Skip to content

docs: add Perplexity, Mistral, and Qoder provider references#1977

Merged
steipete merged 4 commits into
steipete:mainfrom
kiranmagic7:kiran/codexbar-provider-docs-20260708
Jul 9, 2026
Merged

docs: add Perplexity, Mistral, and Qoder provider references#1977
steipete merged 4 commits into
steipete:mainfrom
kiranmagic7:kiran/codexbar-provider-docs-20260708

Conversation

@kiranmagic7

Copy link
Copy Markdown
Contributor

Summary

  • Add source-backed provider detail pages for Perplexity, Mistral, and Qoder.
  • Link Perplexity and Mistral from the README provider list, and add the missing Qoder README entry.
  • Add provider overview Details links for the three new pages.

Tests

  • node Scripts/check-documentation-links.mjs
  • node Scripts/check-site-locales.mjs
  • node Scripts/generate-llms.mjs --check
  • bash Scripts/lint.sh lint-linux
  • git diff --check

Compatibility risk

Docs-only. No provider behavior, auth handling, Keychain access, browser import behavior, dependencies, or build scripts changed.

@clawsweeper

clawsweeper Bot commented Jul 8, 2026

Copy link
Copy Markdown

Codex review: needs real behavior proof before merge. Reviewed July 9, 2026, 4:42 AM ET / 08:42 UTC.

Summary
The branch adds Perplexity, Mistral, and Qoder provider docs, links them from the README and provider overview, and adds an unreleased changelog entry.

Reproducibility: not applicable. this is a documentation PR, so the relevant check is whether the documented setup paths, endpoints, and links match current main source.

Review metrics: 1 noteworthy metric.

  • Docs surface: 6 files changed; 3 provider pages added. The patch is limited to provider documentation, README navigation, and the unreleased changelog, so review should focus on source accuracy and link coverage.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🌊 off-meta tidepool
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

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

Rank-up moves:

  • none.

Next step before merge

  • [P1] No ClawSweeper repair work is needed because the docs-only patch has no concrete line-level defect from source inspection.

Security
Cleared: Docs and changelog changes do not alter credentials, provider behavior, dependencies, scripts, workflows, or other code execution paths.

Review details

Best possible solution:

Merge the provider reference docs after normal maintainer review, keeping the pages synchronized with the current provider source and docs checks.

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

Not applicable; this is a documentation PR, so the relevant check is whether the documented setup paths, endpoints, and links match current main source.

Is this the best way to solve the issue?

Yes; focused provider pages plus README/provider-overview links are the narrow maintainable way to close these docs gaps without changing provider behavior.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against bc848e876b9a.

Label changes

Label justifications:

  • P3: This is low-risk documentation coverage for existing providers with no runtime provider behavior changed.
  • rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
  • status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: The branch changes documentation and release notes only, so runtime after-fix proof is not applicable.
Evidence reviewed

What I checked:

  • Repository policy read: AGENTS.md was present, read in full, and applied to keep this review focused on docs/source accuracy without live provider probes that could touch Keychain or browser-cookie paths. (AGENTS.md:1, bc848e876b9a)
  • PR surface: The PR changes 6 documentation/release-note files, adding 3 provider pages and touching README.md, docs/providers.md, and CHANGELOG.md without runtime source, dependencies, scripts, or workflows. (61454891825c)
  • README links: At the PR head, README.md links Perplexity, Mistral, and Qoder to the new provider pages in the provider list. (README.md:110, 61454891825c)
  • Provider overview links: At the PR head, docs/providers.md adds Details links for Perplexity, Mistral, and Qoder alongside the existing provider summaries. (docs/providers.md:320, 61454891825c)
  • Perplexity source match: Current main supports the documented Perplexity session cookie names, bare-token override, credits endpoint, Origin/Referer headers, and cache/browser/environment resolution path. (Sources/CodexBarCore/Providers/Perplexity/PerplexityUsageFetcher.swift:9, bc848e876b9a)
  • Mistral source match: Current main uses the documented Mistral admin usage and credits endpoints, optional console Vibe request, and scoped forwarding of csrftoken plus ory_session_* cookies. (Sources/CodexBarCore/Providers/Mistral/MistralUsageFetcher.swift:26, bc848e876b9a)

Likely related people:

  • steipete: Current-main blame and history for the provider overview and central provider descriptors route the existing documented behavior to Peter Steinberger, and he also made the latest corrective commits on this PR branch. (role: recent docs and provider-area contributor; confidence: high; commits: a83a83fa4131, 1bc29f9c6b30, 61454891825c; files: docs/providers.md, Sources/CodexBarCore/Providers/Perplexity/PerplexityProviderDescriptor.swift, Sources/CodexBarCore/Providers/Mistral/MistralProviderDescriptor.swift)
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 (1 earlier review cycle)
  • reviewed 2026-07-08T00:44:30.155Z sha e2d95cc :: needs real behavior proof before merge. :: none

@clawsweeper clawsweeper Bot added rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. P3 Low-risk cleanup, docs, polish, ergonomics, or speculative feature. labels Jul 8, 2026
steipete and others added 3 commits July 9, 2026 01:30
Co-authored-by: kiranmagic7 <209323973+kiranmagic7@users.noreply.github.com>
Co-authored-by: kiranmagic7 <209323973+kiranmagic7@users.noreply.github.com>
@steipete

steipete commented Jul 9, 2026

Copy link
Copy Markdown
Owner

Maintainer proof for exact head 61454891825ce81af13233366a0cfb36417da60a:

  • Deep source-to-doc review verified the Perplexity, Mistral, and Qoder setup, auth, endpoint, fallback, display, and cost-history claims against current provider implementations.
  • Repairs: removed the unsupported claim that Qoder surfaces remaining credits; documented that bare manual cookies route to qoder.com, while qoder.com.cn requires a cURL/HTTP capture containing the China URL or Host header.
  • Documentation gates pass: 156 local links, docs list generation, 23 site locales / 139 messages, docs/llms.txt freshness, and git diff --check.
  • Repository gates pass: make check, all 49 make test shards, and clean converged autoreview.
  • Runtime provider probes are intentionally not needed for this docs-only change; exact source and generated-site/link validation are the proportional behavior proof.
  • Public Model Identifier Gate: PASS. Dependency freshness: unchanged; no dependency added or updated.

Thanks for filling these provider documentation gaps, @kiranmagic7!

@steipete steipete merged commit 7f5ef17 into steipete:main Jul 9, 2026
7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

P3 Low-risk cleanup, docs, polish, ergonomics, or speculative feature. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants