Plugin providers are registered from a plugin's `config` hook and credentialed
from its `auth` loader, both inside the running OpenCode process. Nothing about
them reaches `opencode.json` or `auth.json`, so resolution that only reads files
could not see them: selecting such a model failed with "has no known API base
URL" while the same model worked in chat (#2666).
`GET /provider` is where that state is visible. A new `runtime-providers`
module keeps one cached snapshot of it and reports, per provider, the
credential and endpoint OpenCode itself resolved. Credential resolution becomes
config -> runtime -> auth.json, and endpoint resolution config -> openai default
-> runtime -> models.dev catalog.
Providers with a dedicated wire format (Copilot, ChatGPT-plan OpenAI, Anthropic,
Google) are excluded from the runtime credential: for them OpenCode reports an
OAuth access token that their real transport does not accept.
opencode zen is excluded when the user has no zen login. OpenCode then reports
the sentinel `apiKey: "public"` and trims its catalog to free models that run on
its own infrastructure; the sentinel is never read as a credential.
Claude Code stays refused for background actions even when a plugin publishes an
OpenAI-compatible endpoint for it, because that endpoint is a facade over the
Claude Agent SDK and spawns the CLI per request.
No capability probe. Asking `GET /models` does identify a plugin whose protocol
lives in its own `fetch`, but measured across the 166 providers with an `api`
URL in the models.dev catalog it also denies six that work and simply have no
`/models` route. A provider that vanishes from the picker explains nothing,
while one that fails on use says why, so availability stops at credential and
endpoint.
The same list drives the Small Model and Changes Walkthrough pickers.
Validated against a real OpenCode with four plugin providers loaded: offered
providers went from 3 to 7, zen and Claude Code stayed out, and a generation
through a plugin-backed model that previously failed now returns.
A diff is ordered by file path, which is almost never the order in which a
change makes sense. This adds a Walkthrough surface that reorders it: the model
groups related hunks into stops, explains what each group changes about
behavior, and orders the stops so each builds on the last. It explains and
orders; judging code stays with the existing Review action.
Reviews uncommitted work (all, staged, unstaged), a branch against its base, or
a pull request. Generation is always user-initiated — nothing runs on a timer,
on a file change, or as a side effect of opening a panel.
Invariants worth preserving:
- Hunk identity is derived on the server and only there. Ids are content
hashes, so an anchor that no longer resolves is proof the code it described
changed, and staleness needs no heuristics. The client matches ids to ids and
never recomputes them; two implementations would have to agree forever.
- The digest is never truncated. A diff that does not fit the model's context
is refused with an actionable reason, because a walkthrough written against
half a diff reads as confident and is wrong.
- Nothing disappears. Lockfiles and other generated output are excluded from
the model's input by name — never by size — and everything no stop covers is
listed at the end, so "have I seen all of it" stays answerable.
- Cost is explicit. Results are content-addressed, so returning the working
tree to an earlier state costs nothing; generation outlives its request, so a
refresh detaches the client rather than discarding paid-for work, and only an
explicit cancel stops it.
Supporting changes to shared modules:
- git: expose the existing getRangeDiff as GET /api/git
listUntrackedPaths and getUntrackedDiffs. The latter resolve the repository
once for a batch instead of per file, taking a panel
~340ms on an 80-file working tree.
- small-model: structured output across four wire forma
and abort signal, and an onOverflow policy so an oversized prompt fails
loudly instead of being silently clipped. A provider
remembered so the prompt-side fallback goes first next time.
- models.dev metadata: surface structured_output as tri
false blocks a model, a missing field does not, because the catalog omits it
for roughly half of all models.
Desktop and tablet only: VS Code serves Git through its
these routes, and the mobile shell does not consume the surface registry.
Docs: packages/docs walkthrough page in English and all eight locales.
Adds a server-side "small model" capability: direct, cheap LLM calls that
reuse the user's existing OpenCode provider logins — the mechanism OpenCode
uses internally for titles and summaries but does not expose through the
SDK or plugins. Zero new dependencies; plain fetch with per-provider wire
formats, credentials never leave the server.
Core (packages/web/server/lib/small-model):
- Resolution mirrors OpenCode's session scoping: explicit settings override
→ small_model from the OpenCode config → family scan within the session's
provider → the session's own model. The global provider scan only serves
callers without a session context, and background callers forbid it
entirely (restrictToPreferredProvider), so conversation content never
reaches a provider the user didn't pick — explicit choices excepted.
- Per-provider auth replicating OpenCode's plugin loaders: GitHub Copilot
(device token as bearer, no exchange), ChatGPT plan via the codex
Responses API (single-flight OAuth refresh written back to auth.json),
Anthropic messages, Google generateContent, generic OpenAI-compatible.
- OpenCode's free models (opencode/big-pickle, *-free) are never called
directly; unauthenticated providers are skipped by design.
- Prompt clamping to the model's catalog context limit; thinking disabled
where a wire switch exists (Z.AI/GLM, MiniMax-M3, Gemini Flash); robust
content parsing with a clear error when a thinking model spends its whol
budget on reasoning.
- Settings → Sessions gains a Small Model group: use-default checkbox plus
an override picker limited to authenticated providers, persisted with
web/desktop/VS Code sanitization parity.
Consumers:
- Session assist: a server-side watcher on the global SSE hub generates a
short recap and one suggested follow-up after a session idles quietly fo
a minute, stored on session metadata (openchamber.assist). Freshness is
keyed to the last assistant message id, so new activity invalidates the
payload everywhere with no extra writes. The chat shows the recap under
the last message after five quiet minutes and the suggestion as a
dismissible chip above the composer (tap fills the input, never sends).
Gated by a new Chat setting (default on) that is a hard generation
switch. Language is anchored to the conversation itself, with a
script-mismatch guard against model/backend language hallucination.
- TTS: a third input mode, summarized — long replies are condensed to
spoken prose before playback on any TTS engine.
- Git: commit-message and PR generation moved off the active chat session
onto the small model fed with real diffs and the commit list (bodies
included), with a session-transport fallback for free-model-only setups.
- Notes: Add to notes distills long selections into 1-3 dense sentences
preserving exact identifiers, with verbatim fallback on failure.
Fixes along the way:
- The global event watcher now starts unconditionally; it was gated behind
the desktop-notify env, leaving the server-side event hub dead in
packaged apps.
- OpenCode re-emits message.updated for old user messages after idle; the
watcher no longer mistakes those for new activity.
- Session metadata merges from a fresh read right before the PATCH, so
writes made during the generation window (suggestion dismissals, review
links) are preserved; the assist runtime stops during graceful shutdown.
Bohdan Triapitsyn