Commit graph

6 commits

Author SHA1 Message Date
Mario Zechner
6536f80129 feat(ai,agent,coding-agent): validate tool arguments with pi-schema, drop TypeBox
pi-schema: opt-in coercion, compile(schema, { coerce: true }) with coerce() and
parse(), the superset of TypeBox's Value.Convert rules and pi-ai's old coercion;
unresolvedRefs option; url and json-pointer-uri-fragment formats.
pi-ai: Tool takes any JSON Schema; validation through pi-schema; Type, Static
and TSchema are no longer exported (breaking). pi-agent-core and pi-durable:
tools on pi-schema, no TypeBox dependency. Coding agent: extensions keep Type,
Static, TSchema and StringEnum through an extension view of pi-ai; built-in
tools stay on TypeBox.
2026-11-01 10:08:42 +00:00
Armin Ronacher
7f225f25d8 feat(ai,coding-agent): image input for System One classifiers
Jev (TypeSafe, Workers AI), Clef (Workers AI), and OpenRouter decision
models now accept ClassifierContext.images. Each service takes its own
wire form: TypeSafe assets with the opt-in header, Clef images data URLs,
or OpenRouter image_url parts in the state. A new SystemOneCompat
(imageInput, sendImageOptInHeader) selects the form; catalog entries set
it explicitly and models.json provider compat now applies to classifiers.

Adds Clef Omni and Jev 1.14 on Workers AI and fixes Clef Flash and
Workers AI Jev catalog pricing.
2026-10-21 23:53:47 +02:00
Christian Klotz
8efd314fa3
docs(ai,coding-agent): generate models.json reference from schemas (#11038)
* docs(ai,coding-agent): generate models.json reference from schemas

Add npm run generate:references, which renders docs/models-configuration.md
from the models.json TypeBox schemas, and describe provider and model fields
in those schemas. Overrides get their own descriptions without defaults, and
compat sections cover the Responses API aliases.

closes #10790

* Modify changelog

* docs(ai,coding-agent): use shared thinkingLevelMap and promptCache schemas

Replace the per-use schema helpers with fixed schemas whose descriptions
hold for both models and modelOverrides entries.
2026-10-16 21:53:00 +01:00
David Brailovsky
60ac3bcc3b
feat(ai): keep the prompt cache when changing thinking level on OpenAI GPT-6 (#10930)
With an API key, GPT-6 models on the openai provider now keep reasoning.effort
fixed and send the thinking level as configuration_update input items. Each
reply records its level, so earlier items are rebuilt unchanged on every request.
Controlled by compat.supportsMidConvoEffort; skipped for Sign in with ChatGPT
and thinking off.

closes #10853
2026-10-14 10:56:20 +02:00
Christian Klotz
96abe9a5ad
feat(coding-agent): use pi.dev configuration schemas (#10751)
* feat(coding-agent): use pi.dev configuration schemas

* refactor(coding-agent): separate schema URL from output path

* docs(coding-agent): document published schema URLs
2026-10-11 14:48:42 +01:00
Christian Klotz
7f9e1198f2
feat(coding-agent): publish configuration schemas (#9880)
* feat(coding-agent): publish configuration schemas

* fix(coding-agent): preserve config schema metadata

* fix(coding-agent): align schemas with public contracts

* fix(ai): place compatibility schema with providers

* fix(ai,coding-agent): align configuration schema contracts

* fix(ai): reuse session affinity schema

* docs(coding-agent): document strict theme validation

* fix(ai,coding-agent): align runtime and generated schemas

* fix(ai,coding-agent): centralize configuration schema contracts

* fix(ai,coding-agent): preserve schema validation contracts

* fix(coding-agent): validate keybinding schema grammar

* fix(ai,coding-agent): refine configuration schemas

* fix(ai,tui,coding-agent): align schemas with runtime behavior

* fix(tui): normalize shifted symbol keybindings

* fix(ai): preserve compatibility auto-detection
2026-10-08 10:01:17 +02:00