f30da8326a
* feat(#2492): add gates ensuring discuss-phase decisions are translated and verified Two gates close the loop between CONTEXT.md `<decisions>` and downstream work, fixing #2492: - Plan-phase **translation gate** (BLOCKING). After requirements coverage, refuses to mark a phase planned when a trackable decision is not cited (by id `D-NN` or by 6+-word phrase) in any plan's `must_haves`, `truths`, or body. Failure message names each missed decision with id, category, text, and remediation paths. - Verify-phase **validation gate** (NON-BLOCKING). Searches plans, SUMMARY.md, files modified, and recent commit subjects for each trackable decision. Misses are written to VERIFICATION.md as a warning section but do not change verification status. Asymmetry is deliberate — fuzzy-match miss should not fail an otherwise green phase. Shared helper `parseDecisions()` lives in `sdk/src/query/decisions.ts` so #2493 can consume the same parser. Decisions opt out of both gates via `### Claude's Discretion` heading or `[informational]` / `[folded]` / `[deferred]` tags. Both gates skip silently when `workflow.context_coverage_gate=false` (default `true`). Closes #2492 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(#2492): make plan-phase decision gate actually block (review F1, F8, F9, F10, F15) - F1: replace `${context_path}` with `${CONTEXT_PATH}` in the plan-phase gate snippet so the BLOCKING gate receives a non-empty path. The variable was defined in Step 4 (`CONTEXT_PATH=$(_gsd_field "$INIT" ...)`) and the gate snippet referenced the lowercase form, leaving the gate to run with an empty path argument and silently skip. - F15: wrap the SDK call with `jq -e '.data.passed == true' || exit 1` so failure halts the workflow instead of being printed and ignored. The verify-phase counterpart deliberately keeps no exit-1 (non-blocking by design) and now carries an inline note documenting the asymmetry. - F10: tag the JSON example fence as `json` and the options-list fence as `text` (MD040). - F8/F9: anchor the heading-presence test regexes to `^## 13[a-z]?\\.` so prose substrings like "Requirements Coverage Gate" mentioned in body text cannot satisfy the assertion. Added two new regression tests (variable-name match, exit-1 guard) so a future revert is caught. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(#2492): tighten decision-coverage gates against false positives and config drift (review F3,F4,F5,F6,F7,F16,F18,F19) - F3: forward `workstream` arg through both gate handlers so workstream-scoped `workflow.context_coverage_gate=false` actually skips. Added negative test that creates a workstream config disabling the gate while the root config has it enabled and asserts the workstream call is skipped. - F4: restrict the plan-phase haystack to designated sections — front-matter `must_haves` / `truths` / `objective` plus body sections under headings matching `must_haves|truths|tasks|objective`. HTML comments and fenced code blocks are stripped before extraction so a commented-out citation or a literal example never counts as coverage. Verify-phase keeps the broader artifact-wide haystack by design (non-blocking). - F5: reject decisions with fewer than 6 normalized words from soft-matching (previously only rejected when the resulting phrase was under 12 chars AFTER slicing — too lenient). Short decisions now require an explicit `D-NN` citation, with regression tests for the boundary. - F6: walk every `*-SUMMARY.md` independently and use `matchAll` with the `/g` flag so multiple `files_modified:` blocks across multiple summaries are all aggregated. Previously only the first block in the concatenated string was parsed, silently dropping later plans' files. - F7: validate every `files_modified` path stays inside `projectDir` after resolution (rejects absolute paths, `../` traversal). Cap each file read at 256 KB. Skipped paths emit a stderr warning naming the entry. - F16: validate `workflow.context_coverage_gate` is boolean in `loadGateConfig`; warn loudly on numeric or other-shaped values and default to ON. Mirrors the schema-vs-loadConfig validation gap from #2609. - F18: bump verify-phase `git log -n` cap from 50 to 200 so longer-running phases are not undercounted. Documented as a precision-vs-recall tradeoff appropriate for a non-blocking gate. - F19: tighten `QueryResult` / `QueryHandler` to be parameterized (`<T = unknown>`). Drops the `as unknown as Record<string, unknown>` casts in the gate handlers and surfaces shape mismatches at compile time for callers that pass a typed `data` value. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(#2492): harden decisions parser and verify-phase glob (review F11,F12,F13,F14,F17,F20) - F11: strip fenced code blocks from CONTEXT.md before searching for `<decisions>` so an example block inside ``` ``` is not mis-parsed. - F12: accept tab-indented continuation lines (previously required a leading space) so decisions split with `\t` continue cleanly. - F13: parse EVERY `<decisions>` block in the file via `matchAll`, not just the first. CONTEXT.md may legitimately carry more than one block. - F14: `decisions.parse` handler now resolves a relative path against `projectDir` — symmetric with the gate handlers — and still accepts absolute paths. - F17: replace `ls "${PHASE_DIR}"/*-CONTEXT.md | head -1` in verify-phase.md with a glob loop (ShellCheck SC2012 fix). Also avoids spawning an extra subprocess and survives filenames with whitespace. - F20: extend the unicode quote-stripping in the discretion-heading match to cover U+2018/2019/201A/201B and the U+201C-F double-quote variants plus backtick, so any rendering of "Claude's Discretion" collapses to the same key. Each fix has a regression test in `decisions.test.ts`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
71 lines
3.1 KiB
TypeScript
71 lines
3.1 KiB
TypeScript
/**
|
|
* Batch workflow config for orchestration decisions (`check.config-gates`).
|
|
*
|
|
* Replaces many repeated `config-get workflow.*` calls with one JSON object.
|
|
* See `.planning/research/decision-routing-audit.md` §3.3.
|
|
*/
|
|
|
|
import { CONFIG_DEFAULTS, loadConfig } from '../config.js';
|
|
import type { QueryHandler } from './utils.js';
|
|
|
|
/** Treat stringly YAML booleans safely (`Boolean('false')` is true — avoid that). */
|
|
function workflowBool(v: unknown, defaultVal: boolean): boolean {
|
|
if (v === undefined || v === null) return defaultVal;
|
|
if (typeof v === 'boolean') return v;
|
|
if (typeof v === 'string') {
|
|
const s = v.toLowerCase().trim();
|
|
if (s === 'false' || s === '0' || s === 'no' || s === 'off') return false;
|
|
if (s === 'true' || s === '1' || s === 'yes' || s === 'on') return true;
|
|
}
|
|
return Boolean(v);
|
|
}
|
|
|
|
/**
|
|
* Merge workflow defaults with project config, then expose stable keys for workflows.
|
|
*/
|
|
export const checkConfigGates: QueryHandler = async (args, projectDir) => {
|
|
const config = await loadConfig(projectDir);
|
|
const wf: Record<string, unknown> = {
|
|
...CONFIG_DEFAULTS.workflow,
|
|
...(config.workflow as unknown as Record<string, unknown>),
|
|
};
|
|
const root = config as Record<string, unknown>;
|
|
const contextWindow =
|
|
typeof root.context_window === 'number' ? root.context_window : 200000;
|
|
|
|
/** Prefer explicit `plan_checker` when present (alias); else `plan_check` (defaults include only the latter). */
|
|
const w = wf as Record<string, unknown>;
|
|
const planCheckFlag = w.plan_checker !== undefined ? w.plan_checker : w.plan_check;
|
|
|
|
const data: Record<string, unknown> = {
|
|
workflow: args[0] ?? null,
|
|
research_enabled: workflowBool(wf.research, true),
|
|
plan_checker_enabled: workflowBool(planCheckFlag, true),
|
|
nyquist_validation: workflowBool(wf.nyquist_validation, true),
|
|
security_enforcement: workflowBool(wf.security_enforcement, true),
|
|
security_asvs_level: wf.security_asvs_level ?? 1,
|
|
security_block_on: wf.security_block_on ?? 'high',
|
|
ui_phase: workflowBool(wf.ui_phase, true),
|
|
ui_safety_gate: workflowBool(wf.ui_safety_gate, true),
|
|
ui_review: workflowBool(wf.ui_review, true),
|
|
text_mode: workflowBool(wf.text_mode, false),
|
|
auto_advance: workflowBool(wf.auto_advance, false),
|
|
auto_chain_active: workflowBool(wf._auto_chain_active, false),
|
|
code_review: workflowBool(wf.code_review, true),
|
|
code_review_depth: wf.code_review_depth ?? 'standard',
|
|
context_window: contextWindow,
|
|
discuss_mode: String(wf.discuss_mode ?? 'discuss'),
|
|
use_worktrees: workflowBool(wf.use_worktrees, true),
|
|
skip_discuss: workflowBool(wf.skip_discuss, false),
|
|
max_discuss_passes: wf.max_discuss_passes ?? 3,
|
|
node_repair: workflowBool(wf.node_repair, true),
|
|
research_before_questions: workflowBool(wf.research_before_questions, false),
|
|
verifier: workflowBool(wf.verifier, true),
|
|
plan_check: workflowBool(planCheckFlag, true),
|
|
subagent_timeout: wf.subagent_timeout ?? CONFIG_DEFAULTS.workflow.subagent_timeout,
|
|
context_coverage_gate: workflowBool(wf.context_coverage_gate, true),
|
|
};
|
|
|
|
return { data };
|
|
};
|