Best possible solution:

Merge the narrow docs correction after maintainer review, keeping broader Claude CLI runtime, onboarding, or provider billing-policy work separate.

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

Not applicable as a runtime reproduction. Source inspection of current main shows the stale billing text, and the PR diff/head contents show the docs-only correction.

Is this the best way to solve the issue?

Yes. Updating the affected public docs with current official Anthropic support language is the narrowest maintainable fix for the stale guidance; no OpenClaw runtime, config, or product behavior change is needed.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against 891096926e27.

Label justifications:

• P3: This is a low-risk docs-only correction to time-sensitive provider billing guidance.
• rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🌊 off-meta tidepool and patch quality is 🦞 diamond lobster.
• status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Not applicable: Real behavior proof is not required because this PR only changes files under docs/.

PR surface:

Docs +22. Total +22 across 4 files.

What I checked:

• Repository policy applied: Root AGENTS.md and docs/AGENTS.md were read fully; the relevant rules require source-backed docs, current dependency/support-doc checks, and Mintlify-compatible links. Public docs: docs/AGENTS.md. (docs/AGENTS.md:1, 891096926e27)
• Current main still has stale provider billing wording: Current main says subscription-plan claude -p usage starts drawing from a separate Agent SDK credit on June 15, 2026. Public docs: docs/providers/anthropic.md. (docs/providers/anthropic.md:16, 891096926e27)
• Current main has matching stale wording in related docs: The same June 15 separate-credit wording appears in the model FAQ and Claude Max API proxy docs, and the live-testing guide still references extra-usage billing instead of normal subscription limits. Public docs: docs/help/faq-models.md. (docs/help/faq-models.md:545, 891096926e27)
• PR head updates the central provider page: At PR head, the Anthropic provider page says Anthropic paused the June 15, 2026 support update and that Claude Agent SDK, claude -p, and third-party app usage still draw from subscription usage limits for now. Public docs: docs/providers/anthropic.md. (docs/providers/anthropic.md:16, eaba7be77421)
• PR head updates the sibling docs: At PR head, the model FAQ, live-testing guide, and Claude Max API proxy page all use the paused-change / subscription-limit wording instead of the old separate-credit claim. Public docs: docs/providers/claude-max-api-proxy.md. (docs/providers/claude-max-api-proxy.md:18, eaba7be77421)
• Stale phrase check at PR head: The exact stale June 15 / separate-credit phrases checked across the four touched files return no matches at PR head. (eaba7be77421)

Likely related people:

• steipete: Peter Steinberger authored the earlier Anthropic subscription and extra-usage billing guidance that this PR updates. (role: prior billing-doc author; confidence: high; commits: 45675c1698f2, 37301cbc3b33; files: docs/providers/anthropic.md)
• vincentkoc: Vincent Koc rewrote the Anthropic provider page into its current Mintlify structure and refreshed the docs snapshot containing the affected pages. (role: recent adjacent docs contributor; confidence: medium; commits: af38536fb900, aa69b12d0086; files: docs/providers/anthropic.md, docs/help/faq-models.md, docs/help/testing-live.md)
• llagy009: Current blame for the affected docs lines points to a recent main commit that reintroduced the docs files, though the commit subject is unrelated to billing guidance. (role: recent line-blame contributor; confidence: low; commits: b5c662f4f54c; files: docs/providers/anthropic.md, docs/help/faq-models.md, docs/help/testing-live.md)

• 🦀 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.

• 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.