Files
get-shit-done/tests/bug-2549-2550-2552-discuss-phase-context.test.cjs
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

101 lines
4.6 KiB
JavaScript

'use strict';
/**
* Bugs #2549, #2550, #2552: discuss-phase context bloat and cache invalidation.
*
* #2549: load_prior_context must cap prior CONTEXT.md reads (was O(phases))
* #2550: scout_codebase must select maps by phase type (was always all 7)
* #2552: scout_codebase must not instruct split reads of the same file
*/
const { test, describe } = require('node:test');
const assert = require('node:assert/strict');
const fs = require('node:fs');
const path = require('node:path');
const DISCUSS_PHASE = path.join(
__dirname, '..', 'get-shit-done', 'workflows', 'discuss-phase.md',
);
// After #2551 progressive-disclosure refactor, the scout_codebase phase-type
// table and split-reads warning live in references/scout-codebase.md.
const SCOUT_REF = path.join(
__dirname, '..', 'get-shit-done', 'references', 'scout-codebase.md',
);
function readDiscussContext() {
// Both files are required after #2551 — fail loudly if either is missing
// rather than silently weakening the regression coverage.
for (const p of [DISCUSS_PHASE, SCOUT_REF]) {
assert.ok(fs.existsSync(p), `Required discuss-phase context source missing: ${p}`);
}
return [DISCUSS_PHASE, SCOUT_REF].map(p => fs.readFileSync(p, 'utf-8')).join('\n');
}
describe('discuss-phase context fixes (#2549, #2550, #2552)', () => {
let src;
test('discuss-phase.md source exists', () => {
assert.ok(fs.existsSync(DISCUSS_PHASE), 'discuss-phase.md must exist');
assert.ok(
fs.existsSync(SCOUT_REF),
'references/scout-codebase.md must exist after #2551 extraction',
);
src = readDiscussContext();
});
// ─── #2549: load_prior_context cap ──────────────────────────────────────
test('#2549: load_prior_context must NOT instruct reading ALL prior CONTEXT.md files', () => {
if (!src) src = readDiscussContext();
assert.ok(
!src.includes('For each CONTEXT.md where phase number < current phase'),
'load_prior_context must not unboundedly read all prior CONTEXT.md files',
);
});
test('#2549: load_prior_context must reference a bounded read (3 phases or DECISIONS-INDEX)', () => {
// Read ONLY the parent file — `src.includes('3')` against the
// concatenated source can be satisfied by unrelated occurrences of "3"
// in scout-codebase.md (e.g., "3-5 most relevant files"), masking a
// regression where the parent drops the bounded-read instruction.
const parent = fs.readFileSync(DISCUSS_PHASE, 'utf-8');
const hasBound = /\b(?:most recent|latest|last|up to)\s+3\b[\s\S]{0,160}\bprior CONTEXT\.md\b/i.test(parent);
const hasIndex = parent.includes('DECISIONS-INDEX.md');
assert.ok(
hasBound || hasIndex,
'load_prior_context must reference a bounded read (e.g., most recent 3 phases) or DECISIONS-INDEX.md',
);
});
// ─── #2550: scout_codebase phase-type selection ──────────────────────────
test('#2550: scout_codebase must not instruct reading all 7 codebase maps', () => {
if (!src) src = readDiscussContext();
assert.ok(
!src.includes('Read the most relevant ones (CONVENTIONS.md, STRUCTURE.md, STACK.md based on phase type)'),
'scout_codebase must not use the old vague "most relevant" instruction without a selection table',
);
});
test('#2550: scout_codebase must include a phase-type-to-maps selection table', () => {
if (!src) src = readDiscussContext();
// The table maps phase types to specific map selections
assert.ok(
src.includes('Phase type') && src.includes('Read these maps'),
'scout_codebase must include a phase-type to map-selection table',
);
// Key phase types must be covered
assert.ok(src.includes('UI') || src.includes('frontend'), 'Table must cover UI/frontend phases');
assert.ok(src.includes('Backend') || src.includes('API'), 'Table must cover backend phases');
assert.ok(src.includes('Testing'), 'Table must cover testing phases');
assert.ok(src.includes('Mixed'), 'Table must have a fallback for mixed/unclear phases');
});
// ─── #2552: no split reads ───────────────────────────────────────────────
test('#2552: scout_codebase must explicitly prohibit split reads of the same file', () => {
if (!src) src = readDiscussContext();
const prohibitsSplit = src.includes('split reads') || src.includes('split read');
assert.ok(
prohibitsSplit,
'scout_codebase must explicitly warn against split reads (same file, two offsets) that break prompt cache',
);
});
});