Fix Anthropic CLI auth routing for shorthand refs by joshavant · Pull Request #84374 · openclaw/openclaw

joshavant · 2026-05-20T00:32:03Z

Summary:

Route Anthropic execution through Claude CLI when the selected Anthropic auth profile resolves to the Claude CLI backend.
Preserve shorthand and future Anthropic model refs while seeding canonical Claude CLI runtime policy where known.
Add regression coverage for config defaults, migration, runtime aliasing, followup/command execution, and pruning defaults.

Verification:

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=.tmp/vitest-cache-84222-fix-$(date +%s) node scripts/run-vitest.mjs extensions/anthropic/cli-migration.test.ts extensions/anthropic/index.test.ts src/agents/model-runtime-aliases.test.ts src/agents/command/attempt-execution.cli.test.ts src/config/config.pruning-defaults.test.ts src/auto-reply/reply/followup-runner.test.ts src/auto-reply/reply/agent-runner-execution.test.ts
AUTOREVIEW_AUTO_TESTS=0 AUTOREVIEW_OPENCLAW_MAINTAINER_VALIDATION=1 .agents/skills/autoreview/scripts/autoreview --mode auto --reviewer auto --fallback-reviewer claude
git diff --check

Behavior addressed: Anthropic model refs such as anthropic/opus-4.7 selected with Claude CLI auth could execute via embedded Anthropic instead of the configured Claude CLI runtime.
Real environment tested: AWS Crabbox run_a735ed7021d6, lease cbx_5152ee2b4bab, provider aws, type c7a.8xlarge, live Telegram E2E with Convex telegram credential.
Exact steps or command run after this patch: Built the synced branch on AWS Crabbox, configured Telegram with anthropic/opus-4.7 and anthropic:claude-cli, installed an absolute fake Claude CLI command, started the gateway, sent a live Telegram message, and asserted routing/output/billing behavior.
Evidence after fix: Gateway log included provider=claude-cli; fake Claude CLI was called with --model opus; observed Telegram messages included the CLI marker OPENCLAW_84222_CLI_OK; embedded Anthropic billing trap request count was 0.
Observed result after fix: The live Telegram reply came from the Claude CLI route and did not touch embedded Anthropic billing.
What was not tested: A real paid Claude CLI account was not used; the live proof used a fake Claude CLI process to make routing and billing isolation deterministic.

Refs #84222

clawsweeper · 2026-05-20T00:35:14Z

Codex review: needs maintainer review before merge.

Workflow note: Future ClawSweeper reviews update this same comment in place.

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.

Summary
The PR routes Anthropic shorthand refs selected under Claude CLI auth through the Claude CLI runtime, preserves raw and canonical model policies, and adds focused regression coverage plus a changelog entry.

Reproducibility: yes. at source level: current main misses the provider-qualified shorthand ref when collecting Claude CLI runtime policy, and the linked issue reports that exact anthropic/opus-4.7 upgrade shape. I did not run a live current-main repro in this read-only review.

PR rating
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
Patch quality: 🐚 platinum hermit
Summary: Strong live proof and focused tests support the fix, while auth-provider routing remains a maintainer-reviewed merge risk.

Rank-up moves:

Maintainer review should confirm the mixed Anthropic API plus Claude CLI profile precedence before merge.

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.

Real behavior proof
Sufficient (live_output): The PR body includes after-fix real behavior proof from an AWS Crabbox live Telegram E2E run with gateway logs showing provider=claude-cli, fake Claude CLI invocation, Telegram output, and zero embedded Anthropic billing-trap requests.

Risk before merge

The maintainer label is protected, so this PR needs explicit maintainer handling rather than cleanup automation.
The patch intentionally changes Anthropic auth/runtime routing; maintainers should confirm the mixed Anthropic API plus Claude CLI profile precedence is the desired upgrade behavior.

Maintainer options:

Land After Auth-Provider Review (recommended)
A maintainer can accept the routing change after confirming the tested profile precedence matches the intended Anthropic API versus Claude CLI behavior.
Ask For More Upgrade Proof
If maintainers want stronger assurance, request a fresh-install and upgrade proof for mixed Anthropic API plus Claude CLI profiles before merge.

Next step before merge
Protected maintainer labeling and auth-provider merge risk call for human review rather than a ClawSweeper repair PR.

Security
Cleared: No concrete security or supply-chain regression was found; the diff changes existing auth-routing logic without adding dependencies, workflows, downloads, or broader secret access.

Review details

Best possible solution:

Land the narrow Anthropic auth-routing fix after auth-provider review confirms the precedence rules and the listed focused tests or CI pass on the PR head.

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

Yes, at source level: current main misses the provider-qualified shorthand ref when collecting Claude CLI runtime policy, and the linked issue reports that exact anthropic/opus-4.7 upgrade shape. I did not run a live current-main repro in this read-only review.

Is this the best way to solve the issue?

Yes, the PR targets the owning Anthropic plugin/defaulting and runtime-alias seams instead of adding a channel-specific workaround. The remaining decision is maintainer acceptance of the auth-profile precedence behavior, not a different technical direction.

Label changes:

add P1: The PR addresses a recent regression that can break real gateway-mediated agent replies by routing Claude CLI users to Anthropic API billing.
add merge-risk: 🚨 auth-provider: The diff changes how auth profiles select the Claude CLI backend for Anthropic model refs, so a mistake could route credentials or billing to the wrong provider.
add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix real behavior proof from an AWS Crabbox live Telegram E2E run with gateway logs showing provider=claude-cli, fake Claude CLI invocation, Telegram output, and zero embedded Anthropic billing-trap requests.
add rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🦞 diamond lobster, patch quality is 🐚 platinum hermit, and Strong live proof and focused tests support the fix, while auth-provider routing remains a maintainer-reviewed merge risk.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes after-fix real behavior proof from an AWS Crabbox live Telegram E2E run with gateway logs showing provider=claude-cli, fake Claude CLI invocation, Telegram output, and zero embedded Anthropic billing-trap requests.

Label justifications:

P1: The PR addresses a recent regression that can break real gateway-mediated agent replies by routing Claude CLI users to Anthropic API billing.
merge-risk: 🚨 auth-provider: The diff changes how auth profiles select the Claude CLI backend for Anthropic model refs, so a mistake could route credentials or billing to the wrong provider.
rating: 🐚 platinum hermit: Current PR rating is 🐚 platinum hermit because proof is 🦞 diamond lobster, patch quality is 🐚 platinum hermit, and Strong live proof and focused tests support the fix, while auth-provider routing remains a maintainer-reviewed merge risk.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes after-fix real behavior proof from an AWS Crabbox live Telegram E2E run with gateway logs showing provider=claude-cli, fake Claude CLI invocation, Telegram output, and zero embedded Anthropic billing-trap requests.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix real behavior proof from an AWS Crabbox live Telegram E2E run with gateway logs showing provider=claude-cli, fake Claude CLI invocation, Telegram output, and zero embedded Anthropic billing-trap requests.

What I checked:

Linked regression context: The linked issue reports that OpenClaw v2026.5.18 gateway-mediated Telegram/UI turns with anthropic/opus-4.7 and Claude CLI auth fell through to Anthropic API billing while direct CLI still worked.
Current-main source gap: Current main only collects Claude CLI runtime refs whose parsed model starts with claude-, so provider-qualified shorthand such as anthropic/opus-4.7 is not collected by this path. (extensions/anthropic/config-defaults.ts:180, ff5354ee4fbd)
Runtime policy dependency: Current runtime selection depends on exact model/provider runtime policy before switching an Anthropic run to a CLI backend. (src/agents/model-runtime-policy.ts:190, ff5354ee4fbd)
PR implementation: The PR adds shared Anthropic/Claude CLI ref resolution, backfills both raw and canonical shorthand refs, and passes selected auth profile information into runtime alias selection. (src/agents/model-runtime-aliases.ts:182, cdde8bc8abec)
Regression coverage in patch: The diff adds tests for shorthand routing, config defaults, migration behavior, command execution, and followup/agent runner execution paths. (src/agents/model-runtime-aliases.test.ts:1, cdde8bc8abec)
Feature history: The earlier Claude CLI gateway runtime migration fix touched the same Anthropic migration/defaulting files and gateway live coverage. (extensions/anthropic/cli-migration.ts:20, 62cf54484ff7)

Likely related people:

amknight: Authored the earlier merged Claude CLI gateway runtime migration fix that changed the same Anthropic migration/defaulting surface. (role: feature-history owner; confidence: high; commits: 62cf54484ff7, c438dadc5c65; files: extensions/anthropic/cli-migration.ts, extensions/anthropic/config-defaults.ts, extensions/anthropic/index.test.ts)
FullerStackDev: Current-main blame for the runtime alias/defaulting call sites points to the recent auth/provider refactor commit that carried this code forward. (role: recent area contributor; confidence: medium; commits: 896fd13b1c61; files: extensions/anthropic/config-defaults.ts, src/agents/model-runtime-aliases.ts, src/agents/command/attempt-execution.ts)
vincentkoc: Introduced earlier Claude CLI model-switch seeding in the Anthropic plugin, which is adjacent to the defaulting and allowlist behavior changed here. (role: adjacent Anthropic CLI contributor; confidence: medium; commits: 9efc03343477; files: extensions/anthropic/cli-migration.ts, extensions/anthropic/config-defaults.ts, extensions/anthropic/register.runtime.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against ff5354ee4fbd.

clawsweeper · 2026-05-20T00:42:40Z

ClawSweeper PR egg

✨ Hatched: 💎 rare Clockwork Crabkin

       _..------.._          
    .-'  .-.  .-.  '-.       
   /    ( * )( * )    \      
  |        .--.        |     
  |   <\   ====   />   |     
   \    '.______.'    /      
    '-._   ____   _.-'       
        `-.____.-'           
       __/|_||_|\__          
      /__.'    '.__\         
       `-----------'         
 +===================+

Rarity: 💎 rare.
Trait: keeps receipts.
Image traits: location branch lighthouse; accessory tiny test log scroll; palette moss green and polished brass; mood curious; pose balancing on a branch marker; shell smooth pearl shell; lighting moonlit rim light; background small green status lights.
How to hatch it: once this PR reaches status: 👀 ready for maintainer look or status: 🚀 automerge armed, the PR author or a maintainer can comment @clawsweeper hatch to turn this ASCII egg into its generated creature image.
Share on X: post this hatch
Copy: My PR egg hatched a 💎 rare Clockwork Crabkin 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.
Hatchable usually means sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness.
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.

Takhoffman · 2026-05-20T00:49:36Z

@clawsweeper hatch

clawsweeper · 2026-05-20T00:51:24Z

🦞👀
ClawSweeper PR egg hatch requested.

I queued a comment sync for this PR. If the egg is hatchable, ClawSweeper will generate the image once and update the existing review comment.
Action: PR egg hatch queued (workflow sweep.yml, event repository_dispatch).
The ASCII egg stays as the fallback.

joshavant · 2026-05-20T00:55:51Z

Posted the requested fresh-install and upgrade proof for mixed Anthropic API plus Claude CLI profiles.

PR head: cdde8bc8abec1f28d32b7f8d3afc077bb4488dbc

AWS Crabbox proof:

Run: run_52ce7562a6af
Provider/id: provider=aws, leaseId=cbx_f9f817dd66a9, slug=crimson-prawn, type=c7a.8xlarge
Fresh install step: corepack enable then pnpm install --frozen-lockfile
Mixed-profile proof step: registered the Anthropic plugin through the normal plugin SDK capture path, applied Anthropic config defaults, and resolved runtime selection with resolveCliRuntimeExecutionProvider using fresh temp HOME config files and a fake Claude CLI binary. No real Anthropic or Claude credentials were used because the behavior under review is config/profile precedence and runtime routing, not provider billing.
Focused regression step: node scripts/run-vitest.mjs extensions/anthropic/index.test.ts src/agents/model-runtime-aliases.test.ts src/agents/command/attempt-execution.cli.test.ts

Observed mixed-profile results:

Fresh direct-first order, anthropic:api before anthropic:claude-cli: auto route stayed embedded Anthropic API; explicit Claude CLI profile resolved claude-cli; no Claude CLI runtime policy was seeded onto the raw shorthand or canonical Anthropic refs.
Fresh Claude CLI-first order, anthropic:claude-cli before anthropic:api: auto route resolved claude-cli; defaulting seeded Claude CLI runtime policy for both anthropic/opus-4.7 and anthropic/claude-opus-4-7 while preserving existing model params.
Upgrade direct-first order with an existing shorthand model entry: auto route stayed embedded Anthropic API; explicit Claude CLI profile resolved claude-cli; existing shorthand model config was preserved and no Claude CLI runtime policy was added.
Upgrade Claude CLI-first order with an existing shorthand model entry: auto route resolved claude-cli; existing shorthand params/alias were preserved; Claude CLI runtime policy was added to the raw shorthand ref and seeded for the canonical ref.

Focused regression result: 4 files / 86 tests passed.

…026.5.20) (#615) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.19` → `2026.5.20` | --- > ⚠️ **Warning** > > Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/567) for more information. --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.20`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026520) [Compare Source](openclaw/openclaw@v2026.5.19...v2026.5.20) ##### Changes - Exec approvals: remove the old `cat SKILL.md && printf ... && <skill-wrapper>` allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed. - Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. ([#84264](openclaw/openclaw#84264)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Discord/voice: include bounded `IDENTITY.md`, `USER.md`, and `SOUL.md` profile context in realtime voice session instructions by default, with `voice.realtime.bootstrapContextFiles: []` available to disable it. ([#84499](openclaw/openclaw#84499)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Dependencies: bump the bundled Codex harness to `@openai/codex` `0.132.0` and refresh the app-server model-list docs for the new catalog. - CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. ([#80407](openclaw/openclaw#80407)) Thanks [@giodl73-repo](https://github.com/giodl73-repo). - Agents/config: allow `agents.list[].experimental.localModelLean` so lean local-model mode can be enabled for one configured agent instead of globally. - Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. ([#84005](openclaw/openclaw#84005)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Providers/OpenRouter: honor provider-level `params.provider` routing policy for OpenRouter requests, with model and agent params overriding the defaults. Thanks [@amknight](https://github.com/amknight). ##### Fixes - CLI/tasks: include stale-running task maintenance decisions in `openclaw tasks maintenance --json` so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. ([#84691](openclaw/openclaw#84691)) Thanks [@efpiva](https://github.com/efpiva). - Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. ([#84736](openclaw/openclaw#84736)) Thanks [@JARVIS-Glasses](https://github.com/JARVIS-Glasses). - Providers/MiniMax music: stop advertising `durationSeconds` control and remove prompt-injected duration hints, so `music_generate` reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes [#84508](openclaw/openclaw#84508). Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Doctor: warn when sandbox tool policy hides configured MCP server tools before provider requests. ([#84699](openclaw/openclaw#84699)) Thanks [@nxmxbbd](https://github.com/nxmxbbd). - WhatsApp: update Baileys to `7.0.0-rc12`. - Build: suppress per-locale `rolldown-plugin-dts:fake-js` CommonJS dts warnings emitted while bundling the intentionally-inlined `zod/v4/locales/*.d.cts` files, so `pnpm build` output stays readable after the 0.25.1 plugin bump. Thanks [@romneyda](https://github.com/romneyda). - CLI/nodes: route lazy plugin-registration logs to stderr for JSON-mode `openclaw nodes` commands so stdout stays parseable. ([#84684](openclaw/openclaw#84684)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Approvals: route manual `/approve` decisions through the trusted approval runtime so active exec and plugin approvals no longer look unknown or expired. - Mac app: update the About settings copyright year to 2026. ([#84385](openclaw/openclaw#84385)) Thanks [@pejmanjohn](https://github.com/pejmanjohn). - Dependencies: update `@openclaw/fs-safe` to `0.2.7` so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS. - Infra/secrets: restore the fail-closed contract for `tryReadSecretFileSync` so credential loaders that pass `rejectSymlink: true` (Telegram, LINE, Zalo, IRC, Nextcloud Talk tokens) refuse symlinked credential files instead of silently accepting them, and the infra-state CI shard's secret-file symlink test passes again. Thanks [@romneyda](https://github.com/romneyda). - Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. ([#84595](openclaw/openclaw#84595)) - Doctor: remove unrecognized `models.providers.*.models[*].compat.thinkingFormat` values during `doctor --fix` so stale provider model config can validate after upgrade. Fixes [#77803](openclaw/openclaw#77803). - Doctor: warn when `openclaw.json` stores plaintext secret-bearing config fields, including model provider API keys and sensitive provider headers. ([#84718](openclaw/openclaw#84718)) Thanks [@lukaIvanic](https://github.com/lukaIvanic). - Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from `agents.defaults.model.primary`. - WebChat: clear stale typing indicators when session change events mark the active chat run complete. - Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports. - macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows. - Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed. - fix(mattermost): fail closed on missing channel type \[AI]. ([#84091](openclaw/openclaw#84091)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Recheck rebuilt system.run argv \[AI]. ([#84090](openclaw/openclaw#84090)) Thanks [@pgondhi987](https://github.com/pgondhi987). - CLI: keep the private QA subcommand out of exported command descriptors unless `OPENCLAW_ENABLE_PRIVATE_QA_CLI=1`, so root help and subcommand markers match runtime registration. ([#84519](openclaw/openclaw#84519)) - CLI/cron: bound `openclaw cron show` job lookup pagination so non-advancing or unbounded `cron.list` responses fail instead of hanging the command. Fixes [#83856](openclaw/openclaw#83856). ([#83989](openclaw/openclaw#83989)) - Agents/messages: stop message-tool-only turns after a successful source-channel `message` send while keeping transcript mirrors under the session write lock. ([#84289](openclaw/openclaw#84289)) - Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. ([#83477](openclaw/openclaw#83477)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving `strict=false` fallback behavior. Fixes [#82930](openclaw/openclaw#82930). ([#82933](openclaw/openclaw#82933)) Thanks [@galiniliev](https://github.com/galiniliev). - Agents/code mode: spell out the `exec` tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. ([#84269](openclaw/openclaw#84269)) Thanks [@Kaspre](https://github.com/Kaspre). - Codex: give `image_generate` dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. ([#84254](openclaw/openclaw#84254)) Thanks [@moritzmmayerhofer](https://github.com/moritzmmayerhofer). - Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. ([#82937](openclaw/openclaw#82937)) Thanks [@galiniliev](https://github.com/galiniliev). - CLI/message: include a stable top-level `messageId` in `openclaw message --json` output when channel sends return one. ([#84191](openclaw/openclaw#84191)) Thanks [@100menotu001](https://github.com/100menotu001). - Cron: preserve legacy top-level array `jobs.json` stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes [#60799](openclaw/openclaw#60799). ([#84433](openclaw/openclaw#84433)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Gateway/agents: use an agent's `identity.name` in Gateway agent summaries when `agents.list[].name` is unset, so configured agent labels remain visible in clients. ([#84355](openclaw/openclaw#84355); refs [#57835](openclaw/openclaw#57835)) Thanks [@luoyanglang](https://github.com/luoyanglang). - Channels/replies: keep normal `/verbose` failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. ([#84303](openclaw/openclaw#84303)) Thanks [@VACInc](https://github.com/VACInc). - Plugins/hooks: apply a default 30-second timeout to `before_compaction` and `after_compaction` hooks so a hung plugin handler no longer blocks compaction completion. ([#84153](openclaw/openclaw#84153)) - Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. ([#84188](openclaw/openclaw#84188)) Thanks [@100menotu001](https://github.com/100menotu001). - Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes [#83887](openclaw/openclaw#83887). ([#84244](openclaw/openclaw#84244)) Thanks [@hclsys](https://github.com/hclsys). - Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes [#82766](openclaw/openclaw#82766). ([#82767](openclaw/openclaw#82767)) Thanks [@galiniliev](https://github.com/galiniliev). - Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. ([#84067](openclaw/openclaw#84067)) Thanks [@abnershang](https://github.com/abnershang). - Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. ([#84045](openclaw/openclaw#84045)) Thanks [@abnershang](https://github.com/abnershang). - Plugins/perf: thread explicit plugin discovery results through `loadBundledCapabilityRuntimeRegistry`, `resolveBundledPluginSources`, and `listChannelCatalogEntries` so callers that already hold a discovery result skip redundant filesystem walks. Thanks [@SebTardif](https://github.com/SebTardif). - harden update restart script creation \[AI]. ([#84088](openclaw/openclaw#84088)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes [#83613](openclaw/openclaw#83613). ([#83626](openclaw/openclaw#83626)) Thanks [@YuanHanzhong](https://github.com/YuanHanzhong). - CLI/channels: preserve the first line of `openclaw channels logs` output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed `readLogSlice` behavior in `src/logging/log-tail.ts`. - Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. ([#84057](openclaw/openclaw#84057)) - CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. ([#83995](openclaw/openclaw#83995)) Thanks [@ThiagoCAltoe](https://github.com/ThiagoCAltoe). - Matrix/config: accept `messages.queue.byChannel.matrix` queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost. Thanks [@bdjben](https://github.com/bdjben). - CLI: format `openclaw acp client` failures through the shared error formatter so object-shaped errors stay readable instead of printing `[object Object]`. Fixes [#83904](openclaw/openclaw#83904). ([#84080](openclaw/openclaw#84080)) - Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when `/api/show` omits capabilities. ([#84055](openclaw/openclaw#84055)) Thanks [@dutifulbob](https://github.com/dutifulbob). - Installer/Windows: launch `install.ps1` onboarding as an attached child process so fresh native Windows installs do not freeze visibly at `Starting setup...` or corrupt the wizard's terminal rendering. - CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so `openclaw update` no longer silently switches the gateway to a different Node binary when multiple Node installations are present. Thanks [@amknight](https://github.com/amknight). - CLI/gateway: include the running Gateway version in `gateway status` JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes [#56222](openclaw/openclaw#56222). Thanks [@galiniliev](https://github.com/galiniliev). - Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. ([#83858](openclaw/openclaw#83858)) Thanks [@brokemac79](https://github.com/brokemac79). - CLI/nodes: request pending node surface approval scopes before `openclaw nodes approve` so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with `missing scope: operator.admin`. ([#84392](openclaw/openclaw#84392)) Thanks [@joshavant](https://github.com/joshavant). - Gateway: reject slow node event sends before outbound buffers grow unbounded and log the rejected payload diagnostic. ([#84387](openclaw/openclaw#84387)) Thanks [@samzong](https://github.com/samzong). - Agents: include bounded trajectory queued-writer diagnostics in `pi-trajectory-flush` timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes [#82961](openclaw/openclaw#82961). ([#82962](openclaw/openclaw#82962)) Thanks [@galiniliev](https://github.com/galiniliev). - Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes [#83699](openclaw/openclaw#83699). ([#83700](openclaw/openclaw#83700)) Thanks [@galiniliev](https://github.com/galiniliev). - Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes [#84040](openclaw/openclaw#84040). ([#84357](openclaw/openclaw#84357)) Thanks [@joshavant](https://github.com/joshavant). - Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as `anthropic/opus-4.7` no longer fall back to embedded Anthropic billing. Fixes [#84222](openclaw/openclaw#84222). ([#84374](openclaw/openclaw#84374)) Thanks [@joshavant](https://github.com/joshavant). - Agents: honor explicit `models.providers.<id>.timeoutSeconds` values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at \~120s when the provider timeout is higher. ([#83979](openclaw/openclaw#83979)) Thanks [@yujiawei](https://github.com/yujiawei). - Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes [#83836](openclaw/openclaw#83836). ([#84367](openclaw/openclaw#84367)) Thanks [@joshavant](https://github.com/joshavant). - Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing `reason=no_active_run` queue noise. ([#82964](openclaw/openclaw#82964)) Thanks [@galiniliev](https://github.com/galiniliev). - CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. ([#83931](openclaw/openclaw#83931)) Thanks [@honor2030](https://github.com/honor2030). - Media: decode URL path basenames before using them as remote media fallback filenames, so files like `My%20Report.pdf` are surfaced as `My Report.pdf`. Fixes [#84050](openclaw/openclaw#84050). ([#84052](openclaw/openclaw#84052)) Thanks [@jbetala7](https://github.com/jbetala7). - WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to `channels.whatsapp.groups` without changing routing or sender authorization. ([#83846](openclaw/openclaw#83846)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. ([#79083](openclaw/openclaw#79083)) Thanks [@Oviemudiaga](https://github.com/Oviemudiaga). - CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. ([#83640](openclaw/openclaw#83640)) Thanks [@se7en-agent](https://github.com/se7en-agent). - Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. ([#83684](openclaw/openclaw#83684)) Thanks [@ngutman](https://github.com/ngutman). - iOS: repair Release archive compilation for the TestFlight build. ([#84255](openclaw/openclaw#84255)) Thanks [@ngutman](https://github.com/ngutman). - Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. ([#84083](openclaw/openclaw#84083)) Thanks [@100yenadmin](https://github.com/100yenadmin). - Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. ([#42197](openclaw/openclaw#42197)) Thanks [@Rain120](https://github.com/Rain120). - Codex: respect explicit `models auth order set` and `config.auth.order` precedence over stale `lastGood` in `/codex account`, and show `no working credential` when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes [#84386](openclaw/openclaw#84386). ([#84412](openclaw/openclaw#84412)) Thanks [@openperf](https://github.com/openperf). - Agents: honor `messages.suppressToolErrors` for mutating tool failures so configured chat surfaces do not receive separate warning payloads. ([#81561](openclaw/openclaw#81561)) Thanks [@moeedahmed](https://github.com/moeedahmed). - Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes [#79396](openclaw/openclaw#79396). ([#79489](openclaw/openclaw#79489)) Thanks [@aayushprsingh](https://github.com/aayushprsingh). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/615

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

Fix Anthropic CLI auth routing

e776ee9

openclaw-barnacle Bot added agents Agent runtime and tooling extensions: anthropic size: L maintainer Maintainer-authored PR labels May 20, 2026

Add changelog for Anthropic CLI routing

cdde8bc

joshavant merged commit f6de2b3 into main May 20, 2026
137 of 141 checks passed

joshavant deleted the fix/anthropic-cli-runtime-alias-routing branch May 20, 2026 00:58

joshavant mentioned this pull request May 20, 2026

[Bug]: [reopen #82344] Regression after upgrading from 2026.5.7 → 2026.5.18: embedded runtime detected as third-party harness while direct Claude CLI still works #84222

Closed

Haderach-Ram mentioned this pull request May 20, 2026

Ecosystem Digest — 2026-05-20 Haderach-Ram/openclaw-radar#13

Open

github-actions Bot mentioned this pull request May 20, 2026

📡 Upstream Digest — 2026-05-20 02:34 UTC curtismercier/openclaw-mods#901

Open

This was referenced May 20, 2026

[Bug]: Successful auto-compaction can still end in a 120s embedded timeout and generic /new fallback #67750

Open

Agents: add claude-sdk runtime with native-tool bridge + Phase 3 default flip #68961

Closed

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 24, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

a5d119e

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 24, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

45126b8

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 24, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

ff68571

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 24, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

1ed8ad4

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

galiniliev pushed a commit to galiniliev/openclaw that referenced this pull request May 25, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

64f9d39

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 26, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

187e6fc

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 26, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

c590e9b

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

SebTardif pushed a commit to SebTardif/openclaw that referenced this pull request May 26, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

d808ff1

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

jameslcowan pushed a commit to jameslcowan/openclaw that referenced this pull request Jun 2, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

61191d7

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

SYU8384 pushed a commit to SYU8384/openclaw that referenced this pull request Jun 3, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

a8ff41c

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

sablehead pushed a commit to sablehead/openclaw that referenced this pull request Jun 10, 2026

Fix Anthropic CLI auth routing for shorthand refs (openclaw#84374)

06b6166

* Fix Anthropic CLI auth routing * Add changelog for Anthropic CLI routing

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Fix Anthropic CLI auth routing for shorthand refs#84374

Fix Anthropic CLI auth routing for shorthand refs#84374
joshavant merged 2 commits into
mainfrom
fix/anthropic-cli-runtime-alias-routing

joshavant commented May 20, 2026

Uh oh!

clawsweeper Bot commented May 20, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 20, 2026 •

edited

Loading

Uh oh!

Takhoffman commented May 20, 2026

Uh oh!

clawsweeper Bot commented May 20, 2026

Uh oh!

joshavant commented May 20, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

joshavant commented May 20, 2026

Uh oh!

clawsweeper Bot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Takhoffman commented May 20, 2026

Uh oh!

clawsweeper Bot commented May 20, 2026

Uh oh!

joshavant commented May 20, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

clawsweeper Bot commented May 20, 2026 •

edited

Loading

clawsweeper Bot commented May 20, 2026 •

edited

Loading