mirror of https://github.com/garrytan/gstack.git
55dfb9e26c
Regex detectors (isNumberedOptionListVisible, isProseAUQVisible) are
fast and free, but PTY rendering quirks fragment prose AUQ option
lists across logical lines that no regex can reliably reassemble.
When detection misses, polling loops time out at the full budget
even though the model is correctly waiting for user input.
Adds judgePtyState — a Haiku-graded trichotomy classifier:
- waiting: agent surfaced a question/options, sitting at input prompt
- working: spinner / tool calls / generation in progress
- hung: stopped without surfacing anything (rare crash signal)
Wired as a fallback into the polling loops of runPlanSkillObservation
and runPlanSkillFloorCheck: after 60s with no regex hit, snapshot the
TTY every 30s and call the judge. On 'waiting' verdict, return
outcome=asked / auq_observed early. On 'working' or 'hung', enrich the
eventual timeout summary with the verdict so failures are diagnosable.
Implementation:
- Spawns `claude -p --model claude-haiku-4-5 --max-turns 1` synchronously
with prompt piped via stdin (subscription auth, no API key env required)
- In-process cache keyed by SHA-1 of normalized last-4KB so identical
spinner-frame snapshots don't re-charge
- Best-effort JSONL log to ~/.gstack/analytics/pty-judge.jsonl with
timestamp, testName, state, reasoning, hash, judge wall time
- 30s timeout per call; returns state='unknown' with diagnostic on any
failure mode (timeout, malformed JSON, missing claude binary)
Snapshot logging: when GSTACK_PTY_LOG=1 is set, dump last 4KB of visible
TTY at every judge tick to ~/.gstack/analytics/pty-snapshots/<test>-
<elapsed>ms.txt — postmortem trail for debugging flakes.
Cost: ~$0.0005 per call; ~10 calls per 5-min test budget; ~$0.005 per
test added in worst case (only when regex detectors miss).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| providers | ||
| agent-sdk-runner.ts | ||
| benchmark-judge.ts | ||
| benchmark-runner.ts | ||
| claude-pty-runner.ts | ||
| claude-pty-runner.unit.test.ts | ||
| codex-session-runner.ts | ||
| e2e-helpers.ts | ||
| eval-store.test.ts | ||
| eval-store.ts | ||
| gemini-session-runner.test.ts | ||
| gemini-session-runner.ts | ||
| llm-judge.ts | ||
| observability.test.ts | ||
| pricing.ts | ||
| secret-sink-harness.ts | ||
| session-runner.test.ts | ||
| session-runner.ts | ||
| skill-parser.ts | ||
| tool-map.ts | ||
| touchfiles.ts | ||