Feature Request: Add ClinePass provider support

[jellydn]

What

Add ClinePass as a new provider in CodexBar — a $9.99/month subscription from Cline that provides 2-5x API rate limits for popular open coding models.

ClinePass was officially released on June 29, 2026 and is already available in Cline CLI v3.0.28+ and the VS Code extension.

Why

Users who subscribe to ClinePass need to track their usage against three windows:

• 5-hour rolling window — usage within a rolling 5-hour period
• Weekly — usage over the calendar week
• Monthly — usage over the calendar month

This is the exact kind of usage visibility that CodexBar excels at. CodexBar already supports similar pass/subscription patterns (e.g., Kilo Pass / Kilo provider) and has an existing Cline provider that shares the same auth infrastructure — making this a natural extension.

How / Implementation Notes

Auth

• ClinePass reuses Cline's existing WorkOS OAuth credentials (same auth token storage as the cline provider)
• CodexBar's existing Cline provider already handles this OAuth flow — ClinePass can likely reuse it with a separate provider config entry

API Endpoints (sourced from cline/cline source)

• GET /api/v1/users/{uid}/balance — credit balance / subscription status
• GET /api/v1/users/{uid}/usages — usage transactions
• Base URL: https://api.cline.bot
• Auth: Authorization: Bearer <token> (same Bearer token as Cline provider)

Models (10 models, cline-pass/ prefix)

Model	Model ID
GLM-5.2	cline-pass/glm-5.2
Kimi K2.7 Code	cline-pass/kimi-k2.7-code
Kimi K2.6	cline-pass/kimi-k2.6
DeepSeek V4 Pro	cline-pass/deepseek-v4-pro
DeepSeek V4 Flash	cline-pass/deepseek-v4-flash
MiMo-V2.5	cline-pass/mimo-v2.5
MiMo-V2.5-Pro	cline-pass/mimo-v2.5-pro
MiniMax M3	cline-pass/minimax-m3
Qwen3.7 Max	cline-pass/qwen3.7-max
Qwen3.7 Plus	cline-pass/qwen3.7-plus

Potential approach

Mirror the existing Cline provider implementation, creating a ClinePass provider that:

1. Shares the WorkOS OAuth credentials with Cline
2. Fetches usage from the ClinePass-specific endpoints above
3. Displays the three usage windows (5-hour / weekly / monthly)

References

• ClinePass announcement
• ClinePass docs
• Cline CLI v3.0.28 release
• ClinePass PR in cline/cline SDK

[clawsweeper]

Codex review: keeping this open for maintainer follow-up; there is still a little grit to resolve. Reviewed June 29, 2026, 3:44 PM ET / 19:44 UTC.

Summary
Keep open: current main has no Cline or ClinePass provider, and the request is aligned with CodexBar’s provider-coverage vision but needs maintainer sign-off because it adds provider/auth/config surface and the issue assumes an existing Cline provider that is not present.

Reproducibility: not applicable. this is a feature request rather than a bug. Source inspection gives a high-confidence absence check: current main has no Cline or ClinePass provider enum, descriptor, implementation, docs, or tests.

Ways to help us reproduce this

• Add a screenshot or short recording showing the behavior.
• Add expected vs actual behavior.

Next step
Manual review is the safer lane because this is new provider/auth/config surface and the requested auth reuse conflicts with the current codebase shape.

Review details

Best possible solution:

Confirm the supported ClinePass auth contract first, then add it through the existing descriptor, fetch strategy, settings, docs, and parser-test patterns without live account or Keychain-prompting validation.

Do we have a high-confidence way to reproduce the issue?

Not applicable; this is a feature request rather than a bug. Source inspection gives a high-confidence absence check: current main has no Cline or ClinePass provider enum, descriptor, implementation, docs, or tests.

Is this the best way to solve the issue?

Unclear until maintainers confirm auth direction. A separate provider appears consistent with CodexBar’s provider architecture, but the proposed reuse of an existing CodexBar Cline provider is not valid because that provider is absent on current main.

AGENTS.md: found and applied where relevant.

Remaining risk / open question:

• The request assumes an existing CodexBar Cline provider and reusable WorkOS OAuth path, but current main has no Cline provider at all.
• ClinePass auth needs maintainer confirmation because upstream docs mention external API-key usage while the issue proposes shared OAuth credentials.
• Adding this provider would introduce new provider/config/auth surface, so privacy and token-storage behavior should be reviewed before implementation.

Codex review notes: model internal, reasoning high; reviewed against f5340ad62732.

Label changes

Label changes:

• add P3: This is a useful but speculative provider expansion request, not a regression or broken existing workflow.
• add impact:auth-provider: The requested work is primarily about adding provider routing and credential handling for a new ClinePass provider.
• add issue-rating: 🌊 off-meta tidepool: Current issue advisory state selects this label.
• add clawsweeper:no-new-fix-pr: Current issue advisory state selects this label.
• add clawsweeper:needs-maintainer-review: Current issue advisory state selects this label.
• add clawsweeper:needs-product-decision: Current issue advisory state selects this label.

Label justifications:

• P3: This is a useful but speculative provider expansion request, not a regression or broken existing workflow.
• impact:auth-provider: The requested work is primarily about adding provider routing and credential handling for a new ClinePass provider.

Evidence reviewed

Acceptance criteria:

• swift test --filter ClinePassUsageFetcherTests
• swift test --filter ProviderRegistryTests
• swift test --filter ConfigurationDocsProviderIDTests
• make check

What I checked:

• Repository policy read: AGENTS.md was read fully; it asks provider changes to reuse existing helpers, add focused XCTest coverage, avoid live Keychain-prompting validation, and keep provider data siloed. (AGENTS.md:1, f5340ad62732)
• Vision fit: VISION.md says CodexBar should keep adding useful provider coverage through shared provider-driven UI, while new features and auth/privacy-affecting provider additions need sign-off. (VISION.md:3, f5340ad62732)
• Current provider enum lacks ClinePass: UsageProvider lists the current supported provider IDs and has no cline or clinepass case. (Sources/CodexBarCore/Providers/Providers.swift:5, f5340ad62732)
• Current registry lacks ClinePass descriptor: ProviderDescriptorRegistry maps every supported provider to a descriptor; there is no Cline or ClinePass entry. (Sources/CodexBarCore/Providers/ProviderDescriptor.swift:55, f5340ad62732)
• Repository-wide Cline search: No cline, clinepass, or cline-pass matches were found in Sources, Tests, docs, README, or Package.swift, so the issue’s claimed existing CodexBar Cline provider is not on current main. (f5340ad62732)
• Adjacent provider pattern exists: Kilo shows the nearest current pattern: provider descriptor, API/CLI fetch strategies, settings implementation, and pass usage mapping. (Sources/CodexBarCore/Providers/Kilo/KiloProviderDescriptor.swift:3, f5340ad62732)

Likely related people:

• Peter Steinberger: git blame and log tie the central provider enum, descriptor registry, Kilo provider pattern, and recent Sakana provider addition to this author in the available history. (role: recent provider architecture contributor; confidence: medium; commits: f380287041b8, 87635bcc755b; files: Sources/CodexBarCore/Providers/Providers.swift, Sources/CodexBarCore/Providers/ProviderDescriptor.swift, Sources/CodexBar/Providers/Shared/ProviderImplementationRegistry.swift)

How this review workflow works

• ClawSweeper keeps one durable marker-backed review comment per issue or PR.
• Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
• A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
• PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
• Maintainers can also comment @clawsweeper review to request a fresh review only.
• Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
• Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
• Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

[steipete]

Contract audit (2026-07-01, CodexBar main 24490b6434d491a5478ea6636f014744ada3cbeb): this is not implementable accurately from the current public contract.

• ClinePass documentation defines separate 5-hour, weekly, and monthly limits and directs users to Cline's dashboard for usage. It does not document a response schema with used/limit/reset values for those windows.
• Cline's public account API does document /balance and /usages, but these are Cline credit balance/transaction endpoints. The current upstream ClineAccountBalance contains only balance and userId; it cannot represent ClinePass's three quota windows.
• Upstream ClinePass reuses the user's Cline OAuth account. That proves Cline's own integration, not a supported third-party billing/quota contract for CodexBar.

Smallest safe future implementation: a separate clinepass provider using an explicitly supplied Cline API key or documented third-party OAuth flow; fetch three quota windows; map each to CodexBar RateWindows; never import Cline refresh tokens or browser sessions implicitly.

Needed proof before code:

1. A supported endpoint for ClinePass quota, including auth/scopes.
2. A sanitized real response containing used, limit, and reset for all three windows.
3. Confirmation that API keys are authorized for this endpoint and that its schema is intended for third-party clients.

Recommendation: keep open, no speculative provider or dashboard scraping. The currently cited balance/history endpoints would show the wrong product metric.