Edison42 cef5dd4d61 fix(kiro): map GPT-5.6 reasoning effort fields ...

Route GPT-5.6 reasoning effort through Kiro's native reasoning.effort field instead of the legacy Claude output_config.effort path. GPT-5.6 models now emit reasoning.effort for low/medium/high/xhigh, with max mapped to the xhigh wire value.

Preserve the Responses API reasoning.effort through the OpenAI intermediate by copying it to reasoning_effort before the field is dropped. Skip legacy thinking_mode prompt tags when a supported native GPT effort is emitted, while keeping the legacy fallback for unsupported values (auto/minimal/ultra) and explicit disable semantics (none/off/disabled). Claude adaptive effort continues to use thinking plus output_config.effort.

2026-07-20 11:11:37 +07:00

..

__snapshots__

fix(thinking): send explicit thinking:{type:adaptive} alongside output_config.effort

2026-07-16 11:17:08 +07:00

real

feat(nvidia): add new models and capabilities for NVIDIA provider

2026-07-03 12:15:58 +07:00

AGENTS.md

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

bugs-antigravity.test.js

fix(antigravity): align provider fingerprint with IDE Desktop 2.1.1 (#2389)

2026-07-08 10:17:47 +07:00

bugs-claudeCode-context.test.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

bugs-codexCli-responses.test.js

fix(translator): preserve developer instructions in openai-responses conversion (#2434)

2026-07-07 11:54:07 +07:00

bugs-gemini-cursor-commandcode.test.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

bugs-kiro.test.js

fix(kiro): map GPT-5.6 reasoning effort fields

2026-07-20 11:11:37 +07:00

bugs-openai-bridge.test.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

bugs-toClaude-context.test.js

fix(claude): reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381)

2026-07-05 17:38:16 +07:00

claude-kiro-direct.test.js

fix(kiro): map GPT-5.6 reasoning effort fields

2026-07-20 11:11:37 +07:00

coverage-all-models.test.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

format-roundtrip.test.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

golden-request.test.js

fix(gemini-cli): raise output floor for thinking and add validated toolConfig (#2486)

2026-07-10 11:32:11 +07:00

golden-response-stream.test.js

refactor(open-sse): extract chunkBuilder, dedup chat.completion.chunk (B1)

2026-06-13 17:05:42 +07:00

golden-translator-concerns.test.js

refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

2026-06-14 18:49:38 +07:00

golden-url-header.test.js

test(open-sse): add P0 golden tests (url/header, response stream, request body)

2026-06-13 16:22:00 +07:00

matrix.js

test(translator): add data-driven coverage, bug-exposing cases, and real provider smoke

2026-06-06 12:19:59 +07:00

registerAll.js

feat(kiro): headless API-key auth + direct Claude/Kiro route

2026-06-17 10:01:30 +07:00

thinking-unified.test.js

Merge remote-tracking branch 'upstream/master'

2026-07-16 11:59:46 +07:00