Samuel Reed 51fd17a8c3 fix(catalog): register plain Codex route for worker -wm SKUs ...

Codex backend discovery advertises worker-mode SKUs under a `-wm` suffix (gpt-5.6-luna-wm). Authoritative discovery replaced the bundled catalog and kept those slugs verbatim, so a configured `openai-codex/gpt-5.6-luna` vanished from the resolved catalog and the resolver's fuzzy fallback selected `-wm` instead — a route some ChatGPT accounts reject.

Model discovery now recognizes the `-wm` suffix: when the bundled Codex catalog ships the plain SKU, the `-wm` row is also registered under its plain id (re-derived so the 1M-window floor and daybreak pricing keyed on that slug still apply). Unknown `-wm` SKUs keep their authoritative verbatim slug and non-worker models are untouched, so distinct models and other providers are unaffected.

2026-08-18 16:23:02 -04:00

..

fixtures

test: refactored test suites to eliminate time-based sleeps and polling loops

2026-08-13 19:32:22 +02:00

aiand-provider.test.ts

feat: introduced aiand provider registry entry and model catalog

2026-08-01 08:30:37 +02:00

alibaba-token-plan.test.ts

fix(catalog): toggle qwen3.8 max thinking on wire

2026-08-08 19:38:31 +02:00

amazon-bedrock-openai.test.ts

fix(catalog): made bedrock-mantle dynamic discovery authoritative

2026-08-03 14:36:57 +02:00

amazon-bedrock-opus-5.test.ts

fix(ai,catalog): widen Bedrock stream-stall watchdog via model compat

2026-08-07 14:18:46 +08:00

amazon-bedrock-us-gov.test.ts

fix(catalog): emit AWS GovCloud us-gov Bedrock Claude inference profiles

2026-08-04 13:13:18 -05:00

anthropic-copilot-signing-compat.test.ts

fix(catalog,ai): moved anthropic-messages signing detection to hosts

2026-07-02 11:46:42 +00:00

anthropic-zenmux-signing-compat.test.ts

fix(catalog,ai): moved anthropic-messages signing detection to hosts

2026-07-02 11:46:42 +00:00

azure-provider.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

baseten-provider.test.ts

fix(catalog): expose Baseten Kimi K3 thinking levels

2026-08-12 19:26:23 -04:00

bedrock-prompt-cache.test.ts

fix(ai,catalog): widen Bedrock stream-stall watchdog via model compat

2026-08-07 14:18:46 +08:00

bedrock-stream-idle-timeout.test.ts

fix(ai,catalog): widen Bedrock stream-stall watchdog via model compat

2026-08-07 14:18:46 +08:00

build.test.ts

fix(catalog): keep xhigh on Grok multi-agent Responses models

2026-08-14 22:03:11 -07:00

bundled-reference-laziness.test.ts

test: refactored test suites to eliminate time-based sleeps and polling loops

2026-08-13 19:32:22 +02:00

canonical-limit-fallback.test.ts

fix(coding-agent): avoided blocking auth resolution during model switches

2026-06-13 15:39:04 +02:00

cerebras-provider.test.ts

fix(catalog): marked cerebras gemma vision capable

2026-06-30 02:48:08 +00:00

codex-discovery.test.ts

fix(catalog): register plain Codex route for worker -wm SKUs

2026-08-18 16:23:02 -04:00

coreweave-provider.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

cursor-discovery.test.ts

feat: introduced aiand provider registry entry and model catalog

2026-08-01 08:30:37 +02:00

descriptors.test.ts

fix(providers): switched xiaomi validation to mimo-v2.5

2026-07-01 05:53:42 +00:00

discovery-null-limits.test.ts

fix(catalog): wrapped model discovery fetches to support extra ca certificates

2026-07-02 01:51:10 +02:00

fireworks-fast.test.ts

chore(format): applied biome formatting and removed dead code from merged prs

2026-08-11 15:14:15 +02:00

fireworks-serverless-discovery.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

gateway-reference.test.ts

feat(gateway): map Vercel Responses cache anchors

2026-07-23 15:18:37 -04:00

generated-policies.test.ts

feat(catalog): updated context window floor and pricing parameters for gpt models

2026-08-17 10:47:30 +03:00

github-copilot-model-limits.test.ts

fix(catalog): scope Copilot model cache by credential

2026-08-14 05:12:06 +00:00

github-copilot-wire.test.ts

fix(auth): routed copilot business endpoint

2026-06-17 12:47:19 +00:00

gitlab-duo-workflow-discovery.test.ts

test: cleaned test suites and documented filtering guidelines

2026-08-13 08:28:42 +02:00

gmi-cloud-provider.test.ts

fix(catalog,ai): seeded GMI Cloud default model into bundled catalog

2026-07-31 18:40:09 +02:00

google-aistudio-compat.test.ts

fix(catalog): disable store field for Google AI Studio openai-compat host

2026-07-31 12:29:21 -04:00

google-vertex-discovery.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

hosts.test.ts

fix: google-vertex support multi-region endpoints

2026-07-27 19:36:48 +02:00

identity-family.test.ts

fix(catalog): advertise xhigh on first-party grok-4.6 Responses

2026-08-14 22:41:26 -07:00

issue-772-repro.test.ts

Drop Xiaomi ASR models from catalog

2026-06-15 05:35:19 -07:00

issue-830-repro.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

issue-847-repro.test.ts

refactor(catalog)!: split model catalog from pi-ai

2026-06-10 04:06:57 +02:00

issue-1617-repro.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

issue-1846-repro.test.ts

feat(ai): consolidated OpenAI-family streaming and add OpenRouter API support

2026-06-17 21:36:48 +02:00

issue-1849-repro.test.ts

fix(catalog): restored regenerated models.json with behavior-level tests

2026-07-17 06:22:44 +02:00

issue-2105-repro.test.ts

feat(catalog/provider-models): added OpenAI model provider descriptors

2026-06-15 10:40:48 +02:00

issue-2113-repro.test.ts

fix(catalog): corrected moonshot kimi request shaping

2026-06-11 05:28:17 +00:00

issue-2299-repro.test.ts

fix: resolved Fireworks Qwen models to openai thinking format

2026-06-20 09:25:36 +02:00

issue-2558-repro.test.ts

test(catalog): sourced Model and ModelSpec types from pi-catalog

2026-06-14 11:14:18 +00:00

issue-2883-moonshot-china.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

issue-3067-repro.test.ts

fix(catalog): retired stale Claude 4.6 wire ids and healed the bundled Sonnet route

2026-06-19 22:25:48 +02:00

issue-4297-repro.test.ts

fix(catalog): recognized bedrock and azure anthropic hosts as signing

2026-07-02 12:06:22 +00:00

issue-5572-repro.test.ts

fix(ai): gated custom eager streaming on compat provenance

2026-07-15 11:52:55 +00:00

issue-5598-repro.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

issue-5756-repro.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

issue-6563-repro.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

issue-6664-repro.test.ts

fix(catalog): gate copilot claude reasoning inference on the id classifier

2026-07-26 10:54:53 +00:00

issue-8315-repro.test.ts

fix(catalog): bound openai-compatible model discovery with default timeout

2026-08-12 05:26:49 +00:00

kimi-code-provider.test.ts

fix(catalog): derive kimi-code output caps per family

2026-07-26 14:41:32 +00:00

litellm-provider.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

lm-studio-provider.test.ts

fix(catalog): use LM Studio's loaded context window not the max

2026-07-21 20:55:05 +00:00

meta-provider.test.ts

address review: fix test, changelog and models.json newline

2026-08-09 18:50:43 +03:00

minimax-bundled-catalog.test.ts

fix(catalog): pinned MiniMax-M3 contextWindow to 1M on minimax-code(-cn) providers

2026-06-20 03:07:50 +00:00

model-id-affixes.test.ts

refactor(catalog)!: split model catalog from pi-ai

2026-06-10 04:06:57 +02:00

model-provider-priority.test.ts

refactor(catalog)!: split model catalog from pi-ai

2026-06-10 04:06:57 +02:00

model-thinking.test.ts

fix(catalog): advertise xhigh on first-party grok-4.6 Responses

2026-08-14 22:41:26 -07:00

nanogpt-model-limits.test.ts

refactor(catalog): baked thinking metadata into buildModel pipeline

2026-06-10 07:22:11 +02:00

novita-provider.test.ts

fix(providers): corrected novita discovery and login

2026-07-10 12:08:44 +02:00

ollama-cloud-output-caps.test.ts

fix(catalog): cap ollama cloud deepseek-v4 output at 65536

2026-08-01 15:30:17 +00:00

ollama-cloud-provider.test.ts

feat: introduced max reasoning effort tier across model and rpc systems

2026-07-10 13:39:42 +02:00

ollama-provider.test.ts

feat: introduced max reasoning effort tier across model and rpc systems

2026-07-10 13:39:42 +02:00

openai-daybreak.test.ts

fix(catalog): complete GPT-5.6 off and pricing support

2026-08-13 02:00:59 +02:00

opencode-provider.test.ts

fix(catalog): routed opencode-go deepseek-v4-flash through the responses api

2026-08-08 20:57:10 +02:00

provider-cache-id.test.ts

fix(catalog): preserved Ollama cache path prefixes

2026-07-30 13:39:17 +00:00

sakana-provider.test.ts

feat: introduced max reasoning effort tier across model and rpc systems

2026-07-10 13:39:42 +02:00

siliconflow-provider.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

synthetic-provider.test.ts

fix(catalog): keep Synthetic's wire-off reasoning through the manager merge

2026-07-31 11:52:23 +01:00

umans-provider.test.ts

feat(catalog): migrated model catalog endpoints to stencil.so with ETag and ZStd

2026-07-31 20:38:49 +02:00

variant-collapse.test.ts

feat(coding-agent): supported allSettled and any promise combinators in browser scope

2026-08-14 00:11:04 +02:00

venice-provider.test.ts

fix umans max token cap

2026-06-15 23:38:48 -07:00

wafer.test.ts

chore: update tests

2026-07-05 16:53:07 +02:00

xai-api-key-responses.test.ts

feat(catalog): default paid xAI and SuperGrok to grok-4.6

2026-08-16 16:29:14 -07:00

xai-oauth-bundle.test.ts

feat(catalog): default paid xAI and SuperGrok to grok-4.6

2026-08-16 16:29:14 -07:00

xai-responses-thinking-policy.test.ts

fix(catalog): advertise xhigh on first-party grok-4.6 Responses

2026-08-14 22:41:26 -07:00

zai-bundled-catalog.test.ts

test(catalog): fix zai catalog test types

2026-06-13 13:04:23 -07:00

zenmux-provider.test.ts

fix(model-discovery): auto-update ZenMux models into models.db without a key

2026-07-02 13:50:06 +09:00

zhipu-compat.test.ts

feat(catalog): add GLM-5.3 support with uniform low/high/max effort ladder and mandatory thinking

2026-08-13 23:18:17 -07:00