Add ClinePass usage provider

[joeVenner]

Summary

• Adds the ClinePass provider as a standalone branch.
• Covers API-key usage-limit fetching, provider registration, settings, docs, icons, and parser hash update.
• Tolerates future/unknown usage-limit types without dropping known 5-hour, weekly, and monthly windows.
• Regenerates the social card artifact after the provider-count update.

Verification

• swift test --filter ClinePass
• make check

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 3cb9d0d995

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Use dashboard auth for ClinePass usage

With the current settings flow, users paste the CLINE_API_KEY documented for Cline's Chat Completions API, but this is the dashboard usage-limits request; Cline's ClinePass docs direct usage checks to the signed-in dashboard, whose request is authenticated by the cline_session_id cookie rather than the Chat Completions Bearer key. In that documented setup the provider reports 401/403 even though the user is subscribed, so the new provider cannot display ClinePass usage unless this endpoint is authenticated with the web session/cookie or a documented usage API.

Useful? React with 👍 / 👎.

[clawsweeper]

Codex review: needs real behavior proof before merge. Reviewed July 16, 2026, 4:01 PM ET / 20:01 UTC.

Summary
Adds ClinePass as a configurable usage provider with API-key fetching, app and CLI registration, tests, icons, and provider documentation.

Reproducibility: not applicable. This PR adds a provider rather than fixing a reproducible current-main bug. The relevant validation is a real-account ClinePass fetch through the app or CLI.

Review metrics: 3 noteworthy metrics.

• Provider surface: 28 files affected. The change spans core fetching, app and CLI registration, widgets, tests, icons, and generated documentation, so proof should exercise the integrated path rather than parsing alone.
• Patch size: 818 added, 87 removed. Most additions are bounded provider code and focused coverage, but the breadth makes end-to-end credential validation important.
• Credential inputs: 1 config field, 2 environment keys. All supported credential entry paths converge on the same unproven live endpoint.

Root-cause cluster
Relationship: canonical
Canonical: #2219
Summary: This standalone PR is the viable ClinePass extraction from the closed, unmerged provider-batch PR.

Members:

• superseded: Add provider usage integrations batch #2215 - The closed, unmerged batch contained the earlier ClinePass implementation, while this PR isolates and continues that provider work.

Proposal only: this assessment does not dispatch repair, suppress jobs, mutate sibling items, close, or merge anything.

Merge readiness
Overall: 🦪 silver shellfish
Proof: 🦪 silver shellfish
Patch quality: 🐚 platinum hermit
Result: blocked until real behavior proof from a real setup is added.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

• [P1] Add redacted real-account evidence showing a successful ClinePass fetch and the 5-hour, weekly, and monthly windows that the account returns.

Proof guidance:

• [P1] Needs real behavior proof before merge: The PR supplies focused tests and clean CI but no after-fix real-account output; add redacted terminal output, runtime logs, or a fresh CodexBar capture showing a successful ClinePass fetch, then update the PR body to trigger review or ask a maintainer to comment @clawsweeper re-review.

Risk before merge

• [P1] The exact ClinePass subscription-limit endpoint is not listed in the public endpoint table, and the PR lacks a redacted real-account run confirming that a configured API key can retrieve the account's 5-hour, weekly, and monthly limits.

Maintainer options:

1. Require live credential proof (recommended)
   Keep merge blocked until a redacted real ClinePass account run shows the configured key successfully returns and renders the available limit windows.
2. Accept the authentication inference
   Merge based on the documented Bearer-token contract and automated tests while accepting that the exact subscription endpoint has not been demonstrated with a contributor account.

Next step before merge

• [P1] Keep merge blocked for contributor-supplied real-account proof; there is no concrete automated code repair until the credential path is exercised.

Security
Cleared: The diff adds a fixed-host HTTPS fetch and established config-based secret handling without new dependencies, workflow permissions, executable downloads, or cross-provider identity leakage.

Review details

Best possible solution:

Keep the API-key design if a redacted real-account run confirms the exact subscription endpoint and rendered windows; otherwise use a documented account-auth source without exposing credentials or changing provider identity semantics.

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

Not applicable: this PR adds a provider rather than fixing a reproducible current-main bug. The relevant validation is a real-account ClinePass fetch through the app or CLI.

Is this the best way to solve the issue?

Unclear: the API-key path matches current Bearer-auth guidance and CodexBar's established provider architecture, but it is not confirmed as the best solution until the exact subscription endpoint succeeds in a real setup.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 2f153f4f6b05.

Label changes

Label changes:

• add rating: 🦪 silver shellfish: Overall readiness is 🦪 silver shellfish; proof is 🦪 silver shellfish and patch quality is 🐚 platinum hermit.
• remove rating: 🧂 unranked krab: Current PR rating is rating: 🦪 silver shellfish, so this older rating label is no longer current.

Label justifications:

• P2: This is a normal-priority provider addition with bounded blast radius and no demonstrated regression to existing providers.
• merge-risk: 🚨 auth-provider: Merging could expose a provider that appears configured but cannot fetch subscription limits if the exact endpoint rejects the supplied API-key credential.
• rating: 🦪 silver shellfish: Overall readiness is 🦪 silver shellfish; proof is 🦪 silver shellfish and patch quality is 🐚 platinum hermit.
• status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs real behavior proof before merge: The PR supplies focused tests and clean CI but no after-fix real-account output; add redacted terminal output, runtime logs, or a fresh CodexBar capture showing a successful ClinePass fetch, then update the PR body to trigger review or ask a maintainer to comment @clawsweeper re-review.

Evidence reviewed

What I checked:

• Credential implementation: The provider resolves a configured API key or CLINE_API_KEY/CLINEPASS_API_KEY and uses it for the ClinePass usage fetch. (Sources/CodexBarCore/Providers/ClinePass/ClinePassSettingsReader.swift:4, a01488d5a43b)
• Provider isolation: The resulting identity is explicitly scoped to ClinePass and labels the login method as API key, consistent with the repository requirement not to mix provider identity data. (Sources/CodexBarCore/Providers/ClinePass/ClinePassUsageFetcher.swift:48, a01488d5a43b)
• Focused coverage: The branch adds macOS and Linux coverage for settings registration, credential resolution, response parsing, unknown limit types, HTTP errors, and the three supported usage windows. (TestsLinux/ClinePassProviderLinuxTests.swift:10, a01488d5a43b)
• Automated validation: All reported GitHub checks completed successfully, including lint, Linux builds, the macOS test shards, and GitGuardian; these checks remain supplemental rather than real-account proof. (a01488d5a43b)
• Proof remains absent: The PR body and follow-up comments report focused tests and make check, but provide no redacted live output, runtime logs, recording, or app capture showing a successful ClinePass account fetch. (a01488d5a43b)
• Earlier review continuity: The parser robustness and stale social-card concerns were addressed at the current head; the remaining prior blocker is now the absence of real-account credential proof rather than a discrete source-level defect. (docs/social.png, a01488d5a43b)

Likely related people:

• steipete: Introduced and repeatedly maintained the descriptor-driven provider architecture and has merged provider integrations across the same registry and documentation surfaces. (role: provider architecture owner; confidence: high; commits: 70a02eb, 5bcd5d1, 17cdc54; files: Sources/CodexBarCore/Providers/ProviderDescriptor.swift, docs/providers.md)
• ratulsarna: Recent history shows repeated work integrating and hardening API-backed providers and updating the central provider documentation. (role: recent provider integrator; confidence: medium; commits: 8348c85, 043cebd, d2aad5a; files: Sources/CodexBarCore/Providers, docs/providers.md)

What the crustacean ranks mean

• 🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
• 🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
• 🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
• 🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
• 🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
• 🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
• 🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

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.

Review history (6 earlier review cycles)

• reviewed 2026-07-16T12:34:57.400Z sha ee60da1 :: needs real behavior proof before merge. :: [P1] Use a credential supported by the usage endpoint
• reviewed 2026-07-16T13:28:29.271Z sha ee60da1 :: needs real behavior proof before merge. :: [P1] Authenticate usage limits with the dashboard session | [P3] Regenerate the social image after changing its count
• reviewed 2026-07-16T16:18:58.791Z sha a01488d :: needs real behavior proof before merge. :: [P1] Prove or replace the usage endpoint credential
• reviewed 2026-07-16T17:02:51.166Z sha a01488d :: needs real behavior proof before merge. :: [P1] Authenticate usage limits with a supported credential
• reviewed 2026-07-16T18:29:58.289Z sha a01488d :: needs real behavior proof before merge. :: none
• reviewed 2026-07-16T19:14:56.751Z sha a01488d :: needs real behavior proof before merge. :: [P1] Authenticate usage limits with a supported credential

[joeVenner]

@clawsweeper re-review

Addressed the ClinePass parser robustness and stale social-card findings at a01488d: unknown limits[].type values are now skipped instead of failing the whole payload, focused regression coverage preserves 5-hour, weekly, and monthly windows, and docs/social.png was regenerated from the 61-provider social card source. Local verification passed: swift test --filter ClinePass; make check.

[clawsweeper]

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

[joeVenner]

@clawsweeper re-review

The previous review placeholder for a01488d appears stale after its lease expired. Current head addresses parser robustness for unknown limits[].type values and regenerates the social-card artifact, with local verification: swift test --filter ClinePass; make check. Please re-review current head.

[clawsweeper]

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

• State: Complete
• Detail: The durable review comment was published and its verdict was queued for target-serialized routing.
• Run: https://github.com/openclaw/clawsweeper/actions/runs/29533566642
• Updated: 2026-07-16T20:51:48.647Z

[joeVenner]

@clawsweeper re-review

The review placeholder for a01488d expired without a verdict. Current head fixes unknown limit parsing and regenerates the social card, with local verification in the PR body. Please re-review current head.

[joeVenner]

@clawsweeper re-review

The review placeholder for a01488d expired again without a verdict. Current head includes the ClinePass parser/social-card fixes and verification; one macOS shard is still finishing, but please re-review current head when available.

[joeVenner]

@clawsweeper re-review

The review placeholder for a01488d expired again without a verdict. CI is clean; current head includes the ClinePass parser/social-card fixes and PR verification. Please re-review current head.

[joeVenner]

@clawsweeper re-review

The review placeholder for a01488d expired again without a verdict. CI is clean; current head includes the ClinePass parser/social-card fixes and PR verification. Please re-review current head.

[steipete]

Verified and merged at head 3abb077705494e759f5be8e0d45ab4eb9f8c74ed.

• Read the complete final diff and provider path. The implementation sends one authenticated GET request to the official api.cline.bot usage-limits endpoint, maps the five-hour, weekly, and monthly windows, and does not log response bodies.
• swift test --filter ClinePass: 9 tests passed across 3 suites.
• make check: locales, docs links, generated parser hash, package tests, SwiftFormat, and strict SwiftLint all passed; 0 lint violations.
• Final maintainer autoreview: no accepted or actionable findings.
• Exact-head CI: all required checks green, including both macOS test shards, both Linux CLI builds, lint, aggregate gate, and GitGuardian.

Live account verification was unavailable for this provider. Merge commit: ee84dca1a734b3c9c97f7d274237f7a73d7c4f49.