Root cause: two proven corruption mechanisms — (M1) non-idempotent apply
stamped the same block N times when a quantized model re-emitted the same
edit_file call or a turn was retried; (M2) Levenshtein tier 4 was fail-open
with no uniqueness guard, silently splicing into the wrong location.
Fixes applied at every layer of the pipeline:
Matcher (fuzzy-match.ts): raise SIMILARITY_THRESHOLD 0.66 → 0.85; add
AMBIGUITY_EPSILON uniqueness guard — two windows within 0.05 of the top
score → ambiguous, not a guess; add block-anchor gate (≥3-line needles
require first+last line exact match before a window is scored).
Edit planner (pending_changes.ts): extract planEdit() as a pure function;
idempotency guards detect already-applied states (anchored insert re-stamp,
old-gone-but-new-present); findPendingDuplicate() collapses identical
pending rows at queue time so M1 never reaches applyOne.
Atomic writes (pending_changes.ts): temp-file + rename on the same
filesystem so a crash can't leave a half-written source file; realpath()
first so symlinks survive the rename.
Per-file mutex (pending_changes.ts): withFileLock() serializes concurrent
read-modify-write on the same path via a chained-Promise Map.
EOL preservation (pending_changes.ts): normalize CRLF → LF for matching,
restore native line ending on write so Windows-style files stay clean.
Context isolation (inference_context.ts): replace module-level singleton
with AsyncLocalStorage so concurrent inference runs (arena parallel
dispatch, dispatcher poll racing a user message) each get their own
scoped context with no clobbering.
Tests: plan-edit.test.ts (pure planEdit unit tests), extended fuzzy-match
and pending_changes_integration suites, ALS isolation test that proves
overlapping runs get correct session IDs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Arena is a new pane kind for competitive AI evaluation. A Battle runs
the same prompt against 2-6 Contestants across two concurrent lanes:
local lane (llama-swap models, serial) and cloud lane (parallel).
Added to all three registries: @boocode/contracts WsFrameSchema,
server InferenceFrame, and web WsFrame.
Backend (apps/coder):
- arena-runner: battle scheduler, lane classifier, benchmark, results
writer, resume, user winner override
- arena-analyzer: two-stage digest→judge analysis on DEFAULT_MODEL
- arena-decisions: status transitions and resume logic (unit-tested)
- arena-analyzer-helpers: pure helper functions (unit-tested)
- arena-model-call: model call utility for analysis
- arena routes: create/get/list/stop/analyze/cross-examine/winner/diff
- schema: battles, contestants, cross_examinations tables (idempotent)
- remove old /api/arena* routes and tasks.arena_id column
Frontend (apps/web):
- ArenaLauncherDialog: battle type, prompt, contestant selection
- ArenaPane: live roster, streaming output, analysis, cross-exam
- DiffView: unified diff with line-by-line color for coding contests
- Winner override per-row dropdown (Trophy icon)
- battle_updated WS handler for live winner/analysis updates
- arena pane kind in Workspace, ChatTabBar, useSidebar
Cross-app:
- ArenaState and ArenaContestantShape/WsFrame types (contracts)
- battle_* frames in WsFrameSchema, InferenceFrame, and web WsFrame
- manifest.json written per battle results folder
- /Arena added to .gitignore
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Replace the raw per-agent mode dropdown in the BooCoder composer with a
curated three-option permission ladder mapped generically onto each
provider's native modes: `plan` id -> Plan, default -> Ask, isUnattended
-> Bypass (claude bypassPermissions, qwen yolo, opencode full-access).
modeId stays the single wire field; the active unified mode is derived
from it (no contracts change).
Native BooCode gains its own mode set: Ask stages to the pending-changes
queue (today's behavior), Bypass auto-applies the queue to disk after the
turn (interactive messages path + task dispatcher path), Plan falls back
to Ask. The shared apps/server inference engine is left untouched.
Also preserve isUnattended on live-probed ACP modes so opencode's bypass
mode stays detectable from the wire.
Coder 373 tests green; coder + web typecheck clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Give the expand chevrons the BooCoder outline-button look (border-border
bg-background, hover:bg-muted, filled when expanded) instead of the borderless
ghost style. Applies to both BooChat's flat menu and BooCoder's grouped menu.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Most plugin/han SKILL.md and command files write `description:` as a folded
block scalar (`>` / `|`) with the text on the following indented lines. The
old single-line frontmatter reader captured the literal `>`, so the slash
menu showed garbage/blank descriptions for nearly all of them. frontmatterField
now collapses folded blocks (join with spaces) and preserves literal blocks.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Document the in-app Orchestrator engine and its load-bearing read-only
invariant in apps/coder/CLAUDE.md, and note that apps/coder/.env.host is
now gitignored (recreated from .env.example with CLAUDE_SDK_BACKEND=1).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bring README current (was v2.2.1): add the Orchestrator, the Files/Git diff
panel, persistent agent sessions + claude Agent-SDK, fix the provider list
(5 — cursor/copilot retired), drop the broken AGENTS.md link, update latest
release + planned. Refresh CURRENT.md to v2.7.17 on main.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Untrack the host env file (git rm --cached, kept on disk for the boocoder
service) and widen .gitignore to .env.* (re-including .env.example) so env
files no longer get committed. The file's prior contents (dev DB password +
internal Tailscale URLs; no API keys) remain in history — left as-is given the
single-user Tailscale-only threat model.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Move openspec/changes/{contracts-ssot,orchestrator} → archived/ (both shipped,
v2.7.13 and v2.7.17). Mark the roadmap's "Write/edit robustness" and "Claude
provider SDK" milestones as shipped (fuzzy-match.ts + checkpoints.ts; the
claude-sdk backend is live via CLAUDE_SDK_BACKEND in .env.host) and add a
v2.7.12–v2.7.17 shipped summary. Flag DEFERRED-WORK.md as superseded.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Each flow row in the launcher and each command in the / slash picker now
shows an always-on one-liner with a chevron that expands a 1-2 sentence
what/when blurb (condensed from the Han skill descriptions). Launcher gets a
read-only pill and a per-row Run separate from expand; the fast/concise
toggle is now wired through to the conductor workers. Shared ChatInput, so
the slash explanations cover both BooChat and BooCoder. Web tsc clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Brings the deterministic Han-flow conductor into BooCode: launch any read-only
flow from BooChat or BooCoder, watch each agent stream live in a Paseo-style
run pane, get an evidence-disciplined report — on local Qwen, persisted and
resumable. Read-only enforced hard via qwen --approval-mode plan (orchestrator
tasks fail closed if qwen is unavailable; never fall to write-capable native).
Backend (apps/coder): re-homed conductor defs, flow_runs/flow_steps schema,
flow-runner + dispatcher onTaskTerminal hook, restart-resume, runs routes
(launch/list/get/cancel), user-channel WS. Contracts: two flow_run_* frames.
Web: orchestrator pane kind + OrchestratorPane, Workflow button + slash flows
(BooChat/BooCoder parity), FlowLauncherDialog, "New Orchestrator" in the + and
split menus, runs history + export. Plan: openspec/changes/orchestrator.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Second checkpoint of in-flight work (sessions route, api types, ChatTabBar,
PaneHeaderActions, Workspace, useWorkspacePanes) so the Orchestrator branch
can rebase onto current main before merge.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Port the boolab FX controls: localStorage-backed Density, Speed, and
Opacity sliders in the theme settings, shown when a canvas-background
theme is active (Density is matrix-rain-only). Speed is a multiplier over
each field's native base; values feed MatrixRain / NeonField live.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Checkpoint of in-flight work so the orchestrator branch can rebase onto a
clean main: ContextBar → ContextMeter, model-label helper, model/agent picker
+ provider-snapshot/registry changes, inference payload + message-columns.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a warm orange glow (static rim + drop, gentle gated idle pulse) on the
primary action for BooCode Classic, matching Override's treatment but
calmer (no glitch). Also fix the context-meter ring on both warm themes:
its `stroke-muted` track ≈ the background, so only the fill showed — give
the track a faint warm stroke so the full ring reads.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The AppShell root carries `bg-background`; on a full-viewport element that
~86%-opaque panel token painted a sheet over the z-0 canvas, hiding the
matrix rain (Classic) and neon field (Override) behind it while pseudo-
element effects like the scanline still showed. Make the root transparent
for both canvas themes so the field shows through; the opaque html backstop
stays the base and panels keep their own translucent backgrounds.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Override now uses the BooCode Classic warm tokens (orange/amber/rust on
warm near-black) instead of neon magenta/cyan/violet, with its neon-grid
field, glitch, scanlines, and bloom recoloured to match — a hotter,
glitchier Classic. Updates the NeonField canvas hues, the --bco-* effect
vars, and the picker preview anchors.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add three opt-in dark themes (BooCode+, BooCode Classic, BooCode
Override) plus an in-place Ember polish, on a class-scoped effects
engine: matrix rain, a neon grid field, and frosted glass, all gated
by a localStorage "Animated background" toggle and prefers-reduced-
motion. Extend the server theme_id whitelist so the new ids persist,
and replace the Home landing wordmark with the stacked mascot +
wordmark banner.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
