mateclaw/mateclaw-server
matevip 7ba8fe602b feat(llm): track primary health + split BILLING / MODEL_NOT_FOUND from generic client errors
Track the primary model health, not just fallback entries
- NodeStreamingChatHelper accepts primaryProviderId via a new 5-arg
  constructor; AgentGraphBuilder passes ModelConfigEntity.getProvider()
- Before the 5-retry primary loop, check
  healthTracker.isInCooldown(primaryProviderId): if true, log + broadcast
  "主模型暂时不可用(冷却中),直接尝试备选模型..." and short-circuit
  straight to the fallback chain. Prevents a degraded primary from
  burning 30+ seconds of backoff on every conversation turn.
- recordPrimary(success/failure) now fires on every primary verdict —
  AUTH, BILLING, MODEL_NOT_FOUND, EMPTY_RESPONSE, generic UNKNOWN, and
  the explicit success path. Three consecutive failures push the
  primary provider into cooldown automatically.
- Legacy 1/2/3-arg constructors leave primaryProviderId null; tracking
  silently disables for them so existing tests/wiring keep working.

Split BILLING and MODEL_NOT_FOUND out of CLIENT_ERROR / AUTH_ERROR
- BILLING (HTTP 402, "insufficient_quota", "credit balance is too low",
  "billing_hard_limit_reached", "quota exceeded"): payment failure on
  primary does not kill the call — a different provider may have credits.
  Skips same-model retries and heads to fallback chain.
- MODEL_NOT_FOUND (HTTP 404, "Model not exist", "model_not_found",
  DashScope "[InvalidParameter] url error"): unknown model id will not
  start working on retry. Was previously misclassified as CLIENT_ERROR
  and terminated the whole call; now routes to fallback so a different
  provider can attempt with its default model.
- classifyError ordering matters: BILLING / MODEL_NOT_FOUND are matched
  BEFORE the generic 400 / Bad Request branch, otherwise they would be
  swallowed by CLIENT_ERROR.

Tests
- ErrorClassificationTest: 11 tests, covers multi-vendor error phrasing
  for both new types + regression checks that 401 / 429 / 400 still
  classify as before
- NodeStreamingChatHelperFallbackChainTest: +2 tests verifying
  primaryProviderId persistence on the new constructor and null on
  legacy ones
- 181 tests pass (was 168 + 13 new)
2026-04-19 17:10:27 +08:00
..
src feat(llm): track primary health + split BILLING / MODEL_NOT_FOUND from generic client errors 2026-04-19 17:10:27 +08:00
Dockerfile chore: bump version to 1.1.137-SNAPSHOT 2026-04-18 21:58:54 +08:00
pom.xml chore: bump version to 1.1.137-SNAPSHOT 2026-04-18 21:58:54 +08:00