3d6acb37b9
fix(ai): regenerate model catalog
...
Includes updated Xiaomi MiMo pricing from models.dev. Closes #6138
2026-06-30 08:33:18 +02:00
6fbeba51af
Merge pull request #5832 from stephanmck/fix/provider-error-body-passthrough-5763
...
fix(ai): surface provider HTTP error body instead of opaque SDK message
2026-06-29 16:58:24 +02:00
b91bdd5a3e
fix(ai): preserve Z.AI thinking content
...
closes #6083
2026-06-29 08:40:20 +02:00
54113731b2
fix(ai): use HTTP timeout for Codex SSE headers
...
Refs #4945
2026-06-28 19:57:47 +02:00
09f1059575
fix(ai): clamp streamSimple max tokens
...
Clamps streamSimple max-token defaults against estimated context, addressing #5595 .
closes #6061
2026-06-25 14:10:28 +02:00
f78b163713
fix(ai): revert minimax max token clamp
2026-06-25 13:36:04 +02:00
62fad94f1a
fix(ai): surface provider HTTP error body instead of opaque SDK message
...
Add a shared normalizeProviderError helper in packages/ai/src/utils/error-body.ts
and route the 8 body-blind / status-only providers through it (amazon-bedrock,
azure-openai-responses, google, google-vertex, images/openrouter,
openai-codex-responses, openai-completions, openai-responses). Non-schema 4xx/5xx
responses from proxies / gateways now show the real reason carried in the response
body alongside the HTTP status, instead of "403 status code (no body)" or
"Unknown: UnknownError".
The helper probes status (statusCode, status, $metadata.httpStatusCode,
$response.statusCode) and body (body, parsed error object, $response.body) across
the Mistral, OpenAI, Google, and Bedrock SDK shapes, truncates the body at a 4000
char cap, and preserves error.message when the SDK already folded the body in
(Anthropic / Google happy path). mistral.ts and anthropic.ts are left untouched.
Provider prefixes and the OpenRouter metadata.raw append are preserved.
closes #5763
2026-06-25 12:07:51 +02:00
b940c52e7e
fix(ai): clamp MiniMax shared budget max tokens
...
closes #6061
2026-06-25 12:00:37 +02:00
8c9dbffa36
fix(ai): preserve responses reasoning for out-of-order items
...
closes #6009
2026-06-25 11:57:52 +02:00
9cd2c81ada
fix(ai): regenerate model catalogues
2026-06-25 11:56:33 +02:00
d7868b0998
feat(ai): add reasoning token counts to Usage
...
Add optional reasoning?: number to Usage as a subset of output. Populate
for Anthropic (output_tokens_details.thinking_tokens), OpenAI
Responses/Codex/Azure (output_tokens_details.reasoning_tokens), OpenAI
Completions (completion_tokens_details.reasoning_tokens), and Google
Generative AI / Vertex (thoughtsTokenCount). Bedrock Converse and Mistral
do not return a reasoning breakdown, so they stay unset.
closes #6057
2026-06-25 10:35:02 +02:00
371adcf371
fix(coding-agent): retry explicit provider retry errors
...
closes #6019
2026-06-24 18:14:06 +02:00
a2e3e9d8b2
Merge pull request #6004 from gukoff/support-azure-foundry-endpoints
...
feat: Normalize modern Microsoft Foundry Responses API endpoints
2026-06-24 10:38:57 +02:00
8277bd6896
Add [Unreleased] section for next cycle
2026-06-23 23:45:39 +02:00
0201806adf
Release v0.80.2
2026-06-23 23:45:36 +02:00
9096d5f9a6
docs: update changelog entries
2026-06-23 23:42:02 +02:00
e1a2dc04f4
fix(ai): restore detectCompat runtime fallback in openai-completions
...
refs #6020
2026-06-23 23:29:44 +02:00
ef231c4910
fix(ai): resolve request-scoped auth before provider calls
...
closes #6021
2026-06-23 23:27:00 +02:00
04fce8099f
Merge remote-tracking branch 'origin/main'
2026-06-23 22:30:15 +02:00
49fbe6834f
fix(ai): align api key credentials with auth json
2026-06-23 22:29:46 +02:00
386d079afa
fix(ai): restore legacy compat stream aliases
...
closes #6016
2026-06-23 22:20:20 +02:00
6184307c39
fix(ai): require explicit anthropic compat metadata
2026-06-23 21:04:59 +02:00
e00074358d
Add [Unreleased] section for next cycle
2026-06-23 20:04:12 +02:00
1c4a9ba7c8
Release v0.80.1
2026-06-23 20:04:09 +02:00
828493b37c
fix(ai): unblock release provider tests
2026-06-23 19:57:29 +02:00
86528dd9ee
Add [Unreleased] section for next cycle
2026-06-23 19:30:35 +02:00
f08e968c83
Release v0.80.0
2026-06-23 19:30:32 +02:00
526351d99a
docs: audit unreleased changelogs
2026-06-23 19:25:26 +02:00
2be6e67028
docs(ai): document bundling behavior
2026-06-23 16:40:46 +02:00
cd95c2749f
fix(ai): require OpenAI Responses terminal events
2026-06-23 16:35:45 +02:00
2285f87964
fix(ai): remove legacy raw API subpaths
2026-06-23 15:58:50 +02:00
e3dcb244f8
Support modern Microsoft Foundry Responses API endpoints:
...
- support *.ai.azure.com endpoints
- normalize away the /responses postfix in the query path which by
default is added on Microsoft Foundry UI
2026-06-23 15:38:43 +02:00
12ace0ba46
docs(ai): reference README in migration guide
2026-06-23 15:33:37 +02:00
15f92260d7
docs(ai): expand models migration guide
2026-06-23 15:32:42 +02:00
129eb460cd
feat(ai): complete models runtime migration
2026-06-23 15:29:46 +02:00
6a4813a7ca
Merge remote-tracking branch 'origin/main'
...
# Conflicts:
# packages/ai/CHANGELOG.md
2026-06-23 13:52:09 +02:00
8eeaa2bcba
fix(ai): honor scoped env in compat API key injection
2026-06-23 13:45:26 +02:00
2cbce395fb
feat(ai): pass provider-resolved env to APIs
2026-06-23 13:42:25 +02:00
5a8ea0bc81
fix(ai): honor scoped AWS profile in Bedrock endpoint resolution
2026-06-23 13:36:44 +02:00
d0e0b84cb9
fix(ai): reconnect Codex websocket on connection limit
...
closes #5973
2026-06-23 00:17:37 +02:00
f7d3331df6
fix(ai): mock copilot models in oauth test
2026-06-22 17:49:18 +02:00
02540acd17
docs(ai): update provider README
2026-06-22 15:08:52 +02:00
732bb1617b
Merge model-registry into main
2026-06-22 14:53:24 +02:00
abbd911693
Merge main into model-registry
2026-06-22 14:00:18 +02:00
71ca9b2b92
fix(ai): expose OpenCode Go GLM-5.2 xhigh effort
...
closes #5967
2026-06-22 13:45:44 +02:00
4f71b2d3b7
fix(coding-agent): clarify ZAI Coding Plan label
...
closes #5965
2026-06-22 13:04:08 +02:00
717a8f958a
fix(ai): revert selective pi-ai base entrypoints
2026-06-22 12:54:32 +02:00
329dceb5f3
Add [Unreleased] section for next cycle
2026-06-22 11:14:46 +02:00
8e1900666f
Release v0.79.10
2026-06-22 11:14:43 +02:00
7d0497fdb7
fix(ai): preserve early reasoning details
...
closes #5114
2026-06-22 10:14:59 +02:00
Vegard Stikbakke