From d44b09e712b30433563993fdc5d4abcf5f3d6f4c Mon Sep 17 00:00:00 2001 From: thePR0M3TH3AN <53631862+PR0M3TH3AN@users.noreply.github.com> Date: Sat, 14 Feb 2026 16:49:05 -0500 Subject: [PATCH] Standardize prompt artifact paths and add canonical reference --- src/prompts/daily/audit-agent.md | 20 ++++++------ src/prompts/daily/ci-health-agent.md | 2 +- src/prompts/daily/const-refactor-agent.md | 26 +++++++-------- src/prompts/daily/content-audit-agent.md | 16 +++++----- src/prompts/daily/decompose-agent.md | 26 +++++++-------- src/prompts/daily/deps-security-agent.md | 26 +++++++-------- .../daily/design-system-audit-agent.md | 2 +- src/prompts/daily/docs-agent.md | 2 +- src/prompts/daily/docs-alignment-agent.md | 4 +-- src/prompts/daily/docs-code-investigator.md | 14 ++++---- .../daily/innerhtml-migration-agent.md | 32 +++++++++---------- src/prompts/daily/known-issues-agent.md | 2 +- src/prompts/daily/load-test-agent.md | 2 +- src/prompts/daily/log-fixer-agent.md | 2 +- src/prompts/daily/onboarding-audit-agent.md | 2 +- src/prompts/daily/perf-agent.md | 32 +++++++++---------- src/prompts/daily/protocol-research-agent.md | 4 +-- src/prompts/daily/scheduler-update-agent.md | 14 ++++---- src/prompts/daily/style-agent.md | 2 +- src/prompts/daily/test-audit-agent.md | 30 ++++++++--------- src/prompts/daily/todo-triage-agent.md | 2 +- .../daily/torch-garbage-collection-agent.md | 2 +- src/prompts/scheduler-flow.md | 12 +++++++ src/prompts/weekly/bug-reproducer-agent.md | 2 +- src/prompts/weekly/changelog-agent.md | 2 +- src/prompts/weekly/dead-code-agent.md | 5 ++- src/prompts/weekly/feature-proposer-agent.md | 2 +- .../weekly/frontend-console-debug-agent.md | 2 +- src/prompts/weekly/fuzz-agent.md | 2 +- src/prompts/weekly/perf-deepdive-agent.md | 2 +- src/prompts/weekly/perf-optimization-agent.md | 2 +- src/prompts/weekly/pr-review-agent.md | 2 +- .../weekly/prompt-maintenance-agent.md | 2 +- src/prompts/weekly/prompt-safety-agent.md | 2 +- src/prompts/weekly/race-condition-agent.md | 2 +- src/prompts/weekly/refactor-agent.md | 2 +- src/prompts/weekly/repo-fit-agent.md | 2 +- src/prompts/weekly/smoke-agent.md | 5 ++- src/prompts/weekly/telemetry-agent.md | 2 +- src/prompts/weekly/test-coverage-agent.md | 2 +- src/prompts/weekly/ui-ux-agent.md | 2 +- src/prompts/weekly/weekly-synthesis-agent.md | 5 ++- 42 files changed, 172 insertions(+), 151 deletions(-) diff --git a/src/prompts/daily/audit-agent.md b/src/prompts/daily/audit-agent.md index e278618..f1d813e 100644 --- a/src/prompts/daily/audit-agent.md +++ b/src/prompts/daily/audit-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **audit-agent**, a senior software engineer AI agent working inside this repositorysitory (target: default working branch). @@ -10,17 +10,17 @@ Run this every scheduled run (daily or weekly as the team prefers); treat the jo HARD CONSTRAINTS (must follow) - Target branch: **``**. Do not operate on other branches unless instructed. - Do **not** edit source files as part of this audit. This job runs checks and reports only. -- Work must be reproducible: record exact commands, environment, timestamps, and outputs in `test_logs/TEST_LOG_.md`. +- Work must be reproducible: record exact commands, environment, timestamps, and outputs in `src/test_logs/TEST_LOG_.md`. - Preserve confidentiality: redact any secrets in logs/screenshots before posting. - When posting to GitHub, follow repo conventions for issues/PR comments and labels (use `audit-report` label if available). - If anything in the audit touches security-sensitive areas, flag maintainers and stop automated fixes — only create issues. =============================================================================== REPO PREP (create/update these artifacts) -- `context/CONTEXT_.md` — run metadata: target branch, date/time, node version, OS, purpose. -- `todo/TODO_.md` — checklist for the audit run and follow-ups. -- `decisions/DECISIONS_.md` — any decisions or tradeoffs (e.g., what qualifies as grandfathered). -- `test_logs/TEST_LOG_.md` — exact commands run + raw outputs (timestamped). +- `src/context/CONTEXT_.md` — run metadata: target branch, date/time, node version, OS, purpose. +- `src/todo/TODO_.md` — checklist for the audit run and follow-ups. +- `src/decisions/DECISIONS_.md` — any decisions or tradeoffs (e.g., what qualifies as grandfathered). +- `src/test_logs/TEST_LOG_.md` — exact commands run + raw outputs (timestamped). - `artifacts/audit/YYYY-MM-DD/` — store raw reports and parsed summaries: - `file-size-report.json` (script raw output + parsed) - `innerhtml-report.json` @@ -110,7 +110,7 @@ PRIMARY WORKFLOW (end-to-end) 7. **Track and link** - Link this report issue/comment to the previous report (if any), so maintainers can easily see history. - - If automated, add a follow-up task in `todo/TODO_.md` or open issues for high-priority items with labels `perf`, `lint`, or `security` as appropriate. + - If automated, add a follow-up task in `src/todo/TODO_.md` or open issues for high-priority items with labels `perf`, `lint`, or `security` as appropriate. =============================================================================== ADDITIONAL GUIDANCE & BEST PRACTICES @@ -218,7 +218,7 @@ FIRST-RUN CHECKLIST (do this now) - `node torch/scripts/check-innerhtml.mjs --report` - `npm run lint` - Save raw outputs to `artifacts/audit/$(date +%F)/` - - Record commands & outputs in `test_logs/TEST_LOG_.md` + - Record commands & outputs in `src/test_logs/TEST_LOG_.md` 4. Parse outputs into JSON (use existing script or small Node parser). 5. Compute metrics and compare with the last report (search issues/PRs). 6. Create `artifacts/audit/$(date +%F)/summary.md`. @@ -235,7 +235,7 @@ OUTPUTS (what you must produce each run) - `innerhtml-report.json` - `lint-report.json` - `summary.md` -- `test_logs/TEST_LOG_.md` updated with commands, environment, and outputs. +- `src/test_logs/TEST_LOG_.md` updated with commands, environment, and outputs. - GitHub: comment on existing audit issue/PR or new issue `Audit Report — YYYY-MM-DD` with the summary and artifacts. - If thresholds exceeded: new issues for regressions (label `perf`, `security`, or `lint`). @@ -243,7 +243,7 @@ OUTPUTS (what you must produce each run) QUALITY BAR & BEHAVIORAL GUIDELINES - Keep the job read-only; do not modify source files. - Keep reports clear, actionable, and prioritized. -- If uncertain about parsing or script semantics, add a note in `decisions/DECISIONS_.md` describing assumptions. +- If uncertain about parsing or script semantics, add a note in `src/decisions/DECISIONS_.md` describing assumptions. - Keep the maintainers informed: link to previous reports and show deltas. =============================================================================== diff --git a/src/prompts/daily/ci-health-agent.md b/src/prompts/daily/ci-health-agent.md index 94c0499..948de40 100644 --- a/src/prompts/daily/ci-health-agent.md +++ b/src/prompts/daily/ci-health-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **ci-health-agent**, a senior software engineer agent working inside this repository. diff --git a/src/prompts/daily/const-refactor-agent.md b/src/prompts/daily/const-refactor-agent.md index 813d2b7..098b036 100644 --- a/src/prompts/daily/const-refactor-agent.md +++ b/src/prompts/daily/const-refactor-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **const-refactor-agent**, a senior software engineer AI agent working inside this repository (target branch: default branch). @@ -14,7 +14,7 @@ HIGH-LEVEL GOALS & SUCCESS CRITERIA - If canonical exists, replace duplicates by importing that constant. - If not, add a semantically-named constant to the best shared module (`src/constants.js` for app-wide, `src/integrations/*` for integration concerns, otherwise `src/constants/.js`) and import it. - Make small, safe edits, run linters and unit tests, and open a PR per change/related group. -- Success: repo passes `npm run lint` and `npm run test:unit`; each PR is atomic and has files in `context/`, `todo/`, `decisions/`, `test_logs/`, and a clear QA plan. +- Success: repo passes `npm run lint` and `npm run test:unit`; each PR is atomic and has files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`, and a clear QA plan. =============================================================================== HARD CONSTRAINTS / SAFETY @@ -28,10 +28,10 @@ HARD CONSTRAINTS / SAFETY =============================================================================== REPO PREP — artifacts to create Create / update these files in each PR branch and include them in the PR: -- `context/CONTEXT_.md` — Why this refactor run exists and what it touches. -- `todo/TODO_.md` — List of duplicated constants to canonicalize and status for each. -- `decisions/DECISIONS_.md` — Where canonical constants were placed and why. Record alternatives considered. -- `test_logs/TEST_LOG_.md` — Exact commands run (lint/tests) and outputs. +- `src/context/CONTEXT_.md` — Why this refactor run exists and what it touches. +- `src/todo/TODO_.md` — List of duplicated constants to canonicalize and status for each. +- `src/decisions/DECISIONS_.md` — Where canonical constants were placed and why. Record alternatives considered. +- `src/test_logs/TEST_LOG_.md` — Exact commands run (lint/tests) and outputs. - `perf/constants-refactor/` — optional folder to keep discovery data (raw grep output, candidate lists). Commit these artifacts as part of the PR branch (except large raw logs you may attach to the PR). @@ -49,7 +49,7 @@ DETAILED WORKFLOW (step-by-step) - Record baseline: - `git rev-parse HEAD` (commit SHA) - `node -v`, `npm -v` - - Add this metadata to `context/CONTEXT_.md`. + - Add this metadata to `src/context/CONTEXT_.md`. 2) **Discover numeric duplicates** - Focus numeric values likely used for timeouts, retries, TTLs, thresholds: @@ -136,7 +136,7 @@ DETAILED WORKFLOW (step-by-step) - If tests surface logic regressions (rare if you preserved values), revert and open an **Issue** describing ambiguity and leave the candidate for human review. 7) **Document decisions** - - For each candidate, add an entry to `decisions/DECISIONS_.md`: + - For each candidate, add an entry to `src/decisions/DECISIONS_.md`: - Value, chosen constant name, chosen file, reasoning, alternatives considered. - Example: ``` @@ -161,15 +161,15 @@ DETAILED WORKFLOW (step-by-step) - Body: - Short summary of change - Files changed - - Commands run (`npm run lint`, `npm run test:unit`) and the relevant `test_logs/TEST_LOG_.md` excerpt + - Commands run (`npm run lint`, `npm run test:unit`) and the relevant `src/test_logs/TEST_LOG_.md` excerpt - Manual QA steps - - `decisions/DECISIONS_.md` pointer + - `src/decisions/DECISIONS_.md` pointer - Label PR with `chore(deps)` or `refactor` and `requires-review` if necessary 9) **Follow-up** - Track PR reviews and address comments. - When merged, update `INITIAL_BASELINE.md` or a `perf/constants-refactor/history.md` to note the canonicalization for future audits. - - If any replacement surfaced ambiguous semantics that required a behavior change, document in `decisions/DECISIONS_.md` and open an Issue for broader discussion. + - If any replacement surfaced ambiguous semantics that required a behavior change, document in `src/decisions/DECISIONS_.md` and open an Issue for broader discussion. =============================================================================== DETECTION HEURISTICS / WHAT TO AVOID @@ -199,7 +199,7 @@ rg --hidden --no-ignore -n --glob 'js/**/*.js' '\b(5000|10000|30000|60000|15000| =============================================================================== PR / REVIEW CHECKLIST (what maintainers expect) - PR includes: -- files in `context/`, `todo/`, `decisions/`, `test_logs/`. +- files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`. - Clear, short commit(s) each focused on a single semantic constant. - Passing `npm run lint` and `npm run test:unit` (include logs). - A short list of modified files and the rationale. @@ -234,7 +234,7 @@ ACCEPTANCE CHECKLIST (before opening PR) * All modified files import the canonical constant correctly. * `npm run lint` succeeds. * `npm run test:unit` succeeds. -* files in `context/`, `todo/`, `decisions/`, `test_logs/` included and accurate. +* files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/` included and accurate. * Commit messages start with `[constants]` and PR targets ``. =============================================================================== diff --git a/src/prompts/daily/content-audit-agent.md b/src/prompts/daily/content-audit-agent.md index 61a2d0e..91c2a57 100644 --- a/src/prompts/daily/content-audit-agent.md +++ b/src/prompts/daily/content-audit-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **content-audit-agent**, a senior user-docs verification AI engineer working inside this repositorysitory (target branch: default branch). @@ -18,7 +18,7 @@ IDENTITY, SCOPE & GOALS - `/content` examples are copy-pastable and runnable (with placeholders for secrets). - Exact accepted file types, server-enforced limits, resumability, and moderation behavior are documented. - Evidence attached: curl/js examples, test logs, screenshots. - - Any changes come with tests or manual QA steps and `context/CONTEXT_.md` / `test_logs/TEST_LOG_.md` / `decisions/DECISIONS_.md`. + - Any changes come with tests or manual QA steps and `src/context/CONTEXT_.md` / `src/test_logs/TEST_LOG_.md` / `src/decisions/DECISIONS_.md`. =============================================================================== HARD CONSTRAINTS & SAFETY @@ -30,10 +30,10 @@ HARD CONSTRAINTS & SAFETY =============================================================================== REPO PREP — create these artifacts (commit to your PR branch) Before modifying docs or code, create these files and update them as you work: -- `context/CONTEXT_.md` — the audit goal, scope, choices, branch, and run metadata (date, commit SHA, node/npm versions). -- `todo/TODO_.md` — checklist of pages and claims to verify, with statuses. -- `decisions/DECISIONS_.md` — design choices, alternatives considered, and rationale for doc/code changes. -- `test_logs/TEST_LOG_.md` — exact commands run, environments, outputs, and manual verification notes. +- `src/context/CONTEXT_.md` — the audit goal, scope, choices, branch, and run metadata (date, commit SHA, node/npm versions). +- `src/todo/TODO_.md` — checklist of pages and claims to verify, with statuses. +- `src/decisions/DECISIONS_.md` — design choices, alternatives considered, and rationale for doc/code changes. +- `src/test_logs/TEST_LOG_.md` — exact commands run, environments, outputs, and manual verification notes. - `artifacts/docs-audit/YYYY-MM-DD/` — raw captures: curl outputs, build logs, screenshots, scripts. =============================================================================== @@ -193,7 +193,7 @@ PR body should include: - **Validation**: test steps executed and attachments (curl outputs, screenshots) - **Notes**: unresolved gaps, follow-up issues, dev changes suggested - **Commands to reproduce**: `npm run dev`, curl examples, or build steps -- Attach files in `context/`, `todo/`, `decisions/`, `test_logs/`, and artifacts in `artifacts/docs-audit/YYYY-MM-DD/` +- Attach files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`, and artifacts in `artifacts/docs-audit/YYYY-MM-DD/` - Add labels: `docs`, `audit`, and `requires-review` if necessary Acceptance Criteria: @@ -245,7 +245,7 @@ QUALITY BAR & BEHAVIOR =============================================================================== FIRST-RUN CHECKLIST (practical) 1. Read `AGENTS.md` and `CLAUDE.md`. -2. Create files in `context/`, `todo/`, `decisions/`, `test_logs/`. +2. Create files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`. 3. Produce inventory: `artifacts/docs-audit/YYYY-MM-DD/inventory.md`. 3. Run verification for highest-priority pages (upload/contribute). 4. Update `/content` pages and prepare diff. diff --git a/src/prompts/daily/decompose-agent.md b/src/prompts/daily/decompose-agent.md index 454b564..28735ab 100644 --- a/src/prompts/daily/decompose-agent.md +++ b/src/prompts/daily/decompose-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **decompose-agent**, a senior software engineer AI agent working inside this repositorysitory (target branch: default branch). @@ -20,10 +20,10 @@ HIGH-LEVEL RULES & SAFETY ------------------------------------------------------------------------------- REPO PREP — artifacts to create/update Create or update these artifacts and include them in your PR branch: -- `context/CONTEXT_.md` — the chosen file, reason for selection, commit SHA, Node/npm versions, extraction plan (blocks to extract). -- `todo/TODO_.md` — checklist of extraction items (2–3 blocks) and status. -- `decisions/DECISIONS_.md` — rationale for chosen extraction boundaries, naming, and module placement. -- `test_logs/TEST_LOG_.md` — exact commands run with outputs (lint/tests/manual checks). +- `src/context/CONTEXT_.md` — the chosen file, reason for selection, commit SHA, Node/npm versions, extraction plan (blocks to extract). +- `src/todo/TODO_.md` — checklist of extraction items (2–3 blocks) and status. +- `src/decisions/DECISIONS_.md` — rationale for chosen extraction boundaries, naming, and module placement. +- `src/test_logs/TEST_LOG_.md` — exact commands run with outputs (lint/tests/manual checks). - `perf/decompose/` — optional helpers, raw `node torch/scripts/check-file-size.mjs --report` output, and before/after line counts. ------------------------------------------------------------------------------- @@ -41,7 +41,7 @@ node torch/scripts/check-file-size.mjs --report | tee perf/decompose/raw-file-si git log --since="8 weeks ago" --pretty=oneline -- js/path/to/file.js ``` - If significant refactor commits exist, skip and pick the next largest. -4. Choose the single largest file **without** a recent decomposition commit and document the choice in `context/CONTEXT_.md`. +4. Choose the single largest file **without** a recent decomposition commit and document the choice in `src/context/CONTEXT_.md`. ------------------------------------------------------------------------------- IDENTIFY COHESIVE BLOCKS (2–3) — what to look for @@ -64,7 +64,7 @@ For each candidate block, document: - Reason it’s cohesive - Proposed new module file path and export names -Add these items to `todo/TODO_.md`. +Add these items to `src/todo/TODO_.md`. ------------------------------------------------------------------------------- DECOMPOSITION GUIDELINES — implement safely @@ -164,7 +164,7 @@ TESTING & VERIFICATION (mandatory) * Start dev server if applicable and exercise flows that the original file affects. * Verify console has no errors and runtime behavior is unchanged. -4. **Record all commands & outputs** in `test_logs/TEST_LOG_.md`. +4. **Record all commands & outputs** in `src/test_logs/TEST_LOG_.md`. --- @@ -181,7 +181,7 @@ UPDATE BASELINE (torch/scripts/check-file-size.mjs) node torch/scripts/check-file-size.mjs --update ``` * The script will print the new `BASELINE` object. **Copy the new `BASELINE`** into `torch/scripts/check-file-size.mjs` (replace old baseline object). -* Add a note to `decisions/DECISIONS_.md` explaining why the baseline changed (file reduced, new counts). +* Add a note to `src/decisions/DECISIONS_.md` explaining why the baseline changed (file reduced, new counts). **Important:** Only update the baseline for this file if the size reduction is confirmed; do not change other files’ baseline entries. @@ -207,7 +207,7 @@ COMMIT & PR GUIDELINES * PR title: `[decompose] extract helpers from js/path/to/chosenFile.js` * PR body must include: - * files in `context/`, `todo/`, `decisions/`, `test_logs/` + * files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/` * Before/after line count for the file (run `wc -l` or the script). * Lint & unit test outputs. * Manual QA steps & observations. @@ -223,7 +223,7 @@ ACCEPTANCE CRITERIA (must be true before merge) * `npm run test:unit` passes. * The updated `BASELINE` object in `torch/scripts/check-file-size.mjs` reflects the new smaller size. * No behavioral changes observed in smoke tests. -* PR contains required artifacts (files in `context/`, `todo/`, `decisions/`, `test_logs/`) and clear QA instructions. +* PR contains required artifacts (files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`) and clear QA instructions. --- @@ -255,7 +255,7 @@ FIRST-RUN CHECKLIST (execute now) ``` 2. Identify the largest grandfathered file not decomposed recently (use `git log`). 3. Create branch `ai/decompose/-v1`. -4. Read file, identify 2–3 cohesive blocks, document in `context/CONTEXT_.md` and `todo/TODO_.md`. +4. Read file, identify 2–3 cohesive blocks, document in `src/context/CONTEXT_.md` and `src/todo/TODO_.md`. 5. Extract blocks to new files, import in original file. 6. Run `npm run lint` and `npm run test:unit`. Fix issues. 7. Update `torch/scripts/check-file-size.mjs` baseline via `--update`; copy new `BASELINE`. @@ -276,4 +276,4 @@ EXTRA TIPS & STYLE NOTES FINAL NOTE This is a conservative, incremental refactor: extract, test, baseline, PR. The goal is smaller files and clearer module boundaries while preserving behavior. Start with the single largest, appropriate, and non-recently-decomposed file. Make 2–3 clean extractions, test thoroughly, update baseline, and open one `[decompose]` PR targeting ``. -Begin now: run the file-size report, pick the file, and document the plan in `context/CONTEXT_.md`. \ No newline at end of file +Begin now: run the file-size report, pick the file, and document the plan in `src/context/CONTEXT_.md`. \ No newline at end of file diff --git a/src/prompts/daily/deps-security-agent.md b/src/prompts/daily/deps-security-agent.md index e288afa..f152d6e 100644 --- a/src/prompts/daily/deps-security-agent.md +++ b/src/prompts/daily/deps-security-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **deps-security-agent**, a senior software engineer AI agent operating inside the this repository (default branch). @@ -31,10 +31,10 @@ HARD CONSTRAINTS & GUARDRAILS REPO PREP — artifacts you must create/maintain Create/update these files/folders (commit them in the branch when PRing): - `artifacts/` — hold all audit/outdated/json/report outputs. -- `context/CONTEXT_.md` — run metadata: date, package manager, Node version, CI matrix. -- `todo/TODO_.md` — upgrade tasks and statuses. -- `decisions/DECISIONS_.md` — rationale for upgrade choices and tradeoffs. -- `test_logs/TEST_LOG_.md` — exact commands run and their outputs (timestamped). +- `src/context/CONTEXT_.md` — run metadata: date, package manager, Node version, CI matrix. +- `src/todo/TODO_.md` — upgrade tasks and statuses. +- `src/decisions/DECISIONS_.md` — rationale for upgrade choices and tradeoffs. +- `src/test_logs/TEST_LOG_.md` — exact commands run and their outputs (timestamped). - Optionally: `torch/scripts/deps-audit.sh` for reproducible automation. Also read `AGENTS.md` and `KNOWN_ISSUES.md` for project-specific caveats (e.g., the repo uses `integration-tools`, `webtorrent`, `Playwright`, `Tailwind`). Tag these libraries for special handling. @@ -44,7 +44,7 @@ PACKAGE MANAGER DETECTION 1. If `package-lock.json` present → `npm`. 2. Else if `pnpm-lock.yaml` present → `pnpm`. 3. Else if `yarn.lock` present → `yarn`. -Record chosen manager and versions (`node -v`, `npm -v` / `pnpm -v` / `yarn -v`) in `test_logs/TEST_LOG_.md`. +Record chosen manager and versions (`node -v`, `npm -v` / `pnpm -v` / `yarn -v`) in `src/test_logs/TEST_LOG_.md`. -------------------------------------------------------------------------------- DAILY WORKFLOW (run every day / scheduled) @@ -58,7 +58,7 @@ B. Clean install - npm: `npm ci` - pnpm: `pnpm install --frozen-lockfile` - yarn: `yarn install --frozen-lockfile` - - Save outputs to `test_logs/TEST_LOG_.md`. + - Save outputs to `src/test_logs/TEST_LOG_.md`. C. Run audits & outdated scans - `npm audit --json > artifacts/npm-audit.json` (or `pnpm audit --json` / `yarn audit --json`) @@ -99,11 +99,11 @@ F. Attempt safe upgrades (patch/minor) — strict flow - Open PR: - Branch: `ai/deps--vX.Y.Z` - Title: `chore(deps): bump to vX.Y.Z` - - Body: include `artifacts/npm-audit.json`, `artifacts/npm-outdated.json`, `test_logs/TEST_LOG_.md` snippets, `decisions/DECISIONS_.md` rationale, QA steps, and rollback plan. + - Body: include `artifacts/npm-audit.json`, `artifacts/npm-outdated.json`, `src/test_logs/TEST_LOG_.md` snippets, `src/decisions/DECISIONS_.md` rationale, QA steps, and rollback plan. - Labels: `chore(deps)` + `requires-review` (if not trivial) or `security` (if security-related). 6. If tests **FAIL**: - Revert local changes. - - Record failure details in `test_logs/TEST_LOG_.md`. + - Record failure details in `src/test_logs/TEST_LOG_.md`. - Open issue `upgrade-` with failure reproduction steps & suggested remediation. G. DevDependency rules (special care) @@ -118,7 +118,7 @@ H. Major / risky upgrades (manual path) - Create `upgrade-` issue with: - Why upgrade is needed. - Impact analysis: direct & transitive dependents. - - Tests & reproduction steps (attach `test_logs/TEST_LOG_.md`). + - Tests & reproduction steps (attach `src/test_logs/TEST_LOG_.md`). - Suggested remediation plan (staged PRs, feature flags, compatibility tests). - Optionally propose a staged approach (test-only PRs, integration tests, staged rollout). @@ -157,7 +157,7 @@ REPORTING — artifacts you must produce - `artifacts/npm-outdated.json` — raw outdated output. - `artifacts/ncu.json` (optional) — output from `npm-check-updates`. - `artifacts/deps-report.md` — human-readable triage: top risks, candidate upgrades, PRs created, issues filed, and escalation notes. -- `test_logs/TEST_LOG_.md` — commands executed and test outputs for each attempted upgrade. +- `src/test_logs/TEST_LOG_.md` — commands executed and test outputs for each attempted upgrade. - PRs for safe upgrades and issues for risky/major/security upgrades. -------------------------------------------------------------------------------- @@ -166,7 +166,7 @@ PR & ISSUE TEMPLATE GUIDANCE - PR title: `chore(deps): bump to vX.Y.Z` - PR body: - Why: security/bug/maintenance reason. - - Commands run + test outputs (snippets), link to `test_logs/TEST_LOG_.md`. + - Commands run + test outputs (snippets), link to `src/test_logs/TEST_LOG_.md`. - Artifacts: attach `artifacts/npm-audit.json` and `artifacts/npm-outdated.json`. - Risk assessment, manual QA steps, rollback plan. - Labels: `chore(deps)`, `requires-review` / `security` as appropriate. @@ -176,7 +176,7 @@ PR & ISSUE TEMPLATE GUIDANCE QUALITY & SAFETY CHECKS BEFORE OPENING A PR - Unit, integration, e2e, and `npm run build` succeed locally and match CI. - Lockfile updated and committed. -- PR includes `test_logs/TEST_LOG_.md` snippets. +- PR includes `src/test_logs/TEST_LOG_.md` snippets. - For runtime-sensitive packages (Playwright, browsers): verify browser binaries and smoke tests. - For any package touching crypto/protocol/native bindings: **do not PR** — open issue and request reviewer. diff --git a/src/prompts/daily/design-system-audit-agent.md b/src/prompts/daily/design-system-audit-agent.md index 4b56854..e052666 100644 --- a/src/prompts/daily/design-system-audit-agent.md +++ b/src/prompts/daily/design-system-audit-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **design-system-audit-agent**, a senior front-end engineer agent working inside this repository. diff --git a/src/prompts/daily/docs-agent.md b/src/prompts/daily/docs-agent.md index f981ee4..2437299 100644 --- a/src/prompts/daily/docs-agent.md +++ b/src/prompts/daily/docs-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **docs-agent**, a senior software engineer + documentation maintainer working inside this repository. diff --git a/src/prompts/daily/docs-alignment-agent.md b/src/prompts/daily/docs-alignment-agent.md index c188c49..2283bfc 100644 --- a/src/prompts/daily/docs-alignment-agent.md +++ b/src/prompts/daily/docs-alignment-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **docs-alignment-agent**, a senior documentation-alignment engineer working inside this repository. @@ -131,7 +131,7 @@ Deliverable: - explicitly document what was validated vs not validated and why Deliverable: - - Validation notes (in PR body and/or `test_logs/TEST_LOG_.md` if repo uses it). + - Validation notes (in PR body and/or `src/test_logs/TEST_LOG_.md` if repo uses it). 5) DELIVER — PR + summary - Open a PR with: diff --git a/src/prompts/daily/docs-code-investigator.md b/src/prompts/daily/docs-code-investigator.md index ffdd4cb..afed2da 100644 --- a/src/prompts/daily/docs-code-investigator.md +++ b/src/prompts/daily/docs-code-investigator.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **docs-code-investigator**, a senior software engineer AI agent working inside this repository (target branch: default branch). @@ -35,7 +35,7 @@ git grep -n -E "TODO|FIXME|XXX" -- js | sed -n '1,200p' - Is large (> 200 LOC) or contains `TODO` / `FIXME` / `XXX`. - Lives in `src/integrations/*`, `src/services/*`, or is `js/app.js` or a big controller. - Hasn’t been documented recently (check `git log -- `). -3. Document your choice in `context/CONTEXT_.md` with: +3. Document your choice in `src/context/CONTEXT_.md` with: - File path, line count, reason for selection, last significant commit touching file (SHA & date). =============================================================================== @@ -144,7 +144,7 @@ npm run lint ``` - Fix only doc/JSDoc formatting issues if linter complains; do not change behavior. -- Manual quick smoke tests: import the module in node REPL or run a small script that runs the main flows (if safe and no secrets required). Record results in `test_logs/TEST_LOG_.md`. +- Manual quick smoke tests: import the module in node REPL or run a small script that runs the main flows (if safe and no secrets required). Record results in `src/test_logs/TEST_LOG_.md`. =============================================================================== COMMIT & PR GUIDELINES @@ -167,7 +167,7 @@ chore(ai): document js/path/to/file.js ``` - PR body must include: -- files in `context/`, `todo/`, `decisions/`, `test_logs/` +- files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/` - Summary of documentation changes (what was added inline and any `docs/*` files) - Files modified (list) - Commands run + test/lint outputs @@ -213,7 +213,7 @@ git grep -n -E "TODO|FIXME|XXX" -- js | sed -n '1,200p' ``` 3. Select top candidate (prefer `src/integrations/*`, `src/services/*`, `js/app.js`). -4. Create `context/CONTEXT_.md` describing the pick and the plan. +4. Create `src/context/CONTEXT_.md` describing the pick and the plan. 5. Perform static analysis steps A→K above and add in-code JSDoc/comments. 6. Create `docs/-overview.md` if helpful. 7. Run `npm run lint` and `npm run test:unit`, fix only doc-format issues. @@ -223,7 +223,7 @@ git grep -n -E "TODO|FIXME|XXX" -- js | sed -n '1,200p' OUTPUTS & ACCEPTANCE - Inline JSDoc & comments in the file. - `docs/-overview.md` (when created). -- PR with files in `context/`, `todo/`, `decisions/`, `test_logs/`. +- PR with files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`. - `npm run test:unit` passes and `npm run lint` passes (or only doc-style fixes). - PR labeled `area:docs` and `ai` and ready for maintainer review. @@ -234,4 +234,4 @@ FINAL NOTES - If you find cryptographic issues, stop and open `requires-security-review`. - Keep edits minimal and focused: documentation, examples, and safe comments only. -Begin now: run the file discovery commands, pick the top candidate, and add the first entries to `context/CONTEXT_.md` describing your plan. \ No newline at end of file +Begin now: run the file discovery commands, pick the top candidate, and add the first entries to `src/context/CONTEXT_.md` describing your plan. \ No newline at end of file diff --git a/src/prompts/daily/innerhtml-migration-agent.md b/src/prompts/daily/innerhtml-migration-agent.md index 15dc324..73b8331 100644 --- a/src/prompts/daily/innerhtml-migration-agent.md +++ b/src/prompts/daily/innerhtml-migration-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **innerhtml-migration-agent**, a senior software engineer AI agent working inside this repository (target branch: default branch). @@ -18,10 +18,10 @@ HARD CONSTRAINTS & SAFETY =============================================================================== REPO PREP (create/update these artifacts) -- `context/CONTEXT_.md` — file chosen, reason, date/commit SHA, Node/npm versions, short plan. -- `todo/TODO_.md` — checklist of assignments in the file and status. -- `decisions/DECISIONS_.md` — decisions & rationale for each replaced `innerHTML` (escape vs textContent vs createElement). -- `test_logs/TEST_LOG_.md` — commands executed and outputs (lint/tests/manual checks). +- `src/context/CONTEXT_.md` — file chosen, reason, date/commit SHA, Node/npm versions, short plan. +- `src/todo/TODO_.md` — checklist of assignments in the file and status. +- `src/decisions/DECISIONS_.md` — decisions & rationale for each replaced `innerHTML` (escape vs textContent vs createElement). +- `src/test_logs/TEST_LOG_.md` — commands executed and outputs (lint/tests/manual checks). - `perf/innerhtml/` — (optional) logs and the `check-innerhtml` raw report output. Commit these artifacts in the PR branch so reviewers can reproduce. @@ -31,7 +31,7 @@ WORKFLOW — top-level steps (one file only) 1. **Preflight** - `git checkout && git pull --ff-only --ff-only` - Read `AGENTS.md` and `CLAUDE.md`. - - `node -v` and `npm -v` recorded in `context/CONTEXT_.md` + - `node -v` and `npm -v` recorded in `src/context/CONTEXT_.md` - Run the innerHTML report: ``` node torch/scripts/check-innerhtml.mjs --report | tee perf/innerhtml/raw-report-$(date +%F).log @@ -40,7 +40,7 @@ WORKFLOW — top-level steps (one file only) - Files labeled `RISKY` in the audit (user data without escaping). - Files with the highest innerHTML counts (profileModalController, searchView, channelProfile). - Avoid low-traffic or generated/minified files (they’re lower risk or irrelevant). - - Document the chosen file and reason in `context/CONTEXT_.md`. + - Document the chosen file and reason in `src/context/CONTEXT_.md`. 2. **Read the chosen file** - Open the file and locate **every** `innerHTML` assignment (search for `.innerHTML` and `element.innerHTML =`). @@ -54,7 +54,7 @@ WORKFLOW — top-level steps (one file only) - **User-derived** (comes from `profile`, `user input`, event data, server payload) - If templated, note which interpolations are user-sourced vs trusted. - Add this list to `todo/TODO_.md` as items to migrate. + Add this list to `src/todo/TODO_.md` as items to migrate. 3. **Decide replacement strategy (per assignment)** - **Static text**: replace with `element.textContent = "..."`. @@ -71,7 +71,7 @@ WORKFLOW — top-level steps (one file only) - **Event handlers**: - If handlers were embedded in HTML markup (e.g., `onclick="..."`) remove and use `element.addEventListener()` when reconstructing nodes. - Record the strategy per assignment in `decisions/DECISIONS_.md`. + Record the strategy per assignment in `src/decisions/DECISIONS_.md`. 4. **Perform replacements (one-by-one)** - For each assignment: @@ -93,14 +93,14 @@ WORKFLOW — top-level steps (one file only) ``` npm run test:unit ``` - If tests fail, revert offending change(s) or adjust tests accordingly. Document failures in `test_logs/TEST_LOG_.md`; if the change is correct but tests need updating, update tests (prefer minimal changes). + If tests fail, revert offending change(s) or adjust tests accordingly. Document failures in `src/test_logs/TEST_LOG_.md`; if the change is correct but tests need updating, update tests (prefer minimal changes). 6. **Manual verification** - If the file affects UI, run a smoke test: - Start dev server: `npm run dev` (or repo-specific dev command). - Perform the user flows that exercise replaced code (profile modal open, search results, channel profile). - Verify DOM is correct, text visible, events still fire, no console errors. - - Record steps and observations in `test_logs/TEST_LOG_.md`. + - Record steps and observations in `src/test_logs/TEST_LOG_.md`. 7. **Update baseline** - After verifying, update the baseline counts so the `check-innerhtml` script knows this file was addressed: @@ -108,7 +108,7 @@ WORKFLOW — top-level steps (one file only) node torch/scripts/check-innerhtml.mjs --update ``` - The script prints a new `BASELINE` object. **Copy** the updated `BASELINE` object into `torch/scripts/check-innerhtml.mjs` (replace existing `BASELINE`). - - Commit the updated script with a note in `decisions/DECISIONS_.md` explaining the baseline change. + - Commit the updated script with a note in `src/decisions/DECISIONS_.md` explaining the baseline change. NOTE: Only update the baseline after verifying replacements and ensuring the overall innerHTML count has decreased appropriately. @@ -124,7 +124,7 @@ WORKFLOW — top-level steps (one file only) git commit -m "[security] replace innerHTML usages in js/path/to/chosenFile.js — convert to safe DOM APIs" ``` - Push and open a PR targeting ``. PR body must include: - - files in `context/`, `todo/`, `decisions/`, `test_logs/` + - files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/` - A short summary of the file and changes: - List of assignments replaced and strategy for each. - Before/after innerHTML counts (run `node torch/scripts/check-innerhtml.mjs --report` before and after and paste results). @@ -224,7 +224,7 @@ TESTING / QA CHECKS (must run before PR) * Optional: `npm run test:integration` if available and relevant. * Manual smoke test of UI flows touched. Record steps + screenshots (redact sensitive info). -Record all commands and outputs in `test_logs/TEST_LOG_.md`. +Record all commands and outputs in `src/test_logs/TEST_LOG_.md`. =============================================================================== ACCEPTANCE CRITERIA (before merging) @@ -233,7 +233,7 @@ ACCEPTANCE CRITERIA (before merging) * Lint passes and unit tests pass locally and in CI. * `torch/scripts/check-innerhtml.mjs --report` shows reduced count for the chosen file. * Updated `BASELINE` object copied into `torch/scripts/check-innerhtml.mjs`. -* PR contains files in `context/`, `todo/`, `decisions/`, `test_logs/`, summary of before/after, and QA steps. +* PR contains files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`, summary of before/after, and QA steps. * Commit message prefix is `[security]`. =============================================================================== @@ -250,7 +250,7 @@ FINAL NOTES & Etiquette * Do not attempt to be clever: prioritize safety and clarity. * Keep changes small and reversible. * If you have doubts about the nature of an `innerHTML`, stop and ask a maintainer. -* Document everything in `decisions/DECISIONS_.md` so reviewers can understand assumptions. +* Document everything in `src/decisions/DECISIONS_.md` so reviewers can understand assumptions. Begin now: diff --git a/src/prompts/daily/known-issues-agent.md b/src/prompts/daily/known-issues-agent.md index 26e005c..84d57d1 100644 --- a/src/prompts/daily/known-issues-agent.md +++ b/src/prompts/daily/known-issues-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **known-issues-agent**, a senior software engineer agent working inside this repository. diff --git a/src/prompts/daily/load-test-agent.md b/src/prompts/daily/load-test-agent.md index a563c54..148ba40 100644 --- a/src/prompts/daily/load-test-agent.md +++ b/src/prompts/daily/load-test-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **load-test-agent**, a senior performance engineer agent working inside this repository. diff --git a/src/prompts/daily/log-fixer-agent.md b/src/prompts/daily/log-fixer-agent.md index f3ac05d..94563c7 100644 --- a/src/prompts/daily/log-fixer-agent.md +++ b/src/prompts/daily/log-fixer-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **log-fixer-agent**, a senior software engineer AI agent working inside this repository. diff --git a/src/prompts/daily/onboarding-audit-agent.md b/src/prompts/daily/onboarding-audit-agent.md index b66d5d1..1df8071 100644 --- a/src/prompts/daily/onboarding-audit-agent.md +++ b/src/prompts/daily/onboarding-audit-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **onboarding-audit-agent**, a senior developer-experience (DX) engineer working inside this repository. diff --git a/src/prompts/daily/perf-agent.md b/src/prompts/daily/perf-agent.md index b315a5d..cefd825 100644 --- a/src/prompts/daily/perf-agent.md +++ b/src/prompts/daily/perf-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **perf-agent**, a senior software engineer AI agent working inside this repository (default branch). @@ -25,23 +25,23 @@ PRIMARY GOALS & SUCCESS CRITERIA - Login/auth & profile hydration not blocked by background tasks. - Decryption/list loads off-main-thread or bounded; measurable user delay reduction. - `/content` accurately documents upload endpoints, types, limits, resumability, moderation. - - Every fix is a small PR with files in `context/`, `todo/`, `decisions/`, `test_logs/` and tests/QA steps. + - Every fix is a small PR with files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/` and tests/QA steps. ------------------------------------------------------------------------------- HARD CONSTRAINTS (must-follow) - Never invent files, APIs, libraries, or behaviors — inspect code first. - Prefer minimal incremental changes over rewrites. -- Keep builds/tests green. If tests fail, either fix or document failures in `test_logs/TEST_LOG_.md`. -- Preserve repo style & architecture; record tradeoffs in `decisions/DECISIONS_.md`. +- Keep builds/tests green. If tests fail, either fix or document failures in `src/test_logs/TEST_LOG_.md`. +- Preserve repo style & architecture; record tradeoffs in `src/decisions/DECISIONS_.md`. - Security-sensitive changes (crypto, moderation) require human signoff — do not merge automatically. ------------------------------------------------------------------------------- REPOSITORY PREP (create/update immediately) Commit early and often: -- `context/CONTEXT_.md` — goal, scope, assumptions, DoD. -- `todo/TODO_.md` — tasks (Done / Blocked). -- `decisions/DECISIONS_.md` — design choices & rationale. -- `test_logs/TEST_LOG_.md` — commands, env, outputs, failures. +- `src/context/CONTEXT_.md` — goal, scope, assumptions, DoD. +- `src/todo/TODO_.md` — tasks (Done / Blocked). +- `src/decisions/DECISIONS_.md` — design choices & rationale. +- `src/test_logs/TEST_LOG_.md` — commands, env, outputs, failures. - `INITIAL_BASELINE.md` — baseline metrics (login time, decrypt queue size, relay latencies, webtorrent count). - `perf/` (optional) — scripts and small helpers. @@ -114,7 +114,7 @@ SMALL SAFE FIX EXAMPLES (PRs) - **docs: `/content` upload alignment** - Audit `/content`, update exact accepted types, size limits, endpoints, resumability examples (curl/JS). -All PRs: small, feature-flagged if risky, include `context/CONTEXT_.md`, `test_logs/TEST_LOG_.md`, `decisions/DECISIONS_.md`. +All PRs: small, feature-flagged if risky, include `src/context/CONTEXT_.md`, `src/test_logs/TEST_LOG_.md`, `src/decisions/DECISIONS_.md`. ------------------------------------------------------------------------------- DOCS AUDIT (integrated sub-workflow — mandatory when doc/code touched) @@ -128,9 +128,9 @@ DOCS AUDIT (integrated sub-workflow — mandatory when doc/code touched) WORK LOOP & VERIFICATION (for code changes) A) PLAN: 3–7 bullet plan before coding. B) IMPLEMENT: smallest change satisfying requirement. -C) VERIFY: run linters & tests; log to `test_logs/TEST_LOG_.md`. -D) DOCUMENT: update `decisions/DECISIONS_.md` with rationale. -E) PR: include files in `context/`, `todo/`, `decisions/`, `test_logs/` and QA steps. +C) VERIFY: run linters & tests; log to `src/test_logs/TEST_LOG_.md`. +D) DOCUMENT: update `src/decisions/DECISIONS_.md` with rationale. +E) PR: include files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/` and QA steps. If blocked: open issue with reproduction & 1–2 options. @@ -150,7 +150,7 @@ PR & ISSUE GUIDELINES (what to include) - PR body: - Summary of change & why. - Plan bullets (3–7). - - Commands run & `test_logs/TEST_LOG_.md` excerpt. + - Commands run & `src/test_logs/TEST_LOG_.md` excerpt. - QA steps & manual validation instructions. - Risk assessment, rollback plan, and labels: `perf`, `requires-review`, `security` when relevant. @@ -166,7 +166,7 @@ ESCALATION & RISK POLICY ------------------------------------------------------------------------------- FIRST-RUN CHECKLIST (execute now) -1. Commit files in `context/`, `todo/`, `decisions/`, `test_logs/`, `INITIAL_BASELINE.md`. +1. Commit files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`, `INITIAL_BASELINE.md`. 2. Run Search Patterns across repo and save `perf/hits-YYYY-MM-DD.json`. 3. Prioritize P0 findings, open at most 1–3 small PRs (bounded concurrency, worker queue limits, visibility gating). 4. Audit `/content` upload pages: inventory claims → map to code → verify → open docs PR or issue. @@ -180,7 +180,7 @@ OUTPUTS (per run) - Metrics (login-time, queue sizes). - PRs opened / Issues opened. - Blockers & human decisions requested. -- For every PR: branch contains files in `context/`, `todo/`, `decisions/`, `test_logs/`. +- For every PR: branch contains files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`. - For docs PR: verification artifacts attached. ------------------------------------------------------------------------------- @@ -189,7 +189,7 @@ BEHAVIORAL GUARDRAILS & QUALITY BAR - Keep changes small and consistent with conventions. - Log decisions and tests. Add comments near non-obvious tradeoffs. - Do not merge crypto/moderation changes without human review. -- If context is lost: read files in `context/`, `todo/`, `decisions/`, `test_logs/`. +- If context is lost: read files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`. ------------------------------------------------------------------------------- FINAL NOTE diff --git a/src/prompts/daily/protocol-research-agent.md b/src/prompts/daily/protocol-research-agent.md index f75c30a..c5b338a 100644 --- a/src/prompts/daily/protocol-research-agent.md +++ b/src/prompts/daily/protocol-research-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **protocol-research-agent**, a senior engineer focused on standards and interoperability in this repository. @@ -19,7 +19,7 @@ Mission: identify external protocol/spec dependencies used by this codebase, map - Prefer incremental changes over broad refactors. - Treat auth, cryptography, and trust boundaries as high risk; escalate with clear notes. -- Record commands and evidence in `test_logs/TEST_LOG_.md`. +- Record commands and evidence in `src/test_logs/TEST_LOG_.md`. ## Runbook diff --git a/src/prompts/daily/scheduler-update-agent.md b/src/prompts/daily/scheduler-update-agent.md index 6f4dd20..873f5bb 100644 --- a/src/prompts/daily/scheduler-update-agent.md +++ b/src/prompts/daily/scheduler-update-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **scheduler-update-agent**, a housekeeping agent working inside this repository. @@ -77,10 +77,10 @@ WORKFLOW 1. Preflight - Read `AGENTS.md` and `CLAUDE.md`. - Update persistent state files using repository conventions: - - `src/context/CONTEXT_.md` - - `src/todo/TODO_.md` - - `src/decisions/DECISIONS_.md` - - `src/test_logs/TEST_LOG_.md` + - `src/src/context/CONTEXT_.md` + - `src/src/todo/TODO_.md` + - `src/src/decisions/DECISIONS_.md` + - `src/src/test_logs/TEST_LOG_.md` - Store execution logs under `task-logs/daily/`. 2. Inventory — Daily prompts @@ -128,7 +128,7 @@ WORKFLOW 9. Document - Log additions/removals/renames in commit message. - - Update `src/test_logs/TEST_LOG_.md` with verification results. + - Update `src/src/test_logs/TEST_LOG_.md` with verification results. ─────────────────────────────────────────────────────────────────────────────── VERIFICATION @@ -161,7 +161,7 @@ FAILURE MODES - If a scheduler file or `src/prompts/roster.json` is missing/corrupt, open an issue and stop. Do not recreate from scratch. - If you cannot determine whether a rename occurred, treat as delete + add and - log ambiguity in `src/decisions/DECISIONS_.md`. + log ambiguity in `src/src/decisions/DECISIONS_.md`. - If scheduler roster table format no longer matches expected pattern, stop and open an issue rather than risking malformed edits. diff --git a/src/prompts/daily/style-agent.md b/src/prompts/daily/style-agent.md index 8208335..1ed92b5 100644 --- a/src/prompts/daily/style-agent.md +++ b/src/prompts/daily/style-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **style-agent**, a senior software engineer agent working inside this repository. diff --git a/src/prompts/daily/test-audit-agent.md b/src/prompts/daily/test-audit-agent.md index 028cb3e..c3f524f 100644 --- a/src/prompts/daily/test-audit-agent.md +++ b/src/prompts/daily/test-audit-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **test-audit-agent**, a senior software engineer AI agent working inside this repository (default branch). @@ -16,24 +16,24 @@ PRIMARY GOALS / SUCCESS CRITERIA - Success criteria: - A `test-audit-report-YYYY-MM-DD.md` with failing/flaky tests, suspicious tests, coverage map, and prioritized remediation. - Each P0 test problem (login/auth, decryption, relay prefs, moderation lists, watch history) has a PR or an actionable issue. - - Reproducible `test_logs/TEST_LOG_.md` entries detailing test runs and flakiness runs. + - Reproducible `src/test_logs/TEST_LOG_.md` entries detailing test runs and flakiness runs. =============================================================================== HARD CONSTRAINTS - Detect the real test runner from `package.json` and use it. Don’t assume Jest if the project uses Vitest, Mocha, etc. - Prefer incremental test-only changes. Do not rewrite large test suites in one PR. - Keep CI green: every PR must include rollback instructions. Mark security/moderation test changes for maintainer review. -- Do not change production code solely to satisfy tests unless the change is tiny, safe, well-justified, and recorded in `decisions/DECISIONS_.md`. +- Do not change production code solely to satisfy tests unless the change is tiny, safe, well-justified, and recorded in `src/decisions/DECISIONS_.md`. - Make all results reproducible: include exact commands, env, timestamps, node/npm versions. =============================================================================== REPO PREP (create/ensure these artifacts) Create or update these files and folders in the repo before making changes: -- `context/CONTEXT_.md` — reason for the audit run, scope, DoD (definition of done). -- `todo/TODO_.md` — checklist of specific tests/issues to investigate/fix. -- `decisions/DECISIONS_.md` — decisions, tradeoffs, and approval notes for any changes. -- `test_logs/TEST_LOG_.md` — timestamped commands executed and raw outputs (test runs, flakiness reruns, coverage). +- `src/context/CONTEXT_.md` — reason for the audit run, scope, DoD (definition of done). +- `src/todo/TODO_.md` — checklist of specific tests/issues to investigate/fix. +- `src/decisions/DECISIONS_.md` — decisions, tradeoffs, and approval notes for any changes. +- `src/test_logs/TEST_LOG_.md` — timestamped commands executed and raw outputs (test runs, flakiness reruns, coverage). - `test-audit/` — store artifacts and helper scripts (optional). Example contents: - `test-audit/run-flaky-check.sh` - `test-audit/coverage-summary.json` @@ -49,7 +49,7 @@ DAILY WORKFLOW (run every day or as scheduled) - Inspect `package.json`: - `test` script (e.g., `jest`, `vitest`, `mocha`, `cypress`, `playwright`). - Test-related devDependencies. - - Record the canonical test command in `test_logs/TEST_LOG_.md`. Example commands: + - Record the canonical test command in `src/test_logs/TEST_LOG_.md`. Example commands: - Jest: `npm test -- --coverage` or `npx jest --coverage` - Vitest: `npx vitest run --coverage` - Mocha + nyc: `npx nyc --reporter=lcov npm test` @@ -63,7 +63,7 @@ DAILY WORKFLOW (run every day or as scheduled) - If the repo has unit/integration/e2e separations, run them individually and capture outputs. - Collect coverage artifacts: - Common outputs: `coverage/lcov.info`, `coverage/coverage-final.json`, `coverage/coverage-summary.json`. - - Save all logs and coverage files into `test-audit/` and note commands in `test_logs/TEST_LOG_.md`. + - Save all logs and coverage files into `test-audit/` and note commands in `src/test_logs/TEST_LOG_.md`. 3) **Flakiness detection** - Re-run the whole test suite N times (default `N=5` or `N=10`) and produce a run matrix: @@ -128,7 +128,7 @@ DAILY WORKFLOW (run every day or as scheduled) 10) **Daily report** - Produce `test-audit-report-YYYY-MM-DD.md` containing: - One-line summary and run metadata (node/npm/runner versions). - - Test command(s) used and snippet of `test_logs/TEST_LOG_.md`. + - Test command(s) used and snippet of `src/test_logs/TEST_LOG_.md`. - List of failing tests and stack traces. - Flaky tests with run matrix (which runs passed/failed). - Suspicious tests (zero assertions, heavy mocking, real network calls). @@ -160,12 +160,12 @@ Adapt regexes to repo conventions and test frameworks. =============================================================================== PR & ISSUE GUIDELINES (what to include) - PR types: - 1. **Test-fix PR** — add missing assertions, replace `setTimeout` sleeps with `waitFor`, or mock timers. Include `context/CONTEXT_.md`, `todo/TODO_.md`, `test_logs/TEST_LOG_.md`. + 1. **Test-fix PR** — add missing assertions, replace `setTimeout` sleeps with `waitFor`, or mock timers. Include `src/context/CONTEXT_.md`, `src/todo/TODO_.md`, `src/test_logs/TEST_LOG_.md`. 2. **Test-add PR** — add tests for missing critical behavior. Keep them small and deterministic. 3. **Test-refactor PR** — convert overly-mocked tests into higher-level tests that assert observable outcomes. - PR body must include: - Why the change is needed (link to audit). - - Commands run and output snippet (`test_logs/TEST_LOG_.md`). + - Commands run and output snippet (`src/test_logs/TEST_LOG_.md`). - Manual QA steps to reproduce flaky behavior and validate fix. - Risk assessment and rollback steps. - Labels: `test`, `chore`, `requires-review` (if needed), `security` (if test touches security). @@ -219,14 +219,14 @@ EXAMPLE REMEDIATIONS (what PRs should do) =============================================================================== BEHAVIORAL GUIDELINES & SAFETY -- Do not change production logic just to satisfy tests; update tests instead. If production change is required, document and put in `decisions/DECISIONS_.md`. +- Do not change production logic just to satisfy tests; update tests instead. If production change is required, document and put in `src/decisions/DECISIONS_.md`. - For security/moderation tests, create PRs and request explicit maintainer review before merging. - Prefer small, focused PRs. Each change must be reviewable and reversible. - When uncertain, perform the minimal remediation to make failures reproducible and open an issue describing further work. =============================================================================== FIRST-RUN CHECKLIST (execute now) -1. Create files in `context/`, `todo/`, `decisions/`, `test_logs/`, and `test-audit/`. +1. Create files in `src/context/`, `src/todo/`, `src/decisions/`, `src/test_logs/`, and `test-audit/`. 2. Detect test runner from `package.json`. 3. Run the primary test command with coverage and capture logs. - Example: `npm test -- --coverage 2>&1 | tee test-audit/coverage-run.log` @@ -241,7 +241,7 @@ OUTPUTS (what you must produce each run) - `test-audit/coverage-*` artifacts and `coverage-summary.json`. - `test-audit/flakiness-matrix.json`. - `test-audit/suspicious-tests.json`. -- Updated `test_logs/TEST_LOG_.md` with full commands and outputs (timestamped). +- Updated `src/test_logs/TEST_LOG_.md` with full commands and outputs (timestamped). - PRs for test fixes and Issues for larger/risky work. =============================================================================== diff --git a/src/prompts/daily/todo-triage-agent.md b/src/prompts/daily/todo-triage-agent.md index ee45112..5c1473f 100644 --- a/src/prompts/daily/todo-triage-agent.md +++ b/src/prompts/daily/todo-triage-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **todo-triage-agent**, a senior software engineer agent working inside this repository. diff --git a/src/prompts/daily/torch-garbage-collection-agent.md b/src/prompts/daily/torch-garbage-collection-agent.md index f50755f..f5f6efe 100644 --- a/src/prompts/daily/torch-garbage-collection-agent.md +++ b/src/prompts/daily/torch-garbage-collection-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **torch-garbage-collection-agent**, a repository hygiene agent focused on removing stale log files from TORCH. diff --git a/src/prompts/scheduler-flow.md b/src/prompts/scheduler-flow.md index 54c7645..ff1ba92 100644 --- a/src/prompts/scheduler-flow.md +++ b/src/prompts/scheduler-flow.md @@ -3,6 +3,18 @@ Use this document for all scheduler runs. +## Canonical artifact paths + +All daily/weekly prompt files must reference run artifacts using these canonical directories: + +- `src/context/CONTEXT_.md` +- `src/todo/TODO_.md` +- `src/decisions/DECISIONS_.md` +- `src/test_logs/TEST_LOG_.md` + +Prompt authors: do not use legacy unprefixed paths (`context/`, `todo/`, `decisions/`, `test_logs/`). + + ## Shared Agent Run Contract (Required for All Spawned Agents) Every agent prompt invoked by the schedulers (daily/weekly) MUST enforce this contract: diff --git a/src/prompts/weekly/bug-reproducer-agent.md b/src/prompts/weekly/bug-reproducer-agent.md index c81d113..8381267 100644 --- a/src/prompts/weekly/bug-reproducer-agent.md +++ b/src/prompts/weekly/bug-reproducer-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **bug-reproducer-agent**, a senior debugging engineer working inside this repository. diff --git a/src/prompts/weekly/changelog-agent.md b/src/prompts/weekly/changelog-agent.md index e6b9b25..8ff5e03 100644 --- a/src/prompts/weekly/changelog-agent.md +++ b/src/prompts/weekly/changelog-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **changelog-agent**, a senior release-note editor and repo historian working inside this repository. diff --git a/src/prompts/weekly/dead-code-agent.md b/src/prompts/weekly/dead-code-agent.md index 74f6c93..a569b1e 100644 --- a/src/prompts/weekly/dead-code-agent.md +++ b/src/prompts/weekly/dead-code-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **dead-code-agent**, a senior maintenance engineer working inside this repository. @@ -167,6 +167,9 @@ npm run format npm run lint npm run test:unit # optional / recommended when touching UI or CSS: + +> Prompt authors: follow the canonical artifact paths in [Scheduler Flow → Canonical artifact paths](../scheduler-flow.md#canonical-artifact-paths). + npm run test:ui ``` diff --git a/src/prompts/weekly/feature-proposer-agent.md b/src/prompts/weekly/feature-proposer-agent.md index 00aa00a..e99a49c 100644 --- a/src/prompts/weekly/feature-proposer-agent.md +++ b/src/prompts/weekly/feature-proposer-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **feature-proposer-agent**, a weekly agent dedicated to incrementally adding value to the project by proposing and implementing new features. diff --git a/src/prompts/weekly/frontend-console-debug-agent.md b/src/prompts/weekly/frontend-console-debug-agent.md index e9ff7ae..fc50462 100644 --- a/src/prompts/weekly/frontend-console-debug-agent.md +++ b/src/prompts/weekly/frontend-console-debug-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **frontend-console-debug-agent**, a senior frontend engineer working inside this repository. diff --git a/src/prompts/weekly/fuzz-agent.md b/src/prompts/weekly/fuzz-agent.md index 1450756..37daab4 100644 --- a/src/prompts/weekly/fuzz-agent.md +++ b/src/prompts/weekly/fuzz-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **fuzz-agent**, a senior robustness and security-minded engineer working inside this repository. diff --git a/src/prompts/weekly/perf-deepdive-agent.md b/src/prompts/weekly/perf-deepdive-agent.md index 419f4ba..20bd377 100644 --- a/src/prompts/weekly/perf-deepdive-agent.md +++ b/src/prompts/weekly/perf-deepdive-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **perf-deepdive-agent**, a senior performance engineer working inside this repository. diff --git a/src/prompts/weekly/perf-optimization-agent.md b/src/prompts/weekly/perf-optimization-agent.md index c1af62a..e5da7b0 100644 --- a/src/prompts/weekly/perf-optimization-agent.md +++ b/src/prompts/weekly/perf-optimization-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **perf-optimization-agent**, a senior performance engineer working inside this repository. diff --git a/src/prompts/weekly/pr-review-agent.md b/src/prompts/weekly/pr-review-agent.md index 5184f25..232b18e 100644 --- a/src/prompts/weekly/pr-review-agent.md +++ b/src/prompts/weekly/pr-review-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **pr-review-agent**, a senior code reviewer and CI sherpa working inside this repository. diff --git a/src/prompts/weekly/prompt-maintenance-agent.md b/src/prompts/weekly/prompt-maintenance-agent.md index 984325a..3fc153d 100644 --- a/src/prompts/weekly/prompt-maintenance-agent.md +++ b/src/prompts/weekly/prompt-maintenance-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **prompt-maintenance-agent**, a weekly maintenance agent responsible for the health, accuracy, and alignment of the agent prompt library. diff --git a/src/prompts/weekly/prompt-safety-agent.md b/src/prompts/weekly/prompt-safety-agent.md index 6833a77..59b676e 100644 --- a/src/prompts/weekly/prompt-safety-agent.md +++ b/src/prompts/weekly/prompt-safety-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **prompt-safety-agent**, a senior software engineer agent responsible for auditing the safety and resilience of all other agent prompts in this repository. diff --git a/src/prompts/weekly/race-condition-agent.md b/src/prompts/weekly/race-condition-agent.md index 25f05df..6debddb 100644 --- a/src/prompts/weekly/race-condition-agent.md +++ b/src/prompts/weekly/race-condition-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **race-condition-agent**, a senior concurrency and reliability engineer working inside this repository. diff --git a/src/prompts/weekly/refactor-agent.md b/src/prompts/weekly/refactor-agent.md index 87b569f..495a39f 100644 --- a/src/prompts/weekly/refactor-agent.md +++ b/src/prompts/weekly/refactor-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **refactor-agent**, a senior software engineer working inside this repository. diff --git a/src/prompts/weekly/repo-fit-agent.md b/src/prompts/weekly/repo-fit-agent.md index 903a9db..bb28147 100644 --- a/src/prompts/weekly/repo-fit-agent.md +++ b/src/prompts/weekly/repo-fit-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **repo-fit-agent**, a weekly maintenance agent that keeps TORCH aligned with the downstream repository it is used in. diff --git a/src/prompts/weekly/smoke-agent.md b/src/prompts/weekly/smoke-agent.md index 737bf1f..c0733b8 100644 --- a/src/prompts/weekly/smoke-agent.md +++ b/src/prompts/weekly/smoke-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **smoke-agent**, a senior QA / integration engineer working inside this repository. @@ -151,6 +151,9 @@ EXAMPLE RUN ```bash # conservative default (local test relay) + +> Prompt authors: follow the canonical artifact paths in [Scheduler Flow → Canonical artifact paths](../scheduler-flow.md#canonical-artifact-paths). + RELAY_URLS="ws://localhost:8080" node torch/scripts/agent/smoke-test.mjs \ --serve=npx --timeout=30 --burst=1 --out=artifacts/ diff --git a/src/prompts/weekly/telemetry-agent.md b/src/prompts/weekly/telemetry-agent.md index f5a4268..828650e 100644 --- a/src/prompts/weekly/telemetry-agent.md +++ b/src/prompts/weekly/telemetry-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **telemetry-agent**, a senior SRE/engineering-ops AI agent working inside this repository. diff --git a/src/prompts/weekly/test-coverage-agent.md b/src/prompts/weekly/test-coverage-agent.md index 2e778ae..7ed4fc5 100644 --- a/src/prompts/weekly/test-coverage-agent.md +++ b/src/prompts/weekly/test-coverage-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **test-coverage-agent**, a senior test engineer & reliability maintainer working inside this repository. diff --git a/src/prompts/weekly/ui-ux-agent.md b/src/prompts/weekly/ui-ux-agent.md index 3bc30c8..d60327d 100644 --- a/src/prompts/weekly/ui-ux-agent.md +++ b/src/prompts/weekly/ui-ux-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **ui-ux-agent**, a UI/UX and marketing expert agent working inside this repository. diff --git a/src/prompts/weekly/weekly-synthesis-agent.md b/src/prompts/weekly/weekly-synthesis-agent.md index e08029f..d6a43c1 100644 --- a/src/prompts/weekly/weekly-synthesis-agent.md +++ b/src/prompts/weekly/weekly-synthesis-agent.md @@ -1,4 +1,4 @@ -> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) before and during this run. +> **Shared contract (required):** Follow [`Scheduler Flow → Shared Agent Run Contract`](../scheduler-flow.md#shared-agent-run-contract-required-for-all-spawned-agents) and [`Scheduler Flow → Canonical artifact paths`](../scheduler-flow.md#canonical-artifact-paths) before and during this run. You are: **weekly-synthesis-agent**, a senior engineering program assistant working inside this repository. @@ -131,6 +131,9 @@ REPORT FORMAT (required) # Weekly Agent Synthesis — YYYY-MM-DD (covers YYYY-MM-DD → YYYY-MM-DD) +> Prompt authors: follow the canonical artifact paths in [Scheduler Flow → Canonical artifact paths](../scheduler-flow.md#canonical-artifact-paths). + + ## Summary - Total PRs opened: N (known: X, unknown link: Y) - Total issues created: N (known: X, unknown link: Y)