The SDK's buildExecutorPrompt told executors to "Create a SUMMARY.md file"
with no directory path, causing them to write it in cwd (project root)
instead of .planning/phases/{phase}/. Thread phaseDir from PhaseRunner
through PromptFactory and into the completion instructions so the executor
gets an explicit path like `.planning/phases/01-auth/01-01-SUMMARY.md`.
Backward compatible — buildExecutorPrompt still accepts a plain string
(agentDef) for existing callers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The discuss step loaded the full interactive workflow prompt which
instructs the agent to use AskUserQuestion, Skill(), and area selection
UIs. In headless auto mode, the agent followed these instructions and
tried to interact with a non-existent user.
Fix: prepend a mandatory headless override BEFORE the workflow prompt
that explicitly forbids interactive tools and instructs the agent to
make all decisions autonomously. Prepending (not appending) ensures
the override takes priority over conflicting instructions later in
the prompt.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bug 1: phasePlanIndex derived empty planId for bare PLAN.md files.
Fixed to use 'PLAN' as the ID, with matching SUMMARY.md detection.
Bug 2: executeSinglePlan passed null to buildPrompt instead of the
actual parsed plan. The executor needs the plan content (tasks,
objectives) to know what to build. Now loads and parses the plan
file before building the prompt.
Bug 3: parseVerificationOutcome checked session exit code, not what
the verifier wrote. A session that runs without errors but writes
status: gaps_found to VERIFICATION.md was treated as 'passed'. Now
queries check.verification-status to read the actual VERIFICATION.md
frontmatter status field.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* chore: add v1.31.0 npm known-issue notice to issue template config
Adds a top-priority contact link to the issue template chooser so users
are redirected to the Discussions announcement before opening a duplicate
issue about v1.31.0 not being on npm.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(phase-runner): add research gate to block planning on unresolved open questions (#1602)
Plan-phase could proceed to planning even when RESEARCH.md had unresolved
open questions in its ## Open Questions section. This caused agents to
plan and execute with fundamental design decisions still undecided.
- Add `research-gate.ts` with pure `checkResearchGate()` function that
parses RESEARCH.md for unresolved open questions
- Integrate gate into PhaseRunner between research (step 2) and plan
(step 3) using existing `invokeBlockerCallback` pattern
- Add Dimension 11 (Research Resolution) to gsd-plan-checker.md agent
- Gate passes when: no Open Questions section, section has (RESOLVED)
suffix, all individual questions marked RESOLVED, or section is empty
- Gate fires `onBlockerDecision` callback with PhaseStepType.Research
and lists the unresolved questions in the error message
- Auto-approves (skip) when no callback registered (headless mode)
- 18 new tests: 13 unit tests for checkResearchGate, 5 integration
tests for PhaseRunner research gate behavior
Closes#1602
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
When running in --auto or headless mode, the discuss step could loop
indefinitely — each pass reads its own CONTEXT.md, finds "gaps" in
referenced types/interfaces, creates new decisions to fill them, and
repeats. Observed: 34 passes, 167 decisions, 7 hours, zero code written.
Fixes:
- Add max_discuss_passes config (default: 3) to WorkflowConfig
- Add single-pass guard instruction to SDK self-discuss prompt
- Add pass cap documentation to CLI discuss-phase workflow
- Add pass guard step to SDK headless discuss-phase prompt
- Add stall detection note to autonomous workflow
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Address review findings from #1454:
1. runVerifyStep now returns success:false when gaps persist after
exhausting retries (was always returning success:true)
2. human_needed + callback accept correctly sets outcome to passed
3. retryOnce skips retry for verification outcomes (gaps_found,
human_needed) which have their own internal retry logic
4. Updated 3 existing tests to expect success:false on exhausted gaps
5. Added 3 regression tests:
- persistent gaps_found does NOT append Advance step
- persistent gaps_found does NOT call phaseComplete
- verifier disabled still advances normally
Previously, the advance step ran unconditionally after verify,
marking phases as complete in ROADMAP.md even when gaps_found.
This caused subsequent auto runs to skip unfinished phases.
Now checks if all verify steps passed before advancing. When
verification fails, the phase remains incomplete so the next
auto run re-attempts it.
