[{"name":"data","kind":"directory","size":0,"lastCommitHash":"796e48b80ed3c652068653e6eae3647cf6a0994b","lastCommitWhen":"2025-08-30T18:37:17+02:00","lastCommitMessage":"feat(ai): Add image input tests for vision-capable models\n\n- Added image tests to OpenAI Completions (gpt-4o-mini)\n- Added image tests to Anthropic (claude-sonnet-4-0)\n- Added image tests to Google (gemini-2.5-flash)\n- Tests verify models can process and describe the red circle test image\n"},{"name":"abort.test.ts","kind":"file","size":9334,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"anthropic-eager-tool-input-compat.test.ts","kind":"file","size":4069,"lastCommitHash":"ffa0f3123984241a6bc72280a3161dbf2fd52567","lastCommitWhen":"2026-04-23T23:12:45+02:00","lastCommitMessage":"fix(ai): support Anthropic eager tool streaming compat\n\ncloses #3575\n"},{"name":"anthropic-eager-tool-input-e2e.test.ts","kind":"file","size":4882,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"anthropic-long-cache-retention-e2e.test.ts","kind":"file","size":4084,"lastCommitHash":"4cd4cfd98ebf57e391b3848e1b66c0d0d41df38a","lastCommitWhen":"2026-04-23T23:43:34+02:00","lastCommitMessage":"fix(ai): support long cache retention compat\n\ncloses #3543\n"},{"name":"anthropic-oauth.test.ts","kind":"file","size":3191,"lastCommitHash":"e645995a4a6d1d512744c386c0aa7068445f8b93","lastCommitWhen":"2026-03-15T15:40:50+01:00","lastCommitMessage":"fix(ai): fix anthropic oauth manual callback and refresh flow closes #2169\n"},{"name":"anthropic-opus-4-7-smoke.test.ts","kind":"file","size":2513,"lastCommitHash":"d1c6cb1e0f8bf7051c33d66588999b347ae08b04","lastCommitWhen":"2026-04-16T19:57:19+02:00","lastCommitMessage":"fix(ai): Fix a configuration bug with Opus 4.7 adaptive thinking (#3286)"},{"name":"anthropic-sse-parsing.test.ts","kind":"file","size":7681,"lastCommitHash":"58c4b7c5960906cd114d06dad873c5f19e97ce9e","lastCommitWhen":"2026-07-20T14:24:54-07:00","lastCommitMessage":"fix prime inference anthropic prompt caching (#478)\n\n* fix(ai): enable prime inference anthropic caching (ENG-4723)\n\n* fix(ai): price long cache writes correctly (fixes #478)\n\n* fix(ai): preserve provider cache pricing (fixes #478)"},{"name":"anthropic-thinking-disable.test.ts","kind":"file","size":7363,"lastCommitHash":"9f7c8ff1f916e5ee6cf3e745fe1221f003cfc17f","lastCommitWhen":"2026-07-01T14:05:46-07:00","lastCommitMessage":"add claude fable 5 support (#302)\n\n* support claude fable 5's always-on thinking and surface it on prime inference\n\n* keep fable off the prime inference curated list"},{"name":"anthropic-tool-name-normalization.test.ts","kind":"file","size":4672,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"azure-openai-base-url.test.ts","kind":"file","size":5218,"lastCommitHash":"9dcde1e3fa3bea29e64a85cb1990eea41748f1b4","lastCommitWhen":"2026-04-27T18:38:03+02:00","lastCommitMessage":"add cognitive services implementation (#3799)"},{"name":"azure-utils.ts","kind":"file","size":897,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"bedrock-endpoint-resolution.test.ts","kind":"file","size":4098,"lastCommitHash":"a0a16c7762e6985adf88f5eae081e3c371e42580","lastCommitWhen":"2026-04-21T13:20:10+02:00","lastCommitMessage":"fix(amazon-bedrock): restore regional endpoint resolution\n\ncloses #3481\ncloses #3485\ncloses #3486\ncloses #3487\ncloses #3488\n"},{"name":"bedrock-models.test.ts","kind":"file","size":1606,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"bedrock-thinking-payload.test.ts","kind":"file","size":7982,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"bedrock-utils.ts","kind":"file","size":211,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"cache-retention.test.ts","kind":"file","size":13131,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"cloudflare-utils.ts","kind":"file","size":339,"lastCommitHash":"a45577bd0020a89ba6f14d744b287b5a998b02b7","lastCommitWhen":"2026-05-01T00:56:05+02:00","lastCommitMessage":"fix(ai): finalize cloudflare gateway provider support\n"},{"name":"codex-websocket-cached-probe.ts","kind":"file","size":10354,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"context-overflow.test.ts","kind":"file","size":22475,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"cross-provider-handoff.test.ts","kind":"file","size":15021,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"empty.test.ts","kind":"file","size":22693,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"fast-mode.test.ts","kind":"file","size":1740,"lastCommitHash":"848081edb1f9a4f4d643cdb1cc01e1d99bc61cfd","lastCommitWhen":"2026-08-21T16:08:23+02:00","lastCommitMessage":"Support /fast with OpenAI API-key authentication (#1609)\n\n* feat(coding-agent): support /fast with OpenAI API-key authentication (ENG-5425)\n\nWidens supportsFastMode() to admit GPT-5.4/GPT-5.5/GPT-5.6 on the openai\nprovider (openai-responses API) in addition to ChatGPT auth, corrects the\nGPT-5.6 fast-pricing multiplier from 2.5x to 2x per OpenAI's current\npricing table, and updates the /fast unavailable message.\n\nResolves discussion #1595.\n\n* docs(ai): trim pricing comments to source reference only\n\n* chore: drop research scratch file from the branch\n\n* chore: restore package-lock.json from main (unrelated npm churn)\n\n* test: update fast-mode unavailable message assertion"},{"name":"faux-provider.test.ts","kind":"file","size":20615,"lastCommitHash":"ef6af5ebbd36b349e1aed594e628cd3781c8578b","lastCommitWhen":"2026-03-29T21:08:50+02:00","lastCommitMessage":"feat(ai,coding-agent): add faux provider and ModelRegistry factories\n"},{"name":"fireworks-models.test.ts","kind":"file","size":1358,"lastCommitHash":"0fa717d4f01265e4418bda57d444aa4c36a6b8d9","lastCommitWhen":"2026-08-28T11:39:18+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1878)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\n* fix(ai): correct OpenCode Go Qwen API mapping and drop dev/ Prime routes\n\n- opencode-go qwen models mislabeled @ai-sdk/anthropic by models.dev now\n  map to openai-completions at /v1 (generalizes the qwen3.5/3.6 fix;\n  affects qwen3.8-flash today)\n- isPrimeInferencePrivateModel also filters dev/ routes, removing\n  dev/kimi-k3-high-throughput ($0 dev route) from the public catalog"},{"name":"github-copilot-anthropic.test.ts","kind":"file","size":3322,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"github-copilot-oauth.test.ts","kind":"file","size":6007,"lastCommitHash":"fd0c7c3bdb5cdced790f2900f2fd878e2cbd6e3b","lastCommitWhen":"2026-03-09T20:15:17+01:00","lastCommitMessage":"fix(ai): improve GitHub Copilot OAuth polling (#1994)"},{"name":"google-shared-convert-tools.test.ts","kind":"file","size":4417,"lastCommitHash":"f732f5e85865996ffff27776ae4919b742e00ced","lastCommitWhen":"2026-04-19T16:54:49+02:00","lastCommitMessage":"fix(ai): strip JSON Schema meta keys for Cloud Code Assist (#3412)"},{"name":"google-shared-gemini3-unsigned-tool-call.test.ts","kind":"file","size":4254,"lastCommitHash":"f7df474084d72b5a68b19354735d603228d13222","lastCommitWhen":"2026-04-30T21:59:21+02:00","lastCommitMessage":"fix google vertex unsigned tool call replay closes #4032\n"},{"name":"google-shared-image-tool-result-routing.test.ts","kind":"file","size":3096,"lastCommitHash":"fe66edd943691f8eac295fef68ce36930c35fa05","lastCommitWhen":"2026-04-30T21:24:36+02:00","lastCommitMessage":"remove gemini cli and antigravity support\n"},{"name":"google-thinking-disable.test.ts","kind":"file","size":5490,"lastCommitHash":"fe66edd943691f8eac295fef68ce36930c35fa05","lastCommitWhen":"2026-04-30T21:24:36+02:00","lastCommitMessage":"remove gemini cli and antigravity support\n"},{"name":"google-thinking-signature.test.ts","kind":"file","size":1523,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"google-vertex-api-key-resolution.test.ts","kind":"file","size":6407,"lastCommitHash":"65a6472bdd372d3cce51c99830a33f778f0127c7","lastCommitWhen":"2026-04-24T00:05:43+02:00","lastCommitMessage":"fix(ai): forward google vertex base url\n\ncloses #3619\n"},{"name":"google-vertex-thinking-budget.test.ts","kind":"file","size":2170,"lastCommitHash":"32aef469a63d8635e2e7f98edcdacf6fc497386d","lastCommitWhen":"2026-07-22T10:53:39+02:00","lastCommitMessage":"fix(ai): align Vertex Flash-Lite thinking budget (#463)\n\n* fix(ai): align Vertex Flash-Lite thinking budget\n\n* test(ai): decouple Vertex preview coverage from catalog"},{"name":"image-tool-result.test.ts","kind":"file","size":15233,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"interleaved-thinking.test.ts","kind":"file","size":5298,"lastCommitHash":"35ff2689ee0a74009db73c697025de88ad86f6fb","lastCommitWhen":"2026-04-22T19:59:33+02:00","lastCommitMessage":"fix(typebox): migrate to v1 with extension compat (#3474)\n\n* fix(typebox): migrate to v1 with extension compat\n\nReplace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.\n\nThis change closes #3112.\n\n* fix(typebox): use canonical imports and harden coercion\n\nSwitch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.\n\nRemove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.\n\nFixes #3112.\n\n---------\n\nCo-authored-by: Mario Zechner <badlogicgames@gmail.com>"},{"name":"kimi-test-model.ts","kind":"file","size":797,"lastCommitHash":"8454794b4878895ec85d60c41b57febcf938ee65","lastCommitWhen":"2026-07-17T09:46:43-07:00","lastCommitMessage":"test(ai): follow live Kimi coding catalog (#465)"},{"name":"lazy-module-load.test.ts","kind":"file","size":3294,"lastCommitHash":"d9c54e19c84b27d1bc889d7ac9472004239ed006","lastCommitWhen":"2026-08-31T21:50:04+09:00","lastCommitMessage":"fix(ai): preload provider modules at process startup\n\nUpgrading a global install rotates the hashed bundle chunk files under a\nstill-running process. Provider adapters load lazily via dynamic import,\nso the first request for a not-yet-loaded adapter after an upgrade\nresolves against the mutated install and fails with \"Cannot find\nmodule\". preloadApiProviderModules() warms every provider module at boot\nin every process that enters main() (interactive client, daemon worker,\ndaemon supervisor), so a running process never resolves provider chunks\nfrom disk again. Load failures still surface per-stream through the\nlazy wrappers.\n"},{"name":"log.test.ts","kind":"file","size":2339,"lastCommitHash":"189bb1466836a474ba98a25a0c3b43751f08fd43","lastCommitWhen":"2026-07-02T13:00:08-07:00","lastCommitMessage":"make provider failures diagnosable from logs (#313)\n\n* add structured logging and provider stream-failure classification\n\n* address review: reserved log keys, sink fallback, body request_id\n\n* address review: never auto-retry structured auth/invalid_request failures\n\n* address review: log serialization must survive circular refs and bigints\n\n* show users a concise classified error, keep the raw cause in the log"},{"name":"mcp-oauth.test.ts","kind":"file","size":18796,"lastCommitHash":"8c749fb98ecd72e0508d4e7990ae83177e054668","lastCommitWhen":"2026-08-21T20:11:07+02:00","lastCommitMessage":"fix(ai): follow MCP protected-resource OAuth discovery (#1591)\n\n* fix(ai): discover path-scoped MCP OAuth resources\n\n* fix(ai): preserve canonical MCP OAuth resources\n\n* fix(ai): allow same-origin OAuth tenant issuers"},{"name":"mistral-reasoning-mode.test.ts","kind":"file","size":2540,"lastCommitHash":"779d0ef39df4a1b5ee68dc06ecc6b3a3f853ea85","lastCommitWhen":"2026-04-30T12:18:17+02:00","lastCommitMessage":"feat(ai): add Mistral Medium 3.5 model (#4009)"},{"name":"mistral-tool-schema.test.ts","kind":"file","size":2004,"lastCommitHash":"35ff2689ee0a74009db73c697025de88ad86f6fb","lastCommitWhen":"2026-04-22T19:59:33+02:00","lastCommitMessage":"fix(typebox): migrate to v1 with extension compat (#3474)\n\n* fix(typebox): migrate to v1 with extension compat\n\nReplace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.\n\nThis change closes #3112.\n\n* fix(typebox): use canonical imports and harden coercion\n\nSwitch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.\n\nRemove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.\n\nFixes #3112.\n\n---------\n\nCo-authored-by: Mario Zechner <badlogicgames@gmail.com>"},{"name":"oauth.ts","kind":"file","size":1887,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"openai-codex-cache-affinity-e2e.test.ts","kind":"file","size":1207,"lastCommitHash":"018b40c30c90e7d745ed3e03bd74c10ce22680ad","lastCommitWhen":"2026-04-14T23:20:13+02:00","lastCommitMessage":"fix: align OpenAI cache affinity and use uuidv7 session ids\n"},{"name":"openai-codex-oauth.test.ts","kind":"file","size":1012,"lastCommitHash":"3029836894d0f2429e2084d9043db984e92c3f0c","lastCommitWhen":"2026-05-06T00:14:40+02:00","lastCommitMessage":"fix(ai): stop Codex OAuth stderr writes\n\ncloses #4141\n"},{"name":"openai-codex-stream.test.ts","kind":"file","size":33417,"lastCommitHash":"848081edb1f9a4f4d643cdb1cc01e1d99bc61cfd","lastCommitWhen":"2026-08-21T16:08:23+02:00","lastCommitMessage":"Support /fast with OpenAI API-key authentication (#1609)\n\n* feat(coding-agent): support /fast with OpenAI API-key authentication (ENG-5425)\n\nWidens supportsFastMode() to admit GPT-5.4/GPT-5.5/GPT-5.6 on the openai\nprovider (openai-responses API) in addition to ChatGPT auth, corrects the\nGPT-5.6 fast-pricing multiplier from 2.5x to 2x per OpenAI's current\npricing table, and updates the /fast unavailable message.\n\nResolves discussion #1595.\n\n* docs(ai): trim pricing comments to source reference only\n\n* chore: drop research scratch file from the branch\n\n* chore: restore package-lock.json from main (unrelated npm churn)\n\n* test: update fast-mode unavailable message assertion"},{"name":"openai-completions-always-thinking.test.ts","kind":"file","size":3386,"lastCommitHash":"4a770d657c741044a547b490f2059c1aafb7f7a7","lastCommitWhen":"2026-08-31T21:52:03+09:00","lastCommitMessage":"make rlm spawns fail-closed: schema-bound results by default, guarded context, explicit unguarded opt-out\n"},{"name":"openai-completions-cache-control-format.test.ts","kind":"file","size":8410,"lastCommitHash":"58c4b7c5960906cd114d06dad873c5f19e97ce9e","lastCommitWhen":"2026-07-20T14:24:54-07:00","lastCommitMessage":"fix prime inference anthropic prompt caching (#478)\n\n* fix(ai): enable prime inference anthropic caching (ENG-4723)\n\n* fix(ai): price long cache writes correctly (fixes #478)\n\n* fix(ai): preserve provider cache pricing (fixes #478)"},{"name":"openai-completions-empty-tools.test.ts","kind":"file","size":7967,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"openai-completions-prompt-cache.test.ts","kind":"file","size":6385,"lastCommitHash":"91154d9757c1da8a7b2ba5be4bf025fe58d53114","lastCommitWhen":"2026-04-24T20:22:16+02:00","lastCommitMessage":"fix: update stale CI test expectations\n"},{"name":"openai-completions-reasoning-replay.test.ts","kind":"file","size":5093,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"openai-completions-response-model.test.ts","kind":"file","size":3866,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"openai-completions-thinking-as-text.test.ts","kind":"file","size":5652,"lastCommitHash":"80f06d3636312a87ad7a9b5d74a726ad62c24d34","lastCommitWhen":"2026-05-02T01:21:06+02:00","lastCommitMessage":"feat: add model thinking level metadata\n\ncloses #3208\n"},{"name":"openai-completions-tool-choice.test.ts","kind":"file","size":31469,"lastCommitHash":"a9b5d88b50db50860088772a408e867f8071b507","lastCommitWhen":"2026-08-24T13:30:05-07:00","lastCommitMessage":"fix: preserve ACP quiescence and Chat reasoning lineage (#1612)\n\n* fix(acp): await terminal quiescence before prompt completion\n\n* docs(changelog): add ACP quiescence fragment\n\n* fix(ai): preserve chat reasoning details on replay\n\n* fix(ai): emit valid reasoning-only chat messages\n\n* fix: preserve streamed reasoning and ACP cancellation\n\nFixes #1612.\n\n* fix(acp): retain ownership through terminal publication\n\nFixes #1612."},{"name":"openai-completions-tool-result-images.test.ts","kind":"file","size":4134,"lastCommitHash":"22e9900d33e6e2451dfc55999eafd149849a33f0","lastCommitWhen":"2026-06-30T15:55:13-07:00","lastCommitMessage":"fix(ai): gate tool-result image placeholder on hasImages (#290)\n\nEmpty-text tool results with no image were serialized to the literal\n\"(see attached image)\" on openai-completions and openai-responses,\nmaking models hallucinate a phantom image. Gate the placeholder on\nhasImages, mirroring google-shared/mistral."},{"name":"openai-responses-cache-affinity-e2e.test.ts","kind":"file","size":1158,"lastCommitHash":"018b40c30c90e7d745ed3e03bd74c10ce22680ad","lastCommitWhen":"2026-04-14T23:20:13+02:00","lastCommitMessage":"fix: align OpenAI cache affinity and use uuidv7 session ids\n"},{"name":"openai-responses-copilot-provider.test.ts","kind":"file","size":7859,"lastCommitHash":"783e96a14431e9cb33299d8c5e162cc5ad6e7c69","lastCommitWhen":"2026-05-07T22:52:54+02:00","lastCommitMessage":"fix(ai): disable OpenAI reasoning where supported\n"},{"name":"openai-responses-empty-tool-result.test.ts","kind":"file","size":2506,"lastCommitHash":"22e9900d33e6e2451dfc55999eafd149849a33f0","lastCommitWhen":"2026-06-30T15:55:13-07:00","lastCommitMessage":"fix(ai): gate tool-result image placeholder on hasImages (#290)\n\nEmpty-text tool results with no image were serialized to the literal\n\"(see attached image)\" on openai-completions and openai-responses,\nmaking models hallucinate a phantom image. Gate the placeholder on\nhasImages, mirroring google-shared/mistral."},{"name":"openai-responses-foreign-toolcall-id.test.ts","kind":"file","size":2650,"lastCommitHash":"b21b42d032919de2f2e6920a76fa9a37c3920c0a","lastCommitWhen":"2026-03-22T05:40:26+01:00","lastCommitMessage":"fix(ai): hash foreign responses tool item ids\n"},{"name":"openai-responses-partial-json-cleanup.test.ts","kind":"file","size":3301,"lastCommitHash":"e2b40dfc8198589f548f409d6986875655168fc4","lastCommitWhen":"2026-04-14T18:56:53+02:00","lastCommitMessage":"fix(ai): strip partialJson from responses tool calls\n\nMutate persisted tool-call blocks in place on function_call completion,\nremove partialJson, and emit the same reference on toolcall_end.\nAdd regression coverage for persisted block cleanup and event identity.\n\nfixes #3078\n"},{"name":"openai-responses-reasoning-replay-e2e.test.ts","kind":"file","size":7797,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"openai-responses-tool-result-images.test.ts","kind":"file","size":7326,"lastCommitHash":"35ff2689ee0a74009db73c697025de88ad86f6fb","lastCommitWhen":"2026-04-22T19:59:33+02:00","lastCommitMessage":"fix(typebox): migrate to v1 with extension compat (#3474)\n\n* fix(typebox): migrate to v1 with extension compat\n\nReplace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.\n\nThis change closes #3112.\n\n* fix(typebox): use canonical imports and harden coercion\n\nSwitch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.\n\nRemove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.\n\nFixes #3112.\n\n---------\n\nCo-authored-by: Mario Zechner <badlogicgames@gmail.com>"},{"name":"openrouter-cache-write-repro.test.ts","kind":"file","size":2394,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"openrouter-reasoning.test.ts","kind":"file","size":3519,"lastCommitHash":"91977ebf065d74ea0defbbba3bf5638a130d7983","lastCommitWhen":"2026-08-12T09:35:33+02:00","lastCommitMessage":"feat(ai): derive reasoning levels from provider metadata (#1258)\n\n* feat(ai): derive reasoning levels from provider metadata\n\n* fix(ai): sync reasoning metadata for rebased catalog\n\n* fix(ai): serialize explicit off for effort models\n\n* slight update to doc / desc of xhigh\n\n---------\n\nCo-authored-by: Alex Zhang <alex.lx.zhang@gmail.com>"},{"name":"overflow.test.ts","kind":"file","size":3129,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"prime-inference-models.test.ts","kind":"file","size":9001,"lastCommitHash":"0fa717d4f01265e4418bda57d444aa4c36a6b8d9","lastCommitWhen":"2026-08-28T11:39:18+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1878)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\n* fix(ai): correct OpenCode Go Qwen API mapping and drop dev/ Prime routes\n\n- opencode-go qwen models mislabeled @ai-sdk/anthropic by models.dev now\n  map to openai-completions at /v1 (generalizes the qwen3.5/3.6 fix;\n  affects qwen3.8-flash today)\n- isPrimeInferencePrivateModel also filters dev/ routes, removing\n  dev/kimi-k3-high-throughput ($0 dev route) from the public catalog"},{"name":"responseid.test.ts","kind":"file","size":4691,"lastCommitHash":"127861591417bab3c426784d5e8415413c45f287","lastCommitWhen":"2026-05-11T12:07:41-07:00","lastCommitMessage":"fix prime-tui review follow-ups and unblock ci (#22)\n\n* fix prime-tui review follow-ups and unblock CI\n\n- transcript ordering: child agent transcript now appends each assistant\n  message in chronological order instead of overwriting the first slot\n  after every tool call. currentAssistantIndex resets on new assistant\n  message_start and on tool_execution_start so tool rows stay between\n  successive assistant turns.\n- quietStartup: default reverted to false, and the brand splash is once\n  again gated on `verbose || !quietStartup`. Setting `quietStartup: true`\n  renders the empty header (no splash, no spacers) like pi-mono did.\n- ci: bump pinned model literal in packages/ai/test/*.ts from\n  \"claude-sonnet-4\" (no longer in the regenerated models.dev union) to\n  \"claude-sonnet-4.5\", which preserves the non-adaptive-thinking\n  semantics those tests rely on. Unblocks tsgo --noEmit on main and on\n  every open PR.\n\n* dedupe final assistant entry when child streamed it already"},{"name":"stream-failure.test.ts","kind":"file","size":6134,"lastCommitHash":"189bb1466836a474ba98a25a0c3b43751f08fd43","lastCommitWhen":"2026-07-02T13:00:08-07:00","lastCommitMessage":"make provider failures diagnosable from logs (#313)\n\n* add structured logging and provider stream-failure classification\n\n* address review: reserved log keys, sink fallback, body request_id\n\n* address review: never auto-retry structured auth/invalid_request failures\n\n* address review: log serialization must survive circular refs and bigints\n\n* show users a concise classified error, keep the raw cause in the log"},{"name":"stream.test.ts","kind":"file","size":50201,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"supports-xhigh.test.ts","kind":"file","size":4764,"lastCommitHash":"4a0b3de73657d1a6422ad83b811c9bcd2f274dfd","lastCommitWhen":"2026-07-09T12:55:16-07:00","lastCommitMessage":"add gpt-5.6 model catalogs (#361)\n\n* feat(ai): add GPT-5.6 model catalogs\n\n* fix(ai): align GPT-5.6 reasoning levels\n\n* fix(ai): disable reasoning for base GPT-5.6"},{"name":"tokens.test.ts","kind":"file","size":10241,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"tool-call-id-normalization.test.ts","kind":"file","size":7433,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"tool-call-without-result.test.ts","kind":"file","size":10951,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"total-tokens.test.ts","kind":"file","size":20454,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"transform-messages-copilot-openai-to-anthropic.test.ts","kind":"file","size":5646,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"unicode-surrogate.test.ts","kind":"file","size":22937,"lastCommitHash":"9bc00557489020e4dc981bef3111cb651c5955e7","lastCommitWhen":"2026-08-25T13:04:54+02:00","lastCommitMessage":"chore(ai): regenerate the model catalog from live provider catalogs (#1759)\n\n* chore(ai): regenerate the model catalog from live provider catalogs\n\nCommits the current `npm run generate-models` output. Net 1260 -> 1231\nmodels. The big mover: models.dev rescoped cloudflare-ai-gateway to\nproxied third-party models only (57 -> 31 ids), dropping the\nworkers-ai/@cf/* mirrors (still served by cloudflare-workers-ai) and\nlegacy OpenAI ids (gpt-4, gpt-4-turbo, o1, o1-pro, o3-pro, gpt-5-pro,\ngpt-5.2/5.3 family, plain gpt-5.6). Other changes: devstral-2512 and\nMiniMax M2.7/M3 free routes on OpenRouter, longcat-2.0 on OpenCode Go,\ngpt-oss-safeguard-120b on Vercel AI Gateway; retired inclusionai\nling/ring and nvidia nemotron free routes. Repricing: gpt-5.6/gpt-5.6-sol\n5/30 -> 4/20 (OpenAI + Azure), kimi-k2.6 raised to 0.95/4, glm-5.1/5.2\nraised, deepseek-v4-pro halved on OpenRouter.\n\nThe removed workers-ai/@cf/moonshotai/kimi-k2.6 gateway id is what broke\nmain's CI (TS2345 in packages/ai tests); this updates the affected\ntests, the gateway default model (now claude-sonnet-4.5), and the\nprovider docs to match the rescoped catalog.\n\nAll provider fetches succeeded during generation; no provider section\nwas emptied by a failed source.\n\n* fix(ai): restore kimi-k2.6 output limit on Prime Inference and drop a history-narrating test comment\n\nOpenRouter stopped publishing max_completion_tokens for moonshotai/kimi-k2.6,\nwhich collapsed the Prime Inference entry to the 8192 default. models.dev\n(moonshotai first-party and openrouter) both list output = context = 262144;\npin that in PRIME_INFERENCE_MODEL_METADATA like the other gap-fills.\n\nThe openrouter-provider entry still shows the 4096 fallback; that fallback is\npre-existing generator behavior affecting 53 models (kimi-k2.5 included on\nmain today) and deserves its own change rather than a rider here.\n\n* fix(ai): restore minimax-m2.7 output limit on Prime Inference\n\nOpenRouter also stopped publishing max_completion_tokens for\nminimax/minimax-m2.7, collapsing the Prime Inference entry to the 8192\ndefault the same way as kimi-k2.6. models.dev (minimax first-party)\nlists output = 131072; pin it in PRIME_INFERENCE_MODEL_METADATA."},{"name":"validation.test.ts","kind":"file","size":3873,"lastCommitHash":"35ff2689ee0a74009db73c697025de88ad86f6fb","lastCommitWhen":"2026-04-22T19:59:33+02:00","lastCommitMessage":"fix(typebox): migrate to v1 with extension compat (#3474)\n\n* fix(typebox): migrate to v1 with extension compat\n\nReplace AJV-based validation with TypeBox-native validation, keep legacy extension imports working (including @sinclair/typebox/compiler), and restore coercion for serialized/plain JSON schemas.\n\nThis change closes #3112.\n\n* fix(typebox): use canonical imports and harden coercion\n\nSwitch first-party code to canonical typebox imports while retaining legacy extension aliases in the loader.\n\nRemove obsolete runtime codegen guards, expand serialized JSON-schema coercion coverage, and update related tests and fixtures.\n\nFixes #3112.\n\n---------\n\nCo-authored-by: Mario Zechner <badlogicgames@gmail.com>"},{"name":"xhigh.test.ts","kind":"file","size":2171,"lastCommitHash":"032e3ee74574ca16efaf8745a1394b821256a5d0","lastCommitWhen":"2026-08-18T12:17:35+02:00","lastCommitMessage":"chore: remove redundant comments and unused internals (#1505)\n\n* chore: remove redundant comments\n\n* chore(tui): remove redundant export comments\n\n* chore(coding-agent): remove redundant example comments\n\n* chore(ai): remove redundant comments\n\n* chore(coding-agent): remove obsolete core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(coding-agent): remove redundant rpc test comments\n\n* chore(coding-agent): remove redundant CLI comments\n\n* chore(agent): remove redundant comments\n\n* chore(tui): remove redundant source comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant mode comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(ai): remove redundant source comments\n\n* chore(coding-agent): remove redundant session comments\n\n* chore(coding-agent): remove redundant core comments\n\n* chore(coding-agent): remove redundant test comments\n\n* chore(tests): remove redundant test comments\n\n* chore: remove unused internal helpers\n\n* docs: restore public API contracts\n\n* chore(coding-agent): restore invariant documentation\n\n* chore(coding-agent): clarify agent family contracts\n\n* style(coding-agent): format restored contracts\n\n* fix: restore intentional catch explanations"},{"name":"zai-test-model.test.ts","kind":"file","size":1470,"lastCommitHash":"8c0b90eea8f6ea2a7123746dd40b4a000e725947","lastCommitWhen":"2026-07-31T19:53:55-07:00","lastCommitMessage":"fix(ai): keep z.ai provider tests compatible with live catalogs (#568)\n\n* fix(ai): select live z.ai test models\n\n* fix(ai): bound z.ai overflow test payload"},{"name":"zai-test-model.ts","kind":"file","size":916,"lastCommitHash":"8c0b90eea8f6ea2a7123746dd40b4a000e725947","lastCommitWhen":"2026-07-31T19:53:55-07:00","lastCommitMessage":"fix(ai): keep z.ai provider tests compatible with live catalogs (#568)\n\n* fix(ai): select live z.ai test models\n\n* fix(ai): bound z.ai overflow test payload"},{"name":"zen.test.ts","kind":"file","size":850,"lastCommitHash":"42579dd9230a0efcf8c8805d0a26bdb2b9075e80","lastCommitWhen":"2026-03-03T16:02:29+01:00","lastCommitMessage":"feat(ai,coding-agent): add OpenCode Go provider support closes #1757\n"}]