shinnmen / internal /runtime /executor /gemini_cli_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(all): replace manual pointer assignments with `new` to enhance code readability and maintainability

    Unverified signature
    2359a6f

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

    Unverified signature
    ae057e3

  1. fix(thinking): fallback to upstream model for thinking support when alias not in registry

    hkfires
    cc7e585
  2. fix(thinking): use model alias for thinking config resolution in mapped models

    hkfires
    d57c140

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

    hkfires
    c37b7ba
  2. fix(executor): use upstream model for thinking config and payload translation

    hkfires
    7559da4

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

    Ben Vargas
    a1a3463

  1. Merge pull request #449 from sususu98/fix/gemini-cli-429-retry-delay-parsing⁠

    Unverified signature
    d2552c8

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

    hkfires
    9cc01d9
  2. refactor(executor): clarify providers and streams⁠

    hkfires
    f3f3cbf

  1. fix(gemini-cli): enhance 429 retry delay parsing⁠

    sususu +1: Claude Opus 4.5
    4ceec71

  1. fix(executor): increase buffer size for stream scanners to 50MB across multiple executors

    sususu
    864db07

  1. fix(executor): centralize default thinking config

    hkfires
    c60202a
  2. feat(executor): normalize thinking budget across all Gemini executors

    hkfires
    ab09327

  1. Fixed: #414⁠

    Unverified signature
    d0b35c1

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

    auroraflux
    82379d5

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

    Unverified signature
    4ae9540

  1. fix(executor): prevent streaming on failed response when no fallback⁠

    Ben Vargas
    8da283a
  2. fix(executor): prevent streaming from 429 response when fallback available⁠

    Ben Vargas
    f7a456b
  3. feat(executor): add intelligent retry logic for 429 rate limits⁠

    Ben Vargas
    8160cb0

  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. feat(gemini-cli): add multi-project support and enhance credential handling⁠

    Unverified signature
    aae5103

  1. fix(executor): remove outdated Gemini model previews from CLI fallback order

    Unverified signature
    f52524a

  1. fix(executor): remove `safetySettings` from payload for Gemini requests

    Unverified signature
    0f6a6da

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

    hkfires
    62f6af9

  1. chore(logging): clarify 429 rate-limit retries in Gemini executor

    hkfires
    20518ca
  2. fix(gemini-cli): correctly strip/normalize thinking config by model

    hkfires
    c32fec0
  3. fix(executor): only apply thinking config to supported models

    hkfires
    c896fd9

  1. fix(gemini): map responseModalities to uppercase IMAGE/TEXT

    hkfires
    80f30e2

  1. feat(executor): add debug logs for rate-limiting retries in Gemini CLI executor

    Unverified signature
    4f358ac

  1. Refactor executor error handling and usage reporting⁠

    Unverified signature
    b9ad503

  1. Enhance logging for API requests and responses across executors⁠

    Unverified signature
    5b50851
  2. Feature: #103⁠

    Unverified signature
    a382a67

  1. feat(registry, executor, util): add support for `gemini-2.5-flash-image-preview` and improve aspect ratio handling⁠

    Unverified signature
    147d05d
  2. feat(registry, executor): add support for `glm-4.6` model and enhance Gemini CLI token handling⁠

    Unverified signature
    7dee760
  3. feat(registry, executor): add support for `gemini-2.5-flash-image` model⁠

    Unverified signature
    4e98339

  1. fix(gemini): Disable thinking config for incompatible models

    hkfires
    5c4667a