feat(providers): add Command Code preset with live model discovery - #923
Merged
Conversation
📝 WalkthroughWalkthroughThe provider registry adds Command Code with key authentication, OpenAI-compatible routing, bounded live model discovery, and unknown API-key validation. Tests cover configuration, discovery, routing, fallback behavior, and parity. English and localized documentation update provider counts and Command Code usage details. ChangesCommand Code provider
Estimated code review effort: 3 (Moderate) | ~20 minutes Sequence Diagram(s)sequenceDiagram
participant OpenCodex
participant CommandCodeModels
participant CommandCodeChat
OpenCodex->>CommandCodeModels: GET /provider/v1/models
CommandCodeModels-->>OpenCodex: Return bounded model catalog
OpenCodex->>CommandCodeChat: POST /provider/v1/chat/completions with bearer key
CommandCodeChat-->>OpenCodex: Return OpenAI-compatible completion
Possibly related issues
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs-site/src/content/docs/guides/providers.md`:
- Line 193: Update the catalog introduction in
docs-site/src/content/docs/guides/providers.md:193-193 and its translations in
docs-site/src/content/docs/ja/guides/providers.md:122-122,
docs-site/src/content/docs/ko/guides/providers.md:122-122,
docs-site/src/content/docs/ru/guides/providers.md:129-129, and
docs-site/src/content/docs/zh-cn/guides/providers.md:114-114 to state that key
validation is provider-specific and Command Code keys are reported as
unverifiable.
- Around line 277-283: Update the Command Code provider documentation to remove
or explicitly mark the Go/Pro CLI auth bridge as not yet available in
docs-site/src/content/docs/guides/providers.md lines 277-283,
docs-site/src/content/docs/ja/guides/providers.md lines 200-206,
docs-site/src/content/docs/ko/guides/providers.md lines 200-206,
docs-site/src/content/docs/ru/guides/providers.md lines 209-215, and
docs-site/src/content/docs/zh-cn/guides/providers.md lines 188-193, preserving
the remaining authentication guidance in each locale.
In `@src/providers/registry.ts`:
- Line 1195: Update the note in the provider registry entry to state that API
access requires the Provider plan and that CLI auth bridging for Go/Pro
subscribers is not yet available; remove wording that implies the bridge
currently provides access.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 1a0bbdd9-4bae-4a47-bb65-d54620045ecb
📒 Files selected for processing (16)
docs-site/src/content/docs/getting-started/quickstart.mddocs-site/src/content/docs/guides/providers.mddocs-site/src/content/docs/ja/getting-started/quickstart.mddocs-site/src/content/docs/ja/guides/providers.mddocs-site/src/content/docs/ko/getting-started/quickstart.mddocs-site/src/content/docs/ko/guides/providers.mddocs-site/src/content/docs/ru/getting-started/quickstart.mddocs-site/src/content/docs/ru/guides/providers.mddocs-site/src/content/docs/zh-cn/getting-started/quickstart.mddocs-site/src/content/docs/zh-cn/guides/providers.mdsrc/oauth/key-providers.tssrc/providers/derive.tssrc/providers/registry.tstests/commandcode-provider.test.tstests/fixtures/commandcode-models.jsontests/provider-registry-parity.test.ts
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: adae0d925d
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
- Seed the default model so discovery failure never empties the catalog - Correct preset counts in all locales (69: 58 key, 7 OAuth, 3 local, 1 forward) - State key validation is provider-specific (Command Code: unverifiable) - Drop the not-yet-available CLI auth bridge claim; add docs URL + verification date
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
docs-site/src/content/docs/guides/providers.md (1)
278-284: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winDocument the complete Command Code provider contract in every locale.
The five sections describe discovery and Bearer authentication, but they do not explicitly document key authentication with
openai-chat,POST {baseUrl}/chat/completions, or the unavailability of OAuth/CLI bridging.
docs-site/src/content/docs/guides/providers.md#L278-L284: add theopenai-chatadapter,POST \https://api.commandcode.ai/provider/v1/chat/completions\``, and explicit OAuth/CLI bridge-unavailable wording.docs-site/src/content/docs/ja/guides/providers.md#L201-L207: add the equivalent Japanese details.docs-site/src/content/docs/ko/guides/providers.md#L201-L207: add the equivalent Korean details.docs-site/src/content/docs/ru/guides/providers.md#L210-L216: add the equivalent Russian details.docs-site/src/content/docs/zh-cn/guides/providers.md#L188-L193: add the equivalent Simplified Chinese details.As per path instructions, provider documentation must match actual CLI/API behavior and document the Command Code
openai-chatcontract.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs-site/src/content/docs/guides/providers.md` around lines 278 - 284, Update the Command Code provider sections in docs-site/src/content/docs/guides/providers.md (278-284), docs-site/src/content/docs/ja/guides/providers.md (201-207), docs-site/src/content/docs/ko/guides/providers.md (201-207), docs-site/src/content/docs/ru/guides/providers.md (210-216), and docs-site/src/content/docs/zh-cn/guides/providers.md (188-193) to document the openai-chat adapter, key-authenticated POST https://api.commandcode.ai/provider/v1/chat/completions requests, and explicitly state that OAuth/CLI authentication bridging is unavailable; provide equivalent localized wording in each translated section while preserving the existing discovery and Bearer-auth details.Source: Path instructions
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs-site/src/content/docs/guides/providers.md`:
- Around line 193-196: Make the built-in provider breakdown explicitly state one
default ChatGPT-forward preset while preserving totals of 69, 58 key-based, 7
OAuth, 3 local, and 1 ChatGPT-forward: update
docs-site/src/content/docs/guides/providers.md lines 193-196,
docs-site/src/content/docs/ru/guides/providers.md lines 129-132, and
docs-site/src/content/docs/zh-cn/guides/providers.md lines 114-116 with each
locale’s equivalent of an explicit count of one.
---
Outside diff comments:
In `@docs-site/src/content/docs/guides/providers.md`:
- Around line 278-284: Update the Command Code provider sections in
docs-site/src/content/docs/guides/providers.md (278-284),
docs-site/src/content/docs/ja/guides/providers.md (201-207),
docs-site/src/content/docs/ko/guides/providers.md (201-207),
docs-site/src/content/docs/ru/guides/providers.md (210-216), and
docs-site/src/content/docs/zh-cn/guides/providers.md (188-193) to document the
openai-chat adapter, key-authenticated POST
https://api.commandcode.ai/provider/v1/chat/completions requests, and explicitly
state that OAuth/CLI authentication bridging is unavailable; provide equivalent
localized wording in each translated section while preserving the existing
discovery and Bearer-auth details.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 5eca9229-02ec-4a59-aa5d-0a34beb41b87
📒 Files selected for processing (12)
docs-site/src/content/docs/getting-started/quickstart.mddocs-site/src/content/docs/guides/providers.mddocs-site/src/content/docs/ja/getting-started/quickstart.mddocs-site/src/content/docs/ja/guides/providers.mddocs-site/src/content/docs/ko/getting-started/quickstart.mddocs-site/src/content/docs/ko/guides/providers.mddocs-site/src/content/docs/ru/getting-started/quickstart.mddocs-site/src/content/docs/ru/guides/providers.mddocs-site/src/content/docs/zh-cn/getting-started/quickstart.mddocs-site/src/content/docs/zh-cn/guides/providers.mdsrc/providers/registry.tstests/commandcode-provider.test.ts
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
docs-site/src/content/docs/guides/providers.md (1)
278-284: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winDocument the
openai-chatadapter in every Command Code guide.The three guides document the endpoint and authentication behavior but leave the provider’s adapter implicit. Add the
openai-chatadapter name in each Command Code section.
docs-site/src/content/docs/guides/providers.md#L278-L284: state that Command Code uses theopenai-chatadapter.docs-site/src/content/docs/ru/guides/providers.md#L210-L216: state that Command Code uses theopenai-chatadapter.docs-site/src/content/docs/zh-cn/guides/providers.md#L188-L193: state that Command Code uses theopenai-chatadapter.As per path instructions, document Command Code as a key-based provider using the
openai-chatadapter.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs-site/src/content/docs/guides/providers.md` around lines 278 - 284, Document Command Code as a key-based provider using the openai-chat adapter in docs-site/src/content/docs/guides/providers.md lines 278-284, docs-site/src/content/docs/ru/guides/providers.md lines 210-216, and docs-site/src/content/docs/zh-cn/guides/providers.md lines 188-193; update each Command Code section while preserving its existing endpoint and authentication details.Source: Path instructions
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@docs-site/src/content/docs/guides/providers.md`:
- Around line 278-284: Document Command Code as a key-based provider using the
openai-chat adapter in docs-site/src/content/docs/guides/providers.md lines
278-284, docs-site/src/content/docs/ru/guides/providers.md lines 210-216, and
docs-site/src/content/docs/zh-cn/guides/providers.md lines 188-193; update each
Command Code section while preserving its existing endpoint and authentication
details.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 15ad58a4-e293-4c0a-9201-c39148442e84
📒 Files selected for processing (3)
docs-site/src/content/docs/guides/providers.mddocs-site/src/content/docs/ru/guides/providers.mddocs-site/src/content/docs/zh-cn/guides/providers.md
Collaborator
Author
[shipping-github] MergeWhy it helps: Fixes #909. |
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
commandcoderegistry preset: OpenAI-compatibleopenai-chatprovider athttps://api.commandcode.ai/provider/v1, API-key auth, dashboard link, and live model discovery from the public/provider/v1/modelscatalog (51 models, slash-namespaced ids preserved, context windows parsed). Default model:deepseek/deepseek-v4-flash, also seeded as the cold-start fallback so a discovery failure never empties the catalog for a fresh config.apiKeyValidation: "unknown"so validation reports "couldn't validate (may still work)" instead of a false positive; the docs now state validation is provider-specific.PROVIDER_REGISTRY.Validation
bun run typecheck— passbun test tests/commandcode-provider.test.ts tests/provider-registry-parity.test.ts— 39 pass, 0 fail (includes the new discovery-failure fallback regression test)bun run test— 7561 tests; 14 fail, all reproduced identically on the upstreamdevtip (Windows symlinkEPERM+ a cmd-shim spawn assertion), unrelated to this changebun run privacy:scan— passGET https://api.commandcode.ai/provider/v1/models— 200, 51 rows (fixture snapshot);POST /provider/v1/chat/completionswithout a key returns401 UNAUTHORIZEDwith an official error-docs linkPrimary-source evidence (per
MAINTAINERS.md/ contributing)/provider/v1/modelsis public by design — verified 200 with and without a key, so there is no authenticated models endpoint to cite for this provider (the entry'sliveModelsreads the public catalog).MAINTAINERS.md) — updates land through the existing provider-registry review flow.Review notes
preserveCustomDestination: truekeeps the registry from retargeting an existing same-named custom provider, including the local-bridge workaround from the issue.reasoningEfforts: []keeps unknown models off Codex's fallback ladder until Command Code publishes a per-model reasoning contract.apiKeyValidationfield overlaps with open PR feat(providers): add SambaNova and Nebius presets #870 (SambaNova/Nebius), which introduces the same policy; whichever lands second needs only a trivial rebase.Limitations
403 MODEL_NOT_IN_PLAN) are passed through from upstream; no client-side per-plan filtering is applied.Fixes #909
Summary by CodeRabbit