Lap Tran
4a2301b077
CI / build (push) Has been cancelled
- Archive 79 completed framework-dev tasks from tasks/ -> tasks/complete/ - status.py: add --cleanup-done and --install-cleanup-schedule commands - Add scripts/automaton-cleanup.sh for periodic task archiving - Dashboard: rename 'Background' tab -> 'Agent', 'Cleanup' agent -> 'Completed Task Archiver', remove redundant group headers and pill badges, dim inactive agent placeholders - .rules.md: add Self-Documenting UI Names rule - New tests: test_cleanup_done.py, expanded test_app.py and test_task.py
35 lines
2.4 KiB
Markdown
35 lines
2.4 KiB
Markdown
# Adversarial Bug Report: fix-context-sizing
|
||
|
||
## Status: NO_NEW_DEFECTS
|
||
|
||
Adversarial review applied the 5 attack vectors from `design/loops/functional.md` §6 to confirm the changes don't introduce enforcement gaps:
|
||
A1. Concurrent state divergence
|
||
A2. Single-session harness loops can merge 2 sessions
|
||
A3. VM/CI environment with no GPU detection
|
||
A4. User types "loop mode" instead of "--loop-mode"
|
||
A5. Model auto-picks "auto" through config.md but isn't detected
|
||
|
||
Note: the loop system itself ( brakes, runner, verifier) is tasks 2–4. This task only ships the *foundation* the loop runner consumes. Adversarial focus is therefore: (a) has the foundation been honestly graded, (b) can it break the existing enforcement layer, (c) does it lie in a way that loops would silently accept bad budgets.
|
||
|
||
## Attacks
|
||
|
||
### A1: Concurrent state divergence
|
||
`vram_detect.py` is read-only w.r.t. task state. No `.state` file mutation. No enforcement-layer coupling. Safe by design.
|
||
|
||
### A2: Single-session harness fails to detect two sessions
|
||
Not in scope for this task. Roles and harness invocation are task 6's `templates/loops/`. This task only adds the `## Loop Role Models` documentation block to `config.md`; no logic affects session binding.
|
||
|
||
### A3: VM/CI environment, GPU detection returns 0
|
||
The fallback chain in `recommend_context` already handles `gpu_vram_gb == 0` (falls through to RAM or model context). The new `--loop-mode` floor check correctly refuses when `max_peak_kb < 16_000`. Manually exercised logic with `gpu_vram_gb=0, ram_gb=8, model_context_kb=0`; `max_peak_kb` computation flows through RAM branch (8 * 750 = 6000), minus overhead, * 75% = under 16k → loop-mode refuses. Behavior correct.
|
||
|
||
### A4: User misspells conf
|
||
Mangled flag is rejected by argparse; not silent. Confirmed `--help` shows the flag; argparse errors on unknown flag. Safe.
|
||
|
||
### A5: Model "auto" in config.md
|
||
Existing flow already handles "auto" by returning None from `_parse_config_model` value check (line 454, 458). When user has left `Model: auto` AND no `Override context window`: `detect_model_context` proceeds to attempt API config probing and ollama probe. If both fail, returns 0, and `--loop-mode` refuses with the exact D13 message. Non-loop mode warns. Matches SPEC intent.
|
||
|
||
## New Defects
|
||
None.
|
||
|
||
## Adversarial Verdict
|
||
Foundation holds. All 5 attacks correctly produce refuse/warn behavior or are out-of-scope for this task. Ready to ship. |