Code

History

Commits on v7.2.13535+
  1. Merge pull request #5026 from router-for-me/coolingLuis Pater committed 2 months ago856ddd8
  2. chore(models): update GPT-5.6 context limits in registry metadataLuis Pater committed 2 months ago745fb38
  3. Refactor cooling management across configuration and handlershkfires committed 2 months ago5bffd15
  4. fix(auth): stop old selectors when replacing manager selector and harden cache stop concurrencyLuis Pater committed 2 months agob8fbe70
  5. docs(readme): remove obsolete ecosystem links for PPAP and AlexLuis Pater committed 2 months ago75e2454
  6. fix(auth): share session affinity across model variant suffixesLuis Pater committed 2 months ago00c4377
  7. feat(auth): add request-scoped error action handling in conductorLuis Pater committed 2 months agoaa10847
  8. Merge pull request #5008 from shengyy/fix/antigravity-schema-semanticsLuis Pater committed 2 months ago361fe95
  9. fix(antigravity): preserve schema semanticsshengyy committed 2 months ago7d55d0d
  10. test(antigravity): cover schema sanitizer semanticsshengyy committed 2 months agoe23395a
  11. feat(claude): map OpenAI `service_tier` to Claude `speed` in responses requestsLuis Pater committed 2 months ago7eefab9
  12. fix(claude,gemini,openai): preserve upstream stream errors when no data payload is emittedLuis Pater committed 2 months ago92f03e6
  13. pref(claude): keep raw Claude tool IDs for deduplication in request translationLuis Pater committed 2 months ago7efe0a7
  14. perf(translator): switch response translators to batched raw-array insertion via `SetRawArrayItems`Luis Pater committed 2 months ago8b3b304
  15. perf(translator): batch assemble translation arrays before writing JSONLuis Pater committed 2 months ago0c58c3c
  16. fix(gemini): simplify OpenAI chat response content and choices serializationLuis Pater committed 2 months agoa581838
  17. perf(translator): batch assemble response arrays and merge multi-choice partsLuis Pater committed 2 months ago124dab6
  18. fix(claude,gemini,antigravity): centralize tool-call ID generation and harden signature sanitizationLuis Pater committed 2 months ago616d1b1
  19. fix(claude): deduplicate duplicate tool outputs in OpenAI-to-Claude request conversionLuis Pater committed 2 months ago1ecb7df
  20. chore(models): remove GPT-5.6 Sol Work Mode registrations from model registry configLuis Pater committed 2 months agoc1ff55f
  21. fix(openai): propagate environment context and sanitize antigravity generation config in interaction adaptersLuis Pater committed 2 months ago10afcc8
  22. fix(gemini): merge conditional schema branches during JSON schema cleanupLuis Pater committed 2 months agof53a2b6
  23. Merge pull request #4994 from router-for-me/modelsChén Mù committed 2 months ago48d0218
  24. fix(auth): make session-affinity updates safe for rebound sessionsLuis Pater committed 2 months ago9169ad5
  25. feat(models): add max_completion_tokens to model definitions and responseshkfires committed 2 months ago046b59e
  26. feat(models): add GPT-5.6 Sol Work Mode model registrations and Codex client config updatesLuis Pater committed 2 months agodd21444
  27. fix(openai): ensure Responses usage includes token detail fieldsLuis Pater committed 2 months agoe0b4956
  28. fix(claude): add Anthropic unified rate-limit parsing helpersLuis Pater committed 2 months agoac82bed
  29. fix(claude): keep tool_result blocks first when injecting currentDatemardausdennis committed 3 months ago297139c
  30. fix(auth): avoid cooldown for request-scoped 401 request-faultsLuis Pater committed 2 months ago203f5b1
  31. Merge pull request #4360 from router-for-me/perf/skip-inactive-request-interceptorsLuis Pater committed 2 months ago810d4dd
  32. Merge pull request #4928 from ramapitecusment/codex/websocket-transcript-allocations-v2Luis Pater committed 2 months ago8b02fed
  33. fix(gemini): preserve `additionalProperties:false` for Antigravity response schemasLuis Pater committed 3 months ago61c4fd8
  34. fix(openai): mark truncated/filtered responses as incomplete and avoid finalizing partial tool callsLuis Pater committed 3 months ago78f0c40
  35. fix(codex): cache multi-agent spawn-agent model data and invalidate on updatesLuis Pater committed 3 months ago98c98d6