBuf = '';
const finish = (err?: Error) => {
if (done) return;
done = true;
clearTimeout(timer);
child.stdout?.off('data', onOut);
child.stderr?.off('data', onErr);
child.off('exit', onExit);
if (err) reject(err);
else resolve();
};
const onOut = (buf: Buffer) => {
if (buf.toString().includes('opencode server listening on')) finish();
};
const onErr = (buf: Buffer) => {
stderrBuf += buf.toString();
};
const onExit = (code: number | null) =>
finish(new Error(`opencode serve exited before ready (code ${code}); stderr: ${stderrBuf.slice(-2000)}`));
const timer = setTimeout(
() => finish(new Error(`opencode serve not ready in ${timeoutMs}ms; stderr: ${stderrBuf.slice(-2000)}`)),
timeoutMs,
);
child.stdout?.on('data', onOut);
child.stderr?.on('data', onErr);
child.on('exit', onExit);
});
}

View File

@@ -1,91 +1,64 @@
/**
* v2.6 Phase 1 — OpenCodeServerBackend.
* v2.6 Phase 1 — OpenCodeServerBackend (slimmed, v2.7 audit reshape).
*
* Warm, multi-turn backend for the `opencode` agent. One `opencode serve` HTTP
* server per BooCoder process; one opencode session per BooCode session (resumed
* on switch-back); one SSE read loop PER session, each scoped to that session's
* worktree directory so sessions in different directories stream concurrently
* (P1.5-a — replaced the Phase-1 single-stream-last-directory model).
* worktree directory so sessions in different directories stream concurrently.
*
* This file is now just the `AgentBackend` SURFACE — ensureSession / prompt /
* accumulateUsage / closeSession + the per-session demux side effects (watchdog,
* reconcile, usage). It composes three extracted collaborators:
* - `OpenCodeServerSupervisor` (opencode-server-process.ts) — child/client/port/
* health lifecycle, spawn/crash/restart/dispose.
* - the per-session SSE loop (opencode-sse.ts) — subscribe + reconnect/backoff.
* - the pure event map (opencode-event-map.ts) — Event → AgentEvent translation,
* dedup gate, dcp-strip, tool-snapshot.
*
* Implements the Phase 0 `AgentBackend` interface. Emits transport-agnostic
* `AgentEvent`s the dispatcher (Phase 1.7, NOT wired in this batch) maps them
* to WS frames. No dispatcher/route references this file yet.
* `AgentEvent`s; the dispatcher maps them to WS frames.
*
* Spec: openspec/changes/v2-6-persistent-agent-sessions/design.md §2 / §2a.
* SDK shapes verified by direct read of @opencode-ai/sdk@1.15.12 dist .d.ts:
* - client methods take FLATTENED params (sessionID/directory/body all inline),
* not {path,query,body}. create→{directory}, promptAsync→{sessionID,directory,
* parts,model}, abort→{sessionID,directory}. model is {providerID,modelID}.
* - client.event() resolves to { stream: AsyncGenerator<GlobalEvent> }; the
* real event is chunk.payload (discriminate on chunk.payload.type).
* - promptAsync is fire-and-forget (204); the turn completes via a
* 'session.idle' event for that opencode session id.
*/
import { spawn, spawnSync, type ChildProcess } from 'node:child_process';
import { createHash } from 'node:crypto';
import { createServer, connect as netConnect } from 'node:net';
import type { FastifyBaseLogger } from 'fastify';
import {
createOpencodeClient,
type OpencodeClient,
type Event,
type Part,
type ToolPart,
type ToolState,
type AssistantMessage,
} from '@opencode-ai/sdk/v2/client';
import type { ToolCallStatus } from '@agentclientprotocol/sdk';
import type { Event, AssistantMessage } from '@opencode-ai/sdk/v2/client';
import type { Sql } from '../../db.js';
import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
import { armAbortGuard, noteTurnActivity, consumeTerminal } from './turn-guard.js';
import { stepEndedToUsage, type StepUsage } from './opencode-usage.js';
import { decideRestart, DEFAULT_HEALTH_FAILURE_THRESHOLD } from './lifecycle-decisions.js';
import { OpenCodeServerSupervisor, type ServerDownInfo } from './opencode-server-process.js';
import {
startSessionEventLoop,
type SessionState,
type TurnState,
type SseLoopDeps,
} from './opencode-sse.js';
import {
classifyPartDelta,
classifyUpdatedPart,
toolCalledSnapshot,
toolSuccessSnapshot,
toolFailedSnapshot,
stripDcpTags,
errMsg,
errToString,
} from './opencode-event-map.js';
import type {
AgentBackend,
AgentEvent,
AgentSessionHandle,
EnsureSessionOpts,
PromptCtx,
TurnResult,
} from '../agent-backend.js';
const READY_TIMEOUT_MS = 30_000;
const SSE_RECONNECT_DELAY_MS = 1_000;
/**
* No-activity backstop for an in-flight turn. opencode streams reasoning/text/tool
* deltas continuously while working, so "zero events for this long" means the turn
* is wedged or its terminal event (session.idle) was lost (see the reconnect race
* below). Generous so a legitimately slow turn never trips it.
* is wedged or its terminal event (session.idle) was lost. Generous so a
* legitimately slow turn never trips it.
*/
const TURN_INACTIVITY_MS = 180_000;
/** One in-flight turn's emitter + completion settler. */
interface TurnState {
onEvent: (e: AgentEvent) => void;
settle: (r: TurnResult) => void;
}
/** Per-(opencode session) demux state. dedup sets scoped here, cleared per turn. */
interface SessionState {
boocodeSessionId: string;
agentSessionId: string;
/** Worktree directory for SDK `directory` routing; refreshed each turn from ctx. */
worktreePath: string;
/** dedup gate: `${type}:${id}` added on delta, deleted-and-tested on updated. Cleared at turn end. */
streamedPartKeys: Set<string>;
/** partID → 'text' | 'reasoning', so a delta with a non-'reasoning' field is still classed right. Cleared at turn end. */
partTypeById: Map<string, string>;
activeTurn: TurnState | null;
/** Inactivity backstop timer for the active turn; null when no turn in flight. */
watchdog: ReturnType<typeof setTimeout> | null;
/** Per-session SSE subscription handle. Non-null while the loop is running;
* aborting it tears down the underlying fetch and exits the loop. */
sseAbort: AbortController | null;
/** F.1 post-abort orphan-terminal guard: swallow the one session.idle/error
* opencode emits for an aborted turn so it can't settle the next turn. */
swallowNextTerminal: boolean;
}
export interface OpenCodeServerBackendDeps {
sql: Sql;
log: FastifyBaseLogger;
@@ -98,36 +71,32 @@ export class OpenCodeServerBackend implements AgentBackend {
private readonly sql: Sql;
private readonly log: FastifyBaseLogger;
private readonly opencodeBinary: string;
private child: ChildProcess | null = null;
private client: OpencodeClient | null = null;
private port: number | null = null;
private up = false;
private serverStarting: Promise<void> | null = null;
// Phase 3 busy-aware health monitor (openchamber lift): consecutive failed
// probes + the start of an unhealthy-while-busy window feed `decideRestart`.
private consecutiveHealthFailures = 0;
private unhealthyBusySince = 0;
private restarting: Promise<void> | null = null;
private readonly supervisor: OpenCodeServerSupervisor;
/** opencode session id → demux state. Maintained by ensureSession; read by the SSE loop. */
private readonly byOpencodeId = new Map<string, SessionState>();
/** Coalesces concurrent ensureSession calls for the same (chat, agent) key. */
private readonly ensuring = new Map<string, Promise<AgentSessionHandle>>();
constructor(deps: OpenCodeServerBackendDeps) {
this.sql = deps.sql;
this.log = deps.log;
this.opencodeBinary = deps.opencodeBinary;
this.supervisor = new OpenCodeServerSupervisor({
opencodeBinary: deps.opencodeBinary,
log: deps.log,
hooks: {
isBusy: () => this.isBusy(),
onServerDown: (info) => this.onServerDown(info),
},
});
}
/** §2: liveness for the health endpoint + dispatcher fallback decision. */
health(): 'up' | 'down' {
return this.up ? 'up' : 'down';
return this.supervisor.health();
}
/** Phase 3: busy iff ANY pooled opencode session has an in-flight turn. The
* pool reads this to skip idle/LRU eviction and the health-monitor to defer a
* restart (never tear down a session mid-stream). */
/** Phase 3: busy iff ANY pooled opencode session has an in-flight turn. */
isBusy(): boolean {
for (const st of this.byOpencodeId.values()) {
if (st.activeTurn) return true;
@@ -135,72 +104,23 @@ export class OpenCodeServerBackend implements AgentBackend {
return false;
}
// ─── Server lifecycle (1.2: spawn once + client + ready; Phase 3 crash-restart) ──
/**
* Lazy: start the single server on first use; re-spawn after a crash. Idempotent
* within one live server — `serverStarting` caches the in-flight start, and is
* reset to null by the crash handler so the NEXT ensureServer re-spawns a fresh
* server (Phase 3 crash recovery). A dead-but-not-yet-reaped child (exit handler
* raced) is also treated as needing a restart.
*/
private ensureServer(): Promise<void> {
const childDead = this.child != null && (this.child.exitCode !== null || this.child.signalCode !== null);
if (!this.serverStarting || (!this.up && childDead)) {
this.serverStarting = this.startServer();
}
return this.serverStarting;
}
private async startServer(): Promise<void> {
const port = await freePort();
// Phase 1: run unsecured on loopback (opencode's documented default — serve.ts
// only WARNS when OPENCODE_SERVER_PASSWORD is unset). The real boundary is the
// 127.0.0.1 bind. Defense-in-depth basic-auth is deferred: the hey-api client's
// auth wiring + opencode's exact scheme must be confirmed against a live server
// first, else every request 401s. Recon explicitly said "do NOT block on it".
const child = spawn(this.opencodeBinary, ['serve', '--hostname', '127.0.0.1', '--port', String(port)], {
stdio: ['ignore', 'pipe', 'pipe'],
env: { ...process.env },
});
this.child = child;
this.port = port;
// Child lifetime is the backend's (the pool's), NOT a request's. We never tie
// it to a per-turn abort signal. Phase 3: on unexpected exit we recover —
// settle any in-flight turns as failed, mark their agent_sessions rows crashed,
// and reset `serverStarting` so the next ensureServer re-spawns. opencode keeps
// sessions on disk, but a fresh server's in-memory state is gone, so the next
// turn's ensureSession (rows now 'crashed') creates fresh opencode sessions.
child.on('exit', (code, signal) => {
// Only react to THIS child's exit (a restart may have swapped in a new one).
if (this.child !== child) return;
this.handleServerCrash(code, signal, port);
});
await waitForReady(child, READY_TIMEOUT_MS);
this.client = createOpencodeClient({ baseUrl: `http://127.0.0.1:${port}` });
this.up = true;
this.log.info({ port }, 'opencode-server: ready');
/** Phase 3 proactive health probe + busy-aware self-restart, run by the pool's
* periodic sweep. Delegates to the supervisor. */
async tickHealth(now: number = Date.now()): Promise<void> {
await this.supervisor.tickHealth(now);
}
/**
* Crash handler (Phase 3, lift of openchamber's restart-on-exit path). The
* server died with N live opencode sessions; we can't restart it here (the next
* turn does, lazily — avoids a restart storm if the binary is broken). We:
* 1. fail every in-flight turn so its dispatcher unblocks + publishes an error,
* 2. mark each session's agent_sessions row 'crashed' so ensureSession won't
* resume a now-dead native session id (it creates fresh),
* 3. tear down the SSE loops + demux state (stale against the dead server),
* 4. reclaim the port + reset state so the next ensureServer re-spawns.
* Server down (crash-exit or forced restart): fail every in-flight turn so its
* dispatcher unblocks, mark each session crashed so ensureSession won't resume a
* now-dead native id, and tear down the SSE loops + demux state. Invoked by the
* supervisor (it owns the process/port reset). Mirrors the original
* handleServerCrash session-half byte-for-byte.
*/
private handleServerCrash(code: number | null, signal: NodeJS.Signals | null, port: number): void {
this.up = false;
private onServerDown(info: ServerDownInfo): void {
const states = [...this.byOpencodeId.values()];
this.log.warn(
{ code, signal, port, liveSessions: states.length },
{ code: info.code, signal: info.signal, port: info.port, liveSessions: states.length },
'opencode-server: child exited — recovering (fail in-flight, mark crashed, re-spawn next turn)',
);
@@ -219,8 +139,6 @@ export class OpenCodeServerBackend implements AgentBackend {
}
// Drop the demux map: every session id is stale against a fresh server.
this.byOpencodeId.clear();
this.client = null;
this.serverStarting = null; // force a re-spawn on the next ensureServer
if (crashedIds.length > 0) {
this.sql`
@@ -230,146 +148,20 @@ export class OpenCodeServerBackend implements AgentBackend {
this.log.warn({ err: errMsg(err) }, 'opencode-server: failed to mark crashed sessions (non-fatal)');
});
}
// Reclaim the port so a re-spawn on a fixed/leaked port isn't blocked. Best
// effort; the next start uses a fresh ephemeral port anyway.
reclaimPort(port);
}
/**
* Phase 3 proactive health monitor (openchamber `runHealthCheckCycle` lift,
* busy-aware). Probes the server's /global/health; on a sustained failure of a
* NON-busy server, force a restart so the next turn isn't blocked by a wedged
* (hung-but-not-exited) process. Busy servers are deferred via the stale-grace in
* `decideRestart` — never tear down live work. Driven by the pool's periodic
* sweep (best-effort; a crash-exit is already handled by `handleServerCrash` +
* lazy `ensureServer` re-spawn, so this only catches the hung case). No-op when
* the server was never started or a restart is already in flight.
*/
async tickHealth(now: number = Date.now()): Promise<void> {
if (!this.child || this.restarting) return;
const childExited = this.child.exitCode !== null || this.child.signalCode !== null;
// An exited child is recovered lazily by ensureServer; don't double-restart it.
if (childExited) return;
// ─── SSE loop wiring ─────────────────────────────────────────────────────────
const healthy = await this.probeHealth();
if (healthy) {
this.consecutiveHealthFailures = 0;
this.unhealthyBusySince = 0;
return;
}
this.consecutiveHealthFailures += 1;
const busy = this.isBusy();
const decision = decideRestart({
processExited: false,
consecutiveFailures: this.consecutiveHealthFailures,
busy,
unhealthyBusySince: this.unhealthyBusySince,
now,
failureThreshold: DEFAULT_HEALTH_FAILURE_THRESHOLD,
});
// Stamp the start of an unhealthy-while-busy window so the stale-grace can fire.
if (busy && this.unhealthyBusySince === 0) this.unhealthyBusySince = now;
if (decision.action === 'restart') {
this.log.warn(
{ failures: this.consecutiveHealthFailures, busy, reason: decision.reason },
'opencode-server: health monitor forcing restart',
);
this.consecutiveHealthFailures = 0;
this.unhealthyBusySince = 0;
await this.restartServer();
}
}
private async probeHealth(): Promise<boolean> {
if (!this.client) return false;
try {
const res = await this.client.global.health();
return !res.error;
} catch {
return false;
}
}
/** Force-kill the current server + reclaim its port; the next ensureServer
* re-spawns (lazy). Mirrors handleServerCrash's state reset but is initiated by
* the health monitor rather than the OS. */
private async restartServer(): Promise<void> {
if (this.restarting) return this.restarting;
this.restarting = (async () => {
const child = this.child;
const port = this.port;
this.up = false;
// Fail in-flight turns + mark sessions crashed via the same path as a crash.
if (child) {
this.handleServerCrash(null, null, port ?? 0);
if (!child.killed) child.kill('SIGTERM');
}
if (port) {
reclaimPort(port);
await waitForPortRelease(port, 3_000);
}
this.child = null;
})().finally(() => {
this.restarting = null;
});
return this.restarting;
}
// ─── SSE read loop + demux + translate (1.3) + dedup (1.4) ───────────────────
/** Per-session SSE subscription, scoped to the session's worktree directory.
* opencode scopes events by the `directory` query param (defaults to the
* server's cwd if omitted), so two sessions in different worktrees each get
* their own dir-scoped stream and never drop each other's events. Idempotent:
* a no-op if this session's loop is already running. Started from ensureSession
* (and defensively from prompt) once worktreePath is known. */
private startSessionEventLoop(state: SessionState): void {
if (state.sseAbort) return; // already running
const abort = new AbortController();
state.sseAbort = abort;
void this.runSessionEventLoop(state, abort).finally(() => {
// Only clear if this controller is still the live one (a later restart may
// have already installed a new one).
if (state.sseAbort === abort) state.sseAbort = null;
});
}
private async runSessionEventLoop(state: SessionState, abort: AbortController): Promise<void> {
const signal = abort.signal;
while (this.up && this.client && !signal.aborted) {
try {
// Re-read worktreePath each (re)subscribe so a directory refresh is picked
// up on reconnect. Passing `signal` lets close/dispose tear down a stream
// that's parked in `for await` between events.
const sub = await this.client.event.subscribe(
{ directory: state.worktreePath },
{ signal },
);
for await (const ev of sub.stream) {
if (signal.aborted) break;
// Dir-scoped streams should only carry this session's events, but two
// sessions sharing a worktree (possible post-P1.5-b) each receive BOTH
// sessions' events — so drop anything that isn't ours, else the other
// session's deltas get processed twice (once per loop).
const sid = eventSessionId(ev);
if (sid != null && sid !== state.agentSessionId) continue;
this.dispatchEvent(ev);
}
if (this.up && !signal.aborted) {
await this.reconcile(state); // recover an idle/error lost during the gap
await sleep(SSE_RECONNECT_DELAY_MS);
}
} catch (err) {
if (!this.up || signal.aborted) break;
this.log.warn(
{ err: errMsg(err), agentSessionId: state.agentSessionId },
'opencode-server: session event loop error; reconnecting',
);
await this.reconcile(state);
await sleep(SSE_RECONNECT_DELAY_MS);
}
}
/** The dependency bundle the per-session SSE loop reads. */
private sseDeps(): SseLoopDeps {
return {
isUp: () => this.supervisor.isUp(),
getClient: () => this.supervisor.client,
dispatchEvent: (ev) => this.dispatchEvent(ev),
reconcile: (st) => this.reconcile(st),
onReconnectGiveUp: (st) => this.onReconnectGiveUp(st),
log: this.log,
};
}
/** Demux one event to the owning session's active turn. Unknown/between-turns → drop. */
@@ -398,15 +190,7 @@ export class OpenCodeServerBackend implements AgentBackend {
const st = this.byOpencodeId.get(p.sessionID);
if (!st?.activeTurn) return;
this.bumpActivity(st);
const snap: AcpToolSnapshot = {
toolCallId: p.callID,
title: p.tool,
kind: null,
status: 'in_progress',
rawInput: p.input,
rawOutput: undefined,
};
st.activeTurn.onEvent({ type: 'tool_call', toolCall: snap });
st.activeTurn.onEvent({ type: 'tool_call', toolCall: toolCalledSnapshot(p) });
return;
}
case 'session.next.tool.success': {
@@ -414,16 +198,7 @@ export class OpenCodeServerBackend implements AgentBackend {
const st = this.byOpencodeId.get(p.sessionID);
if (!st?.activeTurn) return;
this.bumpActivity(st);
const output = p.content?.map((c) => ('text' in c ? (c as { text: string }).text : '')).join('') ?? '';
const snap: AcpToolSnapshot = {
toolCallId: p.callID,
title: p.callID,
kind: null,
status: 'completed',
rawInput: undefined,
rawOutput: output,
};
st.activeTurn.onEvent({ type: 'tool_update', toolCall: snap });
st.activeTurn.onEvent({ type: 'tool_update', toolCall: toolSuccessSnapshot(p) });
return;
}
case 'session.next.tool.failed': {
@@ -431,15 +206,7 @@ export class OpenCodeServerBackend implements AgentBackend {
const st = this.byOpencodeId.get(p.sessionID);
if (!st?.activeTurn) return;
this.bumpActivity(st);
const snap: AcpToolSnapshot = {
toolCallId: p.callID,
title: p.callID,
kind: null,
status: 'failed',
rawInput: undefined,
rawOutput: errToString(p.error),
};
st.activeTurn.onEvent({ type: 'tool_update', toolCall: snap });
st.activeTurn.onEvent({ type: 'tool_update', toolCall: toolFailedSnapshot(p) });
return;
}
// ─── per-step usage (U.6) — token/cost accounting for opencode sessions ──
@@ -449,8 +216,7 @@ export class OpenCodeServerBackend implements AgentBackend {
if (!st?.activeTurn) return;
this.bumpActivity(st);
// Accumulate this step's normalized usage onto the (chat_id, agent) row.
// Fire-and-forget: a DB hiccup must not stall the turn. opencode emits this
// once per LLM step, so a multi-tool turn sums several deltas.
// Fire-and-forget: a DB hiccup must not stall the turn.
const usage = stepEndedToUsage(p);
void this.accumulateUsage(st, usage);
return;
@@ -461,15 +227,8 @@ export class OpenCodeServerBackend implements AgentBackend {
const st = this.byOpencodeId.get(p.sessionID);
if (!st?.activeTurn) return;
this.bumpActivity(st);
const isReasoning = p.field === 'reasoning' || st.partTypeById.get(p.partID) === 'reasoning';
if (isReasoning) {
st.streamedPartKeys.add(`reasoning:${p.partID}`);
st.activeTurn.onEvent({ type: 'reasoning', text: p.delta });
} else if (p.field === 'text') {
st.streamedPartKeys.add(`text:${p.partID}`);
const cleaned = stripDcpTags(p.delta);
if (cleaned) st.activeTurn.onEvent({ type: 'text', text: cleaned });
}
const e = classifyPartDelta(p, st);
if (e) st.activeTurn.onEvent(e);
return;
}
case 'message.part.updated': {
@@ -477,7 +236,8 @@ export class OpenCodeServerBackend implements AgentBackend {
const st = this.byOpencodeId.get(part.sessionID);
if (!st?.activeTurn) return;
this.bumpActivity(st);
this.handleUpdatedPart(part, st);
const e = classifyUpdatedPart(part, st);
if (e) st.activeTurn.onEvent(e);
return;
}
// ─── lifecycle ─────────────────────────────────────────────────────────
@@ -502,40 +262,6 @@ export class OpenCodeServerBackend implements AgentBackend {
}
}
/** Terminal part: dedup gate for text/reasoning; tool parts → tool_call/tool_update. */
private handleUpdatedPart(part: Part, st: SessionState): void {
const turn = st.activeTurn;
if (!turn) return;
if (part.type === 'text' || part.type === 'reasoning') {
st.partTypeById.set(part.id, part.type);
const key = resolvePartDedupeKey(part, part.type);
if (key && st.streamedPartKeys.delete(key)) return; // already streamed via delta
const raw = part.text ?? '';
const text = part.type === 'text' ? stripDcpTags(raw) : raw;
if (text && part.time?.end != null) {
turn.onEvent({ type: part.type, text });
}
return;
}
if (part.type === 'tool') {
const snap = toolPartToSnapshot(part);
const status = part.state?.status;
// tool_call on start (pending/running), tool_update on terminal (completed/error).
// The current ACP path merges both into one frame; the contract keeps them
// distinct because opencode's SSE distinguishes start from result.
const event: AgentEvent =
status === 'completed' || status === 'error'
? { type: 'tool_update', toolCall: snap }
: { type: 'tool_call', toolCall: snap };
turn.onEvent(event);
return;
}
// NOTE: opencode's SSE payload union carries no available-commands event, so the
// AgentEvent 'commands' arm is intentionally never emitted here (1.3).
}
// ─── turn-completion resilience (watchdog + reconnect reconcile) ─────────────
/** Reset the inactivity backstop on any event routed to a session's active turn. */
@@ -550,8 +276,8 @@ export class OpenCodeServerBackend implements AgentBackend {
st.watchdog.unref?.();
}
/** Watchdog fired: reconcile once; if the server says still-running we can't tell, so fail closed.
* Also mark the agent_sessions row crashed so a stale session isn't resumed next turn. */
/** Watchdog fired: reconcile once; if still-running we can't tell, so fail closed.
* Also mark the agent_sessions row crashed so a stale session isn't resumed. */
private async onTurnStall(st: SessionState): Promise<void> {
const settled = await this.reconcile(st);
if (!settled) {
@@ -564,16 +290,27 @@ export class OpenCodeServerBackend implements AgentBackend {
}
}
/** SSE circuit-breaker fired (reconnect gave up): fail the active turn + mark the
* session crashed so it isn't resumed. The next turn re-creates a fresh session. */
private async onReconnectGiveUp(st: SessionState): Promise<void> {
if (!st.activeTurn) return;
await this.sql`
UPDATE agent_sessions SET status = 'crashed'
WHERE agent_session_id = ${st.agentSessionId}
`.catch(() => {});
st.activeTurn?.settle({ ok: false, error: 'opencode SSE stream lost (reconnect gave up)' });
}
/**
* Ask the server whether this session's turn already finished — recovers a
* session.idle/error lost during an SSE gap. Returns true if it settled the turn.
* Inconclusive (still running / call failed) → false; the watchdog covers that.
*/
private async reconcile(st: SessionState): Promise<boolean> {
const turn = st.activeTurn;
if (!turn || !this.client) return false;
const client = this.supervisor.client;
if (!turn || !client) return false;
try {
const res = await this.client.session.messages({
const res = await client.session.messages({
sessionID: st.agentSessionId,
directory: st.worktreePath,
});
@@ -605,10 +342,8 @@ export class OpenCodeServerBackend implements AgentBackend {
/**
* Accumulate one `session.next.step.ended`'s normalized usage onto the session's
* agent_sessions row, keyed by the resumed `agent_session_id` (unique per active
* row — the dispatcher's `(chat_id, agent)` lookup wrote it). Running totals for
* the whole conversation context (not last-step). Zero-delta steps are skipped to
* avoid a no-op write. Errors are swallowed: usage telemetry must never fail a turn.
* agent_sessions row. Running totals for the whole conversation context. Zero-delta
* steps are skipped. Errors are swallowed: usage telemetry must never fail a turn.
*/
private async accumulateUsage(st: SessionState, u: StepUsage): Promise<void> {
if (u.input === 0 && u.output === 0 && u.cost === 0) return;
@@ -631,13 +366,29 @@ export class OpenCodeServerBackend implements AgentBackend {
// ─── ensureSession: create-or-resume against agent_sessions (1.5) ────────────
async ensureSession(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle> {
await this.ensureServer();
if (!this.client) throw new Error('opencode-server: client not ready after ensureServer');
// Coalesce concurrent first-turns for the same (chat, agent) so the SELECT…
// create…upsert can't race into two opencode sessions (the second orphaning
// the first). A single (non-concurrent) call is unaffected — the entry is set
// and removed within this call. Defensive: the dispatcher already serializes
// turns per (chat, agent) via its inflight map.
const key = `${opts.chatId}:${opts.agent}`;
const existing = this.ensuring.get(key);
if (existing) return existing;
const p = this.ensureSessionInner(sessionId, opts).finally(() => {
if (this.ensuring.get(key) === p) this.ensuring.delete(key);
});
this.ensuring.set(key, p);
return p;
}
private async ensureSessionInner(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle> {
await this.supervisor.ensureServer();
const client = this.supervisor.client;
if (!client) throw new Error('opencode-server: client not ready after ensureServer');
const configHash = sessionConfigHash(opts.model);
// P1.5-b: agent_sessions is keyed (chat_id, agent) — the tab/chat is the
// context unit (two tabs in one session = two contexts sharing one worktree).
// session_id + worktree_id are retained as informational (SET NULL) columns.
const [row] = await this.sql<{ agent_session_id: string | null; status: string; config_hash: string | null }[]>`
SELECT agent_session_id, status, config_hash FROM agent_sessions
WHERE chat_id = ${opts.chatId} AND agent = ${opts.agent}
@@ -655,7 +406,7 @@ export class OpenCodeServerBackend implements AgentBackend {
'opencode-server: not resuming stale session, creating fresh');
this.byOpencodeId.delete(agentSessionId);
}
const created = await this.client.session.create({ directory: opts.worktreePath });
const created = await client.session.create({ directory: opts.worktreePath });
if (created.error || !created.data) {
throw new Error(`opencode-server: session.create failed: ${errToString(created.error)}`);
}
@@ -664,7 +415,7 @@ export class OpenCodeServerBackend implements AgentBackend {
INSERT INTO agent_sessions
(chat_id, session_id, worktree_id, agent, backend, agent_session_id, server_port, status, last_active_at, config_hash)
VALUES
(${opts.chatId}, ${sessionId}, ${opts.worktreeId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.port}, 'active', clock_timestamp(), ${configHash})
(${opts.chatId}, ${sessionId}, ${opts.worktreeId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.supervisor.port}, 'active', clock_timestamp(), ${configHash})
ON CONFLICT (chat_id, agent) DO UPDATE SET
session_id = EXCLUDED.session_id,
worktree_id = EXCLUDED.worktree_id,
@@ -678,7 +429,7 @@ export class OpenCodeServerBackend implements AgentBackend {
} else {
await this.sql`
UPDATE agent_sessions
SET status = 'active', last_active_at = clock_timestamp(), server_port = ${this.port}, config_hash = ${configHash}
SET status = 'active', last_active_at = clock_timestamp(), server_port = ${this.supervisor.port}, config_hash = ${configHash}
WHERE chat_id = ${opts.chatId} AND agent = ${opts.agent}
`;
}
@@ -693,24 +444,13 @@ export class OpenCodeServerBackend implements AgentBackend {
state.boocodeSessionId = sessionId;
state.worktreePath = opts.worktreePath;
} else {
state = {
boocodeSessionId: sessionId,
agentSessionId: ocSessionId,
worktreePath: opts.worktreePath,
streamedPartKeys: new Set(),
partTypeById: new Map(),
activeTurn: null,
watchdog: null,
sseAbort: null,
swallowNextTerminal: false,
};
state = this.makeSessionState(sessionId, ocSessionId, opts.worktreePath);
this.byOpencodeId.set(ocSessionId, state);
}
// Start this session's own SSE loop, scoped to its worktree directory. Both
// fresh-create and resume reach here; idempotent, so a re-ensure (e.g. a
// second turn) won't spawn a duplicate loop.
this.startSessionEventLoop(state);
// fresh-create and resume reach here; idempotent.
startSessionEventLoop(state, this.sseDeps());
return {
sessionId,
@@ -719,40 +459,53 @@ export class OpenCodeServerBackend implements AgentBackend {
chatId: opts.chatId,
worktreeId: opts.worktreeId,
agentSessionId: ocSessionId,
serverPort: this.port,
serverPort: this.supervisor.port,
};
}
/** Fresh per-(opencode session) demux state. */
private makeSessionState(boocodeSessionId: string, agentSessionId: string, worktreePath: string): SessionState {
return {
boocodeSessionId,
agentSessionId,
worktreePath,
streamedPartKeys: new Set(),
partTypeById: new Map(),
activeTurn: null,
watchdog: null,
sseAbort: null,
swallowNextTerminal: false,
};
}
// ─── prompt: send one turn (1.6) ─────────────────────────────────────────────
async prompt(handle: AgentSessionHandle, input: string, ctx: PromptCtx): Promise<TurnResult> {
if (!this.client) throw new Error('opencode-server: client not ready');
const client = this.supervisor.client;
if (!client) throw new Error('opencode-server: client not ready');
const oc = handle.agentSessionId;
if (!oc) throw new Error('opencode-server: handle has no agentSessionId');
let state = this.byOpencodeId.get(oc);
if (!state) {
state = {
boocodeSessionId: handle.sessionId,
agentSessionId: oc,
worktreePath: ctx.worktreePath,
streamedPartKeys: new Set(),
partTypeById: new Map(),
activeTurn: null,
watchdog: null,
sseAbort: null,
swallowNextTerminal: false,
};
state = this.makeSessionState(handle.sessionId, oc, ctx.worktreePath);
this.byOpencodeId.set(oc, state);
}
const session = state;
// v2.7 busy-assert: one in-flight turn per session. The dispatcher serializes
// turns per (chat, agent), so this never fires in normal dispatch — but if a
// second prompt arrives while one is live it would silently overwrite the slot
// and orphan the first turn, so reject instead.
if (session.activeTurn) {
return { ok: false, error: 'opencode-server: session already has an in-flight turn' };
}
// Authoritative per-turn directory for SDK routing + reconcile.
session.worktreePath = ctx.worktreePath;
// Defensive: ensureSession normally starts the loop, but if prompt is reached
// with a freshly-created state (no loop yet), start it so the turn streams.
// Idempotent when ensureSession already started one.
this.startSessionEventLoop(session);
const client = this.client;
startSessionEventLoop(session, this.sseDeps());
return await new Promise<TurnResult>((resolve) => {
let settled = false;
@@ -781,7 +534,8 @@ export class OpenCodeServerBackend implements AgentBackend {
settle({ ok: false, error: 'aborted' });
};
session.activeTurn = { onEvent: ctx.onEvent, settle };
const turn: TurnState = { onEvent: ctx.onEvent, settle };
session.activeTurn = turn;
this.bumpActivity(session); // arm the inactivity backstop
if (ctx.signal.aborted) {
@@ -822,39 +576,15 @@ export class OpenCodeServerBackend implements AgentBackend {
}
async dispose(): Promise<void> {
this.up = false;
// Abort every per-session SSE loop so none survive the teardown.
for (const st of this.byOpencodeId.values()) st.sseAbort?.abort();
const child = this.child;
this.child = null;
this.client = null;
this.byOpencodeId.clear();
if (child && !child.killed) {
child.kill('SIGTERM');
const t = setTimeout(() => {
if (!child.killed) child.kill('SIGKILL');
}, 5_000);
t.unref();
}
await this.supervisor.dispose();
}
}
// ─── helpers ──────────────────────────────────────────────────────────────────
/** Extract the opencode sessionID an event belongs to, across event shapes.
* Most carry `properties.sessionID`; `message.part.updated` nests it under
* `properties.part.sessionID`. Returns null when the event has no session
* (the per-session loop then leaves it to dispatchEvent, which drops it). */
function eventSessionId(ev: Event): string | null {
const props = (ev as { properties?: unknown }).properties;
if (!props || typeof props !== 'object') return null;
if (ev.type === 'message.part.updated') {
const part = (props as { part?: { sessionID?: string } }).part;
return part?.sessionID ?? null;
}
return (props as { sessionID?: string }).sessionID ?? null;
}
/** BooCoder model string "provider/model" → opencode's structured {providerID, modelID}. */
function parseModel(model: string | undefined): { providerID: string; modelID: string } | undefined {
if (!model || !model.trim()) return undefined;
@@ -864,199 +594,14 @@ function parseModel(model: string | undefined): { providerID: string; modelID: s
return { providerID: trimmed.slice(0, idx), modelID: trimmed.slice(idx + 1) };
}
// No slash but non-empty → infer llama-swap (the only configured provider).
// Guard against bare '/' or trailing/leading slash.
if (idx < 0 && trimmed.length > 0) {
return { providerID: 'llama-swap', modelID: trimmed };
}
return undefined;
}
/** Ported verbatim from Paseo opencode-agent.ts: id → message-id fallback → null. */
function resolvePartDedupeKey(part: { id: string; messageID: string }, type: string): string | null {
if (part.id.trim().length > 0) return `${type}:${part.id}`;
if (part.messageID.trim().length > 0) return `${type}:message:${part.messageID}`;
return null;
}
/** opencode ToolPart → ACP-shaped snapshot (reuses the existing persist/render path). */
function toolPartToSnapshot(part: ToolPart): AcpToolSnapshot {
const state = part.state;
let rawInput: unknown;
let rawOutput: unknown;
let title: string | undefined;
if (state) {
if ('input' in state) rawInput = (state as { input?: unknown }).input;
if ('output' in state) rawOutput = (state as { output?: unknown }).output;
else if ('error' in state) rawOutput = (state as { error?: unknown }).error;
if ('title' in state) title = (state as { title?: string }).title;
}
return {
toolCallId: part.callID,
title: title ?? part.tool,
kind: null,
status: mapToolStatus(state?.status),
rawInput,
rawOutput,
};
}
function mapToolStatus(s: ToolState['status'] | undefined): ToolCallStatus | null {
switch (s) {
case 'pending':
return 'pending';
case 'running':
return 'in_progress';
case 'completed':
return 'completed';
case 'error':
return 'failed';
default:
return null;
}
}
/**
* Reclaim a loopback port a dead opencode child may still hold (lift of
* openchamber `killProcessOnPort`). Best-effort, POSIX-only (`lsof`/`kill`); a
* failure is harmless because the next spawn allocates a fresh ephemeral port.
* Never kills this process. Synchronous + short-timeout so the crash handler
* doesn't block.
*/
function reclaimPort(port: number | null): void {
if (!port || process.platform === 'win32') return;
try {
const res = spawnSync('lsof', ['-ti', `:${port}`], { encoding: 'utf8', timeout: 3_000, windowsHide: true });
const out = res.stdout || '';
const myPid = process.pid;
for (const pidStr of out.split(/\s+/)) {
const pid = parseInt(pidStr.trim(), 10);
if (pid && pid !== myPid) {
try {
spawnSync('kill', ['-9', String(pid)], { stdio: 'ignore', timeout: 2_000 });
} catch {
// ignore — best effort
}
}
}
} catch {
// lsof absent or failed — the fresh-ephemeral-port spawn doesn't need this.
}
}
/**
* Resolve true once nothing is listening on `port` (lift of openchamber
* `waitForPortRelease`). Used before re-spawning on a fixed port; with ephemeral
* ports it's a fast no-op. Probes 127.0.0.1; resolves false at the deadline.
*/
function waitForPortRelease(port: number, timeoutMs: number): Promise<boolean> {
const deadline = Date.now() + timeoutMs;
return new Promise((resolve) => {
const attempt = () => {
const socket = netConnect({ port, host: '127.0.0.1' });
let settled = false;
const finish = (released: boolean) => {
if (settled) return;
settled = true;
socket.removeAllListeners();
socket.destroy();
if (released || Date.now() >= deadline) {
resolve(released);
return;
}
setTimeout(attempt, 150);
};
socket.once('connect', () => finish(false));
socket.once('error', (err: NodeJS.ErrnoException) => {
if (err && (err.code === 'ECONNREFUSED' || err.code === 'EHOSTUNREACH')) finish(true);
else finish(false);
});
socket.setTimeout(500, () => finish(true));
};
attempt();
});
}
/** Bind-probe an ephemeral port on loopback. */
function freePort(): Promise<number> {
return new Promise((resolve, reject) => {
const srv = createServer();
srv.unref();
srv.on('error', reject);
srv.listen(0, '127.0.0.1', () => {
const addr = srv.address();
if (addr && typeof addr === 'object') {
const { port } = addr;
srv.close(() => resolve(port));
} else {
srv.close(() => reject(new Error('opencode-server: could not determine a free port')));
}
});
});
}
/** Resolve when the child prints the ready line; reject on timeout or early exit. */
function waitForReady(child: ChildProcess, timeoutMs: number): Promise<void> {
return new Promise((resolve, reject) => {
let done = false;
let stderrBuf = '';
const finish = (err?: Error) => {
if (done) return;
done = true;
clearTimeout(timer);
child.stdout?.off('data', onOut);
child.stderr?.off('data', onErr);
child.off('exit', onExit);
if (err) reject(err);
else resolve();
};
const onOut = (buf: Buffer) => {
if (buf.toString().includes('opencode server listening on')) finish();
};
const onErr = (buf: Buffer) => {
stderrBuf += buf.toString();
};
const onExit = (code: number | null) =>
finish(new Error(`opencode serve exited before ready (code ${code}); stderr: ${stderrBuf.slice(-2000)}`));
const timer = setTimeout(
() => finish(new Error(`opencode serve not ready in ${timeoutMs}ms; stderr: ${stderrBuf.slice(-2000)}`)),
timeoutMs,
);
child.stdout?.on('data', onOut);
child.stderr?.on('data', onErr);
child.on('exit', onExit);
});
}
function sleep(ms: number): Promise<void> {
return new Promise((r) => setTimeout(r, ms));
}
/** Strip opencode-dcp plugin tags that render as literal text in the UI. */
function stripDcpTags(s: string): string {
return s.replace(/<dcp-message-id>[^<]*<\/dcp-message-id>/g, '');
}
function errMsg(e: unknown): string {
return e instanceof Error ? e.message : String(e);
}
function errToString(e: unknown): string {
if (e == null) return 'unknown error';
if (typeof e === 'string') return e;
if (e instanceof Error) return e.message;
try {
return JSON.stringify(e);
} catch {
return String(e);
}
}
/** Hash of stable config — detects model changes across sessions without
* invalidating on ephemeral state like the random server port (which changes
* every BooCoder restart). */
* invalidating on ephemeral state like the random server port. */
function sessionConfigHash(model: string): string {
return createHash('sha256').update(`opencode_server|${model}`).digest('hex').slice(0, 16);
}

View File

@@ -0,0 +1,181 @@
/**
* Per-session SSE subscribe loop + reconnect/backoff + eventSessionId demux.
*
* Extracted (v2.7 audit reshape) from `OpenCodeServerBackend.startSessionEventLoop`
* / `runSessionEventLoop`. opencode scopes events by the `directory` query param, so
* each session runs its own dir-scoped stream and never drops a sibling's events.
*
* The loop is intentionally thin: it owns subscribe + the demux filter + reconnect
* timing only. Translating an event into turn side effects (watchdog, usage,
* settle) stays on the backend via the injected `dispatchEvent` / `reconcile`
* callbacks — `opencode-sse` knows nothing about turns or the DB.
*
* v2.7 concurrency hardening: the throw-driven reconnect path now backs off
* exponentially and trips a circuit-breaker (`onReconnectGiveUp`) after a bounded
* number of consecutive failures, instead of looping forever at a flat 1s. The
* HAPPY PATH is unchanged — a clean stream end (server still up) reconnects after
* `baseMs` (1s, as before) and resets the failure counter, so a long-lived session
* that re-subscribes normally never backs off.
*/
import type { FastifyBaseLogger } from 'fastify';
import type { Event, OpencodeClient } from '@opencode-ai/sdk/v2/client';
import type { AgentEvent } from '../agent-backend.js';
import type { TurnResult } from '../agent-backend.js';
import { eventSessionId, errMsg } from './opencode-event-map.js';
export const SSE_RECONNECT_DELAY_MS = 1_000;
/** One in-flight turn's emitter + completion settler. */
export interface TurnState {
onEvent: (e: AgentEvent) => void;
settle: (r: TurnResult) => void;
}
/** Per-(opencode session) demux state. dedup sets scoped here, cleared per turn. */
export interface SessionState {
boocodeSessionId: string;
agentSessionId: string;
/** Worktree directory for SDK `directory` routing; refreshed each turn from ctx. */
worktreePath: string;
/** dedup gate: `${type}:${id}` added on delta, deleted-and-tested on updated. Cleared at turn end. */
streamedPartKeys: Set<string>;
/** partID → 'text' | 'reasoning', so a delta with a non-'reasoning' field is still classed right. Cleared at turn end. */
partTypeById: Map<string, string>;
activeTurn: TurnState | null;
/** Inactivity backstop timer for the active turn; null when no turn in flight. */
watchdog: ReturnType<typeof setTimeout> | null;
/** Per-session SSE subscription handle. Non-null while the loop is running;
* aborting it tears down the underlying fetch and exits the loop. */
sseAbort: AbortController | null;
/** F.1 post-abort orphan-terminal guard: swallow the one session.idle/error
* opencode emits for an aborted turn so it can't settle the next turn. */
swallowNextTerminal: boolean;
}
// ─── reconnect backoff (pure) ────────────────────────────────────────────────
export interface ReconnectPolicy {
/** First retry delay (and the steady-state clean-reconnect delay). */
baseMs: number;
/** Cap on the exponential delay. */
maxMs: number;
/** Consecutive failures tolerated before the breaker trips (give up). */
maxAttempts: number;
}
export const DEFAULT_RECONNECT_POLICY: ReconnectPolicy = {
baseMs: SSE_RECONNECT_DELAY_MS,
maxMs: 30_000,
maxAttempts: 6,
};
export type ReconnectDecision =
| { action: 'reconnect'; delayMs: number }
| { action: 'give-up' };
/**
* Pure backoff decision after `failures` consecutive throwing reconnect attempts
* (1-based: the first failure passes `failures=1`). Returns an exponentially
* growing delay capped at `maxMs`, or `give-up` once the count exceeds
* `maxAttempts`. `failures=1` yields `baseMs`, so the very first retry matches the
* pre-hardening flat delay (happy-path-preserving).
*/
export function reconnectDecision(
failures: number,
policy: ReconnectPolicy = DEFAULT_RECONNECT_POLICY,
): ReconnectDecision {
if (failures > policy.maxAttempts) return { action: 'give-up' };
const exp = policy.baseMs * 2 ** (failures - 1);
return { action: 'reconnect', delayMs: Math.min(policy.maxMs, exp) };
}
// ─── the loop ────────────────────────────────────────────────────────────────
export interface SseLoopDeps {
/** Live iff the server is up (read each iteration so a crash stops the loop). */
isUp: () => boolean;
/** The current opencode client (null between server restarts). */
getClient: () => OpencodeClient | null;
/** Route one demuxed event to its turn (backend side effects live here). */
dispatchEvent: (ev: Event) => void;
/** Recover an idle/error lost during an SSE gap. Returns true if it settled. */
reconcile: (state: SessionState) => Promise<boolean>;
/** Circuit-breaker: called once the backoff gives up; fail the active turn. */
onReconnectGiveUp: (state: SessionState) => Promise<void> | void;
log: FastifyBaseLogger;
/** Injectable for tests; defaults to a real timer sleep. */
sleep?: (ms: number) => Promise<void>;
policy?: ReconnectPolicy;
}
function defaultSleep(ms: number): Promise<void> {
return new Promise((r) => setTimeout(r, ms));
}
/** Per-session SSE subscription, scoped to the session's worktree directory.
* Idempotent: a no-op if this session's loop is already running. */
export function startSessionEventLoop(state: SessionState, deps: SseLoopDeps): void {
if (state.sseAbort) return; // already running
const abort = new AbortController();
state.sseAbort = abort;
void runSessionEventLoop(state, abort, deps).finally(() => {
// Only clear if this controller is still the live one (a later restart may
// have already installed a new one).
if (state.sseAbort === abort) state.sseAbort = null;
});
}
export async function runSessionEventLoop(
state: SessionState,
abort: AbortController,
deps: SseLoopDeps,
): Promise<void> {
const signal = abort.signal;
const sleep = deps.sleep ?? defaultSleep;
const policy = deps.policy ?? DEFAULT_RECONNECT_POLICY;
let failures = 0;
while (deps.isUp() && deps.getClient() && !signal.aborted) {
const client = deps.getClient()!;
try {
// Re-read worktreePath each (re)subscribe so a directory refresh is picked
// up on reconnect. Passing `signal` lets close/dispose tear down a stream
// that's parked in `for await` between events.
const sub = await client.event.subscribe({ directory: state.worktreePath }, { signal });
for await (const ev of sub.stream) {
if (signal.aborted) break;
// Dir-scoped streams should only carry this session's events, but two
// sessions sharing a worktree (possible post-P1.5-b) each receive BOTH
// sessions' events — so drop anything that isn't ours, else the other
// session's deltas get processed twice (once per loop).
const sid = eventSessionId(ev);
if (sid != null && sid !== state.agentSessionId) continue;
deps.dispatchEvent(ev);
}
// Clean stream end — a healthy reconnect, NOT a failure: recover any lost
// terminal then re-subscribe at the base delay (pre-hardening behavior).
failures = 0;
if (deps.isUp() && !signal.aborted) {
await deps.reconcile(state); // recover an idle/error lost during the gap
await sleep(policy.baseMs);
}
} catch (err) {
if (!deps.isUp() || signal.aborted) break;
failures += 1;
const decision = reconnectDecision(failures, policy);
deps.log.warn(
{ err: errMsg(err), agentSessionId: state.agentSessionId, failures, action: decision.action },
'opencode-server: session event loop error; reconnecting',
);
await deps.reconcile(state);
if (decision.action === 'give-up') {
deps.log.warn(
{ agentSessionId: state.agentSessionId, failures },
'opencode-server: SSE reconnect gave up (circuit breaker) — failing active turn',
);
await deps.onReconnectGiveUp(state);
break;
}
await sleep(decision.delayMs);
}
}
}

View File

@@ -0,0 +1,96 @@
/**
* claude-sdk-sessionstore #9 (Part 2) — a tiny PURE pushable async-iterable.
*
* The Claude Agent SDK's streaming-input mode wants `query({ prompt })` where
* `prompt` is an `AsyncIterable<SDKUserMessage>`. To keep ONE `query()` generator
* alive across many turns (the "warm" property), the backend feeds it ONE user
* message per `prompt()` turn through a queue that stays open between turns and is
* only closed at `closeSession`/`dispose`. This is that queue.
*
* Semantics (the bit worth unit-testing — push/close/iterate ordering):
* - `push(v)` enqueues a value. If a consumer is parked in `await next()`, it's
* handed the value immediately; otherwise the value buffers in FIFO order.
* - The async iterator yields buffered/pushed values in push order, and PARKS
* (never busy-loops) when the buffer is empty — so the SDK generator waits for
* the next turn's message instead of seeing end-of-input.
* - `close()` ends the iterable: any parked consumer resolves `{done:true}` and
* all future `next()`s return done. Values pushed after close are dropped.
* - It's single-consumer (one `query()` reads it); concurrent consumers are not a
* supported shape and not needed here.
*
* No SDK import — generic over the pushed value `T` — so the pure push/close/iterate
* ordering is testable without the `SDKUserMessage` shape or a live binary.
*/
export interface Pushable<T> {
/** Enqueue a value (or hand it to a parked consumer). No-op after close. */
push(value: T): void;
/** End the iterable. Idempotent; a parked consumer resolves done. */
close(): void;
/** True once `close()` has been called. */
readonly closed: boolean;
/** The async-iterable the consumer (the SDK `query`) drives. */
readonly iterable: AsyncIterable<T>;
}
export function createPushable<T>(): Pushable<T> {
const buffer: T[] = [];
// A waiting consumer's resolver (null when none is parked). Single-consumer.
let pendingResolve: ((res: IteratorResult<T>) => void) | null = null;
let closed = false;
function push(value: T): void {
if (closed) return;
if (pendingResolve) {
const resolve = pendingResolve;
pendingResolve = null;
resolve({ value, done: false });
return;
}
buffer.push(value);
}
function close(): void {
if (closed) return;
closed = true;
if (pendingResolve) {
const resolve = pendingResolve;
pendingResolve = null;
resolve({ value: undefined, done: true });
}
}
const iterator: AsyncIterator<T> = {
next(): Promise<IteratorResult<T>> {
// Drain the buffer first (FIFO), regardless of close — buffered values
// pushed before close are still delivered.
if (buffer.length > 0) {
return Promise.resolve({ value: buffer.shift() as T, done: false });
}
if (closed) {
return Promise.resolve({ value: undefined, done: true });
}
// Park until the next push/close. Single-consumer: only one waiter at a time.
return new Promise<IteratorResult<T>>((resolve) => {
pendingResolve = resolve;
});
},
return(): Promise<IteratorResult<T>> {
// Consumer abandoned the loop (e.g. `break`) → close so a later push no-ops.
close();
return Promise.resolve({ value: undefined, done: true });
},
};
return {
push,
close,
get closed() {
return closed;
},
iterable: {
[Symbol.asyncIterator]() {
return iterator;
},
},
};
}

View File

@@ -36,29 +36,15 @@
*/
import { spawn, type ChildProcess } from 'node:child_process';
import type { FastifyBaseLogger } from 'fastify';
import {
ClientSideConnection,
type Client,
type SessionNotification,
type RequestPermissionRequest,
type RequestPermissionResponse,
type ReadTextFileRequest,
type ReadTextFileResponse,
type WriteTextFileRequest,
type WriteTextFileResponse,
type CreateTerminalRequest,
type CreateTerminalResponse,
type CreateElicitationRequest,
type CreateElicitationResponse,
} from '@agentclientprotocol/sdk';
import { ClientSideConnection, type Client } from '@agentclientprotocol/sdk';
import type { Sql } from '../../db.js';
import { resolveLaunchSpec } from '../acp-spawn.js';
import { isTurnOkForStopReason } from './warm-acp-routing.js';
import { getResolvedRegistry, type ResolvedProviderDef } from '../provider-config-registry.js';
import { createAcpNdJsonStream } from '../acp-stream.js';
import { mapSessionUpdate } from '../acp-event-map.js';
import { readWorktreeTextFile, writeWorktreeTextFile } from '../acp-client-fs.js';
import { waitForPermissionResponse, waitForElicitationResponse, cancelPendingPermission } from '../permission-waiter.js';
import { buildAcpClient } from '../acp-client.js';
import { cancelPendingPermission } from '../permission-waiter.js';
import { type AcpToolSnapshot, synthesizeCanceledSnapshots } from '../acp-tool-snapshot.js';
import type {
AgentBackend,
@@ -211,47 +197,25 @@ export class WarmAcpBackend implements AgentBackend {
);
}
/** Build the ACP Client callbacks ONCE per connection. They read `this.activeTurn`
* so each turn's events/permissions route to the right place — exactly the
* opencode-server `activeTurn` pattern. Worktree-scoped FS like AcpStreamContext. */
/** Build the ACP Client callbacks ONCE per connection (shared `buildAcpClient`).
* `resolveTurn` reads `this.activeTurn` at each callback so events/permissions
* route to the live turn — exactly the prior behavior. The warm session always
* has a non-empty `sessionId`, so the shared `taskId && sessionId` permission
* gate is equivalent to the old `turn?.taskId` gate. */
private buildClient(worktreePath: string): Client {
return {
sessionUpdate: async (params: SessionNotification): Promise<void> => {
const turn = this.activeTurn;
if (!turn) return; // between turns — drop (no orphan settles a future turn)
for (const event of mapSessionUpdate(params, turn.snapshots)) {
turn.onEvent(event);
}
},
requestPermission: async (params: RequestPermissionRequest): Promise<RequestPermissionResponse> => {
const turn = this.activeTurn;
if (turn?.taskId) {
// Route to the UI via the per-turn task id (same as the one-shot path).
return waitForPermissionResponse(turn.taskId, turn.sessionId, this.agent, turn.modeId, params);
}
const firstOption = params.options[0];
if (firstOption) return { outcome: { outcome: 'selected', optionId: firstOption.optionId } };
return { outcome: { outcome: 'cancelled' } };
},
readTextFile: async (params: ReadTextFileRequest): Promise<ReadTextFileResponse> => {
const content = await readWorktreeTextFile(worktreePath, params.path, params.line, params.limit);
return { content };
},
writeTextFile: async (params: WriteTextFileRequest): Promise<WriteTextFileResponse> => {
await writeWorktreeTextFile(worktreePath, params.path, params.content);
return {};
},
createTerminal: async (_params: CreateTerminalRequest): Promise<CreateTerminalResponse> => {
return { terminalId: 'noop' };
},
unstable_createElicitation: async (params: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
const turn = this.activeTurn;
if (turn?.taskId) {
return waitForElicitationResponse(turn.taskId, turn.sessionId, this.agent, turn.modeId, params);
}
return { action: 'decline' };
},
};
return buildAcpClient(worktreePath, () => {
const turn = this.activeTurn;
if (!turn) return null;
return {
taskId: turn.taskId,
sessionId: turn.sessionId,
modeId: turn.modeId,
agent: this.agent,
onSessionUpdate: (params) => {
for (const event of mapSessionUpdate(params, turn.snapshots)) turn.onEvent(event);
},
};
});
}
// ─── ensureSession: create-or-reuse the warm session (2.1) ───────────────────
@@ -303,6 +267,14 @@ export class WarmAcpBackend implements AgentBackend {
return { ok: false, error: 'warm-acp: no live ACP connection' };
}
// v2.7 busy-assert: one in-flight turn per warm session. The dispatcher
// serializes turns per (chat, agent), so this never fires in normal dispatch —
// but a second concurrent prompt would silently overwrite `activeTurn` and
// orphan the first turn, so reject instead.
if (this.activeTurn) {
return { ok: false, error: 'warm-acp: session already has an in-flight turn' };
}
const snapshots = new Map<string, AcpToolSnapshot>();
// taskId routes permission/elicitation prompts back to the UI. The dispatcher
// passes it (plus mode) on the per-turn PromptCtx; permission-waiter keys on it.

View File

@@ -0,0 +1,50 @@
/**
* F1 — per-task abort registry. A Stop on an external-agent task must reach the
* in-flight run and abort its child / prompt. Each external run-function registers
* its per-turn AbortController here keyed by task id; the cancel route calls
* `cancel(taskId)` to fire it; the run-function's `.finally` deletes the entry.
*
* Idempotent by construction:
* - `cancel()` on an already-aborted controller no-ops (AbortController.abort()
* is idempotent) → a rapid double-Stop is safe.
* - `cancel()` on an unknown / already-finished task returns false → a
* cancel-after-natural-exit (entry already deleted) and a Stop on a native
* boocode task (never registered) are both safe no-ops.
*
* Pure (no DB / child / IO) so the abort wiring + idempotency contract is
* unit-testable in isolation — mirrors the turn-guard / lifecycle-decisions
* pure-helper precedent.
*/
export interface CancelRegistry {
/** Create + store an AbortController for this task, returning it for the run. */
register(taskId: string): AbortController;
/** Abort the task's in-flight run. Returns false when no controller is registered. */
cancel(taskId: string): boolean;
/** Drop the task's entry (called from the run's `.finally`). No-op if absent. */
delete(taskId: string): void;
/** Whether a controller is currently registered for this task. */
has(taskId: string): boolean;
}
export function createCancelRegistry(): CancelRegistry {
const controllers = new Map<string, AbortController>();
return {
register(taskId) {
const ac = new AbortController();
controllers.set(taskId, ac);
return ac;
},
cancel(taskId) {
const ac = controllers.get(taskId);
if (!ac) return false;
ac.abort();
return true;
},
delete(taskId) {
controllers.delete(taskId);
},
has(taskId) {
return controllers.has(taskId);
},
};
}

View File

@@ -0,0 +1,306 @@
/**
* write-edit-robustness #4 — worktree checkpoints.
*
* External agents (opencode / goose / qwen / claude) write DIRECTLY into the
* shared session worktree (`/tmp/booworktrees/sess-<id>`); BooCode's own `rewind`
* only reverses `pending_changes` against the project root, so it has zero coverage
* there. A checkpoint is a pre-turn shadow-commit of the worktree tree (tracked +
* untracked) captured WITHOUT touching the real index/working tree, stored in a
* private GC-safe ref. `restoreCheckpoint` rewinds the worktree to that commit,
* trims the transcript from the anchor message forward, and resets the agent
* backend so the next turn re-establishes a fresh context consistent with the
* restored files.
*
* All git goes through hostExec + shellEscape (BooCoder runs on the host; the
* worktrees live on the host fs). Checkpoint CREATION is best-effort: a failure
* logs and returns null — it must NEVER throw into the dispatch turn.
*/
import { randomUUID } from 'node:crypto';
import type { FastifyBaseLogger } from 'fastify';
import type { Sql } from '../db.js';
import { hostExec } from './host-exec.js';
import { agentPool, OPENCODE_POOL_KEY } from './agent-pool.js';
import type { AgentSessionHandle } from './agent-backend.js';
/** Minimal shell escape for paths/refs (single-quote wrapping). Mirrors worktrees.ts. */
function shellEscape(s: string): string {
return "'" + s.replace(/'/g, "'\\''") + "'";
}
/**
* Pure builder for the shadow-commit command. Captures tracked + untracked files
* in the worktree into a temp index (so the real index/working tree is untouched),
* writes a tree, commits it parented on HEAD, and parks the commit under a private
* ref `refs/boocode/checkpoints/<id>` so git's GC never reclaims it. Prints ONLY
* the resulting SHA on stdout (the trailing `printf '%s'`), so the caller parses
* stdout.trim() directly.
*
* `id` is the row UUID (minted before the ref so the ref name matches the row).
* Both the worktree path and the id are shell-escaped.
*/
export function buildShadowCommitCommand(worktreePath: string, id: string): string {
const wt = shellEscape(worktreePath);
const ref = shellEscape(`refs/boocode/checkpoints/${id}`);
return (
`cd ${wt} && TMP=$(mktemp) && GIT_INDEX_FILE="$TMP" git read-tree HEAD ` +
`&& GIT_INDEX_FILE="$TMP" git add -A ` +
`&& TREE=$(GIT_INDEX_FILE="$TMP" git write-tree) ` +
`&& SHA=$(git commit-tree "$TREE" -p HEAD -m "boocode checkpoint") ` +
`&& git update-ref ${ref} "$SHA" && rm -f "$TMP" && printf '%s' "$SHA"`
);
}
export interface CreateCheckpointArgs {
chatId: string;
sessionId: string | null;
worktreeId: string | null;
worktreePath: string;
messageId: string | null;
label?: string | null;
}
/**
* Capture a pre-turn checkpoint of the session worktree. Best-effort: returns the
* inserted row's { id, commit_sha } on success, or null on any failure (the turn
* proceeds either way — a missing checkpoint just means no restore point for that
* turn). NEVER throws.
*
* The id is minted up front so the git ref name (`refs/boocode/checkpoints/<id>`)
* matches the DB row id, keeping ref and row in lockstep.
*/
export async function createCheckpoint(
sql: Sql,
args: CreateCheckpointArgs,
opts?: { signal?: AbortSignal; log?: FastifyBaseLogger },
): Promise<{ id: string; commit_sha: string } | null> {
const id = randomUUID();
try {
const cmd = buildShadowCommitCommand(args.worktreePath, id);
const res = await hostExec(cmd, { signal: opts?.signal, timeoutMs: 30_000 });
if (res.exitCode !== 0) {
opts?.log?.warn(
{ chatId: args.chatId, worktreePath: args.worktreePath, stderr: res.stderr.trim().slice(0, 500) },
'checkpoint: shadow-commit failed (turn proceeds without a checkpoint)',
);
return null;
}
const commitSha = res.stdout.trim();
if (!commitSha) {
opts?.log?.warn(
{ chatId: args.chatId, worktreePath: args.worktreePath },
'checkpoint: shadow-commit produced no SHA (turn proceeds)',
);
return null;
}
await sql`
INSERT INTO checkpoints (id, chat_id, session_id, worktree_id, message_id, commit_sha, label)
VALUES (${id}, ${args.chatId}, ${args.sessionId}, ${args.worktreeId}, ${args.messageId}, ${commitSha}, ${args.label ?? null})
`;
opts?.log?.info({ checkpointId: id, chatId: args.chatId, commitSha }, 'checkpoint: created');
return { id, commit_sha: commitSha };
} catch (err) {
opts?.log?.warn(
{ chatId: args.chatId, err: err instanceof Error ? err.message : String(err) },
'checkpoint: create threw (turn proceeds without a checkpoint)',
);
return null;
}
}
/** Error the route maps to a 404 when the checkpoint can't be resolved / scoped. */
export class CheckpointNotFoundError extends Error {
constructor(message: string) {
super(message);
this.name = 'CheckpointNotFoundError';
}
}
export interface RestoreCheckpointResult {
checkpoint_id: string;
messages_deleted: number;
worktree_reset: boolean;
backend_reset: boolean;
}
export interface RestoreCheckpointOpts {
signal?: AbortSignal;
log?: FastifyBaseLogger;
/** If set, the checkpoint MUST belong to this session (route scope guard). */
sessionId?: string;
}
interface CheckpointRow {
id: string;
chat_id: string;
session_id: string | null;
worktree_id: string | null;
message_id: string | null;
commit_sha: string;
created_at: Date;
}
/**
* Restore a checkpoint: rewind its worktree to the shadow commit, trim the
* transcript from the anchor message forward, reset the backend session, and drop
* now-orphaned later checkpoints. Throws CheckpointNotFoundError when the
* checkpoint is missing or not in the requested session (route → 404).
*/
export async function restoreCheckpoint(
sql: Sql,
checkpointId: string,
opts?: RestoreCheckpointOpts,
): Promise<RestoreCheckpointResult> {
// 1. Resolve the checkpoint.
const [cp] = await sql<CheckpointRow[]>`
SELECT id, chat_id, session_id, worktree_id, message_id, commit_sha, created_at
FROM checkpoints WHERE id = ${checkpointId}
`;
if (!cp) {
throw new CheckpointNotFoundError('checkpoint not found');
}
// Authorization scope (fail-safe): the checkpoint's chat must belong to the
// requested session. cp.session_id is a denormalized hint that may be null, so
// gating on it directly fails open — resolve the owning session via chats
// (authoritative; chat_id is NOT NULL) and deny on any mismatch or missing row.
if (opts?.sessionId) {
const [owner] = await sql<{ session_id: string | null }[]>`
SELECT session_id FROM chats WHERE id = ${cp.chat_id}
`;
if (!owner || owner.session_id !== opts.sessionId) {
throw new CheckpointNotFoundError('checkpoint not in session');
}
}
// 2. Resolve the worktree path (by worktree_id, else the session's active one).
let worktreePath: string | null = null;
if (cp.worktree_id) {
const [wt] = await sql<{ path: string }[]>`
SELECT path FROM worktrees WHERE id = ${cp.worktree_id}
`;
worktreePath = wt?.path ?? null;
}
if (!worktreePath) {
const sid = cp.session_id ?? opts?.sessionId ?? null;
if (sid) {
const [wt] = await sql<{ path: string }[]>`
SELECT path FROM worktrees WHERE session_id = ${sid} AND status = 'active' LIMIT 1
`;
worktreePath = wt?.path ?? null;
}
}
// 3. Worktree reset — hard-reset to the shadow commit, then clean untracked.
let worktreeReset = false;
if (worktreePath) {
const resetRes = await hostExec(
`git -C ${shellEscape(worktreePath)} reset --hard ${shellEscape(cp.commit_sha)}`,
{ signal: opts?.signal, timeoutMs: 30_000 },
).catch((err) => {
opts?.log?.warn(
{ checkpointId, err: err instanceof Error ? err.message : String(err) },
'checkpoint restore: reset --hard threw',
);
return null;
});
if (resetRes && resetRes.exitCode === 0) {
const cleanRes = await hostExec(
`git -C ${shellEscape(worktreePath)} clean -fd`,
{ signal: opts?.signal, timeoutMs: 30_000 },
).catch(() => null);
worktreeReset = cleanRes != null && cleanRes.exitCode === 0;
if (!worktreeReset) {
opts?.log?.warn({ checkpointId, worktreePath }, 'checkpoint restore: clean -fd did not succeed');
}
} else {
opts?.log?.warn(
{ checkpointId, worktreePath, stderr: resetRes?.stderr?.trim()?.slice(0, 500) },
'checkpoint restore: reset --hard did not succeed',
);
}
} else {
opts?.log?.warn({ checkpointId }, 'checkpoint restore: no worktree path resolved (files not reset)');
}
// 4. Trim the transcript from the anchor message forward. message_parts FK to
// messages is ON DELETE CASCADE (apps/server schema.sql:49), so parts are
// removed with their messages — no explicit parts delete needed.
let messagesDeleted = 0;
if (cp.message_id) {
const deleted = await sql<{ id: string }[]>`
DELETE FROM messages
WHERE chat_id = ${cp.chat_id}
AND created_at >= (SELECT created_at FROM messages WHERE id = ${cp.message_id})
RETURNING id
`;
messagesDeleted = deleted.length;
}
// 5. Backend reset — mark the chat's agent sessions crashed so the next turn
// re-establishes a fresh backend, and evict the live pool session(s) for this
// (chat, agent). Warm backends hold context server-side with no partial
// rewind, so a full reset is the only consistent option (proposal §4).
const agentRows = await sql<{ agent: string; backend: string; agent_session_id: string | null; session_id: string | null; worktree_id: string | null }[]>`
SELECT agent, backend, agent_session_id, session_id, worktree_id
FROM agent_sessions WHERE chat_id = ${cp.chat_id}
`;
await sql`
UPDATE agent_sessions SET status = 'crashed' WHERE chat_id = ${cp.chat_id}
`.catch(() => {});
let backendReset = false;
try {
// opencode runs on the SHARED server (keyed on a sentinel, not the chat) — close
// just this chat's session(s) on it, mirroring the lifecycle close-hook.
const ocBackend = agentPool.peek(OPENCODE_POOL_KEY, 'opencode');
if (ocBackend) {
for (const row of agentRows) {
if (row.backend !== 'opencode_server' || !row.agent_session_id) continue;
const handle: AgentSessionHandle = {
sessionId: row.session_id ?? '',
agent: row.agent,
backend: 'opencode_server',
chatId: cp.chat_id,
worktreeId: row.worktree_id ?? '',
agentSessionId: row.agent_session_id,
serverPort: null,
};
await ocBackend.closeSession(handle).catch((err) => {
opts?.log?.warn(
{ checkpointId, err: err instanceof Error ? err.message : String(err) },
'checkpoint restore: opencode closeSession threw',
);
});
}
}
// Warm-ACP backends are pooled under the chat id — dispose them (kills the
// goose/qwen child). closeChat skips busy backends (a live turn isn't torn down).
const disposed = await agentPool.closeChat(cp.chat_id);
backendReset = true;
opts?.log?.info({ checkpointId, chatId: cp.chat_id, disposed }, 'checkpoint restore: backend reset');
} catch (err) {
opts?.log?.warn(
{ checkpointId, err: err instanceof Error ? err.message : String(err) },
'checkpoint restore: backend reset threw',
);
}
// 6. Drop now-orphaned later checkpoints for this chat (their anchor messages were
// just trimmed). Compare `created_at` SERVER-SIDE via a subquery (NOT the JS
// Date round-trip, which truncates the stored microsecond precision to ms and
// would make this checkpoint delete ITSELF), and exclude this checkpoint's own
// id so it always survives — letting the user re-restore to it.
await sql`
DELETE FROM checkpoints
WHERE chat_id = ${cp.chat_id}
AND id <> ${cp.id}
AND created_at > (SELECT created_at FROM checkpoints WHERE id = ${cp.id})
`.catch(() => {});
return {
checkpoint_id: checkpointId,
messages_deleted: messagesDeleted,
worktree_reset: worktreeReset,
backend_reset: backendReset,
};
}

View File

@@ -1,9 +1,10 @@
import type { Sql } from '../db.js';
import type { FastifyBaseLogger } from 'fastify';
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/server/ws-frames';
import type { WsFrame } from '@boocode/contracts/ws-frames';
import type { Config } from '../config.js';
import { createWorktree, diffWorktree, cleanupWorktree, ensureSessionWorktree } from './worktrees.js';
import { createCheckpoint } from './checkpoints.js';
import { makeDcpStreamStripper } from './dcp-strip.js';
import { dispatchViaAcp } from './acp-dispatch.js';
import { getResolvedRegistry } from './provider-config-registry.js';
@@ -15,8 +16,18 @@ import { snapshotToWireToolCall, type AcpToolSnapshot } from './acp-tool-snapsho
import { agentPool, OPENCODE_POOL_KEY } from './agent-pool.js';
import { OpenCodeServerBackend } from './backends/opencode-server.js';
import { WarmAcpBackend } from './backends/warm-acp.js';
import { ClaudeSdkBackend } from './backends/claude-sdk.js';
import { shouldUseWarmBackend } from './backends/warm-acp-routing.js';
import { shouldUseClaudeSdk } from './backends/claude-sdk-routing.js';
import type { AgentBackend, AgentEvent } from './agent-backend.js';
import { publishAgentStatus } from './agent-status-publish.js';
import type { AgentStatus } from './normalize-agent-status.js';
import { createCancelRegistry } from './cancel-registry.js';
import {
finalizeStreamingMessage,
classifyTerminalStatus,
type TerminalMessageStatus,
} from './finalize-message.js';
interface InferenceRunner {
enqueue: (sessionId: string, chatId: string, assistantId: string, user: string) => void;
@@ -38,7 +49,11 @@ interface Deps {
const POLL_INTERVAL_MS = 2_000;
const COMPLETION_POLL_MS = 2_000;
export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<void> } {
export function createDispatcher(deps: Deps): {
cancelExternalTask(taskId: string): boolean;
start(): void;
stop(): Promise<void>;
} {
const { sql, inference, broker, log, config } = deps;
let timer: ReturnType<typeof setInterval> | null = null;
let listener: { unlisten: () => Promise<void> } | null = null;
@@ -50,6 +65,13 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
// turn at a time.
const inflight = new Map<string, Promise<void>>();
// F1: per-task abort registry. Each external run-function registers its per-turn
// AbortController here (keyed by task id); the cancel route reaches it through the
// exported `cancelExternalTask`; the run's `.finally` deletes the entry. Native
// boocode tasks are never registered, so a Stop on one returns false and falls
// through to the unchanged inference.cancel path.
const taskControllers = createCancelRegistry();
// Shared entry point for both the poll timer and the NOTIFY listener. poll()'s
// `polling`/`stopping` guard makes this safe to call concurrently — a notify
// arriving mid-poll returns immediately and never double-dispatches.
@@ -63,6 +85,55 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
return task.session_id ?? `task:${task.id}`;
}
// agent-status-normalize (#10): publish a normalized per-(chat,agent) status on
// the session channel. Every external-agent path (warm-acp / opencode / claude-sdk /
// pty one-shot) reports `working` at turn start, `idle` on clean completion, and
// `error` on the failure path through this single helper so the four paths stay
// DRY and consistent. Best-effort — publishAgentStatus never throws.
function emitAgentStatus(
sessionId: string,
chatId: string,
agent: string,
status: AgentStatus,
reason: string,
): void {
publishAgentStatus(broker.publishFrame, sessionId, chatId, agent, status, reason);
}
// F1 (OCE-001/OCE-002): finalize a streaming assistant message into a terminal
// state and publish the matching message_complete frame. Best-effort + idempotent
// (the helper's `WHERE status='streaming'` guard) — a failure here must never mask
// the original abort/error, so it logs and swallows.
function finalizeMessage(
sessionId: string,
chatId: string,
assistantId: string,
status: TerminalMessageStatus,
model: string | null,
content?: string,
): Promise<boolean> {
return finalizeStreamingMessage(sql, broker.publishFrame, {
sessionId,
chatId,
assistantId,
status,
model,
content,
}).catch((err) => {
log.error({ err: err instanceof Error ? err.message : String(err), assistantId }, 'dispatcher: finalizeStreamingMessage failed');
return false;
});
}
// F1: the cancel route's reach into an in-flight external run. Idempotent — a
// double-Stop re-aborts an already-aborted controller (no-op) and a Stop on a
// finished/native task returns false. Aborting only fires the backend's per-turn
// cancel (session.abort / session/cancel / interrupt / child.kill); it never kills
// a warm pool process, so persistent worktrees + pooled backends are preserved.
function cancelExternalTask(taskId: string): boolean {
return taskControllers.cancel(taskId);
}
async function poll(): Promise<void> {
// `polling` serializes poll() execution itself (timer + NOTIFY can fire
// concurrently) so we never double-select a task. It does NOT serialize task
@@ -96,6 +167,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
// with the same key is skipped and a concurrent poll can't re-pick it.
const p = runTask(task).finally(() => {
inflight.delete(key);
// F1: drop the abort controller once the run settles. After this, a Stop
// on the (now-finished) task returns false — cancel-after-exit is safe.
taskControllers.delete(task.id);
});
inflight.set(key, p);
}
@@ -130,6 +204,12 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
// existing one-shot worktree-per-task ACP/PTY path untouched.
if (task.agent === 'opencode') {
await runOpenCodeServerTask(task, agentRow.install_path);
} else if (shouldUseClaudeSdk(task)) {
// claude-sdk-sessionstore #9 (Part 2): env-flagged (CLAUDE_SDK_BACKEND, default
// OFF) warm Claude-SDK backend for chat-tab claude tasks. When the flag is off
// (production default) this predicate returns false and claude falls through to
// the UNCHANGED one-shot PTY runExternalAgent path below.
await runClaudeSdkTask(task, agentRow.install_path);
} else if (shouldUseWarmBackend(task)) {
await runWarmAcpTask(task, agentRow.install_path);
} else {
@@ -187,8 +267,8 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
RETURNING id
`;
const [assistantMsg] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
INSERT INTO messages (session_id, chat_id, role, content, status, model, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', ${task.model}, clock_timestamp())
RETURNING id
`;
const assistantId = assistantMsg!.id;
@@ -286,8 +366,16 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
return;
}
// Create an abort controller for this task
const ac = new AbortController();
// F1: register the per-task abort controller so a Stop reaches this run.
const ac = taskControllers.register(taskId);
// #10: hoisted above the try so the catch block can report `error` status with
// the (chat, agent) key. Empty until resolved below; guarded before use.
let sessionId = '';
let chatId = '';
// F1: hoisted so the catch / abort short-circuit can finalize the streaming
// assistant row. Empty until the row is created; finalize no-ops on ''.
let assistantId = '';
try {
// Mark running
@@ -297,9 +385,6 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
WHERE id = ${taskId}
`;
let sessionId: string;
let chatId: string;
if (task.session_id) {
sessionId = task.session_id;
const chats = await sql<{ id: string }[]>`
@@ -352,11 +437,21 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
let acpReasoning = '';
const [assistantMsg] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
INSERT INTO messages (session_id, chat_id, role, content, status, model, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', ${task.model}, clock_timestamp())
RETURNING id
`;
const assistantId = assistantMsg!.id;
assistantId = assistantMsg!.id;
// write-edit-robustness #4: pre-turn worktree checkpoint (best-effort; a
// failure logs and never breaks dispatch). This path uses a per-task worktree
// (createWorktree, not the session worktree), so there's no worktrees-table id
// — pass null for worktreeId, the path is enough for restore's reset.
await createCheckpoint(
sql,
{ chatId, sessionId, worktreeId: null, worktreePath, messageId: assistantId },
{ signal: ac.signal, log },
).catch(() => null);
broker.publishFrame(sessionId, {
type: 'message_started',
@@ -365,6 +460,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
role: 'assistant',
} as WsFrame);
// #10: external-agent turn begins.
emitAgentStatus(sessionId, chatId, agent, 'working', 'turn_start');
const manifestCommands = getManifestCommands(agent);
if (manifestCommands.length > 0) {
setTaskCommands(taskId, manifestCommands);
@@ -399,6 +497,52 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
outputSummary = result.output.slice(0, 500);
await persistExternalAgentTurn(sql, assistantId, result.toolSnapshots, acpReasoning);
} else {
// v#7 (stream-json): claude + qwen run with --output-format stream-json.
// Parse the NDJSON live in pty-dispatch and forward AgentEvents here so we
// publish the SAME live frames the warm-ACP / opencode paths emit (text,
// reasoning, tool) and persist structured parts. Accumulate for the final
// message content + persistence; fall back to the opaque stdout slice when
// nothing parsed (agent ran without the flag, or crashed before emitting).
const ptyTextChunks: string[] = [];
const ptyReasoningChunks: string[] = [];
const ptyToolSnaps = new Map<string, AcpToolSnapshot>();
const onPtyEvent = (e: AgentEvent): void => {
switch (e.type) {
case 'text':
ptyTextChunks.push(e.text);
broker.publishFrame(sessionId, {
type: 'delta',
message_id: assistantId,
chat_id: chatId,
content: e.text,
} as WsFrame);
break;
case 'reasoning':
ptyReasoningChunks.push(e.text);
broker.publishFrame(sessionId, {
type: 'reasoning_delta',
message_id: assistantId,
chat_id: chatId,
content: e.text,
} as WsFrame);
break;
case 'tool_call':
case 'tool_update':
ptyToolSnaps.set(e.toolCall.toolCallId, e.toolCall);
broker.publishFrame(sessionId, {
type: 'tool_call',
message_id: assistantId,
chat_id: chatId,
tool_call: snapshotToWireToolCall(e.toolCall),
} as WsFrame);
break;
case 'commands':
// stream-json carries no commands today; ignore if it ever does.
break;
}
};
const result = await dispatchViaPty({
agent,
task: task.input,
@@ -409,20 +553,50 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
thinkingOptionId: task.thinking_option_id ?? undefined,
signal: ac.signal,
log,
onEvent: onPtyEvent,
});
assistantContent = (result.stdout || result.stderr || '(no output)').slice(0, 50_000);
outputSummary = (result.stdout || result.stderr).slice(0, 500);
if (assistantContent) {
broker.publishFrame(sessionId, {
type: 'delta',
message_id: assistantId,
chat_id: chatId,
content: assistantContent,
} as WsFrame);
if (result.streamed) {
assistantContent = ptyTextChunks.join('').slice(0, 50_000);
// stream-json text can be empty for a tool-only turn — surface stderr or a
// placeholder so the message row isn't blank.
if (!assistantContent) {
assistantContent = (result.stderr || '(no text output)').slice(0, 50_000);
}
outputSummary = (ptyTextChunks.join('') || result.stderr).slice(0, 500);
acpReasoning = ptyReasoningChunks.join('').slice(0, 200_000);
await persistExternalAgentTurn(sql, assistantId, [...ptyToolSnaps.values()], acpReasoning);
} else {
// Fallback: agent produced no parseable NDJSON (ran without the flag, or
// crashed). Preserve today's opaque stdout-slice + single delta behavior.
assistantContent = (result.stdout || result.stderr || '(no output)').slice(0, 50_000);
outputSummary = (result.stdout || result.stderr).slice(0, 500);
if (assistantContent) {
broker.publishFrame(sessionId, {
type: 'delta',
message_id: assistantId,
chat_id: chatId,
content: assistantContent,
} as WsFrame);
}
}
}
// F1: abort short-circuit BEFORE the unconditional 'complete' write. A Stop
// (cancelExternalTask → ac.abort) or shutdown finalizes the streaming row as
// 'cancelled' (keeping whatever streamed) instead of recording 'complete',
// and skips the diff. This one-shot path owns a per-task worktree, so we DO
// tear it down here (unlike the warm paths, which keep their persistent one).
if (ac.signal.aborted || stopping) {
await finalizeMessage(sessionId, chatId, assistantId, 'cancelled', task.model, assistantContent);
await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
emitAgentStatus(sessionId, chatId, agent, 'idle', stopping ? 'shutdown' : 'cancelled');
await cleanupWorktree(projectPath, taskId);
clearTaskCommands(taskId);
return;
}
await sql`
UPDATE messages
SET content = ${assistantContent}, status = 'complete', finished_at = clock_timestamp()
@@ -433,16 +607,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
type: 'message_complete',
message_id: assistantId,
chat_id: chatId,
model: task.model,
} as WsFrame);
if (stopping) {
await sql`
UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}
`;
await cleanupWorktree(projectPath, taskId);
return;
}
// Step 3: Diff the worktree and queue pending changes
log.info({ taskId }, 'dispatcher: diffing worktree');
const diff = await diffWorktree(worktreePath, projectPath, { signal: ac.signal });
@@ -477,18 +644,33 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
WHERE id = ${taskId}
`;
log.info({ taskId, agent, costTokens: extCostTokens }, 'dispatcher: task completed (external)');
// #10: external-agent turn completed cleanly.
emitAgentStatus(sessionId, chatId, agent, 'idle', 'turn_complete');
clearTaskCommands(taskId);
} catch (err) {
const errMsg = err instanceof Error ? err.message : String(err);
const status = classifyTerminalStatus({ aborted: ac.signal.aborted, error: err });
log.error({ taskId, agent, err: errMsg }, 'dispatcher: external agent error');
// Guard `NOT IN ('cancelled','completed')` so a genuine error in the catch
// never overwrites a state the cancel route already wrote (user-Stop wins).
await sql`
UPDATE tasks
SET state = 'failed', ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId}
SET state = ${status}, ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId} AND state NOT IN ('cancelled', 'completed')
`.catch(() => {});
// F1 (OCE-001): finalize the streaming assistant message — the catch
// previously updated only `tasks` and left the message 'streaming' forever
// (the BooChat 5-min sweep runs in a different process and can't reach it).
await finalizeMessage(sessionId, chatId, assistantId, status, task.model);
// #10: external-agent turn failed/crashed. chatId may be unbound if the throw
// preceded its assignment — guard so the status publish never masks the real
// error.
if (chatId) emitAgentStatus(sessionId, chatId, agent, status === 'cancelled' ? 'idle' : 'error', status === 'cancelled' ? 'cancelled' : 'failed');
// Best-effort cleanup
await cleanupWorktree(projectPath, taskId);
clearTaskCommands(taskId);
@@ -541,7 +723,14 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
return;
}
const ac = new AbortController();
// F1: register the per-task abort controller so a Stop reaches this run.
const ac = taskControllers.register(taskId);
// #10: hoisted so the catch can report `error` with the (chat, agent) key.
let sessionId = '';
let chatId = '';
// F1: hoisted so the catch / abort short-circuit can finalize the streaming row.
let assistantId = '';
try {
// execution_path = 'acp' — the schema CHECK has no 'opencode_server' value
@@ -559,8 +748,6 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
// it directly. Session-less creators (arena, MCP, new_task, generic
// /api/tasks) leave it null; fall back to resolving/creating a real chat so
// ensureSession never receives a degenerate (null, agent) key.
let sessionId: string;
let chatId: string;
if (task.chat_id && task.session_id) {
sessionId = task.session_id;
chatId = task.chat_id;
@@ -611,11 +798,20 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
log.info({ taskId, worktreePath }, 'dispatcher: session worktree ready');
const [assistantMsg] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
INSERT INTO messages (session_id, chat_id, role, content, status, model, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', ${task.model}, clock_timestamp())
RETURNING id
`;
const assistantId = assistantMsg!.id;
assistantId = assistantMsg!.id;
// write-edit-robustness #4: pre-turn checkpoint of the persistent session
// worktree (best-effort; never breaks dispatch). worktreeId comes from the
// worktrees table (ensureSessionWorktree above).
await createCheckpoint(
sql,
{ chatId, sessionId, worktreeId, worktreePath, messageId: assistantId },
{ signal: ac.signal, log },
).catch(() => null);
broker.publishFrame(sessionId, {
type: 'message_started',
@@ -624,6 +820,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
role: 'assistant',
} as WsFrame);
// #10: opencode-server turn begins.
emitAgentStatus(sessionId, chatId, agent, 'working', 'turn_start');
const manifestCommands = getManifestCommands(agent);
if (manifestCommands.length > 0) {
setTaskCommands(taskId, manifestCommands);
@@ -731,6 +930,18 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
await persistExternalAgentTurn(sql, assistantId, [...toolSnaps.values()], reasoningText);
// F1: abort short-circuit BEFORE the unconditional 'complete' write — fixes
// the warm success-path recording 'complete' on a Stop'd turn. The abort fired
// session.abort on the prompt only: the persistent session worktree is kept
// (no cleanup) and the pooled opencode server stays warm for the next turn.
if (ac.signal.aborted || stopping) {
await finalizeMessage(sessionId, chatId, assistantId, 'cancelled', task.model, assistantContent);
await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
emitAgentStatus(sessionId, chatId, agent, 'idle', stopping ? 'shutdown' : 'cancelled');
clearTaskCommands(taskId);
return; // worktree persists (no cleanup); backend stays warm
}
await sql`
UPDATE messages
SET content = ${assistantContent}, status = 'complete', finished_at = clock_timestamp()
@@ -740,13 +951,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
type: 'message_complete',
message_id: assistantId,
chat_id: chatId,
model: task.model,
} as WsFrame);
if (stopping) {
await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
return; // worktree persists (no cleanup); backend stays warm
}
// 1.10: diff the persistent worktree against its captured baseline and
// SUPERSEDE the session's prior pending row (latest-wins, one accumulating
// diff) instead of stacking. Stamp agent for DiffPanel attribution.
@@ -783,15 +990,28 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
WHERE id = ${taskId}
`;
log.info({ taskId, agent, finalState, costTokens: extCostTokens }, 'dispatcher: task finished (opencode server)');
// #10: clean completion → idle; backend-reported failure → error.
emitAgentStatus(
sessionId,
chatId,
agent,
result.ok ? 'idle' : 'error',
result.ok ? 'turn_complete' : 'failed',
);
clearTaskCommands(taskId);
} catch (err) {
const errMsg = err instanceof Error ? err.message : String(err);
const status = classifyTerminalStatus({ aborted: ac.signal.aborted, error: err });
log.error({ taskId, agent, err: errMsg }, 'dispatcher: opencode server error');
await sql`
UPDATE tasks
SET state = 'failed', ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId}
SET state = ${status}, ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId} AND state NOT IN ('cancelled', 'completed')
`.catch(() => {});
// F1 (OCE-001): finalize the streaming message (was left 'streaming').
await finalizeMessage(sessionId, chatId, assistantId, status, task.model);
// #10: turn crashed.
if (chatId) emitAgentStatus(sessionId, chatId, agent, status === 'cancelled' ? 'idle' : 'error', status === 'cancelled' ? 'cancelled' : 'crashed');
clearTaskCommands(taskId);
// No worktree cleanup (persistent); backend stays warm for the next turn.
}
@@ -852,7 +1072,10 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
return;
}
const ac = new AbortController();
// F1: register the per-task abort controller so a Stop reaches this run.
const ac = taskControllers.register(taskId);
// F1: hoisted so the catch / abort short-circuit can finalize the streaming row.
let assistantId = '';
try {
await sql`
@@ -870,11 +1093,20 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
log.info({ taskId, worktreePath }, 'dispatcher: session worktree ready (warm ACP)');
const [assistantMsg] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
INSERT INTO messages (session_id, chat_id, role, content, status, model, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', ${task.model}, clock_timestamp())
RETURNING id
`;
const assistantId = assistantMsg!.id;
assistantId = assistantMsg!.id;
// write-edit-robustness #4: pre-turn checkpoint of the persistent session
// worktree (best-effort; never breaks dispatch). Same worktree the opencode
// path uses — a chat that switches opencode↔goose↔qwen shares one worktree.
await createCheckpoint(
sql,
{ chatId, sessionId, worktreeId, worktreePath, messageId: assistantId },
{ signal: ac.signal, log },
).catch(() => null);
broker.publishFrame(sessionId, {
type: 'message_started',
@@ -883,6 +1115,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
role: 'assistant',
} as WsFrame);
// #10: warm-ACP turn begins.
emitAgentStatus(sessionId, chatId, agent, 'working', 'turn_start');
const manifestCommands = getManifestCommands(agent);
if (manifestCommands.length > 0) {
setTaskCommands(taskId, manifestCommands);
@@ -973,6 +1208,18 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
await persistExternalAgentTurn(sql, assistantId, [...toolSnaps.values()], reasoningText);
// F1: abort short-circuit BEFORE the unconditional 'complete' write — fixes
// the warm success-path recording 'complete' on a Stop'd turn. The abort fired
// session/cancel on the warm connection only (never killed the child), so the
// persistent worktree is kept and the pooled (chat,agent) backend stays warm.
if (ac.signal.aborted || stopping) {
await finalizeMessage(sessionId, chatId, assistantId, 'cancelled', task.model, assistantContent);
await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
emitAgentStatus(sessionId, chatId, agent, 'idle', stopping ? 'shutdown' : 'cancelled');
clearTaskCommands(taskId);
return; // worktree persists (no cleanup); backend stays warm
}
await sql`
UPDATE messages
SET content = ${assistantContent}, status = 'complete', finished_at = clock_timestamp()
@@ -982,13 +1229,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
type: 'message_complete',
message_id: assistantId,
chat_id: chatId,
model: task.model,
} as WsFrame);
if (stopping) {
await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
return; // worktree persists (no cleanup); backend stays warm
}
// Diff the persistent worktree against its captured baseline and SUPERSEDE
// the session's prior pending row (latest-wins) — identical to opencode.
const diff = await diffWorktree(worktreePath, projectPath, {
@@ -1024,15 +1267,299 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
WHERE id = ${taskId}
`;
log.info({ taskId, agent, finalState }, 'dispatcher: task finished (warm ACP)');
// #10: clean completion → idle; backend-reported failure → error.
emitAgentStatus(
sessionId,
chatId,
agent,
result.ok ? 'idle' : 'error',
result.ok ? 'turn_complete' : 'failed',
);
clearTaskCommands(taskId);
} catch (err) {
const errMsg = err instanceof Error ? err.message : String(err);
const status = classifyTerminalStatus({ aborted: ac.signal.aborted, error: err });
log.error({ taskId, agent, err: errMsg }, 'dispatcher: warm ACP error');
await sql`
UPDATE tasks
SET state = 'failed', ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId}
SET state = ${status}, ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId} AND state NOT IN ('cancelled', 'completed')
`.catch(() => {});
// F1 (OCE-001): finalize the streaming message (was left 'streaming').
await finalizeMessage(sessionId, chatId, assistantId, status, task.model);
// #10: turn crashed.
emitAgentStatus(sessionId, chatId, agent, status === 'cancelled' ? 'idle' : 'error', status === 'cancelled' ? 'cancelled' : 'crashed');
clearTaskCommands(taskId);
// No worktree cleanup (persistent); backend stays warm for the next turn.
}
}
// ─── Path B (claude SDK): warm Claude-SDK backend (v2.6 #9 Part 2) ───────────
// Claude-SDK backends are per (chat, agent) — each owns ONE persistent query()
// generator driven in streaming-input mode. Pool key = chatId (secondary = agent),
// mirroring agent_sessions' (chat_id, agent) PK + the warm-ACP pooling.
function getClaudeSdkBackend(chatId: string, agent: string, installPath: string | null): ClaudeSdkBackend {
let backend = agentPool.get(chatId, agent);
if (!backend) {
backend = new ClaudeSdkBackend({ sql, log, chatId, agent, installPath });
agentPool.register(chatId, agent, backend);
}
return backend as ClaudeSdkBackend;
}
async function runClaudeSdkTask(
task: {
id: string;
project_id: string;
input: string;
agent: string | null;
model: string | null;
mode_id: string | null;
thinking_option_id: string | null;
session_id: string | null;
chat_id: string | null;
},
installPath: string | null,
): Promise<void> {
const taskId = task.id;
const agent = task.agent!;
// shouldUseClaudeSdk guarantees both non-null before we get here.
const sessionId = task.session_id!;
const chatId = task.chat_id!;
log.info({ taskId, agent, chatId }, 'dispatcher: starting task (path B — claude SDK)');
const [project] = await sql<{ path: string | null }[]>`
SELECT path FROM projects WHERE id = ${task.project_id}
`;
const projectPath = project?.path;
if (!projectPath) {
await sql`
UPDATE tasks
SET state = 'failed', ended_at = clock_timestamp(), output_summary = 'Project has no path — cannot create worktree'
WHERE id = ${taskId}
`;
return;
}
// F1: register the per-task abort controller so a Stop reaches this run.
const ac = taskControllers.register(taskId);
// F1: hoisted so the catch / abort short-circuit can finalize the streaming row.
let assistantId = '';
try {
await sql`
UPDATE tasks
SET state = 'running', started_at = clock_timestamp(), execution_path = 'acp'
WHERE id = ${taskId}
`;
// Persistent, session-keyed worktree (shared across turns + agents; NOT torn
// down per turn — Phase 3 reaps it). Same as the opencode/warm-ACP paths so a
// chat that switches agents shares one worktree.
const { worktreeId, worktreePath, baseCommit } = await ensureSessionWorktree(sql, projectPath, sessionId, {
signal: ac.signal,
});
log.info({ taskId, worktreePath }, 'dispatcher: session worktree ready (claude SDK)');
const [assistantMsg] = await sql<{ id: string }[]>`
INSERT INTO messages (session_id, chat_id, role, content, status, model, created_at)
VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', ${task.model}, clock_timestamp())
RETURNING id
`;
assistantId = assistantMsg!.id;
// write-edit-robustness #4: pre-turn checkpoint of the persistent session
// worktree (best-effort; never breaks dispatch).
await createCheckpoint(
sql,
{ chatId, sessionId, worktreeId, worktreePath, messageId: assistantId },
{ signal: ac.signal, log },
).catch(() => null);
broker.publishFrame(sessionId, {
type: 'message_started',
message_id: assistantId,
chat_id: chatId,
role: 'assistant',
} as WsFrame);
// #10: claude-SDK turn begins.
emitAgentStatus(sessionId, chatId, agent, 'working', 'turn_start');
const manifestCommands = getManifestCommands(agent);
if (manifestCommands.length > 0) {
setTaskCommands(taskId, manifestCommands);
broker.publishFrame(sessionId, {
type: 'agent_commands',
task_id: taskId,
session_id: sessionId,
commands: manifestCommands,
} as WsFrame);
}
// Accumulate the turn's stream for persistence + the final message content.
const textChunks: string[] = [];
const reasoningChunks: string[] = [];
const toolSnaps = new Map<string, AcpToolSnapshot>();
// Map transport-agnostic AgentEvents → the SAME WS frames the warm-ACP /
// opencode paths emit. This boundary attaches message_id/chat_id.
const onEvent = (e: AgentEvent): void => {
switch (e.type) {
case 'text':
textChunks.push(e.text);
broker.publishFrame(sessionId, {
type: 'delta',
message_id: assistantId,
chat_id: chatId,
content: e.text,
} as WsFrame);
break;
case 'reasoning':
reasoningChunks.push(e.text);
broker.publishFrame(sessionId, {
type: 'reasoning_delta',
message_id: assistantId,
chat_id: chatId,
content: e.text,
} as WsFrame);
break;
case 'tool_call':
case 'tool_update':
toolSnaps.set(e.toolCall.toolCallId, e.toolCall);
broker.publishFrame(sessionId, {
type: 'tool_call',
message_id: assistantId,
chat_id: chatId,
tool_call: snapshotToWireToolCall(e.toolCall),
} as WsFrame);
break;
case 'commands':
if (e.commands.length > 0) {
setTaskCommands(taskId, e.commands);
broker.publishFrame(sessionId, {
type: 'agent_commands',
task_id: taskId,
session_id: sessionId,
commands: e.commands,
} as WsFrame);
}
break;
}
};
const model = task.model ?? undefined;
const backend = getClaudeSdkBackend(chatId, agent, installPath);
const handle = await backend.ensureSession(sessionId, {
agent,
model: model ?? '',
chatId,
worktreePath,
worktreeId,
projectId: task.project_id,
});
const result = await backend.prompt(handle, task.input, {
worktreePath,
model: model ?? '',
signal: ac.signal,
onEvent,
taskId,
modeId: task.mode_id ?? undefined,
});
// Phase 3: keep the pooled (chat,agent) backend warm across the turn.
agentPool.touch(chatId, agent);
const assistantContent = textChunks.join('').slice(0, 50_000);
const reasoningText = reasoningChunks.join('').slice(0, 200_000);
const outputSummary = (result.ok ? textChunks.join('') : result.error ?? 'claude SDK turn failed').slice(0, 500);
await persistExternalAgentTurn(sql, assistantId, [...toolSnaps.values()], reasoningText);
// F1: abort short-circuit BEFORE the unconditional 'complete' write — fixes
// the warm success-path recording 'complete' on a Stop'd turn. The abort fired
// the SDK interrupt on the same query generator only (never killed the warm
// process), so the persistent worktree is kept and the backend stays warm.
if (ac.signal.aborted || stopping) {
await finalizeMessage(sessionId, chatId, assistantId, 'cancelled', task.model, assistantContent);
await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
emitAgentStatus(sessionId, chatId, agent, 'idle', stopping ? 'shutdown' : 'cancelled');
clearTaskCommands(taskId);
return; // worktree persists (no cleanup); backend stays warm
}
// ctx_used/ctx_max from the SDK result (1M-aware) → the assistant message, so
// the ContextBar renders a real context-window fill for claude.
await sql`
UPDATE messages
SET content = ${assistantContent}, status = 'complete', finished_at = clock_timestamp(),
ctx_used = ${result.ctxUsed ?? null}, ctx_max = ${result.ctxMax ?? null}
WHERE id = ${assistantId}
`;
broker.publishFrame(sessionId, {
type: 'message_complete',
message_id: assistantId,
chat_id: chatId,
model: task.model,
} as WsFrame);
// Diff the persistent worktree against its captured baseline and SUPERSEDE
// the session's prior pending row (latest-wins) — identical to opencode/ACP.
const diff = await diffWorktree(worktreePath, projectPath, {
signal: ac.signal,
baseRef: baseCommit ?? 'HEAD',
});
if (diff) {
await sql`
DELETE FROM pending_changes WHERE session_id = ${sessionId} AND status = 'pending'
`;
await sql`
INSERT INTO pending_changes (session_id, task_id, file_path, operation, diff, agent)
VALUES (${sessionId}, ${taskId}, ${projectPath}, 'edit', ${diff}, ${agent})
`;
log.info({ taskId, diffLength: diff.length }, 'dispatcher: diff superseded prior pending change (claude SDK)');
} else {
log.info({ taskId }, 'dispatcher: no changes detected in session worktree (claude SDK)');
}
// NO worktree cleanup — persistent (Phase 3 reaps it). Backend stays warm.
const [extCostRow] = await sql<{ total: number | null }[]>`
SELECT SUM(tokens_used)::int AS total
FROM messages
WHERE session_id = ${sessionId} AND tokens_used IS NOT NULL
`;
const extCostTokens = extCostRow?.total ?? null;
const finalState = result.ok ? 'completed' : 'failed';
await sql`
UPDATE tasks
SET state = ${finalState}, ended_at = clock_timestamp(), output_summary = ${outputSummary}, cost_tokens = ${extCostTokens}
WHERE id = ${taskId}
`;
log.info({ taskId, agent, finalState }, 'dispatcher: task finished (claude SDK)');
// #10: clean completion → idle; backend-reported failure → error.
emitAgentStatus(
sessionId,
chatId,
agent,
result.ok ? 'idle' : 'error',
result.ok ? 'turn_complete' : 'failed',
);
clearTaskCommands(taskId);
} catch (err) {
const errMsg = err instanceof Error ? err.message : String(err);
const status = classifyTerminalStatus({ aborted: ac.signal.aborted, error: err });
log.error({ taskId, agent, err: errMsg }, 'dispatcher: claude SDK error');
await sql`
UPDATE tasks
SET state = ${status}, ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
WHERE id = ${taskId} AND state NOT IN ('cancelled', 'completed')
`.catch(() => {});
// F1 (OCE-001): finalize the streaming message (was left 'streaming').
await finalizeMessage(sessionId, chatId, assistantId, status, task.model);
// #10: turn crashed.
emitAgentStatus(sessionId, chatId, agent, status === 'cancelled' ? 'idle' : 'error', status === 'cancelled' ? 'cancelled' : 'crashed');
clearTaskCommands(taskId);
// No worktree cleanup (persistent); backend stays warm for the next turn.
}
@@ -1059,6 +1586,7 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
}
return {
cancelExternalTask,
start() {
log.info('dispatcher: starting poll loop + tasks_new listener');

View File

@@ -0,0 +1,76 @@
import type { Sql } from '../db.js';
import type { WsFrame } from '@boocode/contracts/ws-frames';
export type TerminalMessageStatus = 'cancelled' | 'failed';
/**
* F1 (D-7) — decide the terminal status a Stop'd / errored external turn lands in.
*
* A user Stop (the per-task AbortController fired) or a thrown `AbortError` is a
* deliberate, non-error outcome → `'cancelled'`. A genuine thrown error → `'failed'`.
* Keeping the two distinct keeps the human-inbox / failure surfaces honest.
*
* Pure (no DB / IO) so the mapping is unit-testable in isolation.
*/
export function classifyTerminalStatus(opts: { aborted: boolean; error?: unknown }): TerminalMessageStatus {
if (opts.aborted) return 'cancelled';
if (opts.error instanceof Error && opts.error.name === 'AbortError') return 'cancelled';
return 'failed';
}
/**
* F1 (OCE-001 / OCE-002) — finalize a streaming assistant message into a terminal
* state and publish the matching `message_complete` frame.
*
* Idempotent via `WHERE status = 'streaming'`: a second call (a double-Stop, or an
* abort short-circuit followed by the catch block) updates zero rows and does NOT
* re-publish, so the frontend reducer settles the message exactly once. It also
* never clobbers a row that already finished cleanly (`complete`) — the abort that
* raced a clean finish is a no-op.
*
* Returns `true` iff this call performed the finalization (the row was still
* streaming); `false` if it was already terminal or the id is absent (the throw
* preceded the row's creation).
*/
export async function finalizeStreamingMessage(
sql: Sql,
publishFrame: (sessionId: string, frame: WsFrame) => void,
opts: {
sessionId: string;
chatId: string;
assistantId: string;
status: TerminalMessageStatus;
model: string | null;
/** Partial accumulated text to persist; omit to leave the row's content untouched. */
content?: string;
},
): Promise<boolean> {
const { sessionId, chatId, assistantId, status, model, content } = opts;
if (!assistantId) return false;
const rows =
content !== undefined
? await sql<{ id: string }[]>`
UPDATE messages
SET content = ${content}, status = ${status}, finished_at = clock_timestamp()
WHERE id = ${assistantId} AND status = 'streaming'
RETURNING id
`
: await sql<{ id: string }[]>`
UPDATE messages
SET status = ${status}, finished_at = clock_timestamp()
WHERE id = ${assistantId} AND status = 'streaming'
RETURNING id
`;
if (rows.length === 0) return false;
publishFrame(sessionId, {
type: 'message_complete',
message_id: assistantId,
chat_id: chatId,
model,
status,
} as WsFrame);
return true;
}

View File

@@ -0,0 +1,142 @@
/**
* AgentEvent → WS-frame emitter + turn accumulators.
*
* Extracted (v2.7 audit reshape) from `AcpStreamContext.handleSessionUpdate` in
* `acp-dispatch.ts` — the `AgentEvent → broker.publishFrame` switch that maps a
* backend's normalized events onto the wire frames the UI consumes, while
* accumulating the turn's text / reasoning / tool snapshots for persistence.
*
* The same shape backs the dispatcher's 4 inline `onEvent` copies (DEFERRED while
* dispatcher.ts has uncommitted edits), hence the optional `dcp` stripper + the
* `finalize()` flush: the opencode dispatch path strips dcp tags from text deltas,
* the ACP path does not (passes no `dcp`, so text is emitted verbatim — identical
* to the prior AcpStreamContext behavior).
*
* Publishing is gated on `canStream()` (all of broker/sessionId/chatId/assistantId
* present) exactly as the original — a one-shot dispatch with no broker accumulates
* but never publishes.
*/
import type { Broker } from '@boocode/server/broker';
import type { WsFrame } from '@boocode/contracts/ws-frames';
import type { AgentEvent } from './agent-backend.js';
import { type AcpToolSnapshot, snapshotToWireToolCall } from './acp-tool-snapshot.js';
import { mergeTaskCommands, getTaskCommands } from './agent-commands-cache.js';
import type { DcpStreamStripper } from './dcp-strip.js';
export interface FrameEmitterOpts {
broker?: Broker;
sessionId?: string;
chatId?: string;
/** The assistant message id — the frames' `message_id`. */
assistantId?: string;
/** Per-turn task id, for the agent_commands frame + command cache. */
taskId?: string;
/** Optional cross-chunk dcp stripper for text deltas (opencode path). When
* provided, text is stripped before push/publish and `finalize()` flushes the
* held-back tail. The ACP path passes none → text emitted verbatim. */
dcp?: DcpStreamStripper;
}
export interface FrameEmitter {
/** Map one AgentEvent to its WS frame(s) + accumulate it. */
onEvent: (e: AgentEvent) => void;
/** Flush a dcp stripper's held-back tail at turn end (no-op without `dcp`). */
finalize: () => void;
/** The merge accumulator for tool snapshots (toolCallId → snapshot). */
readonly toolSnapshots: Map<string, AcpToolSnapshot>;
/** Accumulated assistant text (post-dcp-strip when a stripper is set). */
readonly output: string;
/** Accumulated reasoning text. */
readonly reasoningText: string;
/** Tool snapshots in insertion order. */
readonly snapshots: AcpToolSnapshot[];
}
export function makeFrameEmitter(opts: FrameEmitterOpts): FrameEmitter {
const { broker, sessionId, chatId, assistantId, taskId, dcp } = opts;
const textChunks: string[] = [];
const reasoningChunks: string[] = [];
const toolSnapshots = new Map<string, AcpToolSnapshot>();
const canStream = (): boolean => !!(broker && sessionId && chatId && assistantId);
const publishText = (content: string): void => {
textChunks.push(content);
if (canStream()) {
broker!.publishFrame(sessionId!, {
type: 'delta',
message_id: assistantId!,
chat_id: chatId!,
content,
} as WsFrame);
}
};
const onEvent = (e: AgentEvent): void => {
switch (e.type) {
case 'text': {
const safe = dcp ? dcp.push(e.text) : e.text;
if (safe) publishText(safe);
break;
}
case 'reasoning':
reasoningChunks.push(e.text);
if (canStream()) {
broker!.publishFrame(sessionId!, {
type: 'reasoning_delta',
message_id: assistantId!,
chat_id: chatId!,
content: e.text,
} as WsFrame);
}
break;
case 'tool_call':
case 'tool_update':
toolSnapshots.set(e.toolCall.toolCallId, e.toolCall);
if (canStream()) {
broker!.publishFrame(sessionId!, {
type: 'tool_call',
message_id: assistantId!,
chat_id: chatId!,
tool_call: snapshotToWireToolCall(e.toolCall),
} as WsFrame);
}
break;
case 'commands':
if (taskId && e.commands.length > 0) {
mergeTaskCommands(taskId, e.commands);
if (canStream() && sessionId) {
const all = getTaskCommands(taskId) ?? e.commands;
broker!.publishFrame(sessionId, {
type: 'agent_commands',
task_id: taskId,
session_id: sessionId,
commands: all,
} as WsFrame);
}
}
break;
}
};
const finalize = (): void => {
if (!dcp) return;
const tail = dcp.flush();
if (tail) publishText(tail);
};
return {
onEvent,
finalize,
toolSnapshots,
get output() {
return textChunks.join('');
},
get reasoningText() {
return reasoningChunks.join('');
},
get snapshots() {
return [...toolSnapshots.values()];
},
};
}

View File

@@ -0,0 +1,271 @@
// Fuzzy patch locator for staged edits.
//
// Local quantized models (qwen3.6 and friends) frequently reproduce an
// `old_string` with small, semantically-irrelevant drift: trailing whitespace,
// a different indent width, or "smart" unicode punctuation (curly quotes, an
// en/em-dash, a non-breaking space) where the source has the plain ASCII form.
// An exact `String.includes` then fails and the queued edit is lost even though
// a human would say it obviously matches.
//
// `locateMatch` walks a ladder of progressively looser strategies and returns
// the real `[start, end)` byte-offset span in the ORIGINAL content so the caller
// can splice in `new_string` over the true file text (preserving the file's own
// whitespace/unicode, not the model's drifted copy). The ladder stops at the
// first strategy that resolves to a single span:
//
// 1. exact — indexOf; >1 hit is reported `ambiguous` (we refuse to
// guess which occurrence the model meant).
// 2. per-line ws — line-window compare ignoring per-line trailing
// whitespace and leading/trailing blank needle lines.
// 3. unicode canon — same line-window compare after folding smart
// punctuation to ASCII on both sides; the match is
// mapped back to original offsets.
// 4. levenshtein — best line-window by normalized edit-distance
// similarity; accepted only at >= SIMILARITY_THRESHOLD.
//
// Pure and dependency-free (Levenshtein is the standard iterative two-row DP),
// reimplemented from the general technique — no vendored source.
export type MatchResult =
| { kind: 'exact' | 'fuzzy'; start: number; end: number } // [start,end) offsets into content
| { kind: 'ambiguous'; count: number }
| { kind: 'not_found' };
/** Levenshtein similarity floor for the final fuzzy fallback (strategy 4). */
export const SIMILARITY_THRESHOLD = 0.66;
export function locateMatch(content: string, needle: string): MatchResult {
// Empty needle has no meaningful match.
if (needle.length === 0) return { kind: 'not_found' };
// --- 1. Exact ----------------------------------------------------------------
const exact = locateExact(content, needle);
if (exact) return exact;
// --- 2. Per-line whitespace-insensitive -------------------------------------
const ws = locateByLineWindow(content, needle);
if (ws) return ws;
// --- 3. Unicode-canonicalized whitespace pass -------------------------------
const canon = locateCanonical(content, needle);
if (canon) return canon;
// --- 4. Levenshtein similarity ----------------------------------------------
const lev = locateByLevenshtein(content, needle);
if (lev) return lev;
return { kind: 'not_found' };
}
// --- Strategy 1: exact -------------------------------------------------------
function locateExact(content: string, needle: string): MatchResult | null {
const first = content.indexOf(needle);
if (first === -1) return null;
const second = content.indexOf(needle, first + 1);
if (second === -1) {
return { kind: 'exact', start: first, end: first + needle.length };
}
// Count all occurrences so the caller can report a useful number.
let count = 2;
let idx = content.indexOf(needle, second + 1);
while (idx !== -1) {
count++;
idx = content.indexOf(needle, idx + 1);
}
return { kind: 'ambiguous', count };
}
// --- Line-window machinery ---------------------------------------------------
interface Line {
/** Raw line text (no trailing newline). */
text: string;
/** Offset of the first char of this line in the original content. */
start: number;
/** Offset one past the last char of this line (before its newline, if any). */
end: number;
}
/**
* Split content into lines, tracking each line's real offset span. The span
* EXCLUDES the trailing newline so consecutive line spans plus their newlines
* exactly reconstruct the content; the match span we hand back covers from the
* first matched line's start through the last matched line's end (i.e. without a
* trailing newline), which is what an in-place splice wants.
*/
function splitLines(content: string): Line[] {
const lines: Line[] = [];
let start = 0;
for (let i = 0; i <= content.length; i++) {
if (i === content.length || content[i] === '\n') {
lines.push({ text: content.slice(start, i), start, end: i });
start = i + 1;
}
}
return lines;
}
/** Strip leading/trailing all-blank lines; returns the trimmed slice. */
function trimBlankLines(lines: string[]): string[] {
let lo = 0;
let hi = lines.length;
while (lo < hi && lines[lo]!.trim() === '') lo++;
while (hi > lo && lines[hi - 1]!.trim() === '') hi--;
return lines.slice(lo, hi);
}
/**
* Find a contiguous window of content lines whose trailing-whitespace-trimmed
* text equals the needle's (blank-trimmed) lines. Returns the real offset span
* over the matched content lines, or null if zero match. Multiple matches →
* ambiguous. `normalize` lets the caller fold unicode before comparing.
*/
function locateByLineWindow(
content: string,
needle: string,
normalize: (s: string) => string = (s) => s,
): MatchResult | null {
const contentLines = splitLines(content);
const needleLines = trimBlankLines(needle.split('\n'));
const n = needleLines.length;
if (n === 0) return null;
// A single needle line that is itself blank can't be located meaningfully.
if (n === 1 && needleLines[0]!.trim() === '') return null;
const needleKey = needleLines.map((l) => normalize(l.trimEnd())).join('\n');
const hits: Array<{ start: number; end: number }> = [];
for (let i = 0; i + n <= contentLines.length; i++) {
const windowKey = contentLines
.slice(i, i + n)
.map((l) => normalize(l.text.trimEnd()))
.join('\n');
if (windowKey === needleKey) {
hits.push({ start: contentLines[i]!.start, end: contentLines[i + n - 1]!.end });
}
}
if (hits.length === 0) return null;
if (hits.length > 1) return { kind: 'ambiguous', count: hits.length };
return { kind: 'fuzzy', start: hits[0]!.start, end: hits[0]!.end };
}
// --- Strategy 3: unicode canonicalization ------------------------------------
/**
* Fold smart punctuation to its ASCII equivalent. Crucially this is a
* length-PRESERVING, per-character map (every replacement is one char → one
* char), so an offset into the canonical string is also a valid offset into the
* original — letting strategy 3 reuse the line-window matcher and still hand
* back true original-content offsets.
*/
function canonicalizeChar(ch: string): string {
switch (ch) {
// single quotes / apostrophes
case '': // '
case '': // '
case '': //
case '': //
return "'";
// double quotes
case '“': // "
case '”': // "
case '„': // „
case '‟': // ‟
return '"';
// dashes
case '': // en dash
case '—': // — em dash
case '': // figure dash
case '―': // ― horizontal bar
case '': // minus sign
return '-';
// spaces
case ' ': // nbsp
case '': // figure space
case '': // narrow nbsp
return ' ';
default:
return ch;
}
}
function canonicalize(s: string): string {
let out = '';
for (const ch of s) out += canonicalizeChar(ch);
return out;
}
function locateCanonical(content: string, needle: string): MatchResult | null {
// Only worth running if canonicalization actually changes something on either
// side — otherwise it's identical to strategy 2 which already failed.
const canonContent = canonicalize(content);
const canonNeedle = canonicalize(needle);
if (canonContent === content && canonNeedle === needle) return null;
// Offsets are preserved (length-preserving fold), so a match on the canonical
// content maps directly back to the original.
return locateByLineWindow(canonContent, canonNeedle);
}
// --- Strategy 4: Levenshtein similarity --------------------------------------
/** Standard iterative two-row Levenshtein edit distance. */
function levenshtein(a: string, b: string): number {
if (a === b) return 0;
if (a.length === 0) return b.length;
if (b.length === 0) return a.length;
let prev = new Array<number>(b.length + 1);
let curr = new Array<number>(b.length + 1);
for (let j = 0; j <= b.length; j++) prev[j] = j;
for (let i = 1; i <= a.length; i++) {
curr[0] = i;
const ac = a.charCodeAt(i - 1);
for (let j = 1; j <= b.length; j++) {
const cost = ac === b.charCodeAt(j - 1) ? 0 : 1;
curr[j] = Math.min(
prev[j]! + 1, // deletion
curr[j - 1]! + 1, // insertion
prev[j - 1]! + cost, // substitution
);
}
[prev, curr] = [curr, prev];
}
return prev[b.length]!;
}
/** Normalized similarity in [0,1]: 1 - dist / max(len). */
function similarity(a: string, b: string): number {
const maxLen = Math.max(a.length, b.length);
if (maxLen === 0) return 1;
return 1 - levenshtein(a, b) / maxLen;
}
function locateByLevenshtein(content: string, needle: string): MatchResult | null {
const contentLines = splitLines(content);
const needleLines = trimBlankLines(needle.split('\n'));
const n = needleLines.length;
if (n === 0) return null;
if (contentLines.length < n) return null;
const needleJoined = needleLines.map((l) => l.trim()).join('\n');
let best = -1;
let bestSpan: { start: number; end: number } | null = null;
for (let i = 0; i + n <= contentLines.length; i++) {
const window = contentLines.slice(i, i + n);
const windowJoined = window.map((l) => l.text.trim()).join('\n');
const score = similarity(windowJoined, needleJoined);
if (score > best) {
best = score;
bestSpan = { start: window[0]!.start, end: window[n - 1]!.end };
}
}
if (bestSpan && best >= SIMILARITY_THRESHOLD) {
return { kind: 'fuzzy', start: bestSpan.start, end: bestSpan.end };
}
return null;
}

View File

@@ -25,17 +25,21 @@ interface PendingRow {
session_id: string;
}
interface WorktreeRow {
id: string;
worktree_path: string;
agent: string;
started_at: string;
}
interface ProjectPathRow {
path: string;
}
interface MessageRow {
id: string;
session_id: string;
chat_id: string | null;
role: string;
content: string;
status: string;
model: string | null;
created_at: Date;
}
function textResult(data: unknown) {
return { content: [{ type: 'text' as const, text: JSON.stringify(data, null, 2) }] };
}
@@ -196,25 +200,53 @@ export async function startMcpServer(sql: Sql): Promise<void> {
},
);
// 6. boocoder.list_worktrees
// 6. boocoder.view_session_history
server.tool(
'boocoder.list_worktrees',
'List active worktrees from running tasks',
{},
async () => {
const rows = await sql<WorktreeRow[]>`
SELECT id, worktree_path, agent, started_at
FROM tasks
WHERE worktree_path IS NOT NULL AND state = 'running'
ORDER BY started_at DESC
`;
const items = rows.map((r) => ({
task_id: r.id,
worktree_path: r.worktree_path,
agent: r.agent,
started_at: r.started_at,
}));
return textResult(items);
'boocoder.view_session_history',
'Retrieve the most-recent N messages of a session chat transcript (role != system) from messages_with_parts, returned in chronological (oldest→newest) order',
{
session_id: z.string().describe('Session UUID'),
chat_id: z.string().optional().describe('Optional chat UUID — narrows to one chat tab'),
limit: z
.number()
.int()
.min(1)
.max(200)
.optional()
.describe('Max messages to return (default 50, max 200)'),
},
async (args) => {
const effectiveLimit = Math.min(args.limit ?? 50, 200);
let rows: MessageRow[];
if (args.chat_id) {
rows = await sql<MessageRow[]>`
SELECT id, session_id, chat_id, role, content, status, model, created_at
FROM (
SELECT id, session_id, chat_id, role, content, status, model, created_at
FROM messages_with_parts
WHERE session_id = ${args.session_id}
AND chat_id = ${args.chat_id}
AND role != 'system'
ORDER BY created_at DESC
LIMIT ${effectiveLimit}
) sub
ORDER BY created_at ASC
`;
} else {
rows = await sql<MessageRow[]>`
SELECT id, session_id, chat_id, role, content, status, model, created_at
FROM (
SELECT id, session_id, chat_id, role, content, status, model, created_at
FROM messages_with_parts
WHERE session_id = ${args.session_id}
AND role != 'system'
ORDER BY created_at DESC
LIMIT ${effectiveLimit}
) sub
ORDER BY created_at ASC
`;
}
return textResult({ session_id: args.session_id, count: rows.length, messages: rows });
},
);

View File

@@ -0,0 +1,88 @@
/**
* Generic POSIX loopback-port utilities.
*
* Extracted verbatim (v2.7 audit reshape) from `backends/opencode-server.ts`,
* where they were embedded in the backend god-class. They have nothing to do with
* opencode semantics — they reclaim/await/allocate a 127.0.0.1 port — so they live
* here as reusable infra. No behavior change from the original.
*/
import { createServer, connect as netConnect } from 'node:net';
import { spawnSync } from 'node:child_process';
/**
* Reclaim a loopback port a dead child may still hold (lift of openchamber
* `killProcessOnPort`). Best-effort, POSIX-only (`lsof`/`kill`); a failure is
* harmless because the next spawn allocates a fresh ephemeral port. Never kills
* this process. Synchronous + short-timeout so a crash handler doesn't block.
*/
export function reclaimPort(port: number | null): void {
if (!port || process.platform === 'win32') return;
try {
const res = spawnSync('lsof', ['-ti', `:${port}`], { encoding: 'utf8', timeout: 3_000, windowsHide: true });
const out = res.stdout || '';
const myPid = process.pid;
for (const pidStr of out.split(/\s+/)) {
const pid = parseInt(pidStr.trim(), 10);
if (pid && pid !== myPid) {
try {
spawnSync('kill', ['-9', String(pid)], { stdio: 'ignore', timeout: 2_000 });
} catch {
// ignore — best effort
}
}
}
} catch {
// lsof absent or failed — the fresh-ephemeral-port spawn doesn't need this.
}
}
/**
* Resolve true once nothing is listening on `port` (lift of openchamber
* `waitForPortRelease`). Used before re-spawning on a fixed port; with ephemeral
* ports it's a fast no-op. Probes 127.0.0.1; resolves false at the deadline.
*/
export function waitForPortRelease(port: number, timeoutMs: number): Promise<boolean> {
const deadline = Date.now() + timeoutMs;
return new Promise((resolve) => {
const attempt = () => {
const socket = netConnect({ port, host: '127.0.0.1' });
let settled = false;
const finish = (released: boolean) => {
if (settled) return;
settled = true;
socket.removeAllListeners();
socket.destroy();
if (released || Date.now() >= deadline) {
resolve(released);
return;
}
setTimeout(attempt, 150);
};
socket.once('connect', () => finish(false));
socket.once('error', (err: NodeJS.ErrnoException) => {
if (err && (err.code === 'ECONNREFUSED' || err.code === 'EHOSTUNREACH')) finish(true);
else finish(false);
});
socket.setTimeout(500, () => finish(true));
};
attempt();
});
}
/** Bind-probe an ephemeral port on loopback. */
export function freePort(): Promise<number> {
return new Promise((resolve, reject) => {
const srv = createServer();
srv.unref();
srv.on('error', reject);
srv.listen(0, '127.0.0.1', () => {
const addr = srv.address();
if (addr && typeof addr === 'object') {
const { port } = addr;
srv.close(() => resolve(port));
} else {
srv.close(() => reject(new Error('port-utils: could not determine a free port')));
}
});
});
}

View File

@@ -0,0 +1,23 @@
/**
* normalize-agent-status (#10) — clean-room vendor-event → bucket mapping.
*
* Different coding agents (claude, opencode, codex/gemini, goose, qwen) emit
* lifecycle hook events under inconsistent names: PascalCase (`SessionStart`),
* snake_case (`session_start`), camelCase (`sessionStart`), and a handful of
* provider-specific approval events (`exec_approval_request`). This module
* collapses every known event name into one of three coarse signals:
*
* working — the agent is actively progressing a turn
* blocked — the agent is waiting on a human (permission / approval / question)
* done — the turn / session ended cleanly
*
* `null` is returned for anything unrecognized so callers can ignore noise.
*
* Built now for the scoped status-publish, but specifically shaped for reuse by
* the documented config-injection follow-on: a future notify-hook injected into
* each agent's native config will POST the RAW vendor event name to a BooCoder
* endpoint, which runs this helper to derive the normalized status. The names
* below are facts about each agent's hook surface — not copied vendor code.
*/
export type AgentStatus = 'working' | 'blocked' | 'idle' | 'error';

View File

@@ -21,7 +21,8 @@ import { readdir, stat } from 'node:fs/promises';
import { join } from 'node:path';
import type { FastifyBaseLogger } from 'fastify';
import type { Sql } from '../db.js';
import { WORKTREE_BASE, checkWorktreeWorkAtRisk } from './worktrees.js';
import { WORKTREE_BASE } from './worktrees.js';
import { checkWorktreeWorkAtRisk } from './worktree-risk.js';
import { hostExec } from './host-exec.js';
import {
selectOrphanWorktreeTargets,

View File

@@ -2,6 +2,7 @@ import { readFile, writeFile, unlink, mkdir } from 'node:fs/promises';
import { dirname } from 'node:path';
import type { Sql } from '../db.js';
import { resolveWritePath } from './write_guard.js';
import { locateMatch } from './fuzzy-match.js';
// --- Types -------------------------------------------------------------------
@@ -121,10 +122,18 @@ export async function applyOne(
case 'edit': {
const { old: oldStr, new: newStr } = JSON.parse(change.diff) as { old: string; new: string };
const content = await readFile(change.file_path, 'utf8');
if (!content.includes(oldStr)) {
throw new Error('old_string not found in file — file may have changed since the edit was queued');
const match = locateMatch(content, oldStr);
if (match.kind === 'ambiguous') {
throw new Error(
`old_string matches ${match.count} locations — add surrounding context to disambiguate`,
);
}
const updated = content.replace(oldStr, newStr);
if (match.kind === 'not_found') {
throw new Error(
'old_string not found in file (even fuzzily) — file may have changed since the edit was queued',
);
}
const updated = content.slice(0, match.start) + newStr + content.slice(match.end);
await writeFile(change.file_path, updated, 'utf8');
break;
}
@@ -172,10 +181,6 @@ export async function rejectOne(sql: Sql, changeId: string): Promise<void> {
await sql`UPDATE pending_changes SET status = 'rejected' WHERE id = ${changeId} AND status = 'pending'`;
}
export async function rejectAll(sql: Sql, sessionId: string): Promise<void> {
await sql`UPDATE pending_changes SET status = 'rejected' WHERE session_id = ${sessionId} AND status = 'pending'`;
}
// --- Rewind functions --------------------------------------------------------
export async function rewindOne(
@@ -203,10 +208,18 @@ export async function rewindOne(
// Reverse an edit: swap old and new
const { old: oldStr, new: newStr } = JSON.parse(change.diff) as { old: string; new: string };
const content = await readFile(change.file_path, 'utf8');
if (!content.includes(newStr)) {
throw new Error('new_string not found in file — cannot rewind; file may have been modified since apply');
const match = locateMatch(content, newStr);
if (match.kind === 'ambiguous') {
throw new Error(
`new_string matches ${match.count} locations — cannot rewind; add surrounding context to disambiguate`,
);
}
const reverted = content.replace(newStr, oldStr);
if (match.kind === 'not_found') {
throw new Error(
'new_string not found in file (even fuzzily) — cannot rewind; file may have been modified since apply',
);
}
const reverted = content.slice(0, match.start) + oldStr + content.slice(match.end);
await writeFile(change.file_path, reverted, 'utf8');
break;
}

View File

@@ -127,7 +127,3 @@ export function getResolvedRegistry(): Map<string, ResolvedProviderDef> {
return cachedRegistry ?? buildResolvedRegistry(PROVIDERS, { providers: {} });
}
/** Resolved provider ids in registry order. */
export function getResolvedProviderIds(): string[] {
return [...getResolvedRegistry().keys()];
}

View File

@@ -5,42 +5,28 @@
* (see provider-config-registry.ts). Loading NEVER throws at startup (design.md
* §2.1): a missing file, invalid JSON, or schema mismatch all fall back to
* `{ providers: {} }` (built-ins only, all enabled).
*
* Schemas are defined once in @boocode/contracts/provider-config and re-exported
* here so existing importers (routes, tests, registry) don't need path changes.
*/
import { readFileSync, writeFileSync } from 'node:fs';
import { z } from 'zod';
import {
ProviderOverrideSchema,
CoderProvidersFileSchema,
ProviderConfigPatchSchema,
type ProviderOverride,
type CoderProvidersFile,
type ProviderConfigPatch,
} from '@boocode/contracts/provider-config';
// Schemas verbatim from design.md §2.2.
export const ProviderOverrideSchema = z.object({
extends: z.enum(['acp']).optional(), // v2.3: only 'acp' for custom; built-ins omit extends
label: z.string().min(1).optional(),
description: z.string().optional(),
command: z.array(z.string().min(1)).min(1).optional(), // [binary, ...args]
env: z.record(z.string()).optional(),
enabled: z.boolean().optional(), // default true
order: z.number().int().optional(), // UI sort key
models: z.array(z.object({ id: z.string(), label: z.string() })).optional(),
additionalModels: z.array(z.object({ id: z.string(), label: z.string() })).optional(),
});
export const CoderProvidersFileSchema = z.object({
providers: z.record(ProviderOverrideSchema).default({}),
});
export type ProviderOverride = z.infer<typeof ProviderOverrideSchema>;
export type CoderProvidersFile = z.infer<typeof CoderProvidersFileSchema>;
/**
* PATCH body schema (design.md §6.2). A partial providers map where each value
* is either a full override object (REPLACES that id's override) or `null`
* (DELETES the override → revert to the built-in default). Ids absent from the
* patch are left untouched. The route validates the body against this first
* (malformed → 422) so a bad shape can never reach the merge/save step.
*/
export const ProviderConfigPatchSchema = z.object({
providers: z.record(ProviderOverrideSchema.nullable()).default({}),
});
export type ProviderConfigPatch = z.infer<typeof ProviderConfigPatchSchema>;
export {
ProviderOverrideSchema,
CoderProvidersFileSchema,
ProviderConfigPatchSchema,
type ProviderOverride,
type CoderProvidersFile,
type ProviderConfigPatch,
};
/**
* Shallow per-id merge (design.md §6.2 / Paseo `patchConfig`). Each key in

View File

@@ -38,6 +38,12 @@ export const PROVIDERS: ProviderDef[] = [
},
{
name: 'claude',
// transport stays 'pty' — the DEFAULT dispatch path (one-shot `claude
// --output-format stream-json`). claude-sdk-sessionstore #9 (Part 2) adds a warm
// Claude-Agent-SDK backend (services/backends/claude-sdk.ts) routed ONLY when the
// `CLAUDE_SDK_BACKEND` env flag is truthy AND the task is a chat tab; with the flag
// off (production default) claude always uses this PTY path, so the transport label
// is left unchanged. Flip the env var on a host (after a live smoke) to opt in.
label: 'Claude Code',
transport: 'pty',
modelSource: 'static',

View File

@@ -1,61 +1,10 @@
/** Shared provider / snapshot types (Paseo-shaped, BooCoder-native). */
/** Provider snapshot types — re-exported from @boocode/contracts for local consumers. */
export interface ProviderMode {
id: string;
label: string;
description?: string;
/** Auto-approve tool permissions when this mode is selected. */
isUnattended?: boolean;
}
export interface ThinkingOption {
id: string;
label: string;
isDefault?: boolean;
}
export interface ProviderModel {
id: string;
label: string;
description?: string;
isDefault?: boolean;
thinkingOptions?: ThinkingOption[];
defaultThinkingOptionId?: string;
}
// v2.3 phase 2: 'loading' (cache-miss, probe in flight) + 'unavailable'
// (disabled or not installed) restored alongside the terminal 'ready' | 'error'.
export type ProviderSnapshotStatus = 'loading' | 'ready' | 'unavailable' | 'error';
export interface AgentCommand {
name: string;
description?: string;
// v2.5.11: 'skill' (plugin skill) vs 'command' (native/CLI slash command).
// Drives the icon split in the coder slash menu. Undefined → command.
kind?: 'command' | 'skill';
}
// KEEP IN SYNC with apps/web/src/api/types.ts ProviderSnapshotEntry — parity is
// enforced by __tests__/provider-types-parity.test.ts (fails on any field drift).
export interface ProviderSnapshotEntry {
name: string;
label: string;
description?: string;
transport: string;
status: ProviderSnapshotStatus;
enabled: boolean;
installed: boolean;
models: ProviderModel[];
modes: ProviderMode[];
defaultModeId: string | null;
commands: AgentCommand[];
error?: string;
fetchedAt?: string;
}
export interface AgentSessionConfig {
provider: string;
model?: string;
modeId?: string;
thinkingOptionId?: string;
}
export type {
ProviderMode,
ThinkingOption,
ProviderModel,
ProviderSnapshotStatus,
AgentCommand,
ProviderSnapshotEntry,
} from '@boocode/contracts/provider-snapshot';

View File

@@ -1,13 +1,29 @@
/**
* PTY dispatch — runs external agents directly on the host.
*
* claude + qwen run with `--output-format stream-json` and emit Claude-Code's
* stream-json NDJSON on stdout. When an `onEvent` callback is supplied we
* line-buffer that stdout (split on `\n`, hold the partial tail) and feed complete
* lines to `makeStreamJsonParser` so deltas surface live as AgentEvents. The raw
* stdout is still accumulated + returned for back-compat (and the dispatcher's
* fallback when nothing parsed). See `stream-json-parser.ts`.
*/
import type { FastifyBaseLogger } from 'fastify';
import { spawn } from 'node:child_process';
import type { AgentEvent } from './agent-backend.js';
import { makeStreamJsonParser, type StreamJsonUsage } from './stream-json-parser.js';
export interface DispatchResult {
exitCode: number;
stdout: string;
stderr: string;
/** True iff at least one NDJSON AgentEvent was parsed from stdout (v#7). When
* false the dispatcher falls back to slicing stdout as the assistant content. */
streamed: boolean;
/** Final usage parsed from the stream-json `result` / `message_delta`, if any. */
usage?: StreamJsonUsage;
/** Provider session id from the stream-json `system` init line, if any. */
agentSessionId?: string | null;
}
export interface PtyDispatchOpts {
@@ -20,6 +36,10 @@ export interface PtyDispatchOpts {
installPath?: string;
signal?: AbortSignal;
log: FastifyBaseLogger;
/** Optional live event sink. When set, stdout is line-buffered + NDJSON-parsed
* and each AgentEvent is forwarded here as it arrives. Absent → opaque (old)
* behavior: stdout is accumulated and returned, no parsing. */
onEvent?: (e: AgentEvent) => void;
}
interface PtySpawnSpec {
@@ -40,7 +60,9 @@ function buildPtySpawnSpec(
switch (agent) {
case 'claude': {
const args = ['-p'];
// stream-json on -p requires --verbose (Claude Code rejects stream-json
// print mode without it). qwen needs no such flag.
const args = ['-p', '--output-format', 'stream-json', '--verbose'];
if (model) args.push('--model', model);
if (modeId) args.push('--permission-mode', modeId);
if (thinkingOptionId) args.push('--effort', thinkingOptionId);
@@ -73,7 +95,7 @@ function buildPtySpawnSpec(
}
export async function dispatchViaPty(opts: PtyDispatchOpts): Promise<DispatchResult> {
const { agent, task, worktreePath, model, modeId, thinkingOptionId, installPath, signal, log } = opts;
const { agent, task, worktreePath, model, modeId, thinkingOptionId, installPath, signal, log, onEvent } = opts;
const cmd = buildPtySpawnSpec(agent, task, model, modeId, thinkingOptionId, installPath);
if (!cmd) {
@@ -81,6 +103,7 @@ export async function dispatchViaPty(opts: PtyDispatchOpts): Promise<DispatchRes
exitCode: 1,
stdout: '',
stderr: `Agent '${agent}' is not yet supported for PTY dispatch.`,
streamed: false,
};
}
@@ -102,7 +125,32 @@ export async function dispatchViaPty(opts: PtyDispatchOpts): Promise<DispatchRes
let stderr = '';
let killed = false;
child.stdout!.on('data', (chunk: Buffer) => { stdout += chunk.toString(); });
// Live NDJSON parsing (only when a sink is supplied). Line-buffer: split on
// '\n', dispatch complete lines, hold the partial tail until the next chunk.
const parser = onEvent ? makeStreamJsonParser() : null;
let lineBuf = '';
let streamed = false;
const feedLine = (line: string): void => {
if (!parser || !onEvent) return;
for (const e of parser.push(line)) {
streamed = true;
onEvent(e);
}
};
child.stdout!.on('data', (chunk: Buffer) => {
const text = chunk.toString();
stdout += text;
if (!parser) return;
lineBuf += text;
let nl = lineBuf.indexOf('\n');
while (nl !== -1) {
const line = lineBuf.slice(0, nl);
lineBuf = lineBuf.slice(nl + 1);
feedLine(line);
nl = lineBuf.indexOf('\n');
}
});
child.stderr!.on('data', (chunk: Buffer) => { stderr += chunk.toString(); });
const cleanup = () => {
@@ -116,7 +164,7 @@ export async function dispatchViaPty(opts: PtyDispatchOpts): Promise<DispatchRes
if (signal) {
if (signal.aborted) {
cleanup();
resolve({ exitCode: 130, stdout: '', stderr: 'Aborted before start' });
resolve({ exitCode: 130, stdout: '', stderr: 'Aborted before start', streamed: false });
return;
}
signal.addEventListener('abort', cleanup, { once: true });
@@ -124,8 +172,18 @@ export async function dispatchViaPty(opts: PtyDispatchOpts): Promise<DispatchRes
child.on('close', (code) => {
if (signal) signal.removeEventListener('abort', cleanup);
log.info({ agent, exitCode: code }, 'pty-dispatch: completed');
resolve({ exitCode: code ?? 1, stdout, stderr });
// Flush any final line with no trailing newline.
if (lineBuf.trim()) feedLine(lineBuf);
lineBuf = '';
log.info({ agent, exitCode: code, streamed }, 'pty-dispatch: completed');
resolve({
exitCode: code ?? 1,
stdout,
stderr,
streamed,
usage: parser?.usage(),
agentSessionId: parser?.sessionId() ?? null,
});
});
child.on('error', (err) => {

View File

@@ -0,0 +1,296 @@
/**
* Claude-Code-compatible stream-json NDJSON parser (feature #7,
* openspec `sampling-streamjson-tokens`).
*
* qwen (`--output-format stream-json`) and claude (`--output-format stream-json`)
* both emit Claude-Code's stream-json NDJSON on stdout: one JSON object per line.
* This module turns that stream into the same transport-agnostic `AgentEvent`s the
* ACP / opencode-server backends emit, so the PTY dispatch path can publish live
* broker frames + persist structured parts instead of slicing stdout opaque.
*
* Two surfaces:
* - `parseStreamJsonLine(line, state)` — PURE per-line mapping (unit-testable).
* `state` is the caller-owned accumulator (open tool blocks + usage/session_id).
* - `makeStreamJsonParser()` — a thin stateful wrapper holding the state, with a
* `push(line)` that returns the events for that line and getters for the final
* `usage` / `sessionId`.
*
* Defensive by contract: a non-JSON / partial / garbage line yields `[]` and never
* throws. Tool args (`input_json_delta`) arrive fragmented across many lines; we
* accumulate the partial JSON string per content-block index and only surface the
* parsed `rawInput` once the block stops (or, as a fallback, off the terminal
* `assistant` message which carries the fully-assembled `tool_use` blocks).
*
* Schema (keyed on top-level `type`):
* - `system` — init: { session_id, tools, ... }
* - `assistant` — { message: { content: [ {type:'text'|'thinking'|'tool_use', ...} ], usage? } }
* - `user` — tool results (ignored — diffing the worktree captures effects)
* - `result` — final: { usage: { input_tokens, output_tokens }, session_id? }
* - `stream_event` — { event: { type, index?, content_block?, delta?, usage? } }
* event.type:
* content_block_start — { index, content_block: {type, id?, name?} }
* content_block_delta — { index, delta: {type, text?|thinking?|partial_json?} }
* content_block_stop — { index }
* message_delta — { usage: { output_tokens } }
* message_start — { message: { usage } }
*/
import type { AgentEvent } from './agent-backend.js';
import type { AcpToolSnapshot } from './acp-tool-snapshot.js';
/** Convenience alias for the per-line return value. */
export type AgentEventList = AgentEvent[];
export interface StreamJsonUsage {
inputTokens?: number;
outputTokens?: number;
}
/** Per-open-content-block accumulation for tool args assembled across deltas. */
interface OpenToolBlock {
toolCallId: string;
name: string;
/** Concatenated `input_json_delta.partial_json` fragments. */
partialJson: string;
}
export interface StreamJsonState {
/** content-block index → open tool block (only `tool_use` blocks are tracked). */
toolBlocks: Map<number, OpenToolBlock>;
sessionId: string | null;
usage: StreamJsonUsage;
}
export function makeStreamJsonState(): StreamJsonState {
return { toolBlocks: new Map(), sessionId: null, usage: {} };
}
function asRecord(value: unknown): Record<string, unknown> | null {
if (value && typeof value === 'object' && !Array.isArray(value)) {
return value as Record<string, unknown>;
}
return null;
}
function asString(value: unknown): string | undefined {
return typeof value === 'string' ? value : undefined;
}
function asNumber(value: unknown): number | undefined {
return typeof value === 'number' && Number.isFinite(value) ? value : undefined;
}
/** Pull token counts out of an Anthropic-shape `usage` object, mutating state. */
function captureUsage(usage: Record<string, unknown> | null, state: StreamJsonState): void {
if (!usage) return;
const input = asNumber(usage.input_tokens);
const output = asNumber(usage.output_tokens);
if (input !== undefined) state.usage.inputTokens = input;
// output_tokens is reported incrementally on message_delta; keep the latest.
if (output !== undefined) state.usage.outputTokens = output;
}
/** Parse the accumulated tool-arg JSON; tolerate an unparseable/partial body. */
function parseToolInput(partialJson: string): unknown {
const trimmed = partialJson.trim();
if (!trimmed) return {};
try {
return JSON.parse(trimmed);
} catch {
return { _raw: partialJson };
}
}
function toolSnapshot(block: OpenToolBlock, rawInput: unknown, status: AcpToolSnapshot['status']): AcpToolSnapshot {
return {
toolCallId: block.toolCallId,
title: block.name,
kind: null,
status,
rawInput,
};
}
/**
* Map one stream-event sub-object (the `event` field of a `stream_event` line) to
* AgentEvents, mutating `state` for open tool blocks + usage.
*/
function handleStreamEvent(event: Record<string, unknown>, state: StreamJsonState): AgentEvent[] {
const eventType = asString(event.type);
if (!eventType) return [];
switch (eventType) {
case 'content_block_start': {
const index = asNumber(event.index);
const block = asRecord(event.content_block);
if (index === undefined || !block) return [];
if (asString(block.type) !== 'tool_use') return [];
const toolCallId = asString(block.id) ?? `tool_${index}`;
const name = asString(block.name) ?? 'tool';
const open: OpenToolBlock = { toolCallId, name, partialJson: '' };
state.toolBlocks.set(index, open);
// Surface the tool start immediately (running, no args yet) so the UI shows
// the call before the args finish streaming.
return [{ type: 'tool_call', toolCall: toolSnapshot(open, {}, 'in_progress') }];
}
case 'content_block_delta': {
const index = asNumber(event.index);
const delta = asRecord(event.delta);
if (delta === null) return [];
const deltaType = asString(delta.type);
if (deltaType === 'text_delta') {
const text = asString(delta.text);
return text ? [{ type: 'text', text }] : [];
}
if (deltaType === 'thinking_delta') {
const text = asString(delta.thinking);
return text ? [{ type: 'reasoning', text }] : [];
}
if (deltaType === 'input_json_delta') {
// Accumulate tool args; no event until the block stops.
const fragment = asString(delta.partial_json);
if (index !== undefined && fragment) {
const open = state.toolBlocks.get(index);
if (open) open.partialJson += fragment;
}
return [];
}
return [];
}
case 'content_block_stop': {
const index = asNumber(event.index);
if (index === undefined) return [];
const open = state.toolBlocks.get(index);
if (!open) return [];
state.toolBlocks.delete(index);
const rawInput = parseToolInput(open.partialJson);
return [{ type: 'tool_update', toolCall: toolSnapshot(open, rawInput, 'completed') }];
}
case 'message_start': {
const message = asRecord(event.message);
captureUsage(asRecord(message?.usage), state);
return [];
}
case 'message_delta': {
captureUsage(asRecord(event.usage), state);
return [];
}
default:
return [];
}
}
/**
* Map the terminal `assistant` message (post-hoc full message) to AgentEvents. Used
* as a fallback for transports that emit only the assembled `assistant` line and no
* incremental `stream_event`s. When stream_events already streamed a block, the
* caller dedups by toolCallId, so re-emitting the assembled tool_use is harmless.
*/
function handleAssistantMessage(message: Record<string, unknown>, state: StreamJsonState): AgentEvent[] {
captureUsage(asRecord(message.usage), state);
const content = message.content;
if (!Array.isArray(content)) return [];
const out: AgentEvent[] = [];
let toolIdx = 0;
for (const rawBlock of content) {
const block = asRecord(rawBlock);
if (!block) continue;
const blockType = asString(block.type);
if (blockType === 'text') {
const text = asString(block.text);
if (text) out.push({ type: 'text', text });
} else if (blockType === 'thinking') {
const text = asString(block.thinking);
if (text) out.push({ type: 'reasoning', text });
} else if (blockType === 'tool_use') {
const toolCallId = asString(block.id) ?? `tool_${toolIdx}`;
const name = asString(block.name) ?? 'tool';
const rawInput = 'input' in block ? block.input : {};
out.push({
type: 'tool_update',
toolCall: { toolCallId, title: name, kind: null, status: 'completed', rawInput },
});
}
toolIdx++;
}
return out;
}
/**
* Pure per-line mapping. `line` is a single complete NDJSON line (no trailing
* newline required; surrounding whitespace tolerated). Returns the AgentEvents the
* line produces and mutates `state` (open tool blocks, usage, session_id). A blank,
* non-JSON, or unrecognized line yields `[]` and never throws.
*/
export function parseStreamJsonLine(line: string, state: StreamJsonState): AgentEvent[] {
const trimmed = line.trim();
if (!trimmed) return [];
let obj: Record<string, unknown> | null;
try {
const parsed: unknown = JSON.parse(trimmed);
obj = asRecord(parsed);
} catch {
return [];
}
if (!obj) return [];
const type = asString(obj.type);
switch (type) {
case 'system': {
const sid = asString(obj.session_id);
if (sid) state.sessionId = sid;
return [];
}
case 'stream_event': {
const event = asRecord(obj.event);
return event ? handleStreamEvent(event, state) : [];
}
case 'assistant': {
const sid = asString(obj.session_id);
if (sid) state.sessionId = sid;
const message = asRecord(obj.message);
return message ? handleAssistantMessage(message, state) : [];
}
case 'result': {
const sid = asString(obj.session_id);
if (sid) state.sessionId = sid;
captureUsage(asRecord(obj.usage), state);
return [];
}
default:
// `user` (tool results) and any unknown line type — ignore.
return [];
}
}
export interface StreamJsonParser {
/** Feed one complete NDJSON line; returns its AgentEvents (never throws). */
push(line: string): AgentEvent[];
/** Final usage (input/output tokens) accumulated so far. */
usage(): StreamJsonUsage;
/** Provider session id from the init `system` line / `result`, if seen. */
sessionId(): string | null;
}
/**
* Stateful wrapper around `parseStreamJsonLine`. Holds per-tool-block accumulation
* + usage/session_id across the turn. Line-buffering (splitting stdout on `\n` and
* holding the partial tail) is the caller's job — see `pty-dispatch.ts`.
*/
export function makeStreamJsonParser(): StreamJsonParser {
const state = makeStreamJsonState();
return {
push: (line: string) => parseStreamJsonLine(line, state),
usage: () => ({ ...state.usage }),
sessionId: () => state.sessionId,
};
}

View File

@@ -26,9 +26,4 @@ export const WRITE_TOOLS: readonly ToolDef<any>[] = [
checkTaskStatusTool,
];
// eslint-disable-next-line @typescript-eslint/no-explicit-any
export const WRITE_TOOLS_BY_NAME: ReadonlyMap<string, ToolDef<any>> = new Map(
WRITE_TOOLS.map((t) => [t.name, t]),
);
export { editFileTool, createFileTool, deleteFileTool, applyPendingTool, rewindTool, newTaskTool, listTasksTool, checkTaskStatusTool };

View File

@@ -0,0 +1,160 @@
/**
* Worktree work-at-risk assessment (split out of `worktrees.ts`, v2.7 audit
* reshape). The git-worktree create/diff/remove lifecycle stays in `worktrees.ts`;
* this module owns the orthogonal "would deleting this worktree lose work?" gate
* the server consults before a session delete, plus the recoverable stash escape.
*
* Session delete itself lives in apps/server (Docker), which CANNOT see the host
* worktree dirs or run git on them — only BooCoder (host systemd) can — so the
* server calls the routes that wrap these helpers. Behavior is unchanged from the
* original worktrees.ts implementation.
*/
import type { WorktreeRiskReport } from '@boocode/contracts/worktree-risk';
import { hostExec } from './host-exec.js';
/**
* Resolve the project's default branch as a git-usable ref (e.g. "origin/main").
*
* `refs/remotes/origin/HEAD` lives in the repo's COMMON git dir and is shared
* across every linked worktree, so reading it from the session worktree returns
* the REMOTE's default branch — never this worktree's own `session-<id>` branch
* (that would be `symbolic-ref HEAD`, a different ref). Falls back to probing
* common defaults by verified existence when origin/HEAD isn't set (e.g. a repo
* that never ran `git remote set-head`). Returns null if none resolve, in which
* case the unmerged check is skipped (dirty + unpushed still protect the work).
*/
async function detectDefaultBranchRef(
worktreePath: string,
opts?: { signal?: AbortSignal },
): Promise<string | null> {
const head = await hostExec(
`git -C ${shellEscape(worktreePath)} symbolic-ref --short refs/remotes/origin/HEAD`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (head.exitCode === 0) {
const ref = head.stdout.trim(); // e.g. "origin/main"
if (ref) {
const verify = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(ref + '^{commit}')}`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (verify.exitCode === 0 && verify.stdout.trim()) return ref;
}
}
// origin/HEAD unset or unresolvable — probe common defaults. Prefer the
// remote-tracking ref (always resolvable in a fresh worktree) over the local
// head, which may not exist if the default branch lives only in the main tree.
for (const cand of ['origin/main', 'origin/master', 'main', 'master']) {
const verify = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(cand + '^{commit}')}`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (verify.exitCode === 0 && verify.stdout.trim()) return cand;
}
return null;
}
/**
* Inspect a worktree for work that would be lost if its session were deleted.
* Three checks, all via the audited hostExec + shellEscape path (every
* interpolated value — paths, refs — is single-quote-escaped; no bare
* interpolation). Any unexpected git failure is treated as at-risk, never a
* silent pass.
*/
export async function checkWorktreeWorkAtRisk(
worktreePath: string,
opts?: { signal?: AbortSignal },
): Promise<WorktreeRiskReport> {
// Branch name — also doubles as the "is this still a git worktree?" probe.
const br = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-parse --abbrev-ref HEAD`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (br.exitCode !== 0) {
return {
worktreePath,
branch: '',
dirty: false,
unpushed: 0,
unmerged: 0,
atRisk: true,
error: `git rev-parse failed: ${br.stderr.trim() || 'not a git worktree'}`,
};
}
const branch = br.stdout.trim();
// (a) Uncommitted (dirty working tree, including untracked files).
const st = await hostExec(
`git -C ${shellEscape(worktreePath)} status --porcelain`,
{ signal: opts?.signal, timeoutMs: 15_000 },
);
if (st.exitCode !== 0) {
return {
worktreePath,
branch,
dirty: false,
unpushed: 0,
unmerged: 0,
atRisk: true,
error: `git status failed: ${st.stderr.trim()}`,
};
}
const dirty = st.stdout.trim().length > 0;
// (b) Unpushed commits. No upstream configured => work exists only locally;
// treat as unpushed-by-definition (-1) rather than an error.
const up = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape('@{u}..HEAD')}`,
{ signal: opts?.signal, timeoutMs: 15_000 },
);
const unpushed = up.exitCode === 0 ? (parseInt(up.stdout.trim() || '0', 10) || 0) : -1;
// (c) Unmerged commits — on this branch but not in the project default branch.
const defaultRef = await detectDefaultBranchRef(worktreePath, opts);
let unmerged = 0;
if (defaultRef) {
const rl = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape(defaultRef + '..HEAD')}`,
{ signal: opts?.signal, timeoutMs: 15_000 },
);
if (rl.exitCode === 0) unmerged = parseInt(rl.stdout.trim() || '0', 10) || 0;
}
// unpushed only contributes when an upstream actually exists. Session branches
// (session-<id>) never have one (unpushed === -1), and any real local-only work
// there already surfaces as unmerged > 0 — so the no-upstream case adds no
// protection, only friction (it flagged every pristine worktree-backed session).
// The unpushed > 0 arm stays forward-compatible with P1.5 pushable branches.
const hasUpstream = unpushed !== -1;
const atRisk = dirty || unmerged > 0 || (hasUpstream && unpushed > 0);
return { worktreePath, branch, dirty, unpushed, unmerged, atRisk };
}
/**
* Stash a worktree's uncommitted changes (including untracked, via -u) so the
* working tree is clean. Stash entries live in the repo's common git dir, so
* they survive worktree-dir removal — this is the recoverable, safe-by-default
* escape. Note it only clears the *dirty* risk; unpushed/unmerged commits
* remain on the branch, so a re-attempted delete may still block on those.
*/
export async function stashWorktree(
worktreePath: string,
opts?: { signal?: AbortSignal },
): Promise<{ stashed: boolean; error?: string }> {
const r = await hostExec(
`git -C ${shellEscape(worktreePath)} stash push -u -m ${shellEscape('boocode: pre-delete stash')}`,
{ signal: opts?.signal, timeoutMs: 30_000 },
);
if (r.exitCode !== 0) {
return { stashed: false, error: r.stderr.trim() || r.stdout.trim() };
}
// "No local changes to save" => exit 0, nothing stashed — not an error.
const stashed = !/no local changes to save/i.test(r.stdout);
return { stashed };
}
/** Minimal shell escape for paths (single-quote wrapping). */
function shellEscape(s: string): string {
// Replace single quotes with escaped version, wrap in single quotes
return "'" + s.replace(/'/g, "'\\''") + "'";
}

View File

@@ -8,6 +8,8 @@
*/
import type { Sql } from '../db.js';
import { hostExec } from './host-exec.js';
import type { WorktreeRiskReport } from '@boocode/contracts/worktree-risk';
import { checkWorktreeWorkAtRisk } from './worktree-risk.js';
export const WORKTREE_BASE = '/tmp/booworktrees';
@@ -379,163 +381,8 @@ export async function rebaselineWorktreeAfterApply(
}
// ─── Session-delete work-loss guard ─────────────────────────────────────────
/**
* Risk report for a single worktree, returned by checkWorktreeWorkAtRisk.
* `atRisk` is the gate the server reads before allowing a session delete.
* A git error never silently passes — it forces `atRisk` true and surfaces
* the message in `error` (fail-closed).
*/
export interface RiskReport {
worktreePath: string;
branch: string;
dirty: boolean; // uncommitted working-tree changes (incl. untracked)
unpushed: number; // commits ahead of upstream, or -1 if no upstream is set
unmerged: number; // commits on this branch not in the project default branch
atRisk: boolean; // dirty || unmerged > 0 || (upstream && unpushed > 0) || git error
error?: string; // populated on a git failure; presence forces atRisk
}
/**
* Resolve the project's default branch as a git-usable ref (e.g. "origin/main").
*
* `refs/remotes/origin/HEAD` lives in the repo's COMMON git dir and is shared
* across every linked worktree, so reading it from the session worktree returns
* the REMOTE's default branch — never this worktree's own `session-<id>` branch
* (that would be `symbolic-ref HEAD`, a different ref). Falls back to probing
* common defaults by verified existence when origin/HEAD isn't set (e.g. a repo
* that never ran `git remote set-head`). Returns null if none resolve, in which
* case the unmerged check is skipped (dirty + unpushed still protect the work).
*/
async function detectDefaultBranchRef(
worktreePath: string,
opts?: { signal?: AbortSignal },
): Promise<string | null> {
const head = await hostExec(
`git -C ${shellEscape(worktreePath)} symbolic-ref --short refs/remotes/origin/HEAD`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (head.exitCode === 0) {
const ref = head.stdout.trim(); // e.g. "origin/main"
if (ref) {
const verify = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(ref + '^{commit}')}`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (verify.exitCode === 0 && verify.stdout.trim()) return ref;
}
}
// origin/HEAD unset or unresolvable — probe common defaults. Prefer the
// remote-tracking ref (always resolvable in a fresh worktree) over the local
// head, which may not exist if the default branch lives only in the main tree.
for (const cand of ['origin/main', 'origin/master', 'main', 'master']) {
const verify = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(cand + '^{commit}')}`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (verify.exitCode === 0 && verify.stdout.trim()) return cand;
}
return null;
}
/**
* Inspect a worktree for work that would be lost if its session were deleted.
* Three checks, all via the audited hostExec + shellEscape path (every
* interpolated value — paths, refs — is single-quote-escaped; no bare
* interpolation). Any unexpected git failure is treated as at-risk, never a
* silent pass.
*/
export async function checkWorktreeWorkAtRisk(
worktreePath: string,
opts?: { signal?: AbortSignal },
): Promise<RiskReport> {
// Branch name — also doubles as the "is this still a git worktree?" probe.
const br = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-parse --abbrev-ref HEAD`,
{ signal: opts?.signal, timeoutMs: 10_000 },
);
if (br.exitCode !== 0) {
return {
worktreePath,
branch: '',
dirty: false,
unpushed: 0,
unmerged: 0,
atRisk: true,
error: `git rev-parse failed: ${br.stderr.trim() || 'not a git worktree'}`,
};
}
const branch = br.stdout.trim();
// (a) Uncommitted (dirty working tree, including untracked files).
const st = await hostExec(
`git -C ${shellEscape(worktreePath)} status --porcelain`,
{ signal: opts?.signal, timeoutMs: 15_000 },
);
if (st.exitCode !== 0) {
return {
worktreePath,
branch,
dirty: false,
unpushed: 0,
unmerged: 0,
atRisk: true,
error: `git status failed: ${st.stderr.trim()}`,
};
}
const dirty = st.stdout.trim().length > 0;
// (b) Unpushed commits. No upstream configured => work exists only locally;
// treat as unpushed-by-definition (-1) rather than an error.
const up = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape('@{u}..HEAD')}`,
{ signal: opts?.signal, timeoutMs: 15_000 },
);
const unpushed = up.exitCode === 0 ? (parseInt(up.stdout.trim() || '0', 10) || 0) : -1;
// (c) Unmerged commits — on this branch but not in the project default branch.
const defaultRef = await detectDefaultBranchRef(worktreePath, opts);
let unmerged = 0;
if (defaultRef) {
const rl = await hostExec(
`git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape(defaultRef + '..HEAD')}`,
{ signal: opts?.signal, timeoutMs: 15_000 },
);
if (rl.exitCode === 0) unmerged = parseInt(rl.stdout.trim() || '0', 10) || 0;
}
// unpushed only contributes when an upstream actually exists. Session branches
// (session-<id>) never have one (unpushed === -1), and any real local-only work
// there already surfaces as unmerged > 0 — so the no-upstream case adds no
// protection, only friction (it flagged every pristine worktree-backed session).
// The unpushed > 0 arm stays forward-compatible with P1.5 pushable branches.
const hasUpstream = unpushed !== -1;
const atRisk = dirty || unmerged > 0 || (hasUpstream && unpushed > 0);
return { worktreePath, branch, dirty, unpushed, unmerged, atRisk };
}
/**
* Stash a worktree's uncommitted changes (including untracked, via -u) so the
* working tree is clean. Stash entries live in the repo's common git dir, so
* they survive worktree-dir removal — this is the recoverable, safe-by-default
* escape. Note it only clears the *dirty* risk; unpushed/unmerged commits
* remain on the branch, so a re-attempted delete may still block on those.
*/
export async function stashWorktree(
worktreePath: string,
opts?: { signal?: AbortSignal },
): Promise<{ stashed: boolean; error?: string }> {
const r = await hostExec(
`git -C ${shellEscape(worktreePath)} stash push -u -m ${shellEscape('boocode: pre-delete stash')}`,
{ signal: opts?.signal, timeoutMs: 30_000 },
);
if (r.exitCode !== 0) {
return { stashed: false, error: r.stderr.trim() || r.stdout.trim() };
}
// "No local changes to save" => exit 0, nothing stashed — not an error.
const stashed = !/no local changes to save/i.test(r.stdout);
return { stashed };
}
// WorktreeRiskReport single-sourced in @boocode/contracts — edit the package, not here.
export type { WorktreeRiskReport };
/** Minimal shell escape for paths (single-quote wrapping). */
function shellEscape(s: string): string {

View File

@@ -5,5 +5,11 @@ export default defineConfig({
environment: 'node',
globals: false,
include: ['src/**/__tests__/**/*.test.ts'],
// DB-integration suites (checkpoints, claude-session-store, reconnect, etc.)
// each apply the full schema in beforeAll against the one shared dev DB; running
// test files in parallel makes those concurrent DDL applies deadlock under
// DATABASE_URL. Serialize file execution — the suites are fast, so the cost is
// negligible and the default (no-DATABASE_URL) run is unaffected.
fileParallelism: false,
},
});

View File

@@ -1,12 +0,0 @@
<!doctype html>
<html lang="en" class="dark">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>BooCoder</title>
</head>
<body class="bg-zinc-900 text-zinc-100">
<div id="root"></div>
<script type="module" src="/src/main.tsx"></script>
</body>
</html>

View File

@@ -1,29 +0,0 @@
{
"name": "@boocode/coder-web",
"version": "2.0.0",
"private": true,
"type": "module",
"scripts": {
"dev": "vite",
"build": "tsc -b && vite build",
"typecheck": "tsc -b --noEmit",
"preview": "vite preview"
},
"dependencies": {
"lucide-react": "^1.16.0",
"react": "^18.3.1",
"react-dom": "^18.3.1",
"react-markdown": "^10.1.0",
"react-router-dom": "^6.26.0",
"remark-gfm": "^4.0.1"
},
"devDependencies": {
"@tailwindcss/postcss": "^4.3.0",
"@types/react": "^18.3.3",
"@types/react-dom": "^18.3.0",
"@vitejs/plugin-react": "^4.3.1",
"tailwindcss": "^4.3.0",
"typescript": "^5.5.0",
"vite": "^5.3.4"
}
}

View File

@@ -1,5 +0,0 @@
export default {
plugins: {
'@tailwindcss/postcss': {},
},
};

View File

@@ -1,13 +0,0 @@
import { Routes, Route, Navigate } from 'react-router-dom';
import { Home } from './pages/Home';
import { Session } from './pages/Session';
export function App() {
return (
<Routes>
<Route path="/" element={<Home />} />
<Route path="/sessions/:sessionId" element={<Session />} />
<Route path="*" element={<Navigate to="/" replace />} />
</Routes>
);
}

View File

@@ -1,101 +0,0 @@
import type { Project, Session, Chat, Message, PendingChange, AskUserAnswer } from './types';
export class ApiError extends Error {
constructor(
public status: number,
public body: unknown,
) {
super(
typeof body === 'object' && body && 'error' in body
? String((body as { error: unknown }).error)
: `HTTP ${status}`,
);
}
}
async function request<T>(path: string, init: RequestInit = {}): Promise<T> {
const res = await fetch(path, {
...init,
headers: {
'Content-Type': 'application/json',
...(init.headers ?? {}),
},
});
if (res.status === 204) return undefined as T;
const text = await res.text();
const data = text ? JSON.parse(text) : undefined;
if (!res.ok) throw new ApiError(res.status, data);
return data as T;
}
export const api = {
health: () => request<{ ok: boolean; db: boolean; tools: number }>('/api/health'),
projects: {
list: (params?: { status?: 'open' | 'archived' }) =>
request<Project[]>(`/api/projects${params?.status ? `?status=${params.status}` : ''}`),
},
sessions: {
listForProject: (projectId: string, status?: 'open' | 'archived') =>
request<Session[]>(
`/api/projects/${projectId}/sessions${status ? `?status=${status}` : ''}`,
),
get: (id: string) => request<Session>(`/api/sessions/${id}`),
},
chats: {
listForSession: (sessionId: string) =>
request<Chat[]>(`/api/sessions/${sessionId}/chats`),
create: (sessionId: string, body?: { name?: string }) =>
request<Chat>(`/api/sessions/${sessionId}/chats`, {
method: 'POST',
body: JSON.stringify(body ?? {}),
}),
answerUserInput: (chatId: string, toolCallId: string, answers: AskUserAnswer[]) =>
request<{ tool_message_id: string; assistant_message_id: string }>(
`/api/chats/${chatId}/answer_user_input`,
{
method: 'POST',
body: JSON.stringify({ tool_call_id: toolCallId, answers }),
},
),
},
messages: {
send: (sessionId: string, chatId: string, content: string) =>
request<{ user_message_id: string; assistant_message_id: string }>(
`/api/sessions/${sessionId}/messages`,
{
method: 'POST',
body: JSON.stringify({ content, chat_id: chatId }),
},
),
stop: (sessionId: string) =>
request<{ cancelled: boolean }>(`/api/sessions/${sessionId}/stop`, {
method: 'POST',
}),
},
pending: {
list: (sessionId: string) =>
request<PendingChange[]>(`/api/sessions/${sessionId}/pending`),
applyAll: (sessionId: string) =>
request<{ results: Array<{ id: string; success: boolean; error?: string }> }>(
`/api/sessions/${sessionId}/pending/apply`,
{ method: 'POST' },
),
applyOne: (changeId: string) =>
request<{ success: boolean; error?: string }>(`/api/pending/${changeId}/apply`, {
method: 'POST',
}),
rejectOne: (changeId: string) =>
request<{ ok: boolean }>(`/api/pending/${changeId}/reject`, {
method: 'POST',
}),
rewindOne: (changeId: string) =>
request<{ success: boolean; error?: string }>(`/api/pending/${changeId}/rewind`, {
method: 'POST',
}),
},
};

View File

@@ -1,110 +0,0 @@
// Minimal types for the BooCoder frontend.
// Shared DB entities (same schema as BooChat).
export interface Project {
id: string;
name: string;
path: string;
status: 'open' | 'archived';
created_at: string;
updated_at: string;
}
export interface Session {
id: string;
project_id: string;
name: string | null;
model: string | null;
status: 'open' | 'archived';
created_at: string;
updated_at: string;
}
export interface Chat {
id: string;
session_id: string;
name: string | null;
status: 'open' | 'archived';
created_at: string;
updated_at: string;
}
export interface ToolCall {
id: string;
name: string;
args: unknown;
}
export interface ToolResult {
tool_call_id: string;
output: unknown;
truncated?: boolean;
error?: boolean;
}
// Batch 9.7: ask_user_input shapes. The tool_call.args is { questions: AskUserQuestion[] }
// (1-3 entries); the eventual tool_result.output is { answers: AskUserAnswer[] } in the
// same order. AskUserInputCard renders questions and POSTs answers.
export type AskUserQuestionType = 'single_select' | 'multi_select';
export interface AskUserQuestion {
question: string;
type: AskUserQuestionType;
options: string[];
}
export interface AskUserAnswer {
question: string;
selected_options: string[];
free_text: string | null;
}
export interface AskUserAnswerSet {
answers: AskUserAnswer[];
}
export interface Message {
id: string;
session_id: string;
chat_id: string;
role: 'user' | 'assistant' | 'tool' | 'system';
content: string;
kind: string;
tool_calls: ToolCall[] | null;
tool_results: ToolResult | null;
status: 'streaming' | 'complete' | 'failed' | 'cancelled';
tokens_used: number | null;
ctx_used: number | null;
ctx_max: number | null;
started_at: string | null;
finished_at: string | null;
created_at: string;
metadata: unknown;
}
export interface PendingChange {
id: string;
session_id: string;
task_id: string | null;
file_path: string;
operation: 'create' | 'edit' | 'delete';
old_string: string | null;
new_string: string | null;
content: string | null;
diff: string | null;
status: 'pending' | 'applied' | 'rejected' | 'reverted';
created_at: string;
applied_at: string | null;
}
// WebSocket frame types (subset of what the coder backend publishes)
export type WsFrame =
| { type: 'snapshot'; messages: Message[] }
| { type: 'message_started'; message_id: string; chat_id: string; role: Message['role'] }
| { type: 'delta'; message_id: string; chat_id: string; content: string }
| { type: 'tool_call'; message_id: string; chat_id: string; tool_call: ToolCall }
| { type: 'tool_result'; tool_message_id: string; chat_id: string; tool_call_id: string; output: string; truncated?: boolean; error?: boolean }
| { type: 'message_complete'; message_id: string; chat_id: string; tokens_used?: number; ctx_used?: number; ctx_max?: number; started_at?: string; finished_at?: string; metadata?: unknown }
| { type: 'error'; message_id?: string; error: string; reason?: string }
| { type: 'pending_change_added'; change: PendingChange }
| { type: 'pending_change_updated'; change: PendingChange };

View File

@@ -1,323 +0,0 @@
import { useMemo, useState } from 'react';
import { Check } from 'lucide-react';
import { api } from '@/api/client';
import { RadioGroup, RadioGroupItem } from '@/components/ui/radio-group';
import { Button } from '@/components/ui/button';
import type {
AskUserAnswer,
AskUserAnswerSet,
AskUserQuestion,
ToolCall,
ToolResult,
} from '@/api/types';
// Batch 9.7: Inline interactive picker. Renders inside MessageList in place of
// the standard ToolCallLine when the assistant emits an ask_user_input tool
// call. While the tool result is null (server pre-stamps a sentinel with
// output=null), shows the form; once the WS tool_result frame arrives with a
// real AnswerSet, flips to read-only review mode.
interface Props {
toolCall: ToolCall;
toolResult: ToolResult | null;
chatId: string;
}
function parseQuestions(raw: unknown): AskUserQuestion[] {
if (!raw || typeof raw !== 'object' || !('questions' in raw)) return [];
const arr = (raw as { questions: unknown }).questions;
if (!Array.isArray(arr)) return [];
const out: AskUserQuestion[] = [];
for (const item of arr) {
if (!item || typeof item !== 'object') continue;
const q = item as { question?: unknown; type?: unknown; options?: unknown };
if (typeof q.question !== 'string') continue;
if (q.type !== 'single_select' && q.type !== 'multi_select') continue;
if (!Array.isArray(q.options)) continue;
const opts = q.options.filter((o): o is string => typeof o === 'string');
if (opts.length < 2) continue;
out.push({ question: q.question, type: q.type, options: opts });
}
return out;
}
function parseAnswerSet(raw: unknown): AskUserAnswerSet | null {
if (!raw || typeof raw !== 'object' || !('answers' in raw)) return null;
const arr = (raw as { answers: unknown }).answers;
if (!Array.isArray(arr)) return null;
const answers: AskUserAnswer[] = [];
for (const item of arr) {
if (!item || typeof item !== 'object') continue;
const a = item as { question?: unknown; selected_options?: unknown; free_text?: unknown };
if (typeof a.question !== 'string') continue;
if (!Array.isArray(a.selected_options)) continue;
if (a.free_text !== null && typeof a.free_text !== 'string') continue;
const sel = a.selected_options.filter((s): s is string => typeof s === 'string');
answers.push({
question: a.question,
selected_options: sel,
free_text: (a.free_text as string | null) ?? null,
});
}
return { answers };
}
export function AskUserInputCard({ toolCall, toolResult, chatId }: Props) {
const questions = useMemo(() => parseQuestions(toolCall.args), [toolCall.args]);
if (questions.length === 0) {
return (
<div className="rounded border border-destructive/40 bg-destructive/10 text-xs px-3 py-2 text-destructive">
ask_user_input: malformed tool args
</div>
);
}
// Tool result with a non-null output means the answer is already submitted.
// The pending sentinel uses output=null, so this branch only triggers after
// the real WS tool_result frame lands.
const answered = toolResult && toolResult.output !== null;
if (answered) {
const answerSet = parseAnswerSet(toolResult!.output);
return <AnsweredView questions={questions} answers={answerSet} />;
}
return (
<PendingView questions={questions} toolCallId={toolCall.id} chatId={chatId} />
);
}
function PendingView({
questions,
toolCallId,
chatId,
}: {
questions: AskUserQuestion[];
toolCallId: string;
chatId: string;
}) {
// Per-question selections + free text. Selections are option arrays so the
// multi_select case is uniform; single_select just constrains to length 1.
const [selections, setSelections] = useState<string[][]>(() => questions.map(() => []));
const [freeTexts, setFreeTexts] = useState<string[]>(() => questions.map(() => ''));
const [submitting, setSubmitting] = useState(false);
const singleQuestion = questions.length === 1;
const anyFreeText = freeTexts.some((t) => t.trim().length > 0);
// Submit button shows when:
// - more than one question (always batched), OR
// - one question and the user has typed free text (committing it needs an
// explicit Submit so an accidental Tab/click doesn't lose it).
// For one question with no free text, clicking an option submits inline.
const showSubmitButton = !singleQuestion || anyFreeText;
// Every question must have at least one of (option, free text).
const allComplete = questions.every((_, i) => {
return selections[i]!.length > 0 || freeTexts[i]!.trim().length > 0;
});
function buildAnswers(): AskUserAnswer[] {
return questions.map((q, i) => {
const freeText = freeTexts[i]!.trim();
return {
question: q.question,
selected_options: selections[i]!,
free_text: freeText.length > 0 ? freeText : null,
};
});
}
async function submit(answers: AskUserAnswer[]) {
if (submitting) return;
setSubmitting(true);
try {
await api.chats.answerUserInput(chatId, toolCallId, answers);
// Card stays mounted; the incoming WS tool_result frame will flip it
// into AnsweredView via the parent prop change.
} catch (err) {
console.error('ask_user_input submit failed:', err instanceof Error ? err.message : err);
setSubmitting(false);
}
}
function pickSingle(qIdx: number, option: string) {
setSelections((prev) => prev.map((arr, i) => (i === qIdx ? [option] : arr)));
// Immediate submit for the single-question single-select shortcut. Only
// fires when no free text exists anywhere — once the user typed, the
// Submit button takes over so the typed text isn't silently dropped.
if (singleQuestion && !anyFreeText) {
const answers: AskUserAnswer[] = [
{
question: questions[0]!.question,
selected_options: [option],
free_text: null,
},
];
void submit(answers);
}
}
function toggleMulti(qIdx: number, option: string) {
setSelections((prev) =>
prev.map((arr, i) => {
if (i !== qIdx) return arr;
return arr.includes(option) ? arr.filter((o) => o !== option) : [...arr, option];
}),
);
}
function setFreeText(qIdx: number, value: string) {
setFreeTexts((prev) => prev.map((t, i) => (i === qIdx ? value : t)));
}
return (
<div className="rounded-lg border bg-muted/20 text-sm">
<div className="px-4 py-3 space-y-4">
{questions.map((q, i) => (
<div key={i} className="space-y-2">
{questions.length > 1 && (
<div className="text-[10px] uppercase tracking-wide text-muted-foreground/70">
Question {i + 1}
</div>
)}
<div className="font-medium leading-snug">{q.question}</div>
{q.type === 'single_select' ? (
<RadioGroup
value={selections[i]![0] ?? ''}
onValueChange={(v) => pickSingle(i, v)}
disabled={submitting}
className="gap-1.5"
>
{q.options.map((opt, j) => {
const id = `q${i}-opt${j}`;
return (
<label
key={j}
htmlFor={id}
className="flex items-start gap-2 text-sm leading-snug cursor-pointer rounded px-1 py-0.5 hover:bg-muted/40"
>
<RadioGroupItem id={id} value={opt} className="mt-0.5" />
<span>{opt}</span>
</label>
);
})}
</RadioGroup>
) : (
<div className="grid gap-1.5">
{q.options.map((opt, j) => {
const id = `q${i}-opt${j}`;
const checked = selections[i]!.includes(opt);
return (
<label
key={j}
htmlFor={id}
className="flex items-start gap-2 text-sm leading-snug cursor-pointer rounded px-1 py-0.5 hover:bg-muted/40"
>
<input
id={id}
type="checkbox"
checked={checked}
disabled={submitting}
onChange={() => toggleMulti(i, opt)}
className="mt-1 size-3.5 rounded border-input accent-primary"
/>
<span>{opt}</span>
</label>
);
})}
</div>
)}
<div className="pt-1 space-y-1">
<div className="text-[10px] uppercase tracking-wide text-muted-foreground/70">
Or type a custom answer
</div>
<input
type="text"
value={freeTexts[i]}
disabled={submitting}
placeholder="Free text…"
onChange={(e) => setFreeText(i, e.target.value)}
className="w-full rounded border border-input bg-background px-2 py-1 text-sm outline-none focus-visible:ring-2 focus-visible:ring-ring/40 disabled:opacity-60"
/>
</div>
</div>
))}
</div>
{showSubmitButton && (
<div className="flex justify-end gap-2 border-t px-4 py-2">
<Button
type="button"
size="sm"
disabled={!allComplete || submitting}
onClick={() => void submit(buildAnswers())}
>
{submitting ? 'Submitting…' : 'Submit'}
</Button>
</div>
)}
</div>
);
}
function AnsweredView({
questions,
answers,
}: {
questions: AskUserQuestion[];
answers: AskUserAnswerSet | null;
}) {
if (!answers) {
return (
<div className="rounded-lg border bg-muted/20 text-xs px-4 py-3 text-muted-foreground">
ask_user_input: answers unavailable
</div>
);
}
return (
<div className="rounded-lg border bg-muted/10 text-sm">
<div className="px-4 py-3 space-y-3">
{questions.map((q, i) => {
const a = answers.answers[i];
if (!a) return null;
return (
<div key={i} className="space-y-1.5">
{questions.length > 1 && (
<div className="text-[10px] uppercase tracking-wide text-muted-foreground/70">
Question {i + 1}
</div>
)}
<div className="font-medium leading-snug">{q.question}</div>
<div className="space-y-0.5">
{q.options.map((opt, j) => {
const selected = a.selected_options.includes(opt);
return (
<div
key={j}
className={
selected
? 'flex items-start gap-2 text-sm leading-snug text-foreground'
: 'flex items-start gap-2 text-sm leading-snug text-muted-foreground/60 line-through'
}
>
<span className="mt-0.5 size-3.5 shrink-0 inline-flex items-center justify-center">
{selected && <Check className="size-3 text-primary" />}
</span>
<span>{opt}</span>
</div>
);
})}
</div>
{a.free_text && (
<div className="rounded bg-background border px-2 py-1 text-xs font-mono whitespace-pre-wrap">
{a.free_text}
</div>
)}
</div>
);
})}
</div>
</div>
);
}

View File

@@ -1,139 +0,0 @@
import { useState, useRef, useEffect } from 'react';
import { Send, Square } from 'lucide-react';
import type { Message, ToolResult } from '@/api/types';
import { api } from '@/api/client';
import { MessageBubble } from './MessageBubble';
interface Props {
sessionId: string;
chatId: string;
messages: Message[];
isStreaming: boolean;
connected: boolean;
}
export function ChatPane({ sessionId, chatId, messages, isStreaming, connected }: Props) {
const [input, setInput] = useState('');
const [sending, setSending] = useState(false);
const messagesEndRef = useRef<HTMLDivElement>(null);
const textareaRef = useRef<HTMLTextAreaElement>(null);
// Auto-scroll to bottom when messages change
useEffect(() => {
messagesEndRef.current?.scrollIntoView({ behavior: 'smooth' });
}, [messages]);
// Auto-resize textarea
useEffect(() => {
const el = textareaRef.current;
if (!el) return;
el.style.height = 'auto';
el.style.height = Math.min(el.scrollHeight, 200) + 'px';
}, [input]);
const handleSend = async () => {
const content = input.trim();
if (!content || sending || isStreaming) return;
setInput('');
setSending(true);
try {
await api.messages.send(sessionId, chatId, content);
} catch (err) {
console.error('send failed:', err);
// Restore input on failure
setInput(content);
} finally {
setSending(false);
}
};
const handleStop = async () => {
try {
await api.messages.stop(sessionId);
} catch (err) {
console.error('stop failed:', err);
}
};
const handleKeyDown = (e: React.KeyboardEvent) => {
if (e.key === 'Enter' && !e.shiftKey) {
e.preventDefault();
handleSend();
}
};
// Filter out system messages for display (sentinels)
const visibleMessages = messages.filter((m) => m.role !== 'system');
// Build a lookup map from tool_call_id -> ToolResult for all messages
const toolResultsMap: Record<string, ToolResult> = {};
for (const msg of messages) {
if (msg.tool_results) {
toolResultsMap[msg.tool_results.tool_call_id] = msg.tool_results;
}
}
return (
<div className="flex flex-col h-full">
{/* Connection indicator */}
<div className="flex items-center gap-2 px-4 py-2 border-b border-zinc-800 text-xs text-zinc-500">
<div
className={`w-1.5 h-1.5 rounded-full ${connected ? 'bg-green-500' : 'bg-red-500'}`}
/>
<span>{connected ? 'Connected' : 'Disconnected'}</span>
{isStreaming && (
<span className="text-blue-400 ml-auto">Generating...</span>
)}
</div>
{/* Messages list */}
<div className="flex-1 overflow-y-auto px-4 py-4">
{visibleMessages.length === 0 && (
<div className="text-center text-zinc-500 mt-8">
<p className="text-lg font-medium">BooCoder</p>
<p className="text-sm mt-1">Send a message to start coding.</p>
</div>
)}
{visibleMessages.map((msg) => (
<MessageBubble key={msg.id} message={msg} chatId={msg.chat_id} toolResultsMap={toolResultsMap} />
))}
<div ref={messagesEndRef} />
</div>
{/* Input area */}
<div className="border-t border-zinc-800 px-4 py-3">
<div className="flex items-end gap-2">
<textarea
ref={textareaRef}
value={input}
onChange={(e) => setInput(e.target.value)}
onKeyDown={handleKeyDown}
placeholder="Message BooCoder..."
rows={1}
className="flex-1 bg-zinc-800 border border-zinc-700 rounded-lg px-3 py-2 text-sm text-zinc-100 placeholder-zinc-500 resize-none focus:outline-none focus:ring-1 focus:ring-blue-500 focus:border-blue-500"
disabled={sending}
/>
{isStreaming ? (
<button
onClick={handleStop}
className="p-2 rounded-lg bg-red-600 hover:bg-red-500 text-white transition-colors"
title="Stop generation"
>
<Square size={18} />
</button>
) : (
<button
onClick={handleSend}
disabled={!input.trim() || sending}
className="p-2 rounded-lg bg-blue-600 hover:bg-blue-500 disabled:opacity-40 disabled:cursor-not-allowed text-white transition-colors"
title="Send message"
>
<Send size={18} />
</button>
)}
</div>
</div>
</div>
);
}

View File

@@ -1,352 +0,0 @@
import { useState, useEffect, useCallback } from 'react';
import { Check, X, RotateCcw, FileText, FilePlus, Trash2, RefreshCw } from 'lucide-react';
import type { PendingChange } from '@/api/types';
import { api } from '@/api/client';
interface Props {
sessionId: string;
onPendingChange: (cb: (change: PendingChange) => void) => () => void;
}
export function DiffPane({ sessionId, onPendingChange }: Props) {
const [changes, setChanges] = useState<PendingChange[]>([]);
const [loading, setLoading] = useState(true);
const [expandedId, setExpandedId] = useState<string | null>(null);
const fetchPending = useCallback(async () => {
try {
const result = await api.pending.list(sessionId);
setChanges(result);
} catch (err) {
console.error('fetch pending failed:', err);
} finally {
setLoading(false);
}
}, [sessionId]);
// Initial load
useEffect(() => {
fetchPending();
}, [fetchPending]);
// Listen for WS pending change events
useEffect(() => {
const unsub = onPendingChange((change) => {
setChanges((prev) => {
const idx = prev.findIndex((c) => c.id === change.id);
if (idx >= 0) {
const next = [...prev];
next[idx] = change;
return next;
}
return [...prev, change];
});
});
return unsub;
}, [onPendingChange]);
const pendingChanges = changes.filter((c) => c.status === 'pending');
const resolvedChanges = changes.filter((c) => c.status !== 'pending');
const handleApplyOne = async (id: string) => {
try {
await api.pending.applyOne(id);
setChanges((prev) =>
prev.map((c) => (c.id === id ? { ...c, status: 'applied' as const } : c)),
);
} catch (err) {
console.error('apply failed:', err);
}
};
const handleRejectOne = async (id: string) => {
try {
await api.pending.rejectOne(id);
setChanges((prev) =>
prev.map((c) => (c.id === id ? { ...c, status: 'rejected' as const } : c)),
);
} catch (err) {
console.error('reject failed:', err);
}
};
const handleRewindOne = async (id: string) => {
try {
await api.pending.rewindOne(id);
setChanges((prev) =>
prev.map((c) => (c.id === id ? { ...c, status: 'reverted' as const } : c)),
);
} catch (err) {
console.error('rewind failed:', err);
}
};
const handleApplyAll = async () => {
try {
const result = await api.pending.applyAll(sessionId);
const appliedIds = new Set(
result.results.filter((r) => r.success).map((r) => r.id),
);
setChanges((prev) =>
prev.map((c) =>
appliedIds.has(c.id) ? { ...c, status: 'applied' as const } : c,
),
);
} catch (err) {
console.error('apply all failed:', err);
}
};
const handleRejectAll = async () => {
// Reject each pending change individually (no batch reject endpoint)
for (const c of pendingChanges) {
await handleRejectOne(c.id);
}
};
const OpIcon = ({ op }: { op: PendingChange['operation'] }) => {
switch (op) {
case 'create':
return <FilePlus size={14} className="text-green-400" />;
case 'edit':
return <FileText size={14} className="text-blue-400" />;
case 'delete':
return <Trash2 size={14} className="text-red-400" />;
}
};
const StatusBadge = ({ status }: { status: PendingChange['status'] }) => {
const colors: Record<PendingChange['status'], string> = {
pending: 'bg-yellow-500/20 text-yellow-400',
applied: 'bg-green-500/20 text-green-400',
rejected: 'bg-zinc-500/20 text-zinc-400',
reverted: 'bg-orange-500/20 text-orange-400',
};
return (
<span className={`text-[10px] px-1.5 py-0.5 rounded ${colors[status]}`}>
{status}
</span>
);
};
return (
<div className="flex flex-col h-full">
{/* Header */}
<div className="flex items-center justify-between px-4 py-2 border-b border-zinc-800">
<h2 className="text-sm font-medium text-zinc-300">
Pending Changes
{pendingChanges.length > 0 && (
<span className="ml-1.5 text-xs text-zinc-500">
({pendingChanges.length})
</span>
)}
</h2>
<div className="flex items-center gap-1">
<button
onClick={fetchPending}
className="p-1 rounded hover:bg-zinc-800 text-zinc-400 hover:text-zinc-200"
title="Refresh"
>
<RefreshCw size={14} />
</button>
{pendingChanges.length > 0 && (
<>
<button
onClick={handleApplyAll}
className="text-xs px-2 py-1 rounded bg-green-600/80 hover:bg-green-600 text-white"
>
Apply All
</button>
<button
onClick={handleRejectAll}
className="text-xs px-2 py-1 rounded bg-zinc-700 hover:bg-zinc-600 text-zinc-300"
>
Reject All
</button>
</>
)}
</div>
</div>
{/* Changes list */}
<div className="flex-1 overflow-y-auto">
{loading && (
<div className="text-center text-zinc-500 text-sm py-8">Loading...</div>
)}
{!loading && changes.length === 0 && (
<div className="text-center text-zinc-500 text-sm py-8">
No pending changes yet.
</div>
)}
{/* Pending changes first */}
{pendingChanges.map((change) => (
<ChangeItem
key={change.id}
change={change}
expanded={expandedId === change.id}
onToggle={() =>
setExpandedId((prev) => (prev === change.id ? null : change.id))
}
onApply={() => handleApplyOne(change.id)}
onReject={() => handleRejectOne(change.id)}
OpIcon={OpIcon}
StatusBadge={StatusBadge}
/>
))}
{/* Resolved changes */}
{resolvedChanges.length > 0 && pendingChanges.length > 0 && (
<div className="border-t border-zinc-800 my-1" />
)}
{resolvedChanges.map((change) => (
<ChangeItem
key={change.id}
change={change}
expanded={expandedId === change.id}
onToggle={() =>
setExpandedId((prev) => (prev === change.id ? null : change.id))
}
onRewind={
change.status === 'applied'
? () => handleRewindOne(change.id)
: undefined
}
OpIcon={OpIcon}
StatusBadge={StatusBadge}
/>
))}
</div>
</div>
);
}
interface ChangeItemProps {
change: PendingChange;
expanded: boolean;
onToggle: () => void;
onApply?: () => void;
onReject?: () => void;
onRewind?: () => void;
OpIcon: React.ComponentType<{ op: PendingChange['operation'] }>;
StatusBadge: React.ComponentType<{ status: PendingChange['status'] }>;
}
function ChangeItem({
change,
expanded,
onToggle,
onApply,
onReject,
onRewind,
OpIcon,
StatusBadge,
}: ChangeItemProps) {
const fileName = change.file_path.split('/').pop() || change.file_path;
const dirPath = change.file_path.split('/').slice(0, -1).join('/');
return (
<div className="border-b border-zinc-800/50">
<div
className="flex items-center gap-2 px-4 py-2 hover:bg-zinc-800/50 cursor-pointer"
onClick={onToggle}
>
<OpIcon op={change.operation} />
<div className="flex-1 min-w-0">
<span className="text-sm font-mono text-zinc-200 truncate block">
{fileName}
</span>
{dirPath && (
<span className="text-[11px] text-zinc-500 truncate block">
{dirPath}
</span>
)}
</div>
<StatusBadge status={change.status} />
{change.status === 'pending' && (
<div className="flex items-center gap-1 ml-1">
<button
onClick={(e) => {
e.stopPropagation();
onApply?.();
}}
className="p-1 rounded hover:bg-green-600/30 text-green-400"
title="Apply"
>
<Check size={14} />
</button>
<button
onClick={(e) => {
e.stopPropagation();
onReject?.();
}}
className="p-1 rounded hover:bg-red-600/30 text-red-400"
title="Reject"
>
<X size={14} />
</button>
</div>
)}
{change.status === 'applied' && onRewind && (
<button
onClick={(e) => {
e.stopPropagation();
onRewind();
}}
className="p-1 rounded hover:bg-orange-600/30 text-orange-400"
title="Rewind"
>
<RotateCcw size={14} />
</button>
)}
</div>
{expanded && (
<div className="px-4 pb-3">
{change.operation === 'edit' && (
<div className="space-y-2">
{change.old_string && (
<div className="rounded bg-red-950/30 border border-red-900/30 p-2">
<div className="text-[10px] text-red-400 mb-1 font-medium">
Remove
</div>
<pre className="text-xs text-red-200 whitespace-pre-wrap break-all font-mono">
{change.old_string}
</pre>
</div>
)}
{change.new_string && (
<div className="rounded bg-green-950/30 border border-green-900/30 p-2">
<div className="text-[10px] text-green-400 mb-1 font-medium">
Add
</div>
<pre className="text-xs text-green-200 whitespace-pre-wrap break-all font-mono">
{change.new_string}
</pre>
</div>
)}
</div>
)}
{change.operation === 'create' && change.content && (
<div className="rounded bg-green-950/30 border border-green-900/30 p-2">
<div className="text-[10px] text-green-400 mb-1 font-medium">
New file
</div>
<pre className="text-xs text-green-200 whitespace-pre-wrap break-all font-mono max-h-60 overflow-y-auto">
{change.content.length > 2000
? change.content.slice(0, 2000) + '\n... (truncated)'
: change.content}
</pre>
</div>
)}
{change.operation === 'delete' && (
<div className="rounded bg-red-950/30 border border-red-900/30 p-2 text-xs text-red-300">
This file will be deleted.
</div>
)}
</div>
)}
</div>
);
}

View File

@@ -1,62 +0,0 @@
import { useState } from 'react';
import { Code2, MessageSquare, GitPullRequest } from 'lucide-react';
interface Props {
chatPane: React.ReactNode;
diffPane: React.ReactNode;
}
export function Layout({ chatPane, diffPane }: Props) {
const [activeTab, setActiveTab] = useState<'chat' | 'diff'>('chat');
return (
<div className="flex flex-col h-screen bg-zinc-900">
{/* Top bar */}
<header className="flex items-center gap-3 px-4 py-2 border-b border-zinc-800 bg-zinc-900/95">
<Code2 size={20} className="text-blue-400" />
<h1 className="text-sm font-semibold text-zinc-200">BooCoder</h1>
</header>
{/* Mobile tab bar (visible below lg breakpoint) */}
<div className="lg:hidden flex border-b border-zinc-800">
<button
onClick={() => setActiveTab('chat')}
className={`flex-1 flex items-center justify-center gap-1.5 py-2 text-sm ${
activeTab === 'chat'
? 'text-blue-400 border-b-2 border-blue-400'
: 'text-zinc-500'
}`}
>
<MessageSquare size={14} />
Chat
</button>
<button
onClick={() => setActiveTab('diff')}
className={`flex-1 flex items-center justify-center gap-1.5 py-2 text-sm ${
activeTab === 'diff'
? 'text-blue-400 border-b-2 border-blue-400'
: 'text-zinc-500'
}`}
>
<GitPullRequest size={14} />
Changes
</button>
</div>
{/* Desktop split layout */}
<div className="flex-1 hidden lg:flex overflow-hidden">
<div className="w-[60%] border-r border-zinc-800 overflow-hidden">
{chatPane}
</div>
<div className="w-[40%] overflow-hidden">
{diffPane}
</div>
</div>
{/* Mobile: show only the active tab */}
<div className="flex-1 lg:hidden overflow-hidden">
{activeTab === 'chat' ? chatPane : diffPane}
</div>
</div>
);
}

View File

@@ -1,135 +0,0 @@
import Markdown from 'react-markdown';
import remarkGfm from 'remark-gfm';
import type { Message, ToolResult } from '@/api/types';
import { Wrench, AlertCircle, Loader2 } from 'lucide-react';
import { AskUserInputCard } from './AskUserInputCard';
interface Props {
message: Message;
chatId: string;
toolResultsMap: Record<string, ToolResult>;
}
export function MessageBubble({ message, chatId }: Props) {
if (message.role === 'tool') {
return <ToolResultBubble message={message} />;
}
const isUser = message.role === 'user';
const isStreaming = message.status === 'streaming';
const isFailed = message.status === 'failed';
return (
<div className={`flex ${isUser ? 'justify-end' : 'justify-start'} mb-3`}>
<div
className={`max-w-[85%] rounded-lg px-4 py-2.5 ${
isUser
? 'bg-blue-600 text-white'
: 'bg-zinc-800 text-zinc-100 border border-zinc-700'
}`}
>
{isFailed && (
<div className="flex items-center gap-1.5 text-red-400 text-xs mb-1">
<AlertCircle size={12} />
<span>Failed</span>
</div>
)}
{message.tool_calls && message.tool_calls.length > 0 && (
<div className="mb-2 space-y-1">
{message.tool_calls.map((tc) => {
if (tc.name === 'ask_user_input') {
const result = message.tool_results ?? null;
return (
<AskUserInputCard
key={tc.id}
toolCall={tc}
toolResult={result}
chatId={chatId}
/>
);
}
return (
<div
key={tc.id}
className="flex items-center gap-1.5 text-xs text-zinc-400 bg-zinc-900/50 rounded px-2 py-1"
>
<Wrench size={11} />
<span className="font-mono">{tc.name}</span>
<span className="text-zinc-500 truncate max-w-[200px]">
{truncateArgs(tc.args)}
</span>
</div>
);
})}
</div>
)}
{message.content.trim() && (
<div className="prose prose-invert prose-sm max-w-none [&_pre]:bg-zinc-900 [&_pre]:p-3 [&_pre]:rounded [&_pre]:overflow-x-auto [&_code]:text-zinc-300 [&_p]:my-1.5">
<Markdown remarkPlugins={[remarkGfm]}>{message.content}</Markdown>
</div>
)}
{isStreaming && !message.content.trim() && (
<div className="flex items-center gap-1.5 text-zinc-400">
<Loader2 size={14} className="animate-spin" />
<span className="text-xs">Thinking...</span>
</div>
)}
{isStreaming && message.content.trim() && (
<span className="inline-block w-1.5 h-4 bg-zinc-400 animate-pulse ml-0.5 align-middle" />
)}
</div>
</div>
);
}
function ToolResultBubble({ message }: { message: Message }) {
const result = message.tool_results;
if (!result) return null;
const isError = result.error;
const output = result.output != null ? String(result.output) : '';
const displayOutput =
output.length > 300 ? output.slice(0, 300) + '...' : output;
return (
<div className="flex justify-start mb-2 ml-6">
<div
className={`max-w-[80%] rounded px-3 py-2 text-xs font-mono border ${
isError
? 'bg-red-950/30 border-red-800/50 text-red-300'
: 'bg-zinc-800/50 border-zinc-700/50 text-zinc-400'
}`}
>
{result.truncated && (
<span className="text-yellow-500 text-[10px] block mb-1">
[truncated]
</span>
)}
<pre className="whitespace-pre-wrap break-all">{displayOutput}</pre>
</div>
</div>
);
}
function truncateArgs(args: unknown): string {
if (!args) return '';
try {
if (typeof args === 'object' && args !== null) {
const obj = args as Record<string, unknown>;
const keys = Object.keys(obj);
if (keys.length === 0) return '';
const first = keys[0]!;
const val = String(obj[first] ?? '');
const display = val.length > 40 ? val.slice(0, 40) + '...' : val;
return `${first}: ${display}`;
}
const str = String(args);
return str.length > 50 ? str.slice(0, 50) + '...' : str;
} catch {
return String(args).length > 50 ? String(args).slice(0, 50) + '...' : String(args);
}
}

View File

@@ -1,35 +0,0 @@
import * as React from 'react';
export interface ButtonProps
extends React.ButtonHTMLAttributes<HTMLButtonElement> {
variant?: 'default' | 'destructive' | 'outline' | 'secondary' | 'ghost' | 'link';
size?: 'default' | 'sm' | 'lg' | 'icon';
}
const variantClasses: Record<string, string> = {
default: 'bg-primary text-primary-foreground hover:bg-primary/90',
destructive: 'bg-destructive text-destructive-foreground hover:bg-destructive/90',
outline: 'border border-input bg-background hover:bg-accent hover:text-accent-foreground',
secondary: 'bg-secondary text-secondary-foreground hover:bg-secondary/80',
ghost: 'hover:bg-accent hover:text-accent-foreground',
link: 'text-primary underline-offset-4 hover:underline',
};
const sizeClasses: Record<string, string> = {
default: 'h-9 px-4 py-2',
sm: 'h-8 rounded-md px-3 text-xs',
lg: 'h-10 rounded-md px-8',
icon: 'h-9 w-9',
};
const Button = React.forwardRef<HTMLButtonElement, ButtonProps>(
({ className, variant = 'default', size = 'default', ...props }, ref) => {
const base =
'inline-flex items-center justify-center whitespace-nowrap rounded-md text-sm font-medium transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring/40 disabled:pointer-events-none disabled:opacity-60';
const cls = [base, variantClasses[variant] ?? '', sizeClasses[size] ?? '', className ?? ''].join(' ');
return <button className={cls} ref={ref} {...props} />;
},
);
Button.displayName = 'Button';
export { Button };

View File

@@ -1,56 +0,0 @@
import * as React from 'react';
const RadioGroupContext = React.createContext<{
value: string | undefined;
onValueChange: (v: string) => void;
disabled?: boolean;
} | null>(null);
interface RadioGroupProps extends React.HTMLAttributes<HTMLDivElement> {
value?: string;
onValueChange?: (value: string) => void;
disabled?: boolean;
}
const RadioGroup = React.forwardRef<HTMLDivElement, RadioGroupProps>(
({ className, value, onValueChange, disabled, ...props }, ref) => {
const ctx = React.useMemo(() => ({ value, onValueChange: onValueChange ?? (() => {}), disabled }), [value, onValueChange, disabled]);
return (
<RadioGroupContext.Provider value={ctx}>
<div
ref={ref}
role="radiogroup"
className={className}
{...props}
/>
</RadioGroupContext.Provider>
);
},
);
RadioGroup.displayName = 'RadioGroup';
interface RadioGroupItemProps extends React.InputHTMLAttributes<HTMLInputElement> {
value: string;
}
const RadioGroupItem = React.forwardRef<HTMLInputElement, RadioGroupItemProps>(
({ className, value, ...props }, ref) => {
const ctx = React.useContext(RadioGroupContext);
if (!ctx) return <input ref={ref} type="radio" className={className} value={value} {...props} />;
const checked = ctx.value === value;
return (
<input
ref={ref}
type="radio"
checked={checked}
disabled={ctx.disabled}
onChange={() => ctx.onValueChange(value)}
className={className}
{...props}
/>
);
},
);
RadioGroupItem.displayName = 'RadioGroupItem';
export { RadioGroup, RadioGroupItem };

View File

@@ -1,22 +0,0 @@
@import "tailwindcss";
body {
margin: 0;
min-height: 100vh;
}
/* Scrollbar styling for dark theme */
::-webkit-scrollbar {
width: 8px;
height: 8px;
}
::-webkit-scrollbar-track {
background: transparent;
}
::-webkit-scrollbar-thumb {
background: #3f3f46;
border-radius: 4px;
}
::-webkit-scrollbar-thumb:hover {
background: #52525b;
}

View File

@@ -1,230 +0,0 @@
import { useEffect, useRef, useState, useCallback } from 'react';
import type { Message, WsFrame, PendingChange } from '@/api/types';
interface State {
messages: Message[];
connected: boolean;
error: string | null;
}
function applyFrame(state: State, frame: WsFrame): State {
switch (frame.type) {
case 'snapshot': {
return { ...state, messages: frame.messages };
}
case 'message_started': {
const exists = state.messages.some((m) => m.id === frame.message_id);
if (exists) return state;
const newMsg: Message = {
id: frame.message_id,
session_id: '',
chat_id: frame.chat_id,
role: frame.role,
content: '',
kind: 'message',
tool_calls: null,
tool_results: null,
status: frame.role === 'system' ? 'complete' : 'streaming',
tokens_used: null,
ctx_used: null,
ctx_max: null,
started_at: null,
finished_at: null,
created_at: new Date().toISOString(),
metadata: null,
};
return { ...state, messages: [...state.messages, newMsg] };
}
case 'delta': {
const next = state.messages.map((m) =>
m.id === frame.message_id ? { ...m, content: m.content + frame.content } : m,
);
return { ...state, messages: next };
}
case 'tool_call': {
const next = state.messages.map((m) =>
m.id === frame.message_id
? { ...m, tool_calls: [...(m.tool_calls ?? []), frame.tool_call] }
: m,
);
return { ...state, messages: next };
}
case 'tool_result': {
const exists = state.messages.some((m) => m.id === frame.tool_message_id);
if (exists) {
const next = state.messages.map((m) =>
m.id === frame.tool_message_id
? {
...m,
role: 'tool' as const,
tool_results: {
tool_call_id: frame.tool_call_id,
output: frame.output,
truncated: frame.truncated,
...(frame.error ? { error: frame.error } : {}),
},
status: 'complete' as const,
}
: m,
);
return { ...state, messages: next };
}
const newMsg: Message = {
id: frame.tool_message_id,
session_id: '',
chat_id: frame.chat_id,
role: 'tool',
content: '',
kind: 'message',
tool_calls: null,
tool_results: {
tool_call_id: frame.tool_call_id,
output: frame.output,
truncated: frame.truncated,
...(frame.error ? { error: frame.error } : {}),
},
status: 'complete',
tokens_used: null,
ctx_used: null,
ctx_max: null,
started_at: null,
finished_at: null,
created_at: new Date().toISOString(),
metadata: null,
};
return { ...state, messages: [...state.messages, newMsg] };
}
case 'message_complete': {
const next = state.messages.map((m) =>
m.id === frame.message_id
? {
...m,
status: 'complete' as const,
...(frame.tokens_used !== undefined ? { tokens_used: frame.tokens_used } : {}),
...(frame.ctx_used !== undefined ? { ctx_used: frame.ctx_used } : {}),
...(frame.ctx_max !== undefined ? { ctx_max: frame.ctx_max } : {}),
...(frame.started_at !== undefined ? { started_at: frame.started_at } : {}),
...(frame.finished_at !== undefined ? { finished_at: frame.finished_at } : {}),
...(frame.metadata !== undefined ? { metadata: frame.metadata } : {}),
}
: m,
);
return { ...state, messages: next };
}
case 'error': {
const next = frame.message_id
? state.messages.map((m) =>
m.id === frame.message_id ? { ...m, status: 'failed' as const } : m,
)
: state.messages;
return { ...state, messages: next, error: frame.error };
}
case 'pending_change_added':
case 'pending_change_updated':
// These are handled by the pending changes listener, not the message state
return state;
}
}
const RECONNECT_INITIAL_MS = 1000;
const RECONNECT_MAX_MS = 30_000;
interface SessionStreamResult {
messages: Message[];
connected: boolean;
error: string | null;
isStreaming: boolean;
/** Listeners for pending change frames */
onPendingChange: (cb: (change: PendingChange) => void) => () => void;
}
export function useSessionStream(sessionId: string | undefined): SessionStreamResult {
const [state, setState] = useState<State>({ messages: [], connected: false, error: null });
const wsRef = useRef<WebSocket | null>(null);
const pendingListenersRef = useRef<Set<(change: PendingChange) => void>>(new Set());
useEffect(() => {
if (!sessionId) return;
setState({ messages: [], connected: false, error: null });
let unmounted = false;
let reconnectTimer: ReturnType<typeof setTimeout> | null = null;
let reconnectDelay = RECONNECT_INITIAL_MS;
const connect = () => {
if (unmounted) return;
const proto = window.location.protocol === 'https:' ? 'wss' : 'ws';
const url = `${proto}://${window.location.host}/api/ws/sessions/${sessionId}`;
const ws = new WebSocket(url);
wsRef.current = ws;
ws.onopen = () => {
reconnectDelay = RECONNECT_INITIAL_MS;
setState((s) => ({ ...s, connected: true, error: null }));
};
ws.onmessage = (ev) => {
let frame: WsFrame;
try {
frame = JSON.parse(typeof ev.data === 'string' ? ev.data : '') as WsFrame;
} catch {
return;
}
// Notify pending change listeners
if (frame.type === 'pending_change_added' || frame.type === 'pending_change_updated') {
for (const cb of pendingListenersRef.current) {
cb(frame.change);
}
}
setState((s) => applyFrame(s, frame));
};
ws.onerror = () => {
try {
ws.close();
} catch {}
};
ws.onclose = () => {
if (unmounted) return;
setState((s) => ({ ...s, connected: false }));
const delay = reconnectDelay;
reconnectDelay = Math.min(reconnectDelay * 2, RECONNECT_MAX_MS);
reconnectTimer = setTimeout(connect, delay);
};
};
connect();
return () => {
unmounted = true;
if (reconnectTimer) clearTimeout(reconnectTimer);
const ws = wsRef.current;
wsRef.current = null;
if (ws)
try {
ws.close();
} catch {}
};
}, [sessionId]);
const isStreaming = state.messages.some((m) => m.status === 'streaming');
const onPendingChange = useCallback((cb: (change: PendingChange) => void) => {
pendingListenersRef.current.add(cb);
return () => {
pendingListenersRef.current.delete(cb);
};
}, []);
return {
messages: state.messages,
connected: state.connected,
error: state.error,
isStreaming,
onPendingChange,
};
}

View File

@@ -1,13 +0,0 @@
import { StrictMode } from 'react';
import { createRoot } from 'react-dom/client';
import { BrowserRouter } from 'react-router-dom';
import { App } from './App';
import './globals.css';
createRoot(document.getElementById('root')!).render(
<StrictMode>
<BrowserRouter>
<App />
</BrowserRouter>
</StrictMode>,
);

View File

@@ -1,138 +0,0 @@
import { useEffect, useState } from 'react';
import { useNavigate } from 'react-router-dom';
import { Code2, Folder, ArrowRight } from 'lucide-react';
import type { Project, Session } from '@/api/types';
import { api } from '@/api/client';
export function Home() {
const navigate = useNavigate();
const [projects, setProjects] = useState<Project[]>([]);
const [sessions, setSessions] = useState<Session[]>([]);
const [selectedProject, setSelectedProject] = useState<string | null>(null);
const [loading, setLoading] = useState(true);
// Fetch projects on mount
useEffect(() => {
api.projects
.list({ status: 'open' })
.then(setProjects)
.catch(console.error)
.finally(() => setLoading(false));
}, []);
// Fetch sessions when a project is selected
useEffect(() => {
if (!selectedProject) {
setSessions([]);
return;
}
api.sessions
.listForProject(selectedProject, 'open')
.then(setSessions)
.catch(console.error);
}, [selectedProject]);
const handleSessionClick = (session: Session) => {
navigate(`/sessions/${session.id}`);
};
if (loading) {
return (
<div className="min-h-screen bg-zinc-900 flex items-center justify-center">
<div className="text-zinc-500">Loading...</div>
</div>
);
}
return (
<div className="min-h-screen bg-zinc-900 p-6">
<div className="max-w-2xl mx-auto">
{/* Header */}
<div className="flex items-center gap-3 mb-8">
<Code2 size={28} className="text-blue-400" />
<h1 className="text-2xl font-bold text-zinc-100">BooCoder</h1>
</div>
{/* Projects list */}
<div className="mb-8">
<h2 className="text-sm font-medium text-zinc-400 uppercase tracking-wide mb-3">
Projects
</h2>
{projects.length === 0 ? (
<p className="text-zinc-500 text-sm">
No projects found. Create one in BooChat first.
</p>
) : (
<div className="space-y-1">
{projects.map((project) => (
<button
key={project.id}
onClick={() => setSelectedProject(project.id)}
className={`w-full flex items-center gap-3 px-4 py-3 rounded-lg text-left transition-colors ${
selectedProject === project.id
? 'bg-blue-600/20 border border-blue-500/40'
: 'bg-zinc-800/50 border border-zinc-800 hover:bg-zinc-800'
}`}
>
<Folder
size={16}
className={
selectedProject === project.id
? 'text-blue-400'
: 'text-zinc-500'
}
/>
<div className="flex-1 min-w-0">
<div className="text-sm font-medium text-zinc-200 truncate">
{project.name}
</div>
<div className="text-xs text-zinc-500 truncate">
{project.path}
</div>
</div>
</button>
))}
</div>
)}
</div>
{/* Sessions list */}
{selectedProject && (
<div>
<h2 className="text-sm font-medium text-zinc-400 uppercase tracking-wide mb-3">
Sessions
</h2>
{sessions.length === 0 ? (
<p className="text-zinc-500 text-sm">
No open sessions. Create one in BooChat first.
</p>
) : (
<div className="space-y-1">
{sessions.map((session) => (
<button
key={session.id}
onClick={() => handleSessionClick(session)}
className="w-full flex items-center gap-3 px-4 py-3 rounded-lg bg-zinc-800/50 border border-zinc-800 hover:bg-zinc-800 text-left transition-colors group"
>
<div className="flex-1 min-w-0">
<div className="text-sm font-medium text-zinc-200 truncate">
{session.name || 'Untitled session'}
</div>
<div className="text-xs text-zinc-500">
{new Date(session.updated_at).toLocaleDateString()}
</div>
</div>
<ArrowRight
size={16}
className="text-zinc-600 group-hover:text-zinc-400 transition-colors"
/>
</button>
))}
</div>
)}
</div>
)}
</div>
</div>
);
}

View File

@@ -1,86 +0,0 @@
import { useEffect, useState } from 'react';
import { useParams, useNavigate } from 'react-router-dom';
import { ArrowLeft } from 'lucide-react';
import type { Chat } from '@/api/types';
import { api } from '@/api/client';
import { useSessionStream } from '@/hooks/useSessionStream';
import { ChatPane } from '@/components/ChatPane';
import { DiffPane } from '@/components/DiffPane';
import { Layout } from '@/components/Layout';
export function Session() {
const { sessionId } = useParams<{ sessionId: string }>();
const navigate = useNavigate();
const [chat, setChat] = useState<Chat | null>(null);
const [loading, setLoading] = useState(true);
const { messages, connected, isStreaming, onPendingChange } =
useSessionStream(sessionId);
// Get or create a chat for this session
useEffect(() => {
if (!sessionId) return;
api.chats
.listForSession(sessionId)
.then((chats) => {
// Use the first open chat, or create one
const openChat = chats.find((c) => c.status === 'open');
if (openChat) {
setChat(openChat);
} else {
// Create a new chat
return api.chats.create(sessionId).then((newChat) => {
setChat(newChat);
});
}
})
.catch(console.error)
.finally(() => setLoading(false));
}, [sessionId]);
if (!sessionId) {
navigate('/');
return null;
}
if (loading) {
return (
<div className="min-h-screen bg-zinc-900 flex items-center justify-center">
<div className="text-zinc-500">Loading session...</div>
</div>
);
}
if (!chat) {
return (
<div className="min-h-screen bg-zinc-900 flex flex-col items-center justify-center gap-4">
<div className="text-zinc-500">Could not load chat for this session.</div>
<button
onClick={() => navigate('/')}
className="flex items-center gap-2 text-sm text-blue-400 hover:text-blue-300"
>
<ArrowLeft size={14} />
Back to projects
</button>
</div>
);
}
return (
<Layout
chatPane={
<ChatPane
sessionId={sessionId}
chatId={chat.id}
messages={messages}
isStreaming={isStreaming}
connected={connected}
/>
}
diffPane={
<DiffPane sessionId={sessionId} onPendingChange={onPendingChange} />
}
/>
);
}

View File

@@ -1,27 +0,0 @@
{
"compilerOptions": {
"target": "ES2022",
"module": "ESNext",
"moduleResolution": "Bundler",
"strict": true,
"esModuleInterop": true,
"skipLibCheck": true,
"forceConsistentCasingInFileNames": true,
"resolveJsonModule": true,
"allowSyntheticDefaultImports": true,
"isolatedModules": true,
"noUncheckedIndexedAccess": true,
"composite": true,
"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.app.tsbuildinfo",
"lib": ["ES2022", "DOM", "DOM.Iterable"],
"jsx": "react-jsx",
"noEmit": true,
"useDefineForClassFields": true,
"allowImportingTsExtensions": true,
"baseUrl": ".",
"paths": {
"@/*": ["./src/*"]
}
},
"include": ["src"]
}

View File

@@ -1,13 +0,0 @@
{
"files": [],
"references": [
{ "path": "./tsconfig.app.json" },
{ "path": "./tsconfig.node.json" }
],
"compilerOptions": {
"baseUrl": ".",
"paths": {
"@/*": ["./src/*"]
}
}
}

View File

@@ -1,14 +0,0 @@
{
"compilerOptions": {
"target": "ES2022",
"module": "ESNext",
"moduleResolution": "Bundler",
"strict": true,
"esModuleInterop": true,
"skipLibCheck": true,
"composite": true,
"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.node.tsbuildinfo",
"allowSyntheticDefaultImports": true
},
"include": ["vite.config.ts"]
}

Some files were not shown because too many files have changed in this diff Show More