shinnmen / internal /runtime /executor /openai_compat_executor.go

Commit History

  1. refactor(executor): split providers and preserve legacy entrypoints⁠

    shinmentakezo07 +1: Claude Opus 4.6
    3e5ab39

  1. feat: passthrough upstream response headers to clients⁠

    Kirill Turanskiy
    409fbf7

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

    Unverified signature
    1b0fbba
  2. refactor(executor): optimize payload cloning and streamline SDK translator usage⁠

    Unverified signature
    c702df8

  1. fix(openai): drop stream for responses/compact

    Shady Khalifa
    Unverified signature
    7e33f2b

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

    Shady Khalifa
    Unverified signature
    8f7449a

  1. feat(executor): add request_id to error logs⁠

    hkfires
    2511652

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

    hkfires
    69a5340

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

    hkfires
    4771da8

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

    hkfires
    4072514

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

    hkfires
    e934726
  2. refactor: improve thinking logic

    hkfires
    ee9e572

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

    Unverified signature
    a64baa3

  1. Fixed: #942⁠

    Unverified signature
    5708daa

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

    Unverified signature
    ae057e3

  1. refactor(executor): resolve upstream model at conductor level before execution

    hkfires
    c37b7ba

  1. refactor(thinking): export thinking helpers⁠

    hkfires
    ca524b4

  1. fix(executor): add `allowCompat` support for reasoning effort normalization⁠

    Unverified signature
    fcacb47
  2. fix(openai-compat): prevent model alias from being overwritten by ResolveOriginalModel⁠

    hazeruno +1: Amp
    ddd4bb1

  1. Merge pull request #481 from sususu98/fix/increase-buffer-size⁠

    Unverified signature
    a2d15c3
  2. fix(runtime): unify reasoning effort metadata overrides

    hkfires
    da8b2ff
  3. fix(runtime): validate reasoning effort levels

    hkfires
    f4e99ba
  4. feat(runtime): add thinking config normalization

    hkfires
    e9260fd

  1. feat(util): implement dynamic thinking suffix normalization and refactor budget resolution logic⁠

    Unverified signature
    db58889
  2. fix(executor): increase buffer size for stream scanners to 50MB across multiple executors

    sususu
    864db07

  1. **refactor(executor): simplify Gemini CLI execution and remove internal retry logic**⁠

    Unverified signature
    4ae9540

  1. **fix(runtime): simplify scanner buffer allocation in executor implementations**

    Unverified signature
    09adea3

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

    Unverified signature
    a917f9b

  1. fix(executor): ensure usage reporting for upstream responses lacking usage data⁠

    Unverified signature
    e99a11a

  1. feat(config): support HTTP headers across providers

    hkfires
    e6bdaef

  1. refactor(executor): summarize API error bodies of html in debug logs

    hkfires
    62f6af9

  1. Fixed: #140 #133 #80⁠

    Unverified signature
    9a36c01

  1. Refactor executor error handling and usage reporting⁠

    Unverified signature
    b9ad503

  1. Enhance logging for API requests and responses across executors⁠

    Unverified signature
    5b50851

  1. feat(registry/runtime): add Gemini 2.5 model and increase buffer sizes⁠

    Unverified signature
    40079ee

  1. feat(auth): improve OpenAI compatibility normalization and API key handling⁠

    Unverified signature
    de763ab

  1. feat(runtime): introduce `newProxyAwareHTTPClient` for enhanced proxy handling⁠

    Unverified signature
    41556b2

  1. rebuild branch

    Unverified signature
    e83d8c5
  2. remove all

    Unverified signature
    cf2b83d

  1. feat(usage): implement usage tracking infrastructure across executors⁠

    Unverified signature
    13abc2b

  1. feat(executor): add `CountTokens` support across all executors⁠

    Unverified signature
    79e15a8
  2. chore(executor): add debug logging for API request errors⁠

    Unverified signature
    43ab793
  3. feat(openai-compat): enhance provider key handling and model resolution⁠

    Unverified signature
    0dd3f34
  4. chore(logging): add debug logs for executor `Refresh` methods⁠

    Unverified signature
    156078d

  1. refactor: standardize constant naming and improve file-based auth handling⁠

    Unverified signature
    6278f5d
  2. v6 version first commit

    Unverified signature
    d70f595