fix(anthropic): stop migrating current claude-haiku-4-5 to sonnet by alkor2000 · Pull Request #87719 · openclaw/openclaw

alkor2000 · 2026-05-28T17:01:20Z

Summary

Fixes #87680. claude-haiku-4-5 is a current Anthropic production model, but it is classified as retired in both the Claude model-ref resolver (extensions/anthropic/claude-model-refs.ts) and the doctor config migration (src/commands/doctor/shared/legacy-config-migrations.runtime.models.ts). As a result:

openclaw doctor --fix rewrites an explicitly configured claude-haiku-4-5 to claude-sonnet-4-6, silently overriding a user's cost/latency-driven model choice.
The bare haiku family alias resolves to claude-sonnet-4-6 instead of claude-haiku-4-5.

The reporter notes 13 of their 14 cron jobs pin claude-haiku-4-5 and lose that choice on any doctor-fix pass.

This change:

Removes claude-haiku-4-5 / claude-haiku-4.5 (full and dotted) and the bare haiku-4.5 short alias from the retired-to-sonnet upgrade lists in both mirrors.
Adds an explicit current-model guard that returns the ref unchanged, mirroring the existing claude-opus-4-7 / claude-sonnet-4-6 current-model guards.
Repoints DEFAULT_CLAUDE_MODEL_BY_FAMILY.haiku to claude-haiku-4-5.

Genuinely retired refs (Claude 3 Haiku, retired Sonnet/Opus) still upgrade to their canonical targets. Regression coverage is added for the Claude resolver and the doctor migration.

Real behavior proof

Behavior or issue addressed: openclaw doctor --fix and the haiku alias no longer migrate the current claude-haiku-4-5 model to claude-sonnet-4-6, while genuinely retired Claude 3 Haiku still upgrades to the canonical Sonnet.

Real environment tested: Linux (Ubuntu 24.04, WSL2), Node.js 24.14.0, current PR branch run under the repo's runner and via direct invocation of the real resolver entry point.

Exact steps or command run after this patch: ran the real resolveKnownAnthropicModelRef entry point against representative refs, plus the migration regression suites; and verified before/after by temporarily restoring the retired classification (removing the current-model guard and re-adding the haiku entries) to confirm the regression run fails, then restoring the fix.

Evidence after fix: console output from running the real resolver entry point through node, plus the before/after regression run.
$ node --import tsx proof-resolver.mjs
anthropic/claude-haiku-4-5 -> anthropic/claude-haiku-4-5 (keep, current)
anthropic/claude-haiku-4.5 -> anthropic/claude-haiku-4.5 (keep, current)
anthropic/claude-haiku-4-5@anthropic:work -> anthropic/claude-haiku-4-5@anthropic:work (keep, current)
anthropic/claude-3-5-haiku-20241022 -> anthropic/claude-sonnet-4-6 (truly retired, upgraded)
-- BEFORE the fix (retired classification restored): regression run fails --
$ node scripts/run-vitest.mjs extensions/anthropic/cli-migration.test.ts
x preserves the current claude-haiku-4-5 model and its bare alias
AssertionError: expected 'anthropic/claude-sonnet-4-6' to be 'anthropic/claude-haiku-4-5'
-- AFTER the fix: all pass --
$ node scripts/run-vitest.mjs extensions/anthropic/cli-migration.test.ts
17 passed (17)
$ node scripts/run-vitest.mjs src/commands/doctor/shared/legacy-config-migrate.test.ts
96 passed (96)
$ node scripts/run-vitest.mjs src/commands/doctor-legacy-config.migrations.test.ts
51 passed (51)

Observed result after fix: the current claude-haiku-4-5 (full ref, dotted variant, and with an auth-profile suffix) is returned unchanged by the resolver and the doctor migration, the haiku family alias maps to claude-haiku-4-5, and the doctor migration no longer emits a haiku-to-sonnet change. Genuinely retired claude-3-5-haiku-20241022 still upgrades to claude-sonnet-4-6.

What was not tested: a full interactive openclaw doctor --fix CLI run was not captured end-to-end in this environment; the change is confined to the model-ref resolver and the doctor migration table, both verified through their real exported entry point (resolveKnownAnthropicModelRef) and the three migration regression suites named in the issue's acceptance criteria. No real provider credentials or network calls were used.

claude-haiku-4-5 is a current production model but was classified as retired in both the Claude model-ref resolver and the doctor config migration, so doctor --fix and the bare haiku alias rewrote it to claude-sonnet-4-6, overriding explicit user model choices (Fixes openclaw#87680). Remove claude-haiku-4-5 and claude-haiku-4.5 from the retired upgrade lists in both mirrors, add an explicit current-model guard, and repoint the haiku family alias to claude-haiku-4-5. Genuinely retired Claude 3 Haiku still upgrades to sonnet.

clawsweeper · 2026-05-28T17:02:54Z

Codex review: passed. Reviewed May 28, 2026, 2:50 PM ET / 18:50 UTC.

Summary
The branch preserves current Claude Haiku 4.5 refs in the Anthropic resolver and doctor migration, repoints the bare haiku family alias to claude-haiku-4-5, and updates regression tests.

PR surface: Source +5, Tests +21. Total +26 across 4 files.

Reproducibility: yes. Current main source maps the bare haiku alias and explicit Haiku 4.5 migration path to claude-sonnet-4-6; the PR body also supplies before/after terminal proof for the resolver and migration tests.

Review metrics: 1 noteworthy metric.

Model routing surfaces changed: 1 alias default changed, 2 migration mirrors changed. Alias defaults and doctor migrations affect existing upgrades and Anthropic provider/model routing, so maintainers should notice the compatibility impact before merge.

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:

Keep the compatibility decision visible in the merge context so users understand why Haiku 4.5 is no longer migrated to Sonnet.

Risk before merge

[P1] Merging intentionally changes shipped bare haiku alias behavior from claude-sonnet-4-6 to claude-haiku-4-5, so existing users relying on the alias selecting Sonnet will route to Haiku after upgrade.
[P1] Merging intentionally changes openclaw doctor --fix behavior so explicit Haiku 4.5 refs are no longer rewritten to Sonnet; that fixes the reported preference override but is still an Anthropic model-selection compatibility change.

Maintainer options:

Accept Haiku as the correct alias target (recommended)
Proceed with the PR as-is and own preserving explicit/current Haiku 4.5 selections as the desired upgrade behavior.
Keep old alias routing separately
If maintainers need the bare haiku alias to keep selecting Sonnet, preserve that alias while still stopping doctor from rewriting explicit Haiku 4.5 refs.

Next step before merge

[P2] No repair job is needed; the PR is already focused and the remaining gates are exact-head checks plus maintainer ownership of the compatibility tradeoff.

Security
Cleared: The diff only changes local TypeScript resolver/migration logic and colocated tests, with no dependency, workflow, secret, package, or code-execution surface changes.

Review details

Best possible solution:

Merge the focused fix after exact-head checks pass, with the Haiku alias and doctor migration change treated as an intentional compatibility decision.

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

Yes. Current main source maps the bare haiku alias and explicit Haiku 4.5 migration path to claude-sonnet-4-6; the PR body also supplies before/after terminal proof for the resolver and migration tests.

Is this the best way to solve the issue?

Yes. The PR changes the two mirrored model-ref paths and adds focused regression coverage; the main maintainer choice is whether to accept the alias compatibility change as intentional.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against e8f29087ae5b.

Label changes

Label justifications:

P2: The PR fixes a real provider/model routing bug with limited blast radius and no evidence of an emergency outage.
merge-risk: 🚨 compatibility: The PR changes shipped alias and doctor migration behavior for existing configs that mention Haiku 4.5 or the haiku family alias.
merge-risk: 🚨 auth-provider: The changed resolver and migration paths alter Anthropic model selection, including auth-profile-suffixed model refs.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Sufficient (terminal): The PR body includes after-fix terminal output from the real resolver entry point plus before/after regression-suite output, which is sufficient for this non-visual resolver and config migration path.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix terminal output from the real resolver entry point plus before/after regression-suite output, which is sufficient for this non-visual resolver and config migration path.

Evidence reviewed

PR surface:

Source +5, Tests +21. Total +26 across 4 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	2	12	7	+5
Tests	2	25	4	+21
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	4	37	11	+26

What I checked:

Repository policy read: Root AGENTS.md and extensions/AGENTS.md were read; the compatibility guidance is relevant because the PR changes provider model routing and doctor migration behavior. (AGENTS.md:24, e8f29087ae5b)
Current main resolver behavior: Current main maps the bare haiku family alias to claude-sonnet-4-6 and treats claude-haiku-4-5, claude-haiku-4.5, and haiku-4.5 as Sonnet upgrade inputs. (extensions/anthropic/claude-model-refs.ts:4, e8f29087ae5b)
Current main doctor migration mirror: Current main's doctor migration has the same Claude upgrade table, so openclaw doctor --fix rewrites eligible Haiku 4.5 refs to the Sonnet target. (src/commands/doctor/shared/legacy-config-migrations.runtime.models.ts:617, e8f29087ae5b)
Existing regression expectations: The current migration test expects anthropic/claude-haiku-4-5 in config fields and plugin allowed models to become anthropic/claude-sonnet-4-6, matching the reported bug. (src/commands/doctor/shared/legacy-config-migrate.test.ts:1633, e8f29087ae5b)
PR patch scope: The PR head changes only the Anthropic resolver, the doctor migration mirror, and focused resolver/migration tests; it removes Haiku 4.5 from Sonnet upgrade lists and adds current-model guards. (extensions/anthropic/claude-model-refs.ts:4, 64429e23b3cc)
Real behavior proof supplied: The PR body includes after-fix terminal output from the real resolver entry point plus before/after regression suite output for the changed migration paths. (64429e23b3cc)

Likely related people:

steipete: Local blame on the current resolver and doctor migration tables points to the current checkout import commit, and GitHub file history shows recent retired-model catalog work by this contributor in the same model compatibility area. (role: recent area contributor; confidence: high; commits: 5ebf3b039636, b6530beb05da, f4b5e58231c7; files: extensions/anthropic/claude-model-refs.ts, src/commands/doctor/shared/legacy-config-migrations.runtime.models.ts, src/commands/doctor/shared/legacy-config-migrate.test.ts)
joshavant: GitHub file history for the Anthropic resolver includes prior merged work on Anthropic CLI auth routing for shorthand refs, adjacent to this PR's alias and resolver changes. (role: adjacent Anthropic CLI routing contributor; confidence: medium; commits: f6de2b3885ba; files: extensions/anthropic/claude-model-refs.ts)
rendrag-git: GitHub history for the doctor migration runtime shows recent model compatibility migration work in the same shared migration file. (role: recent doctor/model migration contributor; confidence: low; commits: e153eceea5a0; files: src/commands/doctor/shared/legacy-config-migrations.runtime.models.ts)

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.

Takhoffman · 2026-05-28T17:48:05Z

@clawsweeper automerge

clawsweeper · 2026-05-28T17:48:08Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=64429e23b3ccf20c2821b2151081b2e5e8d4a8bb)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-05-28T18:50:37Z
Merge commit: b3db1dba85fe

What merged:

The branch preserves current Claude Haiku 4.5 refs in the Anthropic resolver and doctor migration, repoints the bare haiku family alias to claude-haiku-4-5, and updates regression tests.
PR surface: Source +5, Tests +21. Total +26 across 4 files.
Reproducibility: yes. Current main source maps the bare haiku alias and explicit Haiku 4.5 migration path ... de-sonnet-4-6`; the PR body also supplies before/after terminal proof for the resolver and migration tests.

Automerge notes:

No ClawSweeper repair was needed after automerge opt-in.

The automerge loop is complete.

Automerge progress:

2026-05-28 18:43:24 UTC review queued 64429e23b3cc (queued)

2026-05-28 18:50:18 UTC review passed 64429e23b3cc (structured ClawSweeper verdict: pass (sha=64429e23b3ccf20c2821b2151081b2e5e8d4a...)

2026-05-28 17:55:53 UTC repair queued 64429e23b3cc (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652

2026-05-28 17:57:16 UTC repair started (running) in 0s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 automerge-openclaw-openclaw-87719

2026-05-28 17:57:36 UTC validation plan (passed) in 20s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 pnpm check:changed; pnpm lint; pnpm check:test-types

2026-05-28 17:57:49 UTC Codex write preflight (passed) in 33s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 danger-full-access

2026-05-28 18:11:08 UTC Codex edit 1 64cd4d7b18a9 (complete) in 13m 52s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 exit 0

2026-05-28 18:11:11 UTC validation and review 1 415b58241d27 (running) in 13m 55s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 repair

2026-05-28 18:35:49 UTC repair completed (no branch change) in 38m 33s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 Codex /review timed out after 453035ms

2026-05-28 18:35:51 UTC repair finished (blocked) in 38m 35s Run: https://github.com/openclaw/clawsweeper/actions/runs/26592456652 Codex /review timed out after 453035ms

2026-05-28 18:50:41 UTC merged 64429e23b3cc (merged by ClawSweeper automerge)

…enclaw#87719) Summary: - The branch preserves current Claude Haiku 4.5 refs in the Anthropic resolver and doctor migration, repoints the bare `haiku` family alias to `claude-haiku-4-5`, and updates regression tests. - PR surface: Source +5, Tests +21. Total +26 across 4 files. - Reproducibility: yes. Current main source maps the bare `haiku` alias and explicit Haiku 4.5 migration path ... de-sonnet-4-6`; the PR body also supplies before/after terminal proof for the resolver and migration tests. Automerge notes: - No ClawSweeper repair was needed after automerge opt-in. Validation: - ClawSweeper review passed for head 64429e2. - Required merge gates passed before the squash merge. Prepared head SHA: 64429e2 Review: openclaw#87719 (comment) Co-authored-by: alkor2000 <200923177@qq.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>

…7719) Summary: - The branch preserves current Claude Haiku 4.5 refs in the Anthropic resolver and doctor migration, repoints the bare `haiku` family alias to `claude-haiku-4-5`, and updates regression tests. - PR surface: Source +5, Tests +21. Total +26 across 4 files. - Reproducibility: yes. Current main source maps the bare `haiku` alias and explicit Haiku 4.5 migration path ... de-sonnet-4-6`; the PR body also supplies before/after terminal proof for the resolver and migration tests. Automerge notes: - No ClawSweeper repair was needed after automerge opt-in. Validation: - ClawSweeper review passed for head 64429e2. - Required merge gates passed before the squash merge. Prepared head SHA: 64429e2 Review: #87719 (comment) Co-authored-by: alkor2000 <200923177@qq.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>

…026.5.28) (#759) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.27` → `2026.5.28` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.28`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026528) [Compare Source](openclaw/openclaw@v2026.5.27...v2026.5.28) ##### Highlights - Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive cleanup, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#87409](openclaw/openclaw#87409), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#88129](openclaw/openclaw#88129)) - Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, runtime-config message actions, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#82492](openclaw/openclaw#82492), [#83304](openclaw/openclaw#83304), [#87160](openclaw/openclaw#87160)) - Mobile and chat surfaces got a broader refresh: the iOS Pro UI, hosted push relay default, realtime Talk tab playback, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches. ([#87367](openclaw/openclaw#87367), [#87531](openclaw/openclaw#87531), [#87682](openclaw/openclaw#87682), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@ngutman](https://github.com/ngutman) and [@BunsDev](https://github.com/BunsDev). - Browser, channel, and automation inputs are stricter: Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context. ([#82887](openclaw/openclaw#82887)) - Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87751](openclaw/openclaw#87751), [#87794](openclaw/openclaw#87794)) - CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, workspace dotenv provider credentials are ignored, heartbeat defaults, OAuth/token lifetimes, and local service startup requests are bounded, agent auth health labels are clearer, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924)) Thanks [@vincentkoc](https://github.com/vincentkoc) and [@giodl73-repo](https://github.com/giodl73-repo). - Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, viewer assets, and release-split external plugin packages. ([#86699](openclaw/openclaw#86699)) - Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening. ##### Changes - Status: show active subagent details in status output. - Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. ([#87370](openclaw/openclaw#87370), [#87372](openclaw/openclaw#87372)) Thanks [@RomneyDa](https://github.com/RomneyDa). - ClawHub: add plugin display names plus skill verification and trust surfaces. ([#87354](openclaw/openclaw#87354), [#86699](openclaw/openclaw#86699)) Thanks [@thewilloftheshadow](https://github.com/thewilloftheshadow) and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - iOS: refresh the dev app with Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback wired to gateway sessions, diagnostics, chat, and realtime Talk. ([#87367](openclaw/openclaw#87367), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@Solvely-Colin](https://github.com/Solvely-Colin) and [@ngutman](https://github.com/ngutman). - Docs: clarify Codex computer-use setup, paste-token stdin auth setup, macOS gateway sleep troubleshooting, native Codex hook relay recovery, container model auth, install deployment cards, device-token admin gating, CLI setup flow compatibility, Notte cloud browser CDP setup, and backport targets. ([#87313](openclaw/openclaw#87313), [#63050](openclaw/openclaw#63050), [#87685](openclaw/openclaw#87685)) Thanks [@bdjben](https://github.com/bdjben), [@liaoandi](https://github.com/liaoandi), and [@thewilloftheshadow](https://github.com/thewilloftheshadow). - PDF/tools: use ClawPDF for PDF extraction, support encrypted PDF extraction, and surface MCP structured content in agent tool results. ([#87670](openclaw/openclaw#87670), [#87751](openclaw/openclaw#87751)) - Providers: add Claude Opus 4.8 support, Fal Krea image model schemas, NVIDIA featured model catalogs, MiniMax streaming music responses, and provider-backed voice model catalogs. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87794](openclaw/openclaw#87794)) Thanks [@eleqtrizit](https://github.com/eleqtrizit) and [@vincentkoc](https://github.com/vincentkoc). - Codex/GitHub: add the GitHub Copilot agent runtime and the Codex Supervisor plugin package. - Plugins: externalize GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata. - Workboard: add agent coordination tools for tracking and handing off active agent work. - Discord: show commentary in progress drafts so live Discord runs expose useful in-progress context. ([#85200](openclaw/openclaw#85200)) - Plugin SDK: add a reply payload sending hook for plugins that need to deliver channel-owned replies and flatten package types for SDK declarations. ([#82823](openclaw/openclaw#82823), [#87165](openclaw/openclaw#87165)) Thanks [@piersonr](https://github.com/piersonr) and [@RomneyDa](https://github.com/RomneyDa). - Policy: add policy comparison, ingress-channel conformance, and sandbox-posture conformance checks. ([#85572](openclaw/openclaw#85572), [#85744](openclaw/openclaw#85744), [#86768](openclaw/openclaw#86768)) ##### Fixes - Agents: fall back to local config pruning when the optional `agents delete` Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces. - Tighten phone-control mutation authorization \[AI]. ([#87150](openclaw/openclaw#87150)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Clarify directive persistence authorization policy \[AI]. ([#86369](openclaw/openclaw#86369)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Agents/Codex: keep spawned agent cwd/workspace state separated, forward ACP spawn attachments, keep hook context prompt-local, release session locks on timeout abort and runtime teardown without deleting live OpenClaw-owned locks during cleanup, avoid session event queue self-wait, clean up exec abort listeners, stream assistant deltas incrementally, recover raw missing-thread compaction failures, preserve rotated compaction session identity, keep compaction-timeout snapshots continuable, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts and prune stale bridge files, close native hook relay replacement races, keep Claude live tool progress visible for watchdog recovery, suppress abandoned requester completion handoff, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, bind node auto-review to prepared plans, retry Claude CLI transcript probes, and bound compaction/steering retries. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#86123](openclaw/openclaw#86123), [#88129](openclaw/openclaw#88129), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#72574](openclaw/openclaw#72574), [#87383](openclaw/openclaw#87383), [#87400](openclaw/openclaw#87400), [#83022](openclaw/openclaw#83022), [#87671](openclaw/openclaw#87671), [#87738](openclaw/openclaw#87738), [#87747](openclaw/openclaw#87747), [#87706](openclaw/openclaw#87706), [#87546](openclaw/openclaw#87546), [#87541](openclaw/openclaw#87541), [#81048](openclaw/openclaw#81048)) Thanks [@mbelinky](https://github.com/mbelinky), [@Alix-007](https://github.com/Alix-007), [@luoyanglang](https://github.com/luoyanglang), [@yetval](https://github.com/yetval), [@sjf](https://github.com/sjf), [@joshavant](https://github.com/joshavant), [@benjamin1492](https://github.com/benjamin1492), [@c19354837](https://github.com/c19354837), [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@pfrederiksen](https://github.com/pfrederiksen), and [@dodge1218](https://github.com/dodge1218). - Codex Supervisor: keep real-home app-server MCP session listing on the loaded state path, bound stored history scans, and close WebSocket probes cleanly. - Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, resolve Gateway message actions against the active runtime config, preserve Telegram SecretRef prompt config and polling keepalives, preserve WhatsApp profile auth roots, QR display, document filenames, and plugin hook config, suppress Discord recovered tool warnings, preserve the Discord voice outbound helper, cap Discord/Signal/Zalo channel request and container timeouts, and block untrusted Teams service URLs while keeping TeamsSDK patterns aligned. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87465](openclaw/openclaw#87465), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#76262](openclaw/openclaw#76262), [#83304](openclaw/openclaw#83304), [#82492](openclaw/openclaw#82492), [#87581](openclaw/openclaw#87581), [#77114](openclaw/openclaw#77114), [#86426](openclaw/openclaw#86426), [#85529](openclaw/openclaw#85529), [#87160](openclaw/openclaw#87160)) Thanks [@zeroaltitude](https://github.com/zeroaltitude), [@lukeboyett](https://github.com/lukeboyett), [@jarvis-mns1](https://github.com/jarvis-mns1), [@xiaotian](https://github.com/xiaotian), [@funmerlin](https://github.com/funmerlin), [@joshavant](https://github.com/joshavant), [@eleqtrizit](https://github.com/eleqtrizit), [@heyitsaamir](https://github.com/heyitsaamir), [@amittell](https://github.com/amittell), [@lidge-jun](https://github.com/lidge-jun), [@liorb-mountapps](https://github.com/liorb-mountapps), [@masatohoshino](https://github.com/masatohoshino), [@bladin](https://github.com/bladin), and [@giodl73-repo](https://github.com/giodl73-repo). - CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, ignore workspace dotenv provider credentials, wait for respawn child shutdown, bound heartbeat defaults plus Codex, GitHub Copilot, OpenAI, Anthropic, Google, Feishu, LM Studio, MiniMax, Xiaomi TTS, and local-provider OAuth/token/model requests, harden Codex auth probes, label auth health by agent, preserve explicit agentRuntime pins during Codex model migration, warm provider auth off the main thread, honor Codex response timeouts, stop migrating current Claude Haiku 4.5 profiles to Sonnet, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#87719](openclaw/openclaw#87719), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924), [#84362](openclaw/openclaw#84362)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@samzong](https://github.com/samzong), [@giodl73-repo](https://github.com/giodl73-repo), [@alkor2000](https://github.com/alkor2000), [@mmaps](https://github.com/mmaps), [@nxmxbbd](https://github.com/nxmxbbd), and [@vincentkoc](https://github.com/vincentkoc). - Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks and stale rate-limit cooldown probes, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, clear completed session active runs, clear stale chat stream buffers, and evict current plugin-state namespaces at row caps. ([#87810](openclaw/openclaw#87810), [#87833](openclaw/openclaw#87833), [#75089](openclaw/openclaw#75089)) Thanks [@joshavant](https://github.com/joshavant) and [@litang9](https://github.com/litang9). - Config/parsing/network: reject partial numeric parsing, parse provider/Discord retry headers and dates strictly, honor IPv6 and bare IPv6 `no_proxy` entries, preserve empty plugin allowlists, canonicalize secret target array indexes, and reject malformed media content lengths, inspected TCP ports, marketplace content lengths, cron epochs, sandbox stat fields, unsafe duration values, empty config path segments, noncanonical schema array refs, unsafe Telegram callback pages, and invalid Teams attachment-fetch DNS targets. ([#87883](openclaw/openclaw#87883)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Browser/input hardening: reject invalid tab indexes, excessive viewport resizes, explicit zero CDP ports, malformed geolocation options, unsafe screenshot or permission-grant timeouts, loose response-body limits, invalid cookie expiries, and non-finite Browser tool delays/timeouts. - Cron/automation: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot, and preflight model fallbacks before skipping scheduled work. ([#82887](openclaw/openclaw#82887)) Thanks [@chen-zhang-cs-code](https://github.com/chen-zhang-cs-code). - Auto-reply/directives: respect provider and relayed channel metadata during directive persistence so channel-originated decisions keep their intended context. ([#87683](openclaw/openclaw#87683)) - WhatsApp: resolve the auth directory from the active profile so profile-scoped WhatsApp installs do not drift to the wrong credential root. ([#82492](openclaw/openclaw#82492)) Thanks [@lidge-jun](https://github.com/lidge-jun). - Gateway/session state: clear completed session active runs, avoid cold-loading providers for MCP inventory, cache single-session child indexes, cap handshake timers, and bound preauth, auth-guard, media, transcript, readiness, and port options. - Channels/replies: preserve channel-owned progress callbacks when verbose output is off, keep group-room progress suppression intact, prefer external session delivery context, escape Discord component id delimiters, force final TUI chat repaints, show Slack reasoning previews, and normalize Discord/Matrix/Mattermost channel numeric options. ([#87476](openclaw/openclaw#87476), [#87423](openclaw/openclaw#87423)) - Agents/tool args: harden smart-quoted argument repair for edit arrays and exact escaped arguments so model-produced tool calls recover without corrupting valid input. ([#86611](openclaw/openclaw#86611)) Thanks [@ferminquant](https://github.com/ferminquant). - Providers/agents: preserve seeded Anthropic signatures, preserve signed thinking payloads, concatenate signature-delta chunks, preserve DeepSeek `reasoning_content` replay across tier suffixes, apply OpenRouter strict9 ids to Mistral routes, promote Ollama plain-text tool calls, load NVIDIA featured model catalogs, stream MiniMax music generation responses, and recover empty preflight compaction. ([#87593](openclaw/openclaw#87593), [#87493](openclaw/openclaw#87493), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764)) Thanks [@Pluviobyte](https://github.com/Pluviobyte) and [@eleqtrizit](https://github.com/eleqtrizit). - Media/images: skip CLI image cache refs when resolving generated images, allow trusted generated HTML attachments, and bound generated video downloads so stale refs and slow providers fail cleanly. ([#87523](openclaw/openclaw#87523), [#87982](openclaw/openclaw#87982)) - File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled. - Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, reuse gateway session and plugin metadata paths, skip unchanged store serialization, patch single-entry session writes, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, avoid full session snapshots for entry reads, defer configured Slack full startup, prefer bundled plugin dist entries, and slim current metadata identity caches. ([#87760](openclaw/openclaw#87760)) - Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, isolate npm plugin installs per package, reject incompatible package plugin API installs, drop the leftover root Sharp dependency from package manifests after the Rastermill migration, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, QA-Lab credential broker calls, QA Matrix substrate requests, and release scenario logs, and keep release/google live guards current. ([#87647](openclaw/openclaw#87647), [#87477](openclaw/openclaw#87477)) Thanks [@rohitjavvadi](https://github.com/rohitjavvadi) and [@vincentkoc](https://github.com/vincentkoc). - Release/CI: bound manual git fetches, ClawHub verifier responses, ClawHub owner metadata, dependency-guard error bodies, Parallels limits, startup/test/memory budget parsing, and diffs viewer build warnings so release lanes fail with useful proof instead of hanging. ([#87839](openclaw/openclaw#87839)) </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/759

…enclaw#87719) Summary: - The branch preserves current Claude Haiku 4.5 refs in the Anthropic resolver and doctor migration, repoints the bare `haiku` family alias to `claude-haiku-4-5`, and updates regression tests. - PR surface: Source +5, Tests +21. Total +26 across 4 files. - Reproducibility: yes. Current main source maps the bare `haiku` alias and explicit Haiku 4.5 migration path ... de-sonnet-4-6`; the PR body also supplies before/after terminal proof for the resolver and migration tests. Automerge notes: - No ClawSweeper repair was needed after automerge opt-in. Validation: - ClawSweeper review passed for head 64429e2. - Required merge gates passed before the squash merge. Prepared head SHA: 64429e2 Review: openclaw#87719 (comment) Co-authored-by: alkor2000 <200923177@qq.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>

openclaw-barnacle Bot added commands Command implementations extensions: anthropic size: XS proof: supplied External PR includes structured after-fix real behavior proof. labels May 28, 2026

clawsweeper Bot merged commit b3db1db into openclaw:main May 28, 2026
200 of 214 checks passed

harjothkhara mentioned this pull request Jun 4, 2026

fix(anthropic): resolve Claude Haiku 4.5 static catalog refs #90110

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(anthropic): stop migrating current claude-haiku-4-5 to sonnet#87719

fix(anthropic): stop migrating current claude-haiku-4-5 to sonnet#87719
clawsweeper[bot] merged 1 commit into
openclaw:mainfrom
alkor2000:fix-87680-haiku-4-5-current-model

alkor2000 commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

Takhoffman commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

alkor2000 commented May 28, 2026

Summary

Real behavior proof

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Takhoffman commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

clawsweeper Bot commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading