ROOT CAUSE (post-mortem at docs/reports/TIER2_MCP_REGRESSION_20260624.md): - Tier 1 asserted claims from old reports without re-verifying (SSDL campaign was designed from a static text string '6 nil-check functions' in src/code_path_audit_gen.py:108 that was never a runtime measurement) - Tier 2 (autonomous) made an empty fix commit (2b7e2de1) for the MCP regression; the pre-commit hook silently stripped opencode.json + mcp_paths.toml and the agent reported success without verifying with 'git show HEAD --stat' - Both happened because neither tier read the critical files before acting THE FIX (this commit): 1. .agents/agents/tier1-orchestrator.md: add MANDATORY pre-action reading list (6 files: AGENTS.md, conductor/workflow.md, current track spec/plan, the 3 code_styleguides). Reference the 2026-06-24 SSDL failures. 2. .agents/agents/tier2-tech-lead.md: add MANDATORY pre-action reading list (8 files: AGENTS.md, workflow.md, edit_workflow.md, the githooks forbidden-files.txt, the tier2_leak_prevention spec, the 3 styleguides) + the MANDATORY pre-commit verification gate (3 checks per commit). 3. .agents/agents/tier3-worker.md: add 4-file read list (AGENTS.md, task spec, relevant styleguide, the actual code being modified). Tier 3 doesn't need the full 8-file list — Tier 2's task spec is the contract. 4. .agents/agents/tier4-qa.md: same 4-file read list (analysis context). 5. conductor/tier2/agents/tier2-autonomous.md: add the 8-file MANDATORY pre-action reading list + the MANDATORY pre-commit verification gate. 6. conductor/tier2/commands/tier-2-auto-execute.md: add the 8-file list to the pre-flight section (step 0). 7. conductor/tier2/githooks/pre-commit: change behavior from 'silent strip + commit anyway' to 'strip + ABORT commit with diagnostic message'. The previous behavior led to empty commits (the 2026-06-24 regression). The agent MUST investigate the leak before retrying the commit. ENFORCEMENT (all tiers): - First commit of any track must include 'TIER-N READ <list> before <task>' in the commit message. The failcount contract treats an unacknowledged first commit as a red-phase failure (per the error_handling.md Rule #0 precedent). NOT IN THIS COMMIT (deferred to followup tracks per the post-mortem): - Rule 4 (CI gate for required files via scripts/audit_branch_required_files.py) - AGENTS.md addition of the canonical 'MANDATORY Pre-Action Reading' section (separate track to ensure the project-root rules reflect the same list) - Cross-platform agent files (.opencode/, .claude/, .gemini/) — those are generated from the canonical .agents/agents/ files; this commit updates the canonical sources. 7 files modified, 109 insertions, 6 deletions.
5.4 KiB
description, agent
| description | agent |
|---|---|
| Autonomously execute a conductor track in the Tier 2 sandbox | tier2-autonomous |
/tier-2-auto-execute
Run a track autonomously in the Tier 2 sandboxed mode. No permission: ask prompts.
Arguments
$ARGUMENTS - Track name (required). Examples: result_migration_review_pass, data_structure_strengthening_20260606.
Optional flags: --resume (continue from last completed task), --toast (Windows toast on give-up).
Pre-flight
-
MANDATORY: Read these 8 files IN ORDER before any other action (added 2026-06-24 post-MCP-regression):
AGENTS.md(project root) — operating rulesconductor/workflow.md— workflow + tier conventionsconductor/edit_workflow.md— edit tool contractconductor/tier2/githooks/forbidden-files.txt— file denylistconductor/tracks/tier2_leak_prevention_20260620/spec.md— prior leak incident (DO NOT REPEAT)conductor/code_styleguides/data_oriented_design.md— canonical DODconductor/code_styleguides/error_handling.md—Result[T]conventionconductor/code_styleguides/type_aliases.md— the 10 TypeAliases
The first commit of the track must include "TIER-2 READ before " in the commit message. The failcount contract treats an unacknowledged first commit as a red-phase failure.
-
Verify sandbox is active. This slash command must be invoked from a sandboxed OpenCode session. If
manual-slop_get_ui_performancereturns an error or the run_tier2_sandboxed.ps1 wrapper is not in the parent process, refuse to start. -
Load the track spec. Read
conductor/tracks/<track-name>/spec.mdandplan.mdfrom the current branch. If the track does not exist, abort. -
Check for a previous run. If
tests/artifacts/tier2_state/<track-name>/state.jsonexists AND--resumeis NOT set, abort with: "Previous run found for this track. Use--resumeto continue, or delete the state file to start fresh."
Protocol
git fetch origin master(NOTE: this repo usesmaster, notmain; added 2026-06-17)git switch -c tier2/<track-name> origin/master(NOTgit checkout- it is banned)- Initialize failcount state at
tests/artifacts/tier2_state/<track-name>/state.json(useload_stateor fresh state) - For each task in
plan.md: a. Red: delegate test creation to @tier3-worker b. Run tests viauv run python scripts/run_tests_batched.py(NEVERuv run pytestdirectly; the batched runner provides tier filtering, parallelization, and the summary table — added 2026-06-17) c. If pass unexpectedly, callrecord_red_failureand checkshould_give_upd. Green: delegate implementation to @tier3-worker e. Run tests viascripts/run_tests_batched.py; if fail, callrecord_green_failureand checkshould_give_upf. On green:record_commitandrecord_green_success(resets counters) g. Commit per task withgit add <specific files> && git commit -m "..."and attach git note h. Updateplan.mdwith commit SHA - After all tasks complete, write the end-of-track report (see step 7) and print success summary.
- On give-up: call
write_failure_reportfromscripts.tier2.write_report, print "TRACK ABORTED, see report at ". - End-of-track report (added 2026-06-17): on success, write
docs/reports/TRACK_COMPLETION_<track-name>.mdfollowing the precedent set byTRACK_COMPLETION_tier2_autonomous_sandbox_20260616.md. Updateconductor/tracks/<track-name>/state.tomltostatus = "completed". The user reads this report to decide merge.
Conventions (MUST follow - added 2026-06-17)
- Test runner: use
uv run python scripts/run_tests_batched.py(NOTuv run pytest) - Default branch:
master(this repo never hadmain) - Line endings: preserve existing (CRLF stays CRLF, LF stays LF)
- Throw-away scripts: write to
scripts/tier2/artifacts/<track-name>/, NOT the base directory - Run-time expectation: tracks are 1-4 hours. If context runs out, note progress to disk and continue.
- Temp files (added 2026-06-17, rewritten 2026-06-18, paths updated 2026-06-18 per Tier 2's project-relative relocation; deny patterns expanded 2026-06-19 to catch all env-var forms): All scratch, state, audit-output, and intermediate files MUST live INSIDE the Tier 2 clone. Default locations:
tests/artifacts/tier2_state/<track>/state.jsonfor failcount state,tests/artifacts/tier2_failures/for failure reports,scripts/tier2/artifacts/<track>/for throwaway scripts. NEVER USE APPDATA — the AppData tree is OFF-LIMITS. The full list of forbidden literals (matched against the command string):*AppData\\*,*AppData\Local\Temp\*,*$env:TEMP*,*$env:TMP*,*%TEMP%*,*%TMP%*,*GetTempPath*,*gettempdir*,*mkstemp*. Do NOT attempt to use$env:TEMP,$env:TMP,%TEMP%,%TMP%, or any temp-dir API in any form — every one of those literal command strings is denied at the bash level.
Hard Bans (enforced by 3 layers)
git restore*(any form) — deniedgit push*(any push) — deniedgit checkout*(any form) — denied; usegit switchinsteadgit reset*(any form) — denied
Filesystem access is restricted to the Tier 2 clone (C:\projects\manual_slop_tier2\). The Windows restricted token blocks reads/writes outside this path at the OS level. NEVER USE APPDATA — there is no longer any Tier 2 state or scratch dir on AppData; the *AppData\\* bash deny rule enforces this.