fix(ollama): default unknown capabilities to tools by dutifulbob · Pull Request #84055 · openclaw/openclaw

dutifulbob · 2026-05-19T08:36:57Z

Summary

Ollama models can lose tools when OpenClaw cannot read their capability list.
This change makes that fallback assume native Ollama chat supports tools.
It keeps the fix limited to the one issue reproduced from #81915.

What Changed

The fallback model definition now marks unknown Ollama capabilities as tool-capable.
Models that explicitly report capabilities still use the reported tools flag.

Set supportsTools to true when capabilities are unavailable.
Added a regression assertion for that fallback path.

Testing

I tested the exact fallback path and the focused Ollama provider model test file.
I also checked formatting and whitespace.

node --import tsx --eval 'import { buildOllamaModelDefinition } from "./extensions/ollama/src/provider-models.ts"; const m = buildOllamaModelDefinition("qwen2.5:3b"); console.log(JSON.stringify(m.compat)); if (m.compat?.supportsTools !== true) process.exit(1);'
node scripts/run-vitest.mjs extensions/ollama/src/provider-models.test.ts
pnpm exec oxfmt --check --threads=1 extensions/ollama/src/provider-models.ts extensions/ollama/src/provider-models.test.ts
git diff --check

Real behavior proof

Behavior addressed: OpenClaw omitted supportsTools when Ollama capabilities were unavailable, so an Ollama model could be treated as not tool-capable.
Real environment tested: Local OpenClaw source checkout, Node 22.22.0, pnpm 11.1.0, with a local Ollama-compatible HTTP endpoint that returned /api/tags and /api/show without a capabilities field.
Exact steps or command run after this patch: Ran pnpm openclaw models list --provider ollama --json with OPENCLAW_HOME and OPENCLAW_CONFIG_PATH pointed at the local endpoint, then built the Ollama provider against the same endpoint.
Evidence after fix: Terminal output from the OpenClaw CLI and provider runtime:

OpenClaw CLI command:
$ node scripts/run-node.mjs models list --provider ollama --json
{
  "count": 1,
  "models": [
    {
      "key": "ollama/fallback-tools:latest",
      "name": "fallback-tools:latest",
      "input": "text",
      "contextWindow": 8192,
      "local": true,
      "available": false,
      "tags": [],
      "missing": false
    }
  ]
}

Ollama provider runtime output:
{
  "model": {
    "id": "fallback-tools:latest",
    "input": [
      "text"
    ],
    "contextWindow": 8192,
    "compat": {
      "supportsTools": true,
      "supportsUsageInStreaming": true
    }
  }
}

Observed result after fix: The CLI discovered the Ollama model from the endpoint whose /api/show response had no capabilities field, and the provider model still reported compat.supportsTools as true.
What was not tested: No additional behavior beyond the Ollama unknown-capabilities fallback in this PR.

Risks

The main risk is an Ollama model that truly rejects tools when capabilities cannot be read.
That case can still opt out with compat.supportsTools: false on the model entry.

clawsweeper · 2026-05-19T08:38:16Z

Codex review: passed.

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 makes unknown-capabilities Ollama model definitions report compat.supportsTools: true, adds a focused regression assertion, and adds an Unreleased changelog entry.

Reproducibility: yes. for the metadata gap: current main builds unknown-capabilities Ollama models without an explicit compat.supportsTools, and the PR body shows after-fix live provider output with supportsTools: true. I did not establish an end-to-end current-main tool-loss run in this read-only review.

PR rating
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🐚 platinum hermit
Summary: Good focused PR with sufficient live-output proof and no blocking findings; the remaining concern is the explicit compatibility tradeoff.

Rank-up moves:

none

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.

PR egg
✨ Hatched: 💎 rare Brave Signal Puff

        .--^^^^--.           
     .-'  o    o  '-.        
    /       \__/      \      
   |    /\  ____  /\   |     
   |   /  \/____\/  \  |     
    \  \_.------._/  /       
     '._  `----'  _.'        
        '-.____.-'           
       _/|_|  |_|\_          
      /__|      |__\         
       `-----------'         
 =====================

Rarity: 💎 rare.
Trait: sniffs out flaky tests.
Share on X: post this hatch
Copy: My PR egg hatched a 💎 rare Brave Signal Puff 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.
How to hatch it: reach status: 👀 ready for maintainer look or status: 🚀 automerge armed; that 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.

Real behavior proof
Sufficient (live_output): The PR body includes after-patch live CLI/provider output from a local Ollama-compatible endpoint without capabilities, directly showing the changed provider metadata.

Risk before merge
Why this matters: - Merging this PR intentionally treats unknown-capabilities Ollama models as tool-capable; an Ollama-compatible server that omits capabilities but rejects tool schemas would need an explicit compat.supportsTools: false model entry.

The exact-head check set had a failing label-issues check and running checks at review time, so automerge should wait for required checks to pass or be rerun.

Maintainer options:

Merge the narrow Ollama fallback fix (recommended)
Accept the default because native Ollama chat supports tool calling and incompatible servers can opt out per model with compat.supportsTools: false.
Require an explicit strict fallback policy
Ask for a config or provider policy decision first if maintainers do not want unknown Ollama-compatible endpoints treated as tool-capable by default.
Defer to the broader Ollama PR
Pause this PR if maintainers want the fallback default reviewed together with the wider Ollama timeout, thinking, and keep-alive changes in fix(ollama): propagate supportsTools, disable idle watchdog, fix thinking and keep_alive #81915.

Next step before merge
No further code repair is indicated; keep this PR in the automerge/maintainer gate until exact-head checks settle and maintainers accept the Ollama compatibility default.

Security
Cleared: The diff only changes Ollama provider metadata, a colocated test assertion, and changelog text; it does not touch secrets, CI/workflows, dependencies, install scripts, or downloaded code paths.

Review details

Best possible solution:

Land the narrow provider metadata fix if maintainers accept the documented opt-out for incompatible local models, and keep broader Ollama timeout/thinking/keep-alive behavior in separate review.

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

Yes for the metadata gap: current main builds unknown-capabilities Ollama models without an explicit compat.supportsTools, and the PR body shows after-fix live provider output with supportsTools: true. I did not establish an end-to-end current-main tool-loss run in this read-only review.

Is this the best way to solve the issue?

Yes, with the compatibility caveat: changing buildOllamaModelDefinition is the narrow provider-owned path for this metadata fallback, and the existing per-model compat override is the right escape hatch for incompatible servers.

Label justifications:

P2: This is a focused Ollama provider compatibility fix with limited blast radius and a colocated regression assertion.
merge-risk: 🚨 compatibility: The PR changes the default metadata for unknown-capabilities Ollama-compatible models and could enable tool schemas against a server that does not support them.

What I checked:

Current main fallback metadata gap: On current main, buildOllamaModelDefinition returns only { supportsUsageInStreaming: true } when capabilities === undefined, so unknown-capabilities Ollama models do not explicitly advertise tool support. (extensions/ollama/src/provider-models.ts:257, 1c1c75df7278)
PR implementation is narrow: The PR branch changes only the unknown-capabilities branch to { supportsTools: true, supportsUsageInStreaming: true }; explicit capability lists still decide supportsTools from capabilities.includes("tools"). (extensions/ollama/src/provider-models.ts:257, b7a44bff60a5)
Regression assertion added: The PR adds a direct assertion that a no-capabilities model reports compat.supportsTools === true while preserving the existing streaming-usage assertion. (extensions/ollama/src/provider-models.test.ts:285, b7a44bff60a5)
Existing opt-out contract: Current config types and schema already support compat.supportsTools?: boolean, and docs tell users to set compat.supportsTools: false for models or servers that fail on tool schemas. (src/config/types.models.ts:59, 1c1c75df7278)
Runtime default remains permissive: The shared tool-support helper already treats missing compat.supportsTools as tool-capable and only disables tools when it is explicitly false, so this PR primarily makes Ollama fallback metadata explicit. (src/agents/model-tool-support.ts:1, 1c1c75df7278)
Ollama API contract checked: The upstream Ollama API docs describe /api/chat accepting a tools parameter and returning tool_calls, while /api/show can expose capabilities, supporting the provider-local assumption for native Ollama but not every Ollama-compatible server.

Likely related people:

steipete: Recent commit history and blame show repeated Ollama provider model capability/test changes around the current fallback code path. (role: recent area contributor; confidence: high; commits: a1b89317a8bb, 930b443c9e2b, 7a4574376a79; files: extensions/ollama/src/provider-models.ts, extensions/ollama/src/provider-models.test.ts)
ImLukeF: Recent provider-model history includes the Ollama model-show metadata cache work, which is adjacent to this fallback path for /api/show metadata. (role: adjacent feature contributor/reviewer; confidence: medium; commits: 3da58226bfe6; files: extensions/ollama/src/provider-models.ts)
BruceMacD: The model capability detection history includes the /api/show vision/capability work that established the capability-driven model definition path this PR adjusts. (role: feature contributor/reviewer; confidence: medium; commits: ac3f55504cbe; files: extensions/ollama/src/provider-models.ts, extensions/ollama/src/provider-models.test.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 1c1c75df7278.

osolmaz · 2026-05-19T08:38:21Z

/clawsweeper review

clawsweeper · 2026-05-19T08:40:12Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26086177024
Updated: 2026-05-19T08:47:07.799Z

osolmaz · 2026-05-19T09:09:14Z

/clawsweeper automerge

clawsweeper · 2026-05-19T09:11:27Z

🦞🔧
ClawSweeper saw the passing review, but the PR needs another repair pass before merge.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=b7a44bff60a5e7b6d8b5da792c5236e788a061c1); failed required checks before automerge: Real behavior proof:CANCELLED
Action: repair worker queued. Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411
Model: gpt-5.5

I will update this PR branch, or open a safe credited replacement, if the repair worker finds a narrow CI fix.

Automerge progress:

2026-05-19 09:14:56 UTC validation plan (passed) in 19s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 pnpm check:changed; pnpm lint; pnpm check:test-types

2026-05-19 09:15:13 UTC Codex write preflight (passed) in 36s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 danger-full-access

2026-05-19 09:19:33 UTC Codex edit 1 25ddb03fb9ee (complete) in 4m 56s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 exit 0

2026-05-19 09:20:26 UTC validation and review 1 b7a44bff60a5 (base moved) in 5m 49s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 rebased

2026-05-19 09:20:34 UTC repair completed b7a44bff60a5 (branch updated) in 5m 56s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 initial automerge rebase is delegated to Codex repair

2026-05-19 09:20:33 UTC review queued b7a44bff60a5 (after repair)

2026-05-19 09:20:56 UTC automerge wait b7a44bff60a5 (blocked) in 6m 19s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 GitHub checks failed: label-issues:FAILURE

2026-05-19 09:20:58 UTC repair finished b7a44bff60a5 (pushed) in 6m 20s Run: https://github.com/openclaw/clawsweeper/actions/runs/26087707847 repair_contributor_branch

2026-05-19 09:27:16 UTC review passed b7a44bff60a5 (structured ClawSweeper verdict: pass (sha=b7a44bff60a5e7b6d8b5da792c5236e788a06...)

2026-05-19 09:27:37 UTC repair queued b7a44bff60a5 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411

2026-05-19 09:30:28 UTC repair started (running) in 1s Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411 automerge-openclaw-openclaw-84055

2026-05-19 09:30:44 UTC validation plan (passed) in 16s Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411 pnpm check:changed; pnpm lint; pnpm check:test-types

2026-05-19 09:31:02 UTC Codex write preflight (passed) in 34s Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411 danger-full-access

2026-05-19 09:38:50 UTC Codex edit 1 b7a44bff60a5 (complete) in 8m 22s Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411 exit 0

2026-05-19 09:42:56 UTC validation and review 1 27527716c09e (complete) in 12m 28s Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411 already-current

2026-05-19 09:43:39 UTC repair finished 27527716c09e (opened) in 13m 11s Run: https://github.com/openclaw/clawsweeper/actions/runs/26088501411 open_fix_pr

clawsweeper · 2026-05-19T09:43:36Z

ClawSweeper 🐠 reef update

Thanks for the work here. ClawSweeper could not write to the source branch, so it opened a replacement PR rather than letting the fix drift. attribution still points back here.

Why replacement: ClawSweeper could not update the source PR branch directly; GitHub did not grant sufficient push rights to the bot for that branch.
Replacement PR: #84075
Why close: this run explicitly closes the superseded source PR after the credited replacement PR is open, so review continues in one place.
This source PR is being closed only under the explicit source-close setting for this ClawSweeper run.
The original contribution stays credited in the replacement PR context.
Co-author credit kept:

@dutifulbob: Co-authored-by: Bob 261991368+dutifulbob@users.noreply.github.com

fish notes: model gpt-5.5, reasoning high; reviewed against 2752771.

…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

openclaw-barnacle Bot added extensions: ollama size: XS triage: mock-only-proof Candidate: PR proof only shows tests, mocks, snapshots, lint, typecheck, or CI. labels May 19, 2026

dutifulbob mentioned this pull request May 19, 2026

fix(ollama): propagate supportsTools, disable idle watchdog, fix thinking and keep_alive #81915

Closed

clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. labels May 19, 2026

clawsweeper Bot added the clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge label May 19, 2026

dutifulbob and others added 2 commits May 19, 2026 09:20

fix(ollama): default unknown capabilities to tools

9720dbb

fix(ollama): default unknown capabilities to tools

b7a44bf

clawsweeper Bot force-pushed the fix/ollama-unknown-capabilities-tools branch from 25ddb03 to b7a44bf Compare May 19, 2026 09:20

clawsweeper Bot added status: 🚀 automerge armed This PR is in ClawSweeper's automerge lane. and removed status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. labels May 19, 2026

clawsweeper Bot mentioned this pull request May 19, 2026

fix(ollama): default unknown capabilities to tools #84075

Merged

clawsweeper Bot closed this May 19, 2026

clawsweeper Bot mentioned this pull request May 19, 2026

[Bug]: I Found that Qwen3.5 4b tool calls work at v2026.5.7 but vanish in v2026.5.12 #82633

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(ollama): default unknown capabilities to tools#84055

fix(ollama): default unknown capabilities to tools#84055
dutifulbob wants to merge 2 commits into
openclaw:mainfrom
dutifulbob:fix/ollama-unknown-capabilities-tools

dutifulbob commented May 19, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 19, 2026 •

edited

Loading

Uh oh!

osolmaz commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 19, 2026 •

edited

Loading

Uh oh!

osolmaz commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 19, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

dutifulbob commented May 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

What Changed

Testing

Real behavior proof

Risks

Uh oh!

clawsweeper Bot commented May 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

osolmaz commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

osolmaz commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

dutifulbob commented May 19, 2026 •

edited

Loading

clawsweeper Bot commented May 19, 2026 •

edited

Loading

clawsweeper Bot commented May 19, 2026 •

edited

Loading

clawsweeper Bot commented May 19, 2026 •

edited

Loading