Closes#11678
Changes:
- `catalog/providers/github-copilot.ts`: add `microsoft-decision-1` as a
`typesafe-system-one` classifier (text input, 32768 context, $0.042/M
input, Copilot's static headers).
- `src/providers/github-copilot.ts`: register the classifier and wrap
`typesafeSystemOneApi()` to add `/v1` to the base URL, since Copilot
serves `/v1/systemone` and the OAuth login replaces the base URL with
the account endpoint.
- README and `docs/models.md`: add the model to the classifier tables.
Tests:
- `test/classifier-models.test.ts`: with an OAuth credential, the
request goes to `https://api.enterprise.githubcopilot.com/v1/systemone`
with the Copilot headers, and the model stays available although
`availableModelIds` lists only chat models. With an API key, it goes to
`https://api.individual.githubcopilot.com/v1/systemone`. Both tests fail
without the wrapper.
- Ran against `api.enterprise.githubcopilot.com` with a Copilot login:
bool, choice, and score questions return answers and usage.
Co-authored-by: Hongwei Ma <11957602+Marvae@users.noreply.github.com>
Update the model catalog protocol to pi.dev after a change to stop
pi.dev redirecting released clients to `?pi-version=` URLs and serve
their catalog directly. The released CLI is unaffected.
Plugins import the app's versioned API (createPlugins api option: unlisted
versions, other kinds' modules, mixed versions and direct Chord imports refused),
each other by relative path within a root or by package name across
repositories (npm or git pins), with per-kind files checked by name.
chord.plugins lists a package's plugins. Required roots, single-file plugins,
installPlugin from git or npm, testPlugin with stub facets.
plugin-authoring.md for authors and agents. Examples 49-52.
The non-strict input_schema kept only type/properties/required, so
property $refs into root $defs or definitions pointed at nothing. Claude
then produced wrong arguments (a JSON string instead of an object), and
some Anthropic-compatible gateways rejected the request.
Root anyOf/oneOf/allOf are still left out: Anthropic rejects them with a
400. That part of #9557 and #9134 stays open.
Enable per-message effort for OpenCode Claude models that support it, which
also sends thinking.block_binding drop_block. OpenCode Go rejected replayed
thinking with a 400 after the tool list or system prompt changed.
closes#10954
When a partial assistant reply fails and automatic retry succeeds, pi
appends a `context_edit` that hides the failed attempt from model
context. Branch summarization (`/tree` with summarize) built its input
from raw session entries through `getMessageFromEntry`, which ignored
`context_edit` entries. As a result, the summarizer received the hidden
attempt again. Content replacements were ignored the same way.
What the change does:
- `prepareBranchEntries` now collects the latest `context_edit` for each
target in the branch.
- It applies those edits to the entries it converts, using the same
`projectContextEntry` logic as the live context and compaction:
- an omission (`replacement: null`) drops the entry;
- a replacement swaps its content.
- `projectContextEntry` is now exported from `session-manager.ts` so
both paths share it.
- The existing branch-summary behavior is unchanged: tool results are
still skipped, and compaction or branch-summary entries still become
summary messages.
Testing:
- Added `applies context edits to branch entries` to
`test/branch-summarization.test.ts`. It covers one omitted assistant
entry and one replaced assistant entry. The test fails without the
change and passes with it.
- Ran `branch-summarization`, `branch-summary-extensions`,
`agent-session-branching` and the compaction tests: all pass.
- `npm run check`: biome and the coding-agent checks pass. `tsc` reports
6 errors in `packages/ai` model-catalog tests, and the same 6 errors
occur on unmodified `main`.
- End-to-end reproduction with the faux provider and `AgentSession`: a
failed attempt, a successful retry, then `navigateTree(target, {
summarize: true })`. Before the change, the summary request contained
the failed attempt's text. After the change, it contains only the
successful retry.
Fixes#11602
Requested by @davidbrai
Co-authored-by: triagent <triagent@localhost>
A relayed hold released (or its principal refused or revoked) while the route resolved made #resolve throw before adding the connection, so the spawned host's link was never read and its own upstream references failed unavailable/ready_timeout after readyTimeout. The connection is now added right after resolve; the checks only fail the relay.
Codemode and write rows keep their last highlighting in a CodeHighlighter
that checks theme and grammar changes itself. Markdown reuses the top-level
blocks of its last render, held weakly, and assistant messages reuse their
Markdown instances while streaming. Text.setText() keeps its wrapped lines
for unchanged text.
closes#10971
Schema helpers are a thin layer over pi-schema's builders with the same JSON,
so fingerprints and stored data are unchanged (proven by schema-switch tests and
a store written by the TypeBox code). Checks through pi-schema; error messages
are pi-schema's; format is an annotation. v1 contracts take any JSON Schema.
map(bytes()) works.
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.
- Declared-object checks walk the value's own keys with for...in, whose
property reads V8 serves from the enum cache, instead of reading each
declared name from a list: nested Chord-style arguments 535 -> 409 ns
(TypeBox 474), recursive $ref schemas 1.1 us -> 753 ns.
- Schemas are indexed for references only on the first $ref; base URIs are
derived from $id while compiling. Compiling a new schema 43 -> 21 us.
- Drop the keyed cache of leaf checks: on distinct schemas its entries cost
more than sharing saved. Bare types still share module-level checks and
patterns share their RegExp. 3,200 distinct schemas 7.9 -> 7.1 MB
(cfworker 7.6 MB).
@earendil-works/pi-schema compiles JSON Schema (drafts 2020-12 and 7) once into
plain closures: no eval or new Function, so it runs under a strict CSP. It
passes 2,222 of the 2,223 core tests of the official JSON-Schema-Test-Suite,
checks Chord-style argument schemas within 1.2x of TypeBox's JIT, and keeps
3,200 compiled schemas in 7.9 MB (TypeBox: 54.7 MB).
- compile(schema, options) returns a Validator: check() is the boolean check
(a type guard for builder schemas), errors() reports each failure with a
JSON Pointer path, missing and unknown fields at the field.
- Builders (str, int, obj, opt, union, ...) return plain JSON Schema typed with
the values it accepts (Static<typeof schema>).
- Formats are an optional entry point (./formats), adapted from TypeBox (MIT).
- Tests run the vendored suite (drafts 2020-12 and 7, with optional and format
tests); npm run bench compares conformance, speed, setup cost, memory and
bundle size with TypeBox, @cfworker/json-schema and omptype.
esbuild is a non-dev package through chord's optional peer dependency, so its optional @esbuild/* platform packages are non-dev as well. npm install regenerates this; the committed lockfile had stale dev flags.
