Private
Public Access
fix(tier2): deny %TEMP% writes - use app-data dir for temp files
The Tier 2 agent wrote audit_exception_handling.py output to C:\\Users\\Ed\\AppData\\Local\\Temp\\audit_initial.json via shell redirection. This is OUTSIDE the sandbox allowlist (which is C:\\projects\\manual_slop_tier2 + C:\\Users\\Ed\\AppData\\Local\\ manual_slop\\tier2 + C:\\Users\\Ed\\AppData\\Local\\manual_slop\\ tier2_failures). The OpenCode session-level guard fires the 'ask' prompt for paths outside the project root, which has no answer in an autonomous session, so ops halted mid-track. Fix (3 layers): 1. opencode.json.fragment: add bash deny rule '*AppData\\Local\\Temp\\*': 'deny' to BOTH the top-level permission.bash (for default agents) and the tier2-autonomous agent's permission.bash. The agent physically cannot run shell commands that target the global Temp dir. 2. conductor/tier2/agents/tier2-autonomous.md: add 'Temp files' convention telling the agent to use C:\\Users\\Ed\\AppData\\Local\\manual_slop\\tier2\\ for scratch / audit-output / intermediate files, NOT %TEMP%. 3. conductor/tier2/commands/tier-2-auto-execute.md: same convention in the slash command so the agent sees it at slash-command time. Tests (default-on): - test_agent_denies_temp_writes: agent prompt has the Temp deny in frontmatter bash + the app-data dir note - test_config_fragment_denies_temp_writes: both top-level and agent bash have the deny rule All 16 tier 2 slash command tests pass. Also: cleaned up the leaked audit_initial.json + audit.json + audit_after*.json from %TEMP% (they were leftovers from a prior run). Re-ran setup against the live clone; opencode.json's agent bash and top-level bash both have the deny rule.
This commit is contained in:
@@ -17,6 +17,7 @@ permission:
|
||||
"C:\\Users\\Ed\\AppData\\Local\\manual_slop\\tier2_failures\\**": allow
|
||||
bash:
|
||||
"*": allow
|
||||
"*AppData\\Local\\Temp\\*": deny
|
||||
"git push*": deny
|
||||
"git checkout*": deny
|
||||
"git restore*": deny
|
||||
@@ -43,6 +44,7 @@ You are running inside a Windows restricted token. The OpenCode permission syste
|
||||
- **Throw-away scripts:** write them to `scripts/tier2/artifacts/<track-name>/`, NOT the base `scripts/tier2/` directory. The base directory is reserved for production code that ships with the sandbox (failcount.py, run_track.py, write_report.py, the .ps1 launchers). Throw-away scripts are kept for archival but live in a track-specific subdir so they don't pollute the base.
|
||||
- **End-of-track report:** after all tasks complete, you MUST write `docs/reports/TRACK_COMPLETION_<track-name>.md` (follow the precedent set by `TRACK_COMPLETION_tier2_autonomous_sandbox_20260616.md`) and update `conductor/tracks/<track-name>/state.toml` to `status = "completed"`. This is the handoff document the user reads to decide merge.
|
||||
- **Run-time expectation:** tracks are expected to take 1-4 hours. If the model reports it is running out of context or steps, do not stop. Note progress to disk (the failcount state file) and continue. The user expects autonomous runs to complete without manual intervention.
|
||||
- **Temp files** (added 2026-06-17): NEVER write to `C:\Users\Ed\AppData\Local\Temp\` or `%TEMP%`. Use `C:\Users\Ed\AppData\Local\manual_slop\tier2\` for all scratch / audit-output / temp files. The bash deny rule `*AppData\Local\Temp\*` will block writes to the global Temp dir, and OpenCode's outer guard will fire the "ask" prompt for reads — both halt ops. Examples: `uv run python scripts/audit_exception_handling.py --json > C:\Users\Ed\AppData\Local\manual_slop\tier2\audit_initial.json` (NOT `%TEMP%\audit_initial.json`).
|
||||
|
||||
## Failcount Contract
|
||||
|
||||
|
||||
@@ -43,6 +43,7 @@ Optional flags: `--resume` (continue from last completed task), `--toast` (Windo
|
||||
- **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): NEVER write to `C:\Users\Ed\AppData\Local\Temp\` or `%TEMP%`. Use `C:\Users\Ed\AppData\Local\manual_slop\tier2\` for scratch / audit-output / intermediate files. The bash deny `*AppData\Local\Temp\*` will block writes; the OpenCode session's outer guard will fire the "ask" prompt for reads — both halt autonomous ops.
|
||||
|
||||
## Hard Bans (enforced by 3 layers)
|
||||
|
||||
|
||||
@@ -43,6 +43,7 @@
|
||||
"uv run python scripts/run_tests_batched.py*": "allow",
|
||||
"uv run python scripts/tier2/*": "allow",
|
||||
"pwsh -File scripts/tier2/*": "allow",
|
||||
"*AppData\\Local\\Temp\\*": "deny",
|
||||
"git push*": "deny",
|
||||
"git checkout*": "deny",
|
||||
"git restore*": "deny",
|
||||
@@ -69,6 +70,7 @@
|
||||
},
|
||||
"bash": {
|
||||
"*": "allow",
|
||||
"*AppData\\Local\\Temp\\*": "deny",
|
||||
"git push*": "deny",
|
||||
"git checkout*": "deny",
|
||||
"git restore*": "deny",
|
||||
|
||||
Reference in New Issue
Block a user