claude is PTY (no ACP discovery), so claude-command-discovery.ts reads its enabled set from disk (user-global): ~/.claude/commands/*.md + every enabled plugin's skills/<name>/SKILL.md (kind=skill) and commands/*.md (kind=command), from ~/.claude/settings.json:enabledPlugins + installed_plugins.json install paths, frontmatter-parsed, bare names, deduped. The snapshot claude branch discovers these live (snapshot cache rate-limits the reads). The coder / menu now shows up to three icon'd groups: <agent> commands (Terminal), <agent> skills (Puzzle), BooCoder skills (Sparkles) via a new optional icon on SlashCommandGroup. AgentCommand gains a kind field in both coder + web copies (parity test enforces); mergeCommandsByName made generic to preserve it. Invocation unchanged (literal /name -> claude). Project-local plugins deferred. BooChat unaffected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The cold ACP probe captured available_commands but read probedCommands synchronously right after newSession, racing opencode's async available_commands_update notification -> captured nothing, only the static manifest showed. The probe now waits (poll <=3s + 300ms settle) for the notification. Captured commands persist to a new available_agents.commands column and are served (merged with the manifest) on the tier-2-skip path, so the agent's discovered commands survive once models are warm and show without a dispatch. Boot warms via the force:true startup snapshot. Caveat: relies on opencode emitting available_commands_update on session creation, not only post-prompt.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Coder / menu now shows two groups: the active agent's commands first (manifest + live ACP available_commands), BooCoder skills second. SlashCommandPicker gains an opt-in groups prop (flat items path unchanged -> BooChat byte-identical, parity verified); ChatInput takes slashGroups; CoderPane builds the groups. Skills run under the selected agent: coder skill_invoke accepts a provider and, when external, injects the server-side skill body into a dispatched task instead of native inference. Also folds in the initial-chat skill fix (handleLandingSkill: create chat -> assign to pane -> invoke, same transition as a text send) that resolves the landing-page blank screen. BooChat slash menu + skill invocation unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The AgentComposerBar refresh button wrapped to a second line on mobile: the status dot had ml-auto (pinned to the far-right edge) and the refresh button followed it in DOM order, overflowing past the edge. Group the dot + refresh into one right-aligned (ml-auto) unit so the refresh stays on the top line. Also add an iconOnly option to CompactPicker and render the Mode (permission) picker icon-only on mobile (shield + chevron, no label; aria-label/title + tap-to-open list still convey the selection) to free row width. Desktop unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fix: getProviderSnapshot returned synchronous installed:false 'loading' entries on a cache miss (v2.5.5/Phase 2), which AgentComposerBar filters out — with the Phase 5 client poll not yet built, a single fetch stranded on 'loading' and the picker showed no providers. It now awaits the build and returns terminal entries; the sync loading-return is deferred until Phase 5. Builds stay fast via the tier-2 cold-probe skip.
Feature: wire the v2.3 config schema's models/additionalModels — buildResolvedRegistry carries them onto ResolvedProviderDef (models replace, additionalModels merge) and provider-snapshot applies them to every ready model list, so /data/coder-providers.json can edit any provider's models with no code change. Claude staticModels bumped from the stale 2-entry list to opus/sonnet/haiku latest-aliases + pinned claude-opus-4-8 / claude-sonnet-4-6 / claude-haiku-4-5-20251001 (passed verbatim to claude --model). +2 tests (109 total).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ACP dispatch now spawns from the resolved registry's launch spec instead of a hardcoded per-name switch. acp-spawn.ts gains resolveLaunchSpec(resolved, installPath): launchCommand (config override / custom-ACP command) wins, else the kept resolveAcpSpawnArgs switch is the built-in fallback. acp-dispatch.ts spawns spec.binary/spec.args with env { ...process.env, ...spec.env }; dispatcher.ts loads the resolved def by task.agent and passes it through. Config-defined custom ACP providers dispatch with no new switch case. Built-in dispatch (opencode/goose/qwen) is byte-identical to pre-v2.3 — proven by a regression test (opencode->['acp'], goose->['acp'], qwen->['--acp'], binary=installPath ?? id, empty env -> plain process.env). Deliberate deviation from design's !installPath->null: the installPath ?? id fallback is preserved. setSessionMode/permission/streaming and the dispatcher poll/NOTIFY/running-guard untouched. 7 new acp-spawn.test.ts cases. No routes/UI (Phase 4+).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
provider-snapshot no longer returns null for uninstalled/disabled providers: it emits one entry per registered provider with a lifecycle status (loading|ready|unavailable|error), an enabled flag, and a two-tier probe. Tier-1 is a fast which-style check (command-availability.ts, execFile/no-shell); tier-2 (cold ACP probe) is skipped unless forced, last_probed_at is older than PROVIDER_PROBE_TTL_MS (24h), or DB models are empty — the snapshot-latency win. Cache miss returns status:'loading' synchronously while the build settles via the existing inflight promise. ProviderSnapshotStatus/Entry regain loading/unavailable + gain enabled/description?/fetchedAt? in both coder and web copies, guarded by a runtime parity test (provider-types-parity.test.ts; compile-time cross-project check was blocked by TS6307). Also tracks the data/coder-providers.json seed via a .gitignore exception, completing the Phase 1 config file. No dispatch/route/UI changes (Phase 3+); AgentComposerBar filtering unchanged. 13 snapshot tests (+6) + 6 parity tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a config layer merged over the hardcoded built-ins (tasks 1.1-1.6): CODER_PROVIDERS_PATH env (default /data/coder-providers.json); provider-config.ts (Zod schema + never-throw loader — missing/invalid file falls back to built-ins only — + save); provider-config-registry.ts (ResolvedProviderDef + buildResolvedRegistry merge: override built-ins, add custom extends:'acp' entries, boocode always enabled + singleton); agent-probe now iterates the resolved registry, probes custom-ACP command[0] via execFile (no shell), skips disabled providers (keeps the row), reads enabled from memory only (no DB column). No snapshot/dispatch/route/UI changes (Phase 2+). 6 new unit tests; empty config provably yields exactly the built-ins.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reject qwen3.6 spurious <invoke> tails with path "..." or empty args before
they enter toolCalls, preventing duplicate assistant answers. Dropped blocks
append to flushed text; four new xml-parser tests. DEFERRED-WORK §6 for
console.debug → pino cleanup.
Co-authored-by: Cursor <cursoragent@cursor.com>
- BooCoder moves from Docker to host systemd service (boocoder.service)
- Agent dispatch (ACP + PTY) switches from SSH to direct spawn/exec
- SSH helpers marked @deprecated (kept for one release cycle)
- Provider registry (5 providers: boocode, opencode, goose, claude, qwen)
- Agent probe with direct which/exec + model discovery (qwen settings, static claude models)
- GET /api/providers route with installed status, models, transport fallback
- ProviderPicker frontend component in CoderPane header
- External provider messages route through tasks row instead of inference enqueue
- Smart scroll: MessageList only auto-scrolls when near bottom (150px threshold)
- DB: available_agents gets models, label, transport columns
- Bug fix: loadContext SELECT includes allowed_read_paths
- Bug fix: cap hit sentinel inserted before buildMessagesPayload
- docker-compose.yml: boocoder service commented out, BOOCODER_URL env var added
- CLAUDE.md: updated docs for systemd, provider registry, JSONB gotcha, loadContext
Phase 8 of v2.0. Final hardening pass before production tag.
Path-guard fuzz suite (34 tests): traversal attacks (../ all depths,
encoded %2e%2e, null bytes, absolute escapes, prefix-without-separator,
backslash), secret-file deny list (.env, *.pem, id_rsa*, *.key,
credentials.json, *.kdbx, .netrc), valid-path positives, edge cases
(empty, whitespace, very long, triple-dot, multiple slashes).
write_guard.ts hardened: added null-byte rejection and whitespace-only
rejection (previously only checked empty string).
Pending-changes integration test skeleton: 4 tests covering the full
queue→apply→rewind cycle against a real DB + filesystem. Gated on
DATABASE_URL via describe.runIf (same pattern as apps/server's
tool_cost_stats.test.ts). Skips cleanly when unset.
57 tests passing (23 existing + 34 fuzz), 4 integration skipped.
All builds clean. All services healthy.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
BooCode wrapper tools for the 4 new MCP tools added to the codecontext
sidecar (Go side committed separately at /opt/forks/codecontext).
- get_blast_radius: reverse-edge BFS — "what breaks if I change this?"
- get_hot_files: most-imported files by incoming edge count
- get_routes: Fastify/Express route extraction via tree-sitter AST
- get_middleware: middleware detection via import + registration patterns
Wrappers follow the existing codecontext pattern: Zod input → callCodecontext
→ ToolDef export. Registered in ALL_TOOLS (alpha-sorted). All 4 are read-only.
codecontext sidecar rebuilt from commit b19e646 with the 4 new Go handlers
(2130 lines, 29 tests). Reviewer fixes applied: defer RUnlock on Tier 2
handlers, extractObjectProperty delegates to extractStringValue for
template-literal route paths.
363/363 server tests passing. No schema changes, no frontend changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Generalizes the v1.14.1 single-server Context7 PoC into a multi-server MCP
client registry with per-server graceful degradation. JSON config at
/data/mcp.json (bind-mounted alongside AGENTS.md) matches opencode's
mcpServers schema shape. Config file missing = no MCP (opt-in by presence).
Two transports: Streamable HTTP (remote servers like Context7) and stdio
(local subprocess servers like codecontext). Stdio spawns a persistent child
via the SDK's StdioClientTransport; shutdown hook closes all transports.
Tool prefix generalized from context7_<name> to <serverName>_<toolName> with
a toolToServer reverse map for dispatch routing. AGENTS.md tools: field now
supports glob patterns (context7_*, !web_*) via matchToolGlob — last-match-
wins with ! deny prefix. Replaces exact-match .includes() in stream-phase.ts.
refreshToolNames() in agents.ts rebuilds the DEFAULT_TOOLS snapshot after
appendMcpTools so agents without explicit tools: lists see MCP tools —
reviewer caught that the module-load-time snapshot would permanently exclude
late-registered tools.
Read-only invariant: readOnlyHint === false rejected at discovery. Result
size capped at 5MB. v1.14.1 env vars removed — superseded by config file.
Default data/mcp.json ships with Context7 disabled.
363/363 server tests passing. No schema changes, no frontend changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Validates the MCP-client loop end-to-end against one real MCP server before
the full v1.15 port. New services/mcp-client.ts wraps @modelcontextprotocol/sdk
v1.29.0 with Streamable HTTP transport. On startup (when MCP_CONTEXT7_URL is
set), connects to Context7, discovers tools via tools/list, wraps each as a
ToolDef prefixed context7_<name>, and appends to ALL_TOOLS via appendMcpTools.
Read-only invariant guard rejects any tool with readOnlyHint: false. Tool
dispatch is transparent — executeToolCall routes MCP calls through the ToolDef
execute wrapper, which strips the prefix before calling the MCP server. Result
size capped at 5MB with truncation. Graceful degradation: server down at
startup → zero tools; server down mid-session → error result, model
self-corrects.
Adversarial review caught that a Zod .default() on the URL config made MCP
always-on instead of opt-in — fixed by removing the default. MCP_CONTEXT7_URL
must be explicitly set to enable.
ALL_TOOLS changed from ReadonlyArray to mutable to support late-registration.
appendMcpTools re-sorts and rebuilds TOOLS_BY_NAME after append.
348/348 server tests passing (16 new mcp-client tests). No schema changes,
no frontend changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Converts the ad-hoc executeToolPhase → runAssistantTurn recursion into an
explicit while (stepNumber < effectiveCap) loop. A step is one stream-and-
tool-execute iteration; the loop terminates on non-tool finish, step-cap hit,
doom-loop, budget exhaustion, abort, or synthesis success.
MAX_STEPS = 200 hard ceiling (4x old effective limit from budget). Per-agent
steps: field in AGENTS.md frontmatter sets tighter caps (Refactorer: 5,
Architect: 20, others: unset = bounded only by MAX_STEPS). Resolution:
effectiveCap = Math.min(agent.steps ?? Infinity, MAX_STEPS).
executeToolPhase no longer recurses — returns ToolPhaseResult struct
(action: 'continue' | 'paused' | 'synthesis_done') so the caller decides
whether to continue or break. steps: 0 handled as "no tool calls allowed"
via runTextOnlyTurn (one text-only stream phase, tool calls ignored with
warn log).
Step-cap hits produce a sentinel summary (reuses cap_hit kind so
CapHitSentinel.tsx renders without frontend changes; text distinguishes
"Step limit reached" from "Tool budget exhausted"). Doom-loop check migrated
to top of loop body — same predicate, same threshold (3), break instead of
return.
step_start parts are in the schema CHECK but not emitted as message_parts —
writing before the stream phase creates a sequence-0 collision with
partsFromAssistantMessage. Structured log line emitted instead. Adversarial
review caught the collision pre-deploy.
332/332 server tests passing. No frontend changes. No schema changes.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Removes the dual-write into messages.tool_calls / messages.tool_results JSON
columns and drops the columns. message_parts is now the only source of truth
for tool calls and tool results.
10 dual-write sites stripped (5 in tool-phase.ts, 2 in routes/skills.ts, 2 in
routes/messages.ts, 1 in routes/chats.ts fork-clone). The recon-driven grep
caught 2 sites beyond the original v1.13.2 roadmap inventory and an extra
fixture file (tool_cost_stats.test.ts) with a direct legacy-column INSERT.
messages_with_parts view rewritten to parts-only subselects (COALESCE
fallbacks gone). View runs via CREATE OR REPLACE so it lands before the
column DROPs in startup DDL — Postgres rejects column-drop on view-referenced
cols. v1.12.1 cleanup DO block (DROP CONSTRAINT messages_status_check /
messages_role_check) removed; those one-shots have done their work.
Adversarial review caught a runtime bug the green test suite missed: the
discard_stale endpoint (chats.ts) had a RETURNING ... tool_calls, tool_results
clause that would have crashed on every 60s-no-token-activity recovery in
production. Fixed by switching to two-step UPDATE returning id, then SELECT
from messages_with_parts so parts-synthesized fields keep flowing on the wire.
Message API type retains tool_calls? / tool_results? — the view synthesizes
those keys from parts so the wire shape is unchanged; frontend reads need no
update. Override on the original v1.13.2 plan, captured in the openspec
proposal.
339/339 server tests passing (including 7 DB-integration tests that applied
the schema migration to a live DB and ran the parts-only view end-to-end).
tsc + web build clean.
Pairs with v1.13.0-ai-sdk-v6 (introduced the dual-write) and v1.13.1-B (moved
the read path to messages_with_parts). Umbrella v1.13 tag ships on this same
commit, marking the strangler-fig closed.
CLAUDE.md picks up Sam's pre-existing edits documenting tag-naming and
CHANGELOG conventions — both already in use by v1.13.19 / v1.13.20.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Every assistant message gets an "Open in pane" affordance that opens the
message in the workspace splitter — Markdown pane (Copy + Download .md) by
default; HTML pane (Download .html only) when the model emits a self-contained
<!DOCTYPE html> or fenced ```html artifact. BOOCHAT.md rule keeps Markdown
default at every length; HTML opt-in on explicit user request.
Backend: services/artifacts.ts (slug derivation + write helpers with
symlink-escape guard via realpath-after-mkdir), routes/artifacts.ts (POST
download + GET stream with nosniff + CSP sandbox defense-in-depth), HTML
detection in finalizeCompletion writing a new message_parts.kind='html_artifact'
row (schema CHECK extended via v1.13.13 pattern), graceful 1MB cap via the
pure decideHtmlArtifactWrite helper. PartKind union extended.
Frontend: MarkdownRenderer.tsx extracted from MessageBubble's inline
MarkdownBody for reuse; MarkdownArtifactPane.tsx + HtmlArtifactPane.tsx with
loading/error states; pane state is reference-only ({chat_id, message_id,
title}) — content fetched on mount to keep workspace_panes jsonb small and
avoid 1MB blobs riding session_workspace_updated frames. iframe sandbox
locked to allow-scripts allow-clipboard-write allow-downloads with no
allow-same-origin, srcDoc not src. openInPane discriminates 404 (expected
fallback) from real errors (toast + bail). PanelRightOpen icon button with
mobile 44px tap-target.
31 new server unit tests including a real-symlink filesystem case; 332/332
server tests passing, tsc clean both sides, pnpm -C apps/web build green.
Smoke deferred to first deploy.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Four codecontext sidecar wrappers — get_file_analysis (required
file_path), get_symbol_info, get_dependencies, and get_semantic_neighborhoods
(optional) — forwarded file_path to the HTTP sidecar unchanged. The
sidecar's internal file index is keyed on absolute paths, so any
relative path from the model returned "File not found in graph".
Three back-to-back failures observed in one chat on 2026-05-22
17:56 UTC, ~48 s of wasted tool budget.
## Resolver
Add resolveProjectPath(projectRoot, rawPath) in codecontext_client.ts:
trim check → absolute/relative branch (both go through resolve() so
dot-segments normalise) → realpath with ENOENT fallthrough → escape
check using the realpathed value. Error shape mirrors the existing
target_dir escape error byte-for-byte; only the field name differs.
Wired into callCodecontext at the args-spread site, guarded on
file_path presence + non-empty. All four wrappers benefit from one
call site; wrappers without file_path (overview, framework, watch,
search) are unaffected.
## Schema trim
.trim() added to all four file_path Zod schemas:
get_file_analysis: z.string().trim().min(1)
get_symbol_info: z.string().trim().optional()
get_dependencies: z.string().trim().optional()
get_semantic_neighborhoods: z.string().trim().optional()
Absorbs trailing newlines / whitespace from model output before the
resolver sees the value.
## Adversarial review fixes
Adversarial pass surfaced two P2 findings:
1. Absolute path with `..` resolving outside the project root (e.g.
`<projectRoot>/../etc/passwd`) that ENOENTs at realpath would slip
through the literal prefix-check: the raw string starts with
`<projectRoot>/`. Fix: resolve() the absolute branch's candidate
too, so dot-segments normalise before the prefix check.
2. No symlink-escape test coverage. Realpath's stated purpose
(catching in-project symlinks pointing outside the project) was
never tested. Added: create a tmpdir outside projectRoot,
symlink projectRoot/evil-link → outside file, assert rejection.
## Tests
codecontext_client.test.ts: 19 tests (10 baseline + 9 new file_path
resolution cases). Cases cover: relative→absolute, absolute-inside,
relative-escape, absolute-outside, ENOENT-fallthrough, empty-string,
wrapper-without-file_path, absolute-with-`..`-ENOENT,
symlink-leaving-root.
codecontext_tools.test.ts: one assertion updated to expect the
resolved-absolute file_path on the wire (previously asserted the raw
relative path passed through, which is exactly the bug being fixed).
Full suite: 301 passed, 7 skipped.
## Affected / unaffected
- get_codebase_overview, get_framework_analysis, watch_changes,
search_symbols: no file_path arg → resolver guard skips them. No
behavior change.
- get_semantic_neighborhoods IS in SYNTHESIS_TOOLS — previously-failing
relative-path calls will now successfully synthesize. Desirable, not
a regression.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the agent needed context from another repo, pathGuard rejected every read
with no recovery path. This batch adds a reactive request_read_access flow:
pathGuard's error now hints at the tool, the model emits a structured request,
the inference loop pauses (same mechanism as ask_user_input), the user picks
Allow/Deny via inline chips, and subsequent reads under the granted root succeed
for the rest of the session.
Schema: sessions.allowed_read_paths TEXT[] NOT NULL DEFAULT ARRAY[]::TEXT[]
(idempotent ADD COLUMN IF NOT EXISTS).
Grant unit (design D1): nearest registered projects.path ancestor →
nearest repo-shaped ancestor (.git/ / package.json / go.mod / Cargo.toml)
under PROJECT_ROOT_WHITELIST → else refuse. grant_resolver.ts walks
ancestors with a per-iteration whitelist invariant check so symlinked
input can't escape the whitelist mid-walk (Sam's checkpoint-1 ask).
Path-guard: optional extraRoots arg threaded from session.allowed_read_paths
through executeToolCall to view_file / list_dir / grep / find_files. The
ToolDef.execute signature gets an optional third param; non-FS tools
ignore it. view_file re-anchors the secret-guard check on basename(real)
whenever a relative path starts with "../" so .env / id_rsa* etc. still
deny across grant roots.
Endpoint: POST /api/chats/:id/grant_read_access mirrors /answer_user_input.
On 'allow' it re-resolves the grant root (state may have changed since
prompt — auto-falls to denial reason text on failure, not 500), array_appends
to sessions.allowed_read_paths with in-memory dedup, then publishes
tool_result + session_updated frames and enqueues the next assistant turn.
PATCH /api/sessions/:id allowed_read_paths supports revocation only. Zod
refines absolute + no traversal markers; runtime findUnauthorizedAdditions
guard rejects any entry not already present in the row, so a malicious
curl -X PATCH -d '{"allowed_read_paths":["/etc"]}' returns 400 instead of
bypassing the grant flow (Sam's compliance-review action item).
Frontend: RequestReadAccessCard renders pending (path + reason + Allow/Deny)
and answered (granted/denied summary with the resolved root) variants;
MessageList.flatten/group special-cases the tool name; SettingsPane adds a
per-session grants list with per-row revoke that PATCHes the shortened
array.
Tests: 11 grant_resolver, 8 path_guard, 8 sessions PATCH subset, including
explicit cases for symlink escape mid-walk, walk-bound termination at
whitelist root, /etc bypass attempt via PATCH, and nearest-project
disambiguation. 292 total server tests green.
Pairs with v1.13.16-xml-parser — the model now self-recovers from both
a wrong tool name AND from a refused path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two-part fix for the model-emitted XML drift the v1.13.15-codecontext-synth
investigation surfaced (1 raw <invoke> leak observed out of 190 qwen3.6
turns — qwen3.6-35b-a3b-mxfp4 drifts to the Anthropic format when prompted
as an Architect-style agent because Claude Code documentation in its
pre-training corpus uses that shape).
## Parser extension
xml-parser.ts now recognizes BOTH XML tool-call flavors:
- Qwen/Hermes: <tool_call><function=NAME>...<parameter=K>V</parameter>...</function></tool_call>
- Anthropic: <invoke name="NAME"><parameter name="K">V</parameter></invoke>
Both route through the same synthetic-id xml_call_${idx} ToolCall path.
extractToolCallBlocks() and partialXmlOpenerStart() handle both openers
(<tool_call> and <invoke...) so partial buffers don't get prematurely
flushed during streaming.
The existing Qwen parser was tightened to tolerate whitespace around `=`
(<function = name>, <parameter = key>...) so a stray space doesn't get
absorbed into the function name. Name capture is non-whitespace,
non-`>`.
## Unknown-tool recovery hint
New tool-suggestions.ts exports levenshtein() + suggestToolName() +
formatUnknownToolError(). When tool-phase.ts:executeToolCall receives a
toolCall.name that isn't in TOOLS_BY_NAME, the error returned to the
model now includes a "Did you mean: X?" hint based on Levenshtein
distance ≤3 or substring match against Object.keys(TOOLS_BY_NAME).
Targets the qwen3.6 drift to read_file → suggest view_file. Applies to
all unknown tool names, not just <invoke>-derived ones — at the
dispatch layer we no longer know which format produced the call, and
the extra signal is harmless for Qwen-derived calls.
## Test coverage
xml-parser.test.ts: 46 tests, all green. Covers both parsers
(well-formed, malformed, multi-parameter, nested-content), the
partial-opener detector for both flavors, the unified extraction
helper, and the unknown-tool error formatter.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After a codecontext overview-class tool call lands (get_codebase_overview,
get_framework_analysis, get_semantic_neighborhoods), the pipeline runs a
second inference pass that replaces the recursive runAssistantTurn. The
synth pass auto-fetches the top-N source files referenced in the
codecontext output plus project docs (BOOCHAT.md, AGENTS.md,
*roadmap*.md, CONTEXT.md), applies a 32k-token budget with explicit
drop-priority, and streams a structured response that grounds the model
in real load-bearing code rather than relying on the codecontext summary
alone. Smoke #1 (default) and #2 (Architect) both cite the correct
inference/turn.ts + tool-phase.ts + stream-phase.ts files; smoke #6
(fault injection) verifies the fall-through path marks the synth message
status='failed' and yields cleanly to the recursive turn.
## Truncation-aware extraction
codecontext's wrapper inline-truncates results at 32k chars. Without the
expansion step, the top-N file selection only saw the alphabetical head
of the codebase (apps/booterm/dist/*) and auto-fetched the wrong sources.
The pipeline now calls in-process readTruncation(outputPath) before
extracting referenced files, so top-N selection sees the full 80k+ char
output. The 32k truncated head still ships to the synth model — the
expansion is reference-extraction-only, preserving the token-budget
contract. Graceful degradation on readTruncation null/throw: log warn,
fall back to the truncated head.
## Schema deviation from dispatch
The dispatch claimed no schema migration was needed for the new
'synthesis' part kind. Reality: message_parts.kind has an explicit
CHECK constraint (schema.sql:54) that would reject the new value. Added
a DROP CONSTRAINT IF EXISTS + DO $$ pg_constraint idempotency-guarded
re-add matching the CLAUDE.md migration pattern. The inline CREATE TABLE
constraint also updated so fresh installs land with the extended enum.
## User-abort marks synth-message failed
Deviation from review-time spec ("user-abort path does NOT mark the
message failed"). The outer abort handler in error-handler.ts operates
on the parent turn's assistantMessageId, not the new synth row that
runSynthesisPass created. Without explicit marking, the synth row would
sit in status='streaming' until the 5-min stale-streaming sweeper
(v1.13.1-cleanup-bundle), tripping the frontend's 60s no-token-activity
banner in the meantime — exactly the UX bug class the v1.13.1 sweeper
was added to handle. Marking failed on every catch path (including
user-abort) closes the gap. Cost: one extra DB write + one publish on
the rare user-abort-during-synth path.
## Race-safe synth-tool capture
tool-phase.ts uses synthEntries: Array<{tc, output, error?}> with
per-callback push under Promise.all. find() picks the first non-error
entry by call-order (toolCalls array index). Multiple synth-tools in
one batch are uncommon but handled deterministically.
## Roadmap rebase
Updated boocode_roadmap.md retrospective section + cleanup-order tracker
+ schema-changes summary to use the new vMAJOR.MINOR.PATCH-slug tag
names per the 2026-05-22 retag (CHANGELOG.md is the canonical record).
v1.13.15 listed as "this batch, tag pending"; a one-line follow-up
commit will remove that qualifier after the tag lands.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
