[Feature] Bound repeated tool-validation failures while allowing corrected calls
I maintainer di solito rispondono entro 1 giorno
Nessuno ha ancora preso questa issue.
Valutazione
- Difficoltà
- 5/5
- Tempo stimato
- Più di una settimana
- Idoneità per principianti
- 35/100
Direzione di ricerca
Start by reading #7388 and #7387 for the existing repeated-call notices, then review the runner and tool-validation paths that classify failures before execution. The issue calls for agreement on the threshold, opt-in mechanism, and error classification before a general implementation; verify that corrected calls and successful repeated calls remain available, while unchanged validation failures are bounded within one run.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Descrizione
Feature Description
Provide a bounded recovery policy for repeated, deterministic tool-validation failures while allowing corrected requests to proceed.
In a scheduling incident, the agent made 16 invalid future_task(action="create") calls: 12 omitted the one-time switch and four later omitted reminder content. All failed before persistence. Repeated-call notices were logged, but the run continued making invalid calls.
#7388 already supplies escalating notices after repeated calls. This discussion concerns what should happen when the model continues submitting the same arguments and receives the same deterministic validation error despite those notices.
Proposed Behavior for Discussion
- Identify pre-execution validation failures reliably, preferably through explicit error classification rather than matching arbitrary error text.
- Track the same tool, equivalent arguments, and validation failure within one run. Reset the streak when arguments are corrected or execution succeeds.
- After a small bounded number of unchanged failures, stop executing that offending tool for the current run and have the agent report that the requested operation was not completed. Keep unrelated tools available and restore normal availability on the next run.
- Preserve successful repeated calls and legitimate polling; a repeated tool name alone is insufficient evidence of failure.
- Treat uncertain outcomes such as network timeouts separately. A create request may already have succeeded, so state verification and request idempotency need separate design rather than blind retry.
The threshold, tool opt-in mechanism, and error classification should be agreed before implementing a general runner change. A local future_task-specific mitigation has been isolated and tested, but this issue does not propose importing the broader #6259 patch or claim a generic solution is already implemented.
Use Case
Natural-language reminders and other state-changing tools whose missing arguments can otherwise consume the entire agent step budget without making progress. The focused companion fix for one-time reminder inference is #11085, addressing #11084.
Related Work
- #6259: closed, unmerged proposal containing error-loop protection and other mechanisms.
- #7388 and #7387: repeated-call notices and the original looping report.
- #8163: configurable notice thresholds; related, but does not itself specify a bounded response to deterministic validation failures.
Checklist
- Searched existing issues and PRs; related and historical proposals are linked above.
- This concerns AstrBot core rather than a plugin.
- Read and will follow the project Code of Conduct.
- Lingua principale
- Python
- Stelle
- 46.9k
- Fork
- 3.6k
- Merge medio
- 1g 6h
- PR unite (30g)
- 136
Preparare l'ambiente
- Include un Dockerfile o un file Docker Compose
- Ha un modello di pull request
- Leggi la guida per i contributori
Come iniziare
- Leggi tutta la issue e poi la guida ai contributi del progetto.
- Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
- Fai un fork del repository e lavora su un branch.
- Apri una pull request che faccia riferimento al numero della issue.
Altre issue di AstrBotDevs/AstrBot
-
[Bug] Sending a Telegram message chain twice duplicates mentionsForse già presa @123XieC l’ha presa 5 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
AstrBotDevs/AstrBot#11125 ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug] Telegram album debounce exceeds the maximum waitForse già presa @123XieC l’ha presa 5 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
AstrBotDevs/AstrBot#11123 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 74/100
AstrBotDevs/AstrBot#11034 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug] OpenAI-compatible Gemini 工具 schema const 导致 400Forse già presa @arccat-114 l’ha presa 26 giorni fa. Apertabug
Difficoltà 2/5 1-3 ore Idoneità per principianti 77/100
AstrBotDevs/AstrBot#10720 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
-
[Bug] Discord slash command sync aborts with KeyError when a plugin handler is defined in a submoduleForse già presa @yuexia5 l’ha presa 31 giorni fa. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 77/100
AstrBotDevs/AstrBot#10626 · 1 commento ·
I maintainer di solito rispondono entro 1 giorno
Tutte le issue di AstrBotDevs/AstrBot
Issue simili
-
ready-for-agent
Difficoltà 1/5 1-3 ore Idoneità per principianti 79/100
gregwebs/agent-vm-images#216 ·
I maintainer di solito rispondono entro 1 giorno
-
Layout accepts a step threshold of 0 or less, then in-toto-verify crashes with StopIterationForse già presa @BahaaMattar l’ha presa oggi. Aperta
Difficoltà 2/5 1-3 ore Idoneità per principianti 76/100
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 72/100
gcivil-nyu-org/team5-mon-fall26#145 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 78/100
gcivil-nyu-org/team3-mon-fall26#156 ·
I maintainer di solito rispondono entro 1 giorno
-
Difficoltà 2/5 1-3 ore Idoneità per principianti 82/100
antlr/grammars-v4#5220 ·
I maintainer di solito rispondono entro 1 giorno