22 Commits

Author SHA1 Message Date
ton 367ebc1c7f new_pull 2026-07-26 14:02:37 +07:00
David Brailovsky f16b4e0cda add deferred tools support for kimi in openai-completions api 2026-07-16 12:26:56 +00:00
Petr Houška 298665cfb9 fix(ai): support OpenRouter session affinity (#6496)
Fixes #6366
2026-07-13 09:57:53 +02:00
Samwise Wang 279f53b098 fix(ai): use "(no tool output)" placeholder for empty tool results without images (#6290)
OpenAI Completions and Responses providers unconditionally replaced empty
tool result text with "(see attached image)", even when the result had no
image content. This caused the model to hallucinate image attachments for
commands that produce no output (e.g. curl -s with SSL errors, grep with
no matches, true/false).

Now matches the Google provider behavior: "(see attached image)" is only
used when images are actually present; empty results get "(no tool output)".

Co-authored-by: tzwm <tzwm@users.noreply.github.com>
Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
2026-07-06 21:42:56 +02:00
Mario Zechner abbd911693 Merge main into model-registry 2026-06-22 14:00:18 +02:00
Armin Ronacher 8b97e75c6b feat(ai): add chat-template thinking compat
closes #5673
2026-06-19 23:34:17 +02:00
Mario Zechner 8a0903ebf2 feat(ai): compat entrypoint, core-only root barrel (phase 5)
The root barrel is now core-only and side-effect free: types,
createModels/createProvider, auth substrate, lazyStream/lazyApi, faux,
utils. Generated catalogs, api-registry, env-api-keys, images, global
stream functions, and per-API lazy wrappers leave the root.

New @earendil-works/pi-ai/compat preserves the old surface verbatim as
a strict superset of the root: api-dispatch stream/complete with env
key injection, the builtin registration side effect (skip-if-present so
it cannot clobber earlier overrides), deprecated getModel/getModels/
getProviders aliases of the new getBuiltin* reads in providers/all,
lazy api wrappers + setBedrockProviderModule, and image generation.
Compat dies with the coding-agent ModelManager migration.

Packaging: exports map gains ./compat, ./providers/*, ./api/*;
sideEffects array lists only the effectful modules.

Old-global imports across agent/coding-agent/examples and pi-ai tests
switch to /compat (path-only; compat is a superset). The coding-agent
extension loader resolves the pi-ai ROOT specifier to compat, so
existing user extensions using the old global API keep working at
runtime until compat is removed. vitest configs alias /compat to src;
browser smoke imports old globals from /compat.
2026-06-10 21:17:12 +02:00
Mario Zechner ba93da9a93 feat(ai): move API implementations to src/api with lazy wrappers (phase 2)
Stream implementations move from src/providers/ to src/api/, renamed by
API id (anthropic.ts -> anthropic-messages.ts, google.ts ->
google-generative-ai.ts, mistral.ts -> mistral-conversations.ts,
amazon-bedrock.ts -> bedrock-converse-stream.ts). Every module now
exports exactly stream/streamSimple; shared helpers move alongside.

New ProviderStreams dispatch contract in types.ts, lazyApi() wrapper in
api/lazy.ts, and one .lazy.ts wrapper per API. Bedrock's wrapper keeps
the node-only variable-specifier import and setBedrockProviderModule()
(now taking ProviderStreams).

providers/register-builtins.ts deleted; interim until the compat
entrypoint lands, builtin api-registry registration lives in stream.ts
and lazy wrappers are exported from the root barrel. Old per-API lazy
exports (streamAnthropic, ...) are gone; package.json subpaths retarget
to dist/api/.
2026-06-10 20:08:59 +02:00
Mario Zechner 2e02c74dcb chore: pin dependencies and use native TypeScript 2026-05-20 12:46:17 +02:00
Mario Zechner 80f06d3636 feat: add model thinking level metadata
closes #3208
2026-05-02 01:21:06 +02:00
Mario Zechner 1e33492525 fix(coding-agent): harden clipboard copy
closes #3639
2026-04-24 12:55:58 +02:00
Mario Zechner 4cd4cfd98e fix(ai): support long cache retention compat
closes #3543
2026-04-23 23:43:34 +02:00
Mario Zechner 6af10c9c7f fix(ai): make OpenAI Responses session_id header optional closes #3579 2026-04-23 23:12:24 +02:00
Mario Zechner 3054fd7a3b fix(ai,coding-agent): support anthropic-style cache control for openai compatibles closes #3392 2026-04-20 17:12:05 +02:00
Mario Zechner 4b2caf43a8 fix(ai): add completions session affinity compat closes #3430 2026-04-20 16:55:16 +02:00
Kao Félix 758ede4da0 Enable tool streaming for newer Z.ai models (#2732) 2026-03-31 14:28:24 +02:00
Abdeslam Yassine Agmar eb9f1183ad refactor(ai): migrate mistral provider to conversations sdk 2026-03-03 17:25:50 +00:00
Mario Zechner 7b96041068 fix(ai): map groq qwen3 reasoning effort values closes #1745 2026-03-03 16:44:42 +01:00
Mario Zechner ff0eb3ecd4 fix(ai): omit strict for unsupported openai completions 2026-02-02 00:44:55 +01:00
Ben Vargas e045a9f142 feat(ai): add Vercel AI Gateway routing support (#1051)
* feat(ai): add Vercel AI Gateway routing support

Add vercelGatewayRouting to OpenAICompletionsCompat, parallel to
openRouterRouting. When a model targets ai-gateway.vercel.sh and has
vercelGatewayRouting configured, the openai-completions provider passes
providerOptions.gateway with only/order in the request body.

Changes:
- types.ts: VercelGatewayRouting interface + field on OpenAICompletionsCompat
- openai-completions.ts: buildParams passes providerOptions.gateway,
  detectCompat/getCompat include the new field
- model-registry.ts: VercelGatewayRoutingSchema for models.json validation
- test: updated Required<OpenAICompletionsCompat> in test fixture

* docs(coding-agent): add vercelGatewayRouting to custom models documentation
2026-01-30 01:44:51 +01:00
jake dac7474da2 feat(ai): add OpenRouter provider routing support
Allows custom models to specify which upstream providers OpenRouter
should route requests to via the `openRouterRouting` field in model
definitions.

Supported fields:
- `only`: list of provider slugs to exclusively use
- `order`: list of provider slugs to try in order
2026-01-25 03:34:49 +01:00
Michael Renner 6289c144bf fix(ai): batch tool-result images after consecutive tool results (#902)
Fixes 400 errors when reading multiple images via GitHub Copilot's
Claude models. Claude requires tool_use -> tool_result adjacency with
no user messages interleaved.

Before: assistant(tool_calls) -> tool -> user(images) -> tool -> user(images)
After:  assistant(tool_calls) -> tool -> tool -> user(all images)
2026-01-22 13:10:10 +01:00