Unverified50% confidenceDecision RuleExact time
Configuration errors (such as a model name returning 401/403/404) should terminate the entire run within the first minute rather than being retried with backoff.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
Unverifiedv3.0.71 fixed three issues with scheduled runs: queued runs no longer remain permanently in the pending state; runs whose model calls fail are marked as failed with the error message attached; and after recovering from a service outage, only the most recent missed time point is executed, rather than catching up on all missed runs.68% similarUnverifiedIn the prototype, triggering the message budget or the recipient cap immediately returns a 402 error, and once the kill switch is enabled all send requests return 503.66% similarUnverifiedPreviously, background sessions would fail to open after 45 seconds when the launch directory was deleted, the machine hibernated, or the host startup process was slow; this version has fixed that issue65% similarUnverifiedv4.1.25 fixed the issue where long requests to local models (such as LM Studio and Ollama) that remained silent for more than 5 minutes would fail with a BodyTimeoutError, so long inference is no longer misjudged as a connection interruption.62% similarUnverifiedFixed the issue where sub-agents crashed directly upon encountering a model 404 on the first call; they will now fall back to the session's fallback model chain and return detailed error information.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063944API
curl https://kongchang.com/api/v1/knowledge/claims/1063944MCP
get_claim(id=1063944)