steve/majordomo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(agent): make same-call repeat guard progress-aware #21

Merged
steve merged 2 commits from fix/progress-aware-same-call-guard into main 2026-07-18 23:22:10 +00:00
Conversation 3 Commits 2 Files Changed 2
+104 -13
2 Commits
Author SHA1 Message Date
steveandClaude Opus 4.8 9922166d7a review(agent): address gadfly on progress-aware guard
CI / Tidy (pull_request) Successful in 9m24s
Details
CI / Build & Test (pull_request) Successful in 9m43s
Details 
Merge the parallel callCounts/lastResults maps into one repeatState struct
map (removes the "two maps in sync" smell + double lookup), drop the dead
i<len(results) bounds branch that contradicted the documented index invariant,
and note in-code that exact-string result equality is a deliberate err-toward-
not-tripping choice (a hung job whose poll reports a ticking field is left to
MaxRuntime / the job ceiling rather than risking a false kill of real progress).
No behavior change; guard tests still green.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01HgEuVfZJN9mhRhzEsMEVog
 2026-07-18 19:11:30 -04:00
steveandClaude Opus 4.8 68bf7157d3 fix(agent): make same-call repeat guard progress-aware
CI / Tidy (pull_request) Successful in 9m25s
Details
Gadfly review (reusable) / review (pull_request) Successful in 9m48s
Details
Adversarial Review (Gadfly) / review (pull_request) Successful in 9m48s
Details
CI / Build & Test (pull_request) Successful in 10m33s
Details 
The maxSameCallRepeats guard counted identical (name+arguments) tool calls
across a run and tripped ErrToolLoop past the ceiling — regardless of whether
each call made progress. This killed legitimate polling of long-running
background jobs: code_exec_poll must be called with identical args (same
job_id), so a render/encode that needs more than N polls was guillotined
mid-flight even as each poll returned an advancing result (elapsed/status
moving forward).

Only count an identical call toward the trip when its RESULT is unchanged
from the previous identical call. A call whose result keeps changing is
progress and resets its count; a genuinely stuck call returning the same
output still trips. This can never trip more than before, only less, and
covers every idempotent poller with no per-tool configuration — matching the
progress-over-usage thesis behind the stall-detection work.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01HgEuVfZJN9mhRhzEsMEVog
 2026-07-18 18:56:56 -04:00