Replace the previous implementation with one that registers the Provider API
catalog through pi's own provider layer instead of shipping a custom transport,
cache file, and hand-maintained pricing table.
- models: derive the catalog from the published command-code CLI package
(context windows, reasoning efforts, image input, output limits, rates) and
keep it as the offline baseline; scripts/sync-catalog.mjs regenerates it and
supports --check
- refresh: use refreshModels plus context.publish so pi persists the live
/provider/v1/models listing in models-store.json and restores it offline
- auth: /login browser transfer through a localhost callback server with a
pasted-key fallback; $COMMAND_CODE_API_KEY, --api-key and auth.json keep
working
- streaming: pi's native openai-completions and anthropic-messages adapters;
the generate-transport fallback and Oh My Pi branches are gone
- keep the context-overflow rewrite that enables pi's compaction retry and the
/commandcode-quota command
- tests: 51 cases under tests/<module>/ covering models, catalog sync, auth,
the callback server, overflow handling, quota, and the extension factory
Verified against the live API: chat, tool round trip, image input and
--thinking max on deepseek/deepseek-v4.1-flash, quota output, and catalog
persistence in an interactive session.
Refresh the generated capability catalog from command-code@1.44.0 to
1.53.1. deepseek/deepseek-v4.1-flash now advertises image input and its
low, high, and max reasoning efforts, so pi forwards attached images and
exposes the full thinking-level selector instead of reporting the model
as text-only without selectable levels. The sync also adds gpt-6-astra,
xai/grok-4.6, and inclusionai/ling-3.0-flash-sante:free metadata.
Drop the now-obsolete manual Meta Muse Spark effort overrides because
upstream publishes efforts for meta/muse-spark-1.1 through 1.3-contributor
and MiniMaxAI/MiniMax-M3, and add a regression test for the V4.1
capabilities.
Oh My Pi kept the unresolved $COMMAND_CODE_API_KEY placeholder as a literal config API key that shadowed its /login credential store and was sent as the Bearer token (401). The placeholder is now registered only on pi, where it keeps the API-key auth method and --api-key working next to OAuth; on OMP the provider omits apiKey unless a real key is configured. Host-supplied placeholders are resolved or stripped on every stream path, and the legacy generate transport uses the same rule.
Stored /login OAuth and API-key credentials, --api-key, and env keys are now covered end to end on both pi and Oh My Pi, and CI runs the pi suite against a real binary.
Co-authored-by: ebreen <ebreen@users.noreply.github.com>
The standalone section read like a commit message and sat between Install
and Authentication as if it were a core topic. Keep the part users need
(sibling extensions share the connection and credentials, so their
requests count against Command Code usage) as one sentence under Usage;
the registry mechanics stay in index.ts and the changelog.
google/gemini-3.7-flash currently fails on the Provider API with a
zero-data-retention routing 404 for every request, which made the GOAT
live suite red regardless of provider changes. GPT-5.6 Luna is available
on every plan, accepts image input, and completes the vision request.
PR #69 added efforts for meta/muse-spark-* directly to the generated
catalog, which the drift check flags and the daily sync job reverts.
Keep src/commandcode-catalog.ts byte-identical to upstream and merge a
separate src/commandcode-catalog-overrides.ts over it at load time. A
test fails as soon as upstream publishes efforts for an overridden model
so the override gets removed instead of shadowing the CLI catalog.
Verified against the live endpoint: pi --thinking xhigh sends
reasoning_effort="xhigh" for meta/muse-spark-1.2-contributor and the
request succeeds; --thinking off sends none.
Closes#69
The official CLI marks meta/muse-spark-* as reasoning models but ships no
effort levels for them and sends no effort parameter, so the thinking level
stays off in pi. Document that so the locked footer is not mistaken for a
provider bug.
Refs #69
(cherry picked from commit 263310635a89e35cf0b3da527474555c9687903e)
Every host start awaited a full catalog request before the provider
registered, costing one HTTPS round-trip (up to the discovery timeout on a
hanging connection) even when a cache written seconds earlier was on disk.
Register the cached catalog immediately and run the live refresh in the
background; the live result re-registers the provider when it arrives. A
first start without a cache still awaits the live catalog. The background
refresh is aborted on session_shutdown so print mode does not wait for it.
Closes#63
(cherry picked from commit 142191f9420fe90460cdc3cbae70e26d0c000860)
pi routes the main chat through the registered provider, but sibling
extensions that call streamSimple from @earendil-works/pi-ai/compat with
the active Command Code model resolve model.api through the compat
api-registry, which only knows built-in APIs. On plain pi that failed
with "No API provider registered for api: commandcode-custom".
Register commandcode-custom there and delegate to the transport router.
The registry resolves no credentials for extension providers, so fall
back to the configured Command Code key when the caller passes none.
Closes#68
(cherry picked from commit 7e9659e672771c6a9223b95938e50fb2a051a0a7)
Add claude-fable-5-1, deepseek/deepseek-v4-flash-fast, and
tencent/hy4-preview with their reasoning efforts, add moonshotai/Kimi-K3
efforts, and drop minimax/minimax-m3-free, which the CLI no longer lists.
Synchronize the static model catalog with command-code@1.36.0, which adds
Qwen/Qwen3.8-Flash (reasoning efforts low, medium, xhigh) and
z-ai/glm-5.3-flash (low, high, max), the free minimax/minimax-m3-free
model, and the glm-5.3-flash output limit, and drops the retired
stealth/ox-alpha.
Fetches live account quota from Command Code alpha usage endpoints
(whoami, billing/credits, billing/subscriptions, usage/summary) and
renders a plain-text dashboard via ui.notify.
- Graceful degradation: optional endpoint transport/timeout/parse
failures degrade to null sections instead of aborting; only 401/403
are hard failures. 429 is transient, not fatal.
- Overall deadline bounds the whole command to QUOTA_TIMEOUT_MS
(per-request controllers are chained; post-deadline phases fail fast).
- OMP auth: filter unresolved $COMMANDCODE_API_KEY placeholder and fall
back to the host resolver via pickCommandCodeApiKey.
- ZDR privacy header respected on quota requests.
- Redaction reuses redactCommandCodeErrorText plus JSON-quoted
credential fields; outer-catch errors are redacted too.
- resetAt parsed from seconds, ms, numeric string, or ISO string.
- 21 hermetic unit tests wired into npm test (test:quota).
Resolve the Command Code model cache through the host's getAgentDir helper so pi, OMP, and PI_CODING_AGENT_DIR use their own agent state directory instead of the official Command Code client directory.
Persist the last valid Command Code model catalog and use it when live model discovery fails. Keep first-time offline startup non-fatal, surface clear warnings, and cover cached model selection with unit and pi integration regression tests.
Support OMP as a host alongside pi:
- Convert OMP's array-format system prompts to string via systemPromptToText
- Guard against OMP passing the literal env-var name as the API key value
- Add ~/.omp/agent/auth.json to default auth path lookup
- Fix --list-models output to check both stdout and stderr
- Add OMP compatibility smoke test with isolated temp HOME and mock server
- Deduplicate usage section in README, add OMP install and usage docs
Document the incremental reasoning-delta streaming, live display pricing,
and dynamic model fetch in CHANGELOG.md. Add a Pricing section to
README.md explaining the MODEL_COSTS overlay and how to update prices.
- Add scripts/extract-models.ts to parse command-code npm dist file
- Generate models.json (21 models, 15 pricing entries) with contextWindow
and maxOutputTokens pre-filled; no nulls or hardcoded fallbacks in index.ts
- Rewrite index.ts to load model list and costs from models.json
- Cap gateway model maxOutputTokens at 65536 (API limit for Baseten/Vercel)
- Add 'Update models' section to README documenting the generation flow
- Add npm run extract-models script
cat-shark
