Shinwayy / internal /runtime /executor /aistudio_executor.go

Commit History

  1. track binary files with git-lfs

    Shinway Deploy
    db492de

  1. refactor(translator, executor): remove redundant `bytes.Clone` calls for improved performance⁠

    Unverified signature
    7e8afbe
  2. refactor(executor): optimize payload cloning and streamline SDK translator usage⁠

    Unverified signature
    8953a28

  1. feat(openai): add responses/compact support

    Shady Khalifa
    Unverified signature
    642da09

  1. feat(executor): apply payload rules using requested model

    hkfires
    ba27e38

  1. feat(registry): support provider-specific model info lookup

    hkfires
    a0b18a6

  1. refactor(thinking): pass source and target formats to ApplyThinking for cross-format validation⁠

    hkfires
    0d5d901

  1. fix(executor): properly handle thinking application errors

    hkfires
    6e62482
  2. refactor: improve thinking logic

    hkfires
    c44624a

  1. feat(executor): add HttpRequest support across executors for better http request handling

    Unverified signature
    0268c3b

  1. feat(executor): enhance payload translation with original request context⁠

    Unverified signature
    b08e245

  1. refactor(executor): remove redundant upstream model parameter from translateRequest

    hkfires
    51430d2
  2. refactor(executor): resolve upstream model at conductor level before execution

    hkfires
    5a7ca8b
  3. fix(executor): use upstream model for thinking config and payload translation

    hkfires
    3d1d6fa

  1. fix(gemini): add optional skip for gemini3 thinking conversion

    hkfires
    e8f6c85

  1. fix: apply thinkingLevel from model suffix metadata for Gemini 3⁠

    Ben Vargas
    ba0d597
  2. feat: use thinkingLevel for Gemini 3 models per Google documentation⁠

    Ben Vargas
    6815387

  1. refactor(thinking): export thinking helpers⁠

    hkfires
    784d33c

  1. Fixed: #534⁠

    hkfires
    5ac2280

  1. refactor(executor): clarify executor comments and oauth names

    hkfires
    5b3504c
  2. refactor(executor): clarify providers and streams⁠

    hkfires
    5fa4ee3

  1. fix(executor): centralize default thinking config

    hkfires
    51f4f88
  2. feat(executor): normalize thinking budget across all Gemini executors

    hkfires
    29b3fca
  3. feat(aistudio): normalize thinking budget in request translation

    hkfires
    4e89d32

  1. refactor(executor): dedupe thinking metadata helpers across Gemini executors⁠

    auroraflux
    a3e833c

  1. fix(aistudio): strip Gemini generation config overrides⁠

    hkfires
    0f3aef9

  1. Fixed: #302⁠

    Unverified signature
    aa79092

  1. feat(executor): share SSE usage filtering across streams

    hkfires
    37bfff9

  1. Fixed: #291⁠

    Unverified signature
    436dbcb

  1. **feat(runtime): add payload configuration support for executors**⁠

    Unverified signature
    3374794

  1. fix(executor): remove `safetySettings` from payload in token counting request

    Unverified signature
    5a9a4d7

  1. fix(executor): only apply thinking config to supported models

    hkfires
    c833395

  1. fix(executor): pass authID to relay instead of provider

    hkfires
    6cc1035
  2. feat(registry): unify Gemini models and add AI Studio set

    hkfires
    23f3fd5

  1. fix(aistudio): ensure colon-spaced JSON in responses

    hkfires
    955e811
  2. refactor(wsrelay): rename RoundTrip to NonStream

    hkfires
    caf7d75
  3. fix(aistudio): remove generationConfig and tools when action is countTokens

    hkfires
    616ed67

  1. fix(aistudio): strip usage metadata from non-final stream chunks

    hkfires
    7efa30c
  2. feat(aistudio): track Gemini usage and improve stream errors

    hkfires
    4161485
  3. feat: add websocket routing and executor unregister API⁠

    hkfires
    65414bf