OpenCode/History
2
0
Fork 0
Code Issues 1 Pull Requests Actions Activity

v0.2.0 — LLM reliability + batched-round turn model #9

Merged
kamilkrzywda merged 2 commits from reliability-batched-round into master 2026-10-11 16:46:02 +02:00
Conversation 0 Commits 2 Files Changed 18
+958 -309
2 Commits
Author SHA1 Message Date
kamilkrzywda 9bce14254d batched round: queue actions/diplomacy, jump forward commits one turn (v0.2.0)
CI / build + unit + e2e (pull_request) Successful in 1m51s
Details
2026-10-11 14:36:35 +00:00
kamilkrzywda 3297658c81 reliability: low reasoning_effort, retry-with-backoff, LLM call logging 
- send top-level reasoning_effort: "low" (LLM_REASONING_EFFORT) to cut the qwen3.8-27b CoT ~85%, so content is no longer truncated to null -> the ~50% 502s
- new env: LLM_MAX_TOKENS (default 4000, per-call opts.maxTokens still overrides), LLM_REASONING_EFFORT (default "low", off/empty omits the field)
- chat() retries up to 3 attempts: timeout/abort, 5xx, network errors (ECONNRESET/ECONNREFUSED/socket closed), null/empty content; backoff 2s->3s (2000*1.5^(n-1), +/-20% jitter); 4xx throws immediately
- logging: '[llm] chat ok' {ms, finishReason} on success; '[llm] chat failed' {attempts, lastStatus, message, totalMs} on final failure
- tests: 12 in llm.test.ts (retry success/failure, no 4xx retry, null-content retry, logging spies); AGENTS.md env table + gotchas updated
 2026-10-11 13:46:18 +00:00