Skip to content

feat:Add Xiaomi Token Plan provider support#86179

Merged
steipete merged 11 commits into
openclaw:mainfrom
NianJiuZst:codex/issue-86169-xiaomi-token-plan
May 30, 2026
Merged

feat:Add Xiaomi Token Plan provider support#86179
steipete merged 11 commits into
openclaw:mainfrom
NianJiuZst:codex/issue-86169-xiaomi-token-plan

Conversation

@NianJiuZst

@NianJiuZst NianJiuZst commented May 24, 2026

Copy link
Copy Markdown
Contributor

Summary

  • add first-class xiaomi-token-plan support to the bundled Xiaomi provider plugin
  • add regional Token Plan onboarding/auth choices (China/Europe/Singapore), static v2.5 catalog entries, and tp-... / sk-... key-shape validation
  • wire the new provider through usage/auth/config overlay surfaces and update Xiaomi provider docs
  • set model costs with tiered cache-read pricing: flat input/output per 1M tokens, cache-read pricing steps at 256K input tokens
  • use model catalog names as display aliases instead of generic provider labels

Why

OpenClaw's bundled Xiaomi plugin only supported pay-as-you-go xiaomi setup, while issue #86169 asked for Xiaomi MiMo Token Plan support without requiring manual custom-provider wiring.

Screenshots

Model dropdown showing specific model names instead of generic provider label
image

Model costs

Model Input Output cacheRead (<256K) cacheRead (>=256K)
mimo-v2.5-pro $1/1M $3/1M $0.20/1M $0.40/1M
mimo-v2.5 $0.4/1M $2/1M $0.08/1M $0.16/1M

Prices are USD per million tokens. Cache-read pricing uses tieredPricing with a step at 256,000 input tokens.

Real behavior proof

Behavior addressed: OpenClaw can onboard and resolve Xiaomi MiMo Token Plan as a first-class provider with regional preset endpoints, strict key-prefix validation, and tiered cache-read pricing.

Real environment tested: macOS local source checkout at 1b10c6a with live Xiaomi Token Plan China (cn) region tp-... API key. All three regional endpoints probed; regional key isolation confirmed.

Exact steps or command run after this patch:

  1. curl -s "https://token-plan-cn.xiaomimimo.com/v1/models" -H "Authorization: Bearer tp-***" — HTTP 200, 8 models returned including mimo-v2.5 and mimo-v2.5-pro.
  2. curl -s "https://token-plan-cn.xiaomimimo.com/v1/chat/completions" with mimo-v2.5-pro — HTTP 200, model: mimo-v2.5-pro, usage: prompt=255, completion=20, cacheRead=192.
  3. curl -s "https://token-plan-cn.xiaomimimo.com/v1/chat/completions" with mimo-v2.5 — HTTP 200, valid response.
  4. openclaw agent --local --agent main --model "xiaomi-token-plan/mimo-v2.5" --message "Reply with ok" --thinking off --jsontext: ok, provider xiaomi-token-plan, model mimo-v2.5, fallback: False, usage: input=90, output=2, cacheRead=22656.
  5. openclaw onboard --non-interactive --accept-risk --auth-choice xiaomi-token-plan-cn --xiaomi-token-plan-api-key "tp-***" --json — config written with correct cn region baseUrl, aliases, and auth profile.
  6. curl -s "https://token-plan-sgp.xiaomimimo.com/v1/models" -H "Authorization: Bearer tp-***" — HTTP 401, "message": "Invalid API Key". Confirms CN key is region-locked to CN endpoint.
  7. curl -s "https://token-plan-ams.xiaomimimo.com/v1/models" -H "Authorization: Bearer tp-***" — HTTP 401, "message": "Invalid API Key". Confirms CN key is region-locked to CN endpoint.
  8. node scripts/run-vitest.mjs extensions/xiaomi/ — 3 files, 35 tests passed. pnpm tsgo clean. pnpm build clean.

Evidence after fix: All three regional endpoints respond correctly. CN endpoint returns valid chat completions with working prompt caching (cacheRead observed). SGP and AMS endpoints correctly reject the CN-region key with 401, confirming regional isolation works at the API level. Model dropdown shows specific names (Xiaomi MiMo V2.5 Pro). Non-interactive openclaw onboard with xiaomi-token-plan-cn succeeds end-to-end. Costs flow from manifest to usage tracking with tiered cache-read pricing. Key validation rejects unknown prefixes (bad-key) and cross-prefix entries (tp- for payg, sk- for token-plan). Token Plan catalog requires explicit non-empty regional baseUrl.

Observed result after fix: All live API, agent, and onboarding tests pass for CN region. SGP and AMS endpoints correctly enforce key-region binding (401 Invalid API Key). Provider correctly resolves the cn region base URL, authenticates with tp-... key, and returns valid chat completions. Model dropdown shows specific model names instead of generic labels. Cost tracking uses correct tiered pricing. Strict key-prefix validation works for both payg (sk-) and token-plan (tp-) paths.

What was not tested: The SGP and AMS endpoints with their own regional keys (only a CN key is available for this verification).

Fixes #86169.

@openclaw-barnacle openclaw-barnacle Bot added docs Improvements or additions to documentation commands Command implementations extensions: xiaomi size: L triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 24, 2026
@clawsweeper

clawsweeper Bot commented May 24, 2026

Copy link
Copy Markdown
Contributor

Codex review: needs maintainer review before merge. Reviewed May 30, 2026, 4:24 AM ET / 08:24 UTC.

Summary
The PR adds bundled Xiaomi MiMo Token Plan provider support with regional onboarding choices, tp-/sk- key validation, runtime-owned model catalog discovery, usage-cost metadata, tests, and Xiaomi provider docs.

PR surface: Source +655, Tests +575, Docs +74. Total +1304 across 23 files.

Reproducibility: not applicable. as a feature PR rather than a broken existing-behavior report. Source inspection shows current main lacks a first-class bundled xiaomi-token-plan provider, and the PR body supplies after-fix live CLI/API proof.

Review metrics: 2 noteworthy metrics.

  • Provider Auth Surfaces: 1 provider id added, 1 env var/CLI flag added, 3 auth choices added. These become user-facing setup and upgrade surfaces that need maintainer approval before merge.
  • Config Overlay Surface: 1 built-in overlay id added. Adding xiaomi-token-plan to the built-in provider overlay allowlist changes which config blocks validate without a full provider definition.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
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:

  • Maintainers should explicitly accept or request more proof for SGP/AMS positive regional keys.
  • [P2] Confirm the Token Plan cost metadata should be represented as OpenClaw USD-per-million usage estimates before merge.

Risk before merge

  • [P1] This PR adds a new bundled provider id, auth env var, CLI flag, auth choices, default model overlay, and runtime discovery behavior, so existing setup and provider-routing surfaces need maintainer contract review before merge.
  • [P1] The PR's live proof positively verifies the CN Token Plan key path; SGP and AMS were only tested by confirming a CN key is rejected there, so maintainers should decide whether that regional coverage is enough.
  • [P1] Official Xiaomi docs describe Token Plan as subscription credits with model credit ratios, while the PR encodes OpenClaw USD-per-million cost metadata; maintainers should confirm that representation is intended for /usage cost. (platform.xiaomimimo.com)
  • [P1] A codegraph comment reports overlap with feat: add mention pattern policies #87200 in src/config/zod-schema.core.ts, so this branch may need rebase coordination if that PR lands first.

Maintainer options:

  1. Accept After Provider-Contract Review (recommended)
    Maintainers can land the PR once they confirm the new bundled provider id, auth surfaces, regional defaults, and cost metadata are the intended public contract.
  2. Request More Regional Proof
    Ask the contributor for SGP and AMS positive-key proof, or record that CN live proof plus regional endpoint-selection tests are sufficient for this release.
  3. Pause If Bundling Is Not Desired
    If maintainers prefer Token Plan to stay as docs/custom-provider setup for now, close or pause this PR and keep the linked feature issue as the product decision point.

Next step before merge

  • [P2] This is an open feature PR with provider/auth/config merge risk; the remaining action is maintainer contract review rather than a narrow autonomous repair.

Security
Cleared: No concrete security or supply-chain regression was found; the diff does not add dependencies, workflow changes, lockfile changes, or secret material, and it routes keys through existing credential helpers.

Review details

Best possible solution:

Land a maintainer-approved version that keeps Xiaomi Token Plan ownership inside the Xiaomi plugin, preserves existing pay-as-you-go behavior, and explicitly accepts the regional and pricing contract before merge.

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

Not applicable as a feature PR rather than a broken existing-behavior report. Source inspection shows current main lacks a first-class bundled xiaomi-token-plan provider, and the PR body supplies after-fix live CLI/API proof.

Is this the best way to solve the issue?

Yes, with maintainer review: the implementation keeps auth, onboarding, catalog, and vendor behavior in the Xiaomi plugin and uses a generic provider-discovery adjustment for runtime-owned catalog entries. The safer pre-merge state is explicit maintainer acceptance of the new provider contract, regional proof gap, and cost metadata.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against b09cab4ebd2c.

Label changes

Label changes:

  • add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes redacted after-fix live API, openclaw agent, onboarding, screenshot, and focused test/build output; SGP/AMS own-key proof remains a stated gap but does not make the supplied proof unusable.
  • add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
  • add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes redacted after-fix live API, openclaw agent, onboarding, screenshot, and focused test/build output; SGP/AMS own-key proof remains a stated gap but does not make the supplied proof unusable.
  • remove rating: 🌊 off-meta tidepool: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.

Label justifications:

  • P2: This is a normal-priority provider feature with limited blast radius but real auth/config impact for Xiaomi users.
  • merge-risk: 🚨 compatibility: The diff adds user-facing provider id, setup metadata, CLI flag, docs, config overlay validation, and default model behavior.
  • merge-risk: 🚨 auth-provider: The diff changes provider auth routing by introducing Token Plan keys, regional auth choices, and strict tp-/sk- key validation.
  • rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
  • status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes redacted after-fix live API, openclaw agent, onboarding, screenshot, and focused test/build output; SGP/AMS own-key proof remains a stated gap but does not make the supplied proof unusable.
  • proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes redacted after-fix live API, openclaw agent, onboarding, screenshot, and focused test/build output; SGP/AMS own-key proof remains a stated gap but does not make the supplied proof unusable.
Evidence reviewed

PR surface:

Source +655, Tests +575, Docs +74. Total +1304 across 23 files.

View PR surface stats
Area Files Added Removed Net
Source 10 724 69 +655
Tests 8 601 26 +575
Docs 5 135 61 +74
Config 0 0 0 0
Generated 0 0 0 0
Other 0 0 0 0
Total 23 1460 156 +1304

What I checked:

  • Current main Xiaomi provider surface: Current main's bundled Xiaomi manifest declares only the xiaomi provider and one XIAOMI_API_KEY setup provider; Token Plan hosts are listed only as endpoint hosts, not as a first-class provider or onboarding choice. (extensions/xiaomi/openclaw.plugin.json:7, b09cab4ebd2c)
  • PR provider/auth surface: The PR head declares providers xiaomi and xiaomi-token-plan, adds autoEnableWhenConfiguredProviders, and maps XIAOMI_TOKEN_PLAN_API_KEY through setup metadata. (extensions/xiaomi/openclaw.plugin.json:7, ccec053de7f5)
  • PR runtime registration: The PR registers separate pay-as-you-go and Token Plan providers, with Token Plan auth methods for ams/cn/sgp and runtime catalog resolution that requires configured provider entry and base URL. (extensions/xiaomi/index.ts:393, ccec053de7f5)
  • Key-shape validation: The PR rejects tp- keys on the pay-as-you-go path, rejects sk- keys on Token Plan paths, and emits targeted remediation messages. (extensions/xiaomi/index.ts:126, ccec053de7f5)
  • Runtime-owned catalog handling: The PR changes provider discovery so mixed static/runtime manifest catalogs full-load the runtime-owned plugin surface instead of synthesizing the runtime-owned provider from static manifest rows. (src/plugins/provider-discovery.runtime.ts:241, ccec053de7f5)
  • Docs and config examples: The PR docs describe the two Xiaomi provider ids, regional Token Plan auth choices, XIAOMI_TOKEN_PLAN_API_KEY, and explicit Token Plan config with xiaomi-token-plan/mimo-v2.5-pro. Public docs: docs/providers/xiaomi.md. (docs/providers/xiaomi.md:9, ccec053de7f5)

Likely related people:

  • Peter Steinberger: Current main blame and recent history cover the Xiaomi provider entry, provider discovery runtime, and config schema; he also authored the PR-branch commit that keeps Token Plan discovery runtime-owned. (role: recent area contributor and likely follow-up owner; confidence: high; commits: 05e31bbeddd0, 57130165b20d, fbbd644d7ae2; files: extensions/xiaomi/index.ts, src/plugins/provider-discovery.runtime.ts, src/config/zod-schema.core.ts)
  • Vincent Koc: Recent history shows provider docs and shared provider onboarding test work near the Xiaomi docs and provider test surface touched by this PR. (role: adjacent provider docs/tests contributor; confidence: medium; commits: 4d3ce427adfa, 9c7c360fed6f, a800dfc8f386; files: docs/providers/xiaomi.md, extensions/xiaomi/onboard.test.ts)
  • Jinhao Dong: Earlier Xiaomi provider history added MiMo V2 Pro/Omni and moved the provider to the OpenAI completions API, which is the base provider behavior extended here. (role: Xiaomi provider feature introducer; confidence: medium; commits: 4f00b3b534f2; files: extensions/xiaomi/openclaw.plugin.json, extensions/xiaomi/index.ts, docs/providers/xiaomi.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.

@clawsweeper clawsweeper Bot added rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. P2 Normal backlog priority with limited blast radius. merge-risk: 🚨 auth-provider 🚨 May break OAuth, tokens, provider routing, model choice, or credentials. labels May 24, 2026
@clawsweeper

clawsweeper Bot commented May 24, 2026

Copy link
Copy Markdown
Contributor

ClawSweeper PR egg

✨ Hatched: 🥚 common Clockwork Proofling

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

  • Merged PRs are hatchable.
  • Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
  • Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 🥚 common.
Trait: guards the happy path.
Image traits: location proof lagoon; accessory CI status badge; palette moss green and polished brass; mood patient; pose sitting proudly on a smooth stone; shell translucent glimmer shell; lighting calm overcast light; background subtle branch markers.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Clockwork Proofling in ClawSweeper.

What is this egg doing here?
  • Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
  • The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
  • Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
  • The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
  • Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

@NianJiuZst
NianJiuZst marked this pull request as ready for review May 25, 2026 05:56
@clawsweeper clawsweeper Bot added the merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. label May 25, 2026
@omarshahine

Copy link
Copy Markdown
Contributor

Thanks for the PR. Before this can move forward, please add live proof from the affected surface, not just unit tests, mocked tests, or source inspection.

A useful proof update should include:

  • the exact build/SHA tested
  • the real environment used
  • the command, UI flow, channel flow, provider request, or other live path exercised
  • before/after symptom evidence where applicable
  • the observed result after the patch
  • any remaining proof gaps

Please redact secrets, tokens, phone numbers, and private message content from logs or screenshots.

@NianJiuZst

Copy link
Copy Markdown
Contributor Author

Thanks for the review @omarshahine . I'm currently running live verification against the affected surface — will update the PR

@clawsweeper clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. 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. and removed rating: 🧂 unranked krab Not merge-ready due to missing proof or serious correctness/safety concerns. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. labels May 25, 2026
@openclaw-barnacle openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. proof: sufficient ClawSweeper judged the real behavior proof convincing. labels May 25, 2026
@NianJiuZst

Copy link
Copy Markdown
Contributor Author

@omarshahine Proof updated!

@NianJiuZst NianJiuZst changed the title [codex] Add Xiaomi Token Plan provider support feat:Add Xiaomi Token Plan provider support May 25, 2026
@clawsweeper clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 25, 2026
@openclaw-barnacle openclaw-barnacle Bot removed proof: sufficient ClawSweeper judged the real behavior proof convincing. proof: supplied External PR includes structured after-fix real behavior proof. labels May 26, 2026
@clawsweeper clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 27, 2026
@BingqingLyu

This comment was marked as spam.

@NianJiuZst
NianJiuZst force-pushed the codex/issue-86169-xiaomi-token-plan branch from bd74f3c to 6e87f3c Compare May 30, 2026 06:28
@openclaw-barnacle openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 30, 2026
@NianJiuZst
NianJiuZst force-pushed the codex/issue-86169-xiaomi-token-plan branch from 6e87f3c to 3d676d4 Compare May 30, 2026 06:31
@clawsweeper clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 30, 2026
@steipete steipete self-assigned this May 30, 2026
@openclaw-barnacle openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 30, 2026
@clawsweeper clawsweeper Bot added rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. and removed 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. labels May 30, 2026
@NianJiuZst
NianJiuZst force-pushed the codex/issue-86169-xiaomi-token-plan branch from ee89e35 to ccec053 Compare May 30, 2026 08:15
@clawsweeper clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 30, 2026
@steipete

Copy link
Copy Markdown
Contributor

Verification before merge:

Behavior addressed: Xiaomi Token Plan provider support, including regional base URL selection, token-plan key prefix validation, runtime model pricing/catalog behavior, and provider discovery ownership so Token Plan cannot fall back to a static SGP catalog when runtime region config is required.
Real environment tested: local OpenClaw checkout plus GitHub Actions for PR head ccec053.
Exact steps or command run after this patch:

  • node scripts/run-vitest.mjs src/plugins/provider-discovery.runtime.test.ts extensions/xiaomi/index.test.ts src/plugins/manifest-model-catalog.test.ts src/model-catalog/manifest-planner.test.ts
  • pnpm exec oxfmt --write --threads=1 src/plugins/provider-discovery.runtime.ts src/plugins/provider-discovery.runtime.test.ts
  • git diff --check
  • autoreview --mode local on the PR diff after fixups
    Evidence after fix: focused Vitest lanes passed; git diff --check passed; autoreview returned clean with no accepted/actionable findings; CI run 26678998539 passed all relevant checks except check-prod-types.
    Observed result after fix: Xiaomi Token Plan catalog ownership stays runtime-only, static Xiaomi catalog entries still work, mixed static/runtime manifest catalog plugins full-load when needed, and runtime-only manifest entries are covered by regression tests.
    What was not tested: no live Xiaomi Token Plan key from me; contributor-provided real behavior proof covers the token-plan setup path. The failed check-prod-types job is unrelated to this PR: it reports unused readActionPositiveInteger in extensions/browser/src/browser/routes/agent.act.normalize.ts, and the same unused function is present on latest origin/main (0185d0d) and PR head.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

commands Command implementations docs Improvements or additions to documentation extensions: xiaomi merge-risk: 🚨 auth-provider 🚨 May break OAuth, tokens, provider routing, model choice, or credentials. merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. P2 Normal backlog priority with limited blast radius. proof: sufficient ClawSweeper judged the real behavior proof convincing. proof: supplied External PR includes structured after-fix real behavior proof. rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. size: XL 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.

[Feature]: Add Xiaomi MiMo Token Plan provider support / fix Token Plan connection

4 participants