The validate-milestone prompt was rewritten to use 3 parallel reviewers.
Update the prompt contract test to verify the new structure instead of
the old gsd_validate_milestone tool approach.
Add getMissingAnnotationTasks() to surface which tasks lack IO
annotations and prevent parallel dispatch. Also add subagent_model
to ReactiveExecutionConfig for overriding the model used by
subagents during parallel task execution.
- getMissingAnnotationTasks() with 4 tests
- subagent_model field on ReactiveExecutionConfig type
- Validation for reactive_execution.subagent_model preference
Add dispatch rule that detects when multiple slices need research
simultaneously and dispatches them in parallel via subagents. Also
rewrite validate-milestone prompt to use 3 parallel reviewers
(requirements, integration, UAT) for faster validation.
- New dispatch rule: planning → parallel-research-slices (2+ ready)
- buildParallelResearchSlicesPrompt with per-slice subagent prompts
- Parallel research slices prompt template
- Validate-milestone rewritten for 3 parallel reviewers
Add parallel.worker_model preference so coordinators can assign a
cheaper model to parallel workers (e.g. Haiku for execution) instead
of inheriting the coordinator's model. The override is applied via
GSD_WORKER_MODEL env var during worker bootstrap.
- Add worker_model to ParallelConfig type and validation
- Inject GSD_WORKER_MODEL env in spawnWorker when configured
- Apply override in bootstrapAutoSession for parallel workers
- Document in preferences-reference.md
Move plan-milestone and plan-slice from standard to heavy tier so
planning uses the best configured model (e.g. Opus) and is not
downgraded by dynamic routing. Milestone-level planning analysis
also returns heavy instead of standard.
Show the actual reason from validateDirectory (e.g. "Refusing to run in your
home directory" or "Refusing to run in system directory: /usr") instead of a
generic "No project found" message.
Replace assertSafeDirectory with validateDirectory in projectRoot() and throw a typed
GSDNoProjectError that the dispatcher catches and renders as a user-friendly warning.
Fixes#3023
Add configured remote channel (Discord/Slack/Telegram) as a checkmark
in the tools row alongside Brave/Answers/Jina. Remove verbose remote
status lines and duplicate display from header-renderer and register-hooks.
Previously, headless --verbose mode accumulated text_delta events into a
buffer and displayed a single truncated 120-char [thinking] line before
tool calls. The model's actual text responses between tool calls were
effectively invisible.
Changes:
- Stream text_delta and thinking_delta events directly to stderr in
verbose mode with [text] and [thinking] block markers
- No truncation — full model output is visible
- Fix non-verbose fallback: read from ame.delta (correct field) instead
of ame.text (always undefined for text_delta events)
- Track inTextBlock/inThinkingBlock state to properly close streaming
blocks before tool calls
- Expand summarizeToolArgs with support for async_bash, await_job,
cancel_job, find, ls, lsp, hashline_edit, subagent, browser_navigate,
and gsd_* tools
- Add streaming formatter functions: formatTextStart, formatTextEnd,
formatThinkingStart, formatThinkingEnd
- Update tests for new tool arg summarization and path field handling
Saves in-progress daemon work from M005-m138xe that was sitting uncommitted.
Includes orchestrator expansion, event bridge/formatter enhancements,
message batcher tweaks, and discord bot additions.
checkAutoStartAfterDiscuss() fire-and-forgets startAuto() when a
milestone is ready. The headless runner then chains `/gsd auto`,
calling startAuto() a second time. Two concurrent auto-loops on the
same AutoSession singleton corrupt shared state (counters, dispatch
maps), causing planning/execution to never run after research.
Add an early `s.active` check at the top of startAuto() so the second
call no-ops. Add source-scanning test to enforce the guard exists.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three defects in the completing-milestone dispatch guard caused false
positive blocks on valid validation output:
1. Single-line constraint: [^\n]* stopped at newlines, missing verdicts
on subsequent lines. Fixed with [\s\S]{0,500}? (bounded lazy match).
2. Missing keywords: 'satisfied' and 'partially' were absent from the
alternation. LLMs commonly write 'PARTIALLY SATISFIED' or 'FULLY
SATISFIED'. Added both.
3. Markdown bold delimiters: **Operational** blocked [\s:] after the
word. The new [\s\S] class handles any character including *.
Also adds SATISFIED to the structuredMatch includes check, and ✅ to
the prose regex (overlaps with #2862).
Includes 8 regression test cases covering multi-line formats, satisfied
keyword variants, markdown bold tables, and checkmark emoji.
Bug 1 — Workers exit immediately (#2792):
spawnWorker() used `--print "/gsd auto"` which calls session.prompt()
that returns immediately when ctx.newSession() resets the session inside
the auto-loop. Changed to `headless --json auto` which uses an RPC
client that keeps the process alive until auto-mode completes.
Bug 2 — Dispatch guard blocks parallel workers (#2797):
getPriorSliceCompletionBlocker() checked ALL milestones in queue order,
blocking M012 when M011 had incomplete slices. When GSD_MILESTONE_LOCK
is set, the guard now only checks intra-milestone slice dependencies.
Added test covering cross-milestone bypass + intra-milestone preservation.
Bug 3 — Orphaned RPC children on stop (#2798):
stopParallel() gave only 750ms for SIGTERM before SIGKILL. The headless
parent needs ~1500ms to cascade shutdown to its RPC child via
client.stop(). Increased to 3000ms to prevent orphaned processes holding
auto.lock.
Updated tests:
- dispatch-guard.test.ts: new test for GSD_MILESTONE_LOCK bypass
- parallel-worker-monitoring.test.ts: updated spawn args assertion
The dashboard reads elapsed time, total cost, and tokens used
exclusively from AutoDashboardData. When auto-mode is not active
(e.g. manual /gsd next), auto is null and all three metrics show 0
— even though the status bar displays real values via /api/visualizer.
Add the same projectTotals polling pattern (30s interval via
/api/visualizer) that status-bar.tsx already uses, and wire it into
the fallback chain: projectTotals ?? auto ?? 0.
Closes#2709
When worktrees use shared-WAL mode (R012), the worktree DB path resolves
to the same physical file as the project root DB via symlink. Calling
reconcileWorktreeDb() ATTACHes this WAL-mode file to itself, corrupting
the database with 'database disk image is malformed'.
Fix 1 — auto-worktree.ts mergeMilestoneToMain(): skip reconciliation
when isSamePath() confirms both DB paths resolve to the same file.
Fix 2 — gsd-db.ts reconcileWorktreeDb(): defence-in-depth realpathSync
guard inside the function itself, before the ATTACH statement.
Fix 3 — auto/infra-errors.ts: classify 'database disk image is
malformed' as SQLITE_CORRUPT infrastructure error so the auto-loop
stops immediately instead of burning 3 retries on a guaranteed failure.
Regression tests verify:
1. Same-file via symlink returns zero (no ATTACH)
2. Identical string paths return zero
3. Genuinely different DBs still reconcile normally
4. Malformed DB message classified as infra error
5. Transient SQLITE_BUSY is not falsely classified
Closes#2823
When GSD_WEB_DAEMON_MODE=1 is set, scheduleShutdown() becomes a no-op.
The /api/shutdown endpoint still returns { ok: true } so the client
beacon fires without a network error, but process.exit() is never
called. This allows gsd --web to run as a persistent daemon behind a
reverse proxy without exiting on every browser tab close or refresh.
Closes#2835
Multi-turn commands (auto, next) have their own completion signals via
isTerminalNotification ("Auto-mode stopped..."/"Step-mode stopped...").
The execution_complete event fires after command setup before any real
work begins, causing these commands to exit immediately with zero work done.
Closes#2917
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
mapStatusToExitCode only handled "complete" but RPC v2 emits "completed",
causing all headless sessions to falsely timeout and restart.
Also emits milestone-ready notification in checkAutoStartAfterDiscuss so
headless parent can detect and chain into auto-mode.
Closes#2914
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests cover: provider registration, base URL + API type, reasoning +
context window specs, and non-collision with generated zai models.
Required by CI lint gate (require-tests.sh).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add mount point detection for /media, /mnt, /run/media
- Display mount points as quick-access entries when browsing home dir
- Allow navigation to mount points while maintaining security scope
Fixes#2908
Open the project database before the first auto bootstrap derive so cold-start resume uses DB-backed slice state instead of stale markdown fallback state.
Also recognize glyph completion markers in roadmap tables and lock the new bootstrap ordering with regression coverage.
Closes#2841
Auto-mode selected the correct unit model in runUnitPhase, but a fresh session could drop that selection before the first prompt was sent.
Persist the applied unit model on AutoSession, restore it immediately after newSession(), and cover the seam with a regression test that proves the model is re-applied before dispatch.
Closes#2853
`gsd headless new-milestone --auto --verbose` now works — flags are
parsed regardless of position relative to the command word.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Restructure from flat documentation reference into proper agent-oriented
skill with XML structure, mental model, routing to workflows, and restored
reference content (KNOWLEDGE.md, flags, event streaming, answer injection,
command table).
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The xterm-theme test reads shell-terminal.tsx and main-session-terminal.tsx
via readFileSync relative to import.meta.dirname. When compiled tests run
from dist-test/, this resolves to dist-test/web/components/gsd/ — but only
web/lib/ was being copied by compile-tests.mjs, causing the test to fail.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
