Ramiz Wachtler cbe0e8304f fix(ai): replace stale OpenRouter Llama 4 Maverick test model with Llama 4 Scout (#3421) ...

* fix(ai): replace stale OpenRouter Llama 4 Maverick test model

- Switch OpenRouter Meta test model from `meta-llama/llama-4-maverick` to `meta-llama/llama-4-scout` in AI tests.

- CI failure body:
  - packages/ai/test/context-overflow.test.ts(531,41): error TS2345: Argument of type "meta-llama/llama-4-maverick" is not assignable to parameter of type "...".
  - packages/ai/test/total-tokens.test.ts(520,40): error TS2345: Argument of type "meta-llama/llama-4-maverick" is not assignable to parameter of type "...".

* chore(ai): add changelog entry for OpenRouter test model swap

- Add Unreleased Fixed entry for switching OpenRouter Meta test model to llama-4-scout

- Reference PR #3421 attribution

2026-04-20 13:21:29 +02:00

..

data

feat(ai): Add image input tests for vision-capable models

2025-08-30 18:37:17 +02:00

abort.test.ts

fix(ai): prune deprecated direct minimax models

2026-03-25 22:44:32 +01:00

anthropic-oauth.test.ts

fix(ai): fix anthropic oauth manual callback and refresh flow closes #2169

2026-03-15 15:40:50 +01:00

anthropic-opus-4-7-smoke.test.ts

fix(ai): Fix a configuration bug with Opus 4.7 adaptive thinking (#3286)

2026-04-16 19:57:19 +02:00

anthropic-thinking-disable.test.ts

test(ai): align adaptive thinking payload assertions

2026-04-17 00:35:07 +02:00

anthropic-tool-name-normalization.test.ts

fix(ai): normalize tool names case-insensitively against CC tool list

2026-01-17 21:03:47 +01:00

azure-utils.ts

add Azure deployment name map and refresh generated models

2026-01-24 12:04:34 +01:00

bedrock-models.test.ts

feat(ai): Add Amazon Bedrock provider (#494)

2026-01-13 00:32:59 +01:00

bedrock-thinking-payload.test.ts

fix(ai): use SDK token auth and omit Bedrock display in GovCloud closes #3359

2026-04-18 01:24:13 +02:00

bedrock-utils.ts

feat(ai): Add Amazon Bedrock provider (#494)

2026-01-13 00:32:59 +01:00

cache-retention.test.ts

fix(ai): apply cache_control to string user messages

2026-02-02 19:19:12 +01:00

context-overflow.test.ts

fix(ai): replace stale OpenRouter Llama 4 Maverick test model with Llama 4 Scout (#3421)

2026-04-20 13:21:29 +02:00

cross-provider-handoff.test.ts

fix(ai): prune deprecated direct minimax models

2026-03-25 22:44:32 +01:00

empty.test.ts

fix(ai): prune deprecated direct minimax models

2026-03-25 22:44:32 +01:00

faux-provider.test.ts

feat(ai,coding-agent): add faux provider and ModelRegistry factories

2026-03-29 21:08:50 +02:00

github-copilot-anthropic.test.ts

refactor(ai): fix inconsistencies, trim ai code+replace tests, remove unnceccessary tool_result check

2026-02-12 18:41:12 +01:00

github-copilot-oauth.test.ts

fix(ai): improve GitHub Copilot OAuth polling (#1994)

2026-03-09 20:15:17 +01:00

google-gemini-cli-claude-thinking-header.test.ts

Improve Gemini CLI provider retries and headers (#670)

2026-01-13 01:04:53 +01:00

google-gemini-cli-empty-stream.test.ts

Improve Gemini CLI provider retries and headers (#670)

2026-01-13 01:04:53 +01:00

google-gemini-cli-retry-delay.test.ts

Improve Gemini CLI provider retries and headers (#670)

2026-01-13 01:04:53 +01:00

google-shared-convert-tools.test.ts

fix(ai): strip JSON Schema meta keys for Cloud Code Assist (#3412)

2026-04-19 16:54:49 +02:00

google-shared-gemini3-unsigned-tool-call.test.ts

fix(ai): use skip_thought_signature_validator for unsigned Gemini 3 tool calls

2026-03-05 22:04:00 +01:00

google-shared-image-tool-result-routing.test.ts

fix(ai): keep image tool results inline for gemini 3+ and antigravity closes #2052

2026-03-18 02:17:44 +01:00

google-thinking-disable.test.ts

fix(ai): handle explicit thinking off across providers closes #2490

2026-03-22 20:27:44 +01:00

google-thinking-signature.test.ts

fix(ai): correct Google thinking detection and remove unsupported id fields

2026-01-11 19:25:38 +01:00

google-tool-call-missing-args.test.ts

fix(ai): default tool call arguments to empty object for Google providers

2026-01-25 03:18:02 +01:00

google-vertex-api-key-resolution.test.ts

fix(ai): treat gcp vertex marker as ADC auth (#3221)

2026-04-15 16:20:45 +02:00

image-tool-result.test.ts

fix(ai,coding-agent): replace deprecated kimi k2p5 model closes #3242

2026-04-16 12:06:24 +02:00

interleaved-thinking.test.ts

Extend interleaved thinking test to Anthropic first-party provider (#1413)

2026-02-12 17:27:42 +01:00

lazy-module-load.test.ts

feat(ai): lazy-load provider modules for faster startup fixes #2297

2026-03-17 18:03:24 +01:00

mistral-reasoning-mode.test.ts

fix(ai): use reasoning_effort for Mistral Small 4 closes #3338

2026-04-17 22:44:27 +02:00

mistral-tool-schema.test.ts

fix(ai): sanitize Mistral tool schemas closes #3361

2026-04-18 00:54:46 +02:00

oauth.ts

WIP: Remove global state from pi-ai OAuth/API key handling

2025-12-25 01:01:03 +01:00

openai-codex-cache-affinity-e2e.test.ts

fix: align OpenAI cache affinity and use uuidv7 session ids

2026-04-14 23:20:13 +02:00

openai-codex-stream.test.ts

fix(ai): trust requested Codex service tier (#3307)

2026-04-17 01:50:04 +02:00

openai-completions-tool-choice.test.ts

fix(ai): restore FakeOpenAI mock .withResponse() so openai-completions tests pass

2026-04-16 22:57:30 +02:00

openai-completions-tool-result-images.test.ts

Enable tool streaming for newer Z.ai models (#2732)

2026-03-31 14:28:24 +02:00

openai-responses-cache-affinity-e2e.test.ts

fix: align OpenAI cache affinity and use uuidv7 session ids

2026-04-14 23:20:13 +02:00

openai-responses-copilot-provider.test.ts

fix(ai): set session id headers for all OpenAI compatible responses (#3264)

2026-04-16 22:38:40 +02:00

openai-responses-foreign-toolcall-id.test.ts

fix(ai): hash foreign responses tool item ids

2026-03-22 05:40:26 +01:00

openai-responses-partial-json-cleanup.test.ts

fix(ai): strip partialJson from responses tool calls

2026-04-14 18:56:53 +02:00

openai-responses-reasoning-replay-e2e.test.ts

fix(ai): handle same-provider different-model handoff in OpenAI Responses API

2026-01-22 00:58:49 +01:00

openai-responses-tool-result-images.test.ts

fix(ai): send tool result images in function_call_output closes #2104

2026-03-14 00:49:40 +01:00

openrouter-cache-write-repro.test.ts

fix(ai): preserve cache_write_tokens in completions stream usage closes #2802

2026-04-04 21:39:11 +02:00

overflow.test.ts

fix(ai): fix bedrock throttling misidentification (#2699)

2026-03-30 17:26:03 +02:00

responseid.test.ts

fix(ai): expose provider response ids on assistant messages fixes #2245

2026-03-17 17:11:38 +01:00

stream.test.ts

fix(ai): sanitize Mistral tool schemas closes #3361

2026-04-18 00:54:46 +02:00

supports-xhigh.test.ts

fix(ai): Fix a configuration bug with Opus 4.7 adaptive thinking (#3286)

2026-04-16 19:57:19 +02:00

tokens.test.ts

fix(ai,coding-agent): replace deprecated kimi k2p5 model closes #3242

2026-04-16 12:06:24 +02:00

tool-call-id-normalization.test.ts

fix(ai): normalize pipe-separated tool call IDs for cross-provider handoff

2026-01-29 01:28:12 +01:00

tool-call-without-result.test.ts

fix(ai): prune deprecated direct minimax models

2026-03-25 22:44:32 +01:00

total-tokens.test.ts

fix(ai): replace stale OpenRouter Llama 4 Maverick test model with Llama 4 Scout (#3421)

2026-04-20 13:21:29 +02:00

transform-messages-copilot-openai-to-anthropic.test.ts

refactor(ai): fix inconsistencies, trim ai code+replace tests, remove unnceccessary tool_result check

2026-02-12 18:41:12 +01:00

unicode-surrogate.test.ts

fix(ai): prune deprecated direct minimax models

2026-03-25 22:44:32 +01:00

validation.test.ts

fix(ai): skip AJV validation in restricted runtimes closes #2395

2026-03-19 22:51:12 +01:00

xhigh.test.ts

feat(ai): add strictResponsesPairing for Azure OpenAI Responses API

2026-01-18 20:15:33 +01:00

zen.test.ts

feat(ai,coding-agent): add OpenCode Go provider support closes #1757

2026-03-03 16:02:29 +01:00