Files
msd-core/get-shit-done/workflows/execute-phase/steps/codebase-drift-gate.md
Tom Boucher 41dc475c46 refactor(workflows): extract discuss-phase modes/templates/advisor for progressive disclosure (closes #2551) (#2607)
* refactor(workflows): extract discuss-phase modes/templates/advisor for progressive disclosure (closes #2551)

Splits 1,347-line workflows/discuss-phase.md into a 495-line dispatcher plus
per-mode files in workflows/discuss-phase/modes/ and templates in
workflows/discuss-phase/templates/. Mirrors the progressive-disclosure
pattern that #2361 enforced for agents.

- Per-mode files: power, all, auto, chain, text, batch, analyze, default, advisor
- Templates lazy-loaded at the step that produces the artifact (CONTEXT.md
  template at write_context, DISCUSSION-LOG.md template at git_commit,
  checkpoint.json schema when checkpointing)
- Advisor mode gated behind `[ -f $HOME/.claude/get-shit-done/USER-PROFILE.md ]`
  — inverse of #2174's --advisor flag (don't pay the cost when unused)
- scout_codebase phase-type→map selection table extracted to
  references/scout-codebase.md
- New tests/workflow-size-budget.test.cjs enforces tiered budgets across
  all workflows/*.md (XL=1700 / LARGE=1500 / DEFAULT=1000) plus the
  explicit <500 ceiling for discuss-phase.md per #2551
- Existing tests updated to read from the new file locations after the
  split (functional equivalence preserved — content moved, not removed)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* fix(#2607): align modes/auto.md check_existing with parent (Update it, not Skip)

CodeRabbit flagged drift between the parent step (which auto-selects "Update
it") and modes/auto.md (which documented "Skip"). The pre-refactor file had
both — line 182 said "Skip" in the overview, line 250 said "Update it" in the
actual step. The step is authoritative. Fix the new mode file to match.

Refs: PR #2607 review comment 3127783430

* test(#2607): harden discuss-phase regression tests after #2551 split

CodeRabbit identified four test smells where the split weakened coverage:

- workflow-size-budget: assertion was unreachable (entered if-block on match,
  then asserted occurrences === 0 — always failed). Now unconditional.
- bug-2549-2550-2552: bounded-read assertion checked concatenated source, so
  src.includes('3') was satisfied by unrelated content in scout-codebase.md
  (e.g., "3-5 most relevant files"). Now reads parent only with a stricter
  regex. Also asserts SCOUT_REF exists.
- chain-flag-plan-phase: filter(existsSync) silently skipped a missing
  modes/chain.md. Now fails loudly via explicit asserts.
- discuss-checkpoint: same silent-filter pattern across three sources. Now
  asserts each required path before reading.

Refs: PR #2607 review comments 3127783457, 3127783452, plus nitpicks for
chain-flag-plan-phase.test.cjs:21-24 and discuss-checkpoint.test.cjs:22-27

* docs(#2607): fix INVENTORY count, context.md placeholders, scout grep portability

- INVENTORY.md: subdirectory note said "50 top-level references" but the
  section header now says 51. Updated to 51.
- templates/context.md: footer hardcoded XX-name instead of declared
  placeholders [X]/[Name], which would leak sample text into generated
  CONTEXT.md files. Now uses the declared placeholders.
- references/scout-codebase.md: no-maps fallback used grep -rl with
  "\\|" alternation (GNU grep only — silent on BSD/macOS grep). Switched
  to grep -rlE with extended regex for portability.

Refs: PR #2607 review comments 3127783404, 3127783448, plus nitpick for
scout-codebase.md:32-40

* docs(#2607): label fenced examples + clarify overlay/advisor precedence

- analyze.md / text.md / default.md: add language tags (markdown/text) to
  fenced example blocks to silence markdownlint MD040 warnings flagged by
  CodeRabbit (one fence in analyze.md, two in text.md, five in default.md).
- discuss-phase.md: document overlay stacking rules in discuss_areas — fixed
  outer→inner order --analyze → --batch → --text, with a pointer to each
  overlay file for mode-specific precedence.
- advisor.md: add tie-breaker rules for NON_TECHNICAL_OWNER signals — explicit
  technical_background overrides inferred signals; otherwise OR-aggregate;
  contradictory explanation_depth values resolve by most-recent-wins.

Refs: PR #2607 review comments 3127783415, 3127783437, plus nitpicks for
default.md:24, discuss-phase.md:345-365, and advisor.md:51-56

* fix(#2607): extract codebase_drift_gate body to keep execute-phase under XL budget

PR #2605 added 80 lines to execute-phase.md (1622 -> 1702), pushing it over
the XL_BUDGET=1700 line cap enforced by tests/workflow-size-budget.test.cjs
(introduced by this PR). Per the test's own remediation hint and #2551's
progressive-disclosure pattern, extract the codebase_drift_gate step body to
get-shit-done/workflows/execute-phase/steps/codebase-drift-gate.md and leave
a brief pointer in the workflow. execute-phase.md is now 1633 lines.

Budget is NOT relaxed; the offending workflow is tightened.

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-22 21:57:24 -04:00

2.7 KiB

Step: codebase_drift_gate

Post-execution structural drift detection (#2003). Runs after the last wave commits, before verification. Non-blocking by contract: any internal error here MUST fall through and continue to verify_phase_goal. The phase is never failed by this gate.

DRIFT=$(gsd-sdk query verify.codebase-drift 2>/dev/null || echo '{"skipped":true,"reason":"sdk-failed"}')

Parse JSON for: skipped, reason, action_required, directive, spawn_mapper, affected_paths, elements, threshold, action, last_mapped_commit, message.

If skipped is true (no STRUCTURE.md, missing git, or any internal error): Log one line — Codebase drift check skipped: {reason} — and continue to verify_phase_goal. Do NOT prompt the user. Do NOT block.

If action_required is false: Continue silently to verify_phase_goal.

If action_required is true AND directive is warn: Print the message field verbatim. The format is:

Codebase drift detected: {N} structural element(s) since last mapping.

New directories:
  - {path}
New barrel exports:
  - {path}
New migrations:
  - {path}
New route modules:
  - {path}

Run /gsd:map-codebase --paths {affected_paths} to refresh planning context.

Then continue to verify_phase_goal. Do NOT block. Do NOT spawn anything.

If action_required is true AND directive is auto-remap:

First load the mapper agent's skill bundle (the executor's AGENT_SKILLS from step init_context is for gsd-executor, not the mapper):

AGENT_SKILLS_MAPPER=$(gsd-sdk query agent-skills gsd-codebase-mapper 2>/dev/null || true)

Then spawn gsd-codebase-mapper agents with the --paths hint:

Task(
  subagent_type="gsd-codebase-mapper",
  description="Incremental codebase remap (drift)",
  prompt="Focus: arch
Today's date: {date}
--paths {affected_paths joined by comma}

Refresh STRUCTURE.md and ARCHITECTURE.md scoped to the listed paths only.
Stamp last_mapped_commit in each document's frontmatter.
${AGENT_SKILLS_MAPPER}"
)

If the spawn fails or the agent reports an error: log Codebase drift auto-remap failed: {reason} and continue to verify_phase_goal. The phase is NOT failed by a remap failure.

If the remap succeeds: log Codebase drift auto-remap completed for paths: {affected_paths} and continue to verify_phase_goal.

The two relevant config keys (continue on error / failure if either is invalid):

  • workflow.drift_threshold (integer, default 3) — minimum drift elements before action
  • workflow.drift_action — warn (default) or auto-remap

This step is fully non-blocking — it never fails the phase, and any exception path returns control to verify_phase_goal.