6a5fa59129
* feat(3081): auto-trim review prompts for small-context model reviewers Adds review.max_prompt_tokens and review.max_prompt_tokens_per_reviewer config keys. When configured, the /gsd-review workflow deterministically trims the assembled prompt before sending to each reviewer (drop CONTEXT → RESEARCH → REQUIREMENTS; head-shrink PROJECT.md; tail-truncate PLANs proportionally; reserve disclosure-note tokens upfront). Trim metadata is recorded in REVIEWS.md frontmatter. Reviewer is skipped with a warning if even the minimum review set exceeds the budget. Closes #3081 * fix(3081): register prompt-budget in SDK query registry and update inventory manifest review.md references `gsd-sdk query prompt-budget` at three call sites, but the command had no handler in the SDK registry — failing the registry-integration drift-guard test on all 6 CI matrix legs. Added a native TypeScript SDK handler (sdk/src/query/prompt-budget.ts) that ports the applyBudget logic from the CJS module, registered it in DOMAIN_STATIC_CATALOG, and regenerated docs/INVENTORY-MANIFEST.json to include the new cli_modules/prompt-budget.cjs entry. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3081): bump ws to 8.20.1 and allowlist prompt-budget sibling pair Two additional CI failures after the registry fix: 1. ws moderate CVE (GHSA-58qx-3vcg-4xpx, uninitialized memory disclosure): The advisory covers ws >=8.0.0 <8.20.1. Both root and sdk/package.json pinned ^8.20.0 which resolved to 8.20.0. Bumped both to 8.20.1 to clear the npm audit drift-guard test (bug-3588-npm-audit-clean.test.cjs). 2. lint-shared-module-handsync detected the new prompt-budget.ts / prompt-budget.cjs sibling pair without an allowlist entry. Added a cooperatingSiblings entry to scripts/shared-module-handsync-allowlist.json with classification and justification matching the established pattern. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3081): align prompt-budget skip semantics across CJS and SDK dispatch paths Replace brittle `[ $EXIT -eq 2 ]` guards with `[ $EXIT -ne 0 ]` in all three local-reviewer blocks (Ollama, LM Studio, llama.cpp) in workflows/review.md. Any non-zero exit from prompt-budget now triggers a skip with a descriptive warning — exit 2/11 prints "budget too small", any other non-zero prints "unexpected exit code". This ensures the SDK bridge dispatch path (exit 11 via GSDError(Blocked)) triggers the same skip as the CJS path (exit 2). The SDK handler (sdk/src/query/prompt-budget.ts) already writes both metadata and prompt files before throwing, so no change needed there. The Ollama block also gains the missing OLLAMA_SKIP guard so the reviewer invocation is actually skipped (previously the block only suppressed the OLLAMA_PROMPT_FILE update but still ran the curl invocation). SDK integration path (hardFailed via GSDError(Blocked) → exit 11) is covered by handler unit tests in tests/prompt-budget.test.cjs; no gsd-sdk-*.test.cjs exercising the full bridge dispatch for this command exists yet — that gap remains and is documented here. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix prompt-budget trim ordering and review guard follow-ups * perf: optimize prompt-budget and dedup reviewer trim workflow * fix(3708): drop source-grep theater tests to satisfy lint-no-source-grep All four test files added in commit 2df566ed were pure source-grep theater: they read .cjs / .ts / .md source files and asserted that specific string literals were present or absent. None exercised runtime behaviour. Deleted: - tests/gsd-tools-memory-optimizer.test.cjs — 7 includes() on gsd-tools.cjs - tests/prompt-budget-hotpath-optimizer.test.cjs — includes() on prompt-budget.cjs + .ts - tests/prompt-budget-io-optimizer.test.cjs — includes() on prompt-budget.ts + gsd-tools.cjs - tests/review-workflow-budget-dedup.test.cjs — includes() on review.md Behavioural coverage for the prompt-budget feature already exists in tests/prompt-budget.test.cjs and tests/prompt-budget-cli.test.cjs (also added by this PR). No replacement tests needed. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(3708): correct budget-pressure threshold and minSet accounting Two bugs in applyBudget caused premature trimming and false hard-fails: 1. UNNEEDED_TRIM: budgetUnderPressure compared baseTokens against effectiveBudget - NOTE_RESERVE_TOKENS, triggering trim pressure 80 tokens before the budget was actually exceeded. Fix: compare against effectiveBudget directly; NOTE_RESERVE_TOKENS are still reserved in contentBudget once real pressure is confirmed. 2. FALSE_HARDFAIL: minSet included NOTE_RESERVE_TOKENS unconditionally, treating the note as mandatory even when no trim would occur and no note would be injected. Fix: exclude NOTE_RESERVE_TOKENS from minSet; a prompt that fits untrimmed needs no note and must not hard-fail. Both fixes applied in CJS and TypeScript implementations. Two regression tests added (cycles 11 and 12) that reproduce each case behaviorally. --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
75 lines
3.0 KiB
JSON
75 lines
3.0 KiB
JSON
{
|
|
"name": "@gsd-build/sdk",
|
|
"version": "1.50.0-canary.0",
|
|
"description": "GSD SDK — programmatic interface for running GSD plans via the Agent SDK",
|
|
"type": "module",
|
|
"main": "dist/index.js",
|
|
"types": "dist/index.d.ts",
|
|
"exports": {
|
|
".": {
|
|
"import": "./dist/index.js",
|
|
"types": "./dist/index.d.ts"
|
|
}
|
|
},
|
|
"bin": {
|
|
"gsd-sdk": "./dist/cli.js"
|
|
},
|
|
"files": [
|
|
"dist",
|
|
"shared",
|
|
"prompts"
|
|
],
|
|
"repository": {
|
|
"type": "git",
|
|
"url": "git+https://github.com/gsd-build/get-shit-done.git",
|
|
"directory": "sdk"
|
|
},
|
|
"homepage": "https://github.com/gsd-build/get-shit-done/tree/main/sdk",
|
|
"bugs": {
|
|
"url": "https://github.com/gsd-build/get-shit-done/issues"
|
|
},
|
|
"author": "TÂCHES",
|
|
"license": "MIT",
|
|
"engines": {
|
|
"node": ">=22.0.0"
|
|
},
|
|
"scripts": {
|
|
"build": "tsc",
|
|
"check:alias-drift": "npm run build && node scripts/check-command-aliases-fresh.mjs",
|
|
"gen:state-document": "npm run build && npx tsx scripts/gen-state-document.ts",
|
|
"check:state-document-fresh": "npm run build && node scripts/check-state-document-fresh.mjs",
|
|
"gen:configuration": "npm run build && node scripts/gen-configuration.mjs",
|
|
"check:configuration-fresh": "npm run build && node scripts/check-configuration-fresh.mjs",
|
|
"gen:workstream-inventory-builder": "npm run build && node scripts/gen-workstream-inventory-builder.mjs",
|
|
"check:workstream-inventory-builder-fresh": "npm run build && node scripts/check-workstream-inventory-builder-fresh.mjs",
|
|
"gen:project-root": "npm run build && node scripts/gen-project-root.mjs",
|
|
"check:project-root-fresh": "npm run build && node scripts/check-project-root-fresh.mjs",
|
|
"gen:plan-scan": "npm run build && node scripts/gen-plan-scan.mjs",
|
|
"check:plan-scan-fresh": "npm run build && node scripts/check-plan-scan-fresh.mjs",
|
|
"gen:secrets": "npm run build && node scripts/gen-secrets.mjs",
|
|
"check:secrets-fresh": "npm run build && node scripts/check-secrets-fresh.mjs",
|
|
"gen:schema-detect": "npm run build && node scripts/gen-schema-detect.mjs",
|
|
"check:schema-detect-fresh": "npm run build && node scripts/check-schema-detect-fresh.mjs",
|
|
"gen:decisions": "npm run build && node scripts/gen-decisions.mjs",
|
|
"check:decisions-fresh": "npm run build && node scripts/check-decisions-fresh.mjs",
|
|
"gen:workstream-name-policy": "npm run build && node scripts/gen-workstream-name-policy.mjs",
|
|
"check:workstream-name-policy-fresh": "npm run build && node scripts/check-workstream-name-policy-fresh.mjs",
|
|
"prepublishOnly": "rm -rf dist && tsc && chmod +x dist/cli.js",
|
|
"test": "vitest run",
|
|
"test:unit": "vitest run --project unit",
|
|
"test:integration": "vitest run --project integration"
|
|
},
|
|
"dependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "^0.2.84",
|
|
"synckit": "^0.11.12",
|
|
"ws": "8.20.1"
|
|
},
|
|
"devDependencies": {
|
|
"@types/node": "^22.0.0",
|
|
"@types/ws": "^8.18.1",
|
|
"tsx": "^4.22.0",
|
|
"typescript": "^5.7.0",
|
|
"vitest": "^3.1.1"
|
|
}
|
|
}
|