Update WinNode CLI live tool discovery - #525

• 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.

• 🦀 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.

Best possible solution:

Merge the CLI mode if maintainers accept the new flag after real Windows tray proof shows it lists live MCP tools with bearer-token auth and CI/validation passes.

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

Not applicable as a feature PR. Source review shows current main lacks --list-tools, while existing MCP code already has a live tools/list surface that the PR can call.

Is this the best way to solve the issue?

Yes, the implementation direction is narrow: it reuses the existing CLI endpoint/token path and existing MCP tools/list method rather than adding a parallel discovery mechanism.

Label changes:

• add P3: The PR is a low-risk CLI ergonomics and documentation improvement with focused tests, not an urgent user-impacting regression.
• add rating: 🧂 unranked krab: Current PR rating is 🧂 unranked krab because proof is 🧂 unranked krab, patch quality is 🐚 platinum hermit, and The patch looks focused from source review, but missing live behavior proof keeps the PR below merge-ready quality.
• add status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs real behavior proof before merge: The PR needs redacted live proof, such as terminal output or a terminal screenshot showing winnode --list-tools against a real tray MCP server; updating the PR body should trigger re-review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Label justifications:

• P3: The PR is a low-risk CLI ergonomics and documentation improvement with focused tests, not an urgent user-impacting regression.
• rating: 🧂 unranked krab: Current PR rating is 🧂 unranked krab because proof is 🧂 unranked krab, patch quality is 🐚 platinum hermit, and The patch looks focused from source review, but missing live behavior proof keeps the PR below merge-ready quality.
• status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs real behavior proof before merge: The PR needs redacted live proof, such as terminal output or a terminal screenshot showing winnode --list-tools against a real tray MCP server; updating the PR body should trigger re-review, or a maintainer can comment @clawsweeper re-review. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

What I checked:

• Current CLI lacks list mode: Current main requires --command before any MCP request, so the new flag is a real CLI feature rather than an already-implemented path. (src/OpenClaw.WinNode.Cli/Program.cs:71, b41fe8243cc3)
• Existing MCP live list surface: Current main already exposes tools/list through McpToolBridge, and HandleToolsList reads the provided capability list each call. (src/OpenClaw.Shared/Mcp/McpToolBridge.cs:93, b41fe8243cc3)
• Tray supplies live capabilities to MCP: NodeService.StartMcpServer builds the bridge from a locked live snapshot of registered capabilities plus MCP-only capabilities, matching the PR's live discovery goal. (src/OpenClaw.Tray.WinUI/Services/NodeService.cs:586, b41fe8243cc3)
• PR diff adds focused CLI dispatch: The patch adds WinNodeOptions.ListTools, rejects combining it with --command, and routes list mode to a new BuildToolsListBody() JSON-RPC envelope. (src/OpenClaw.WinNode.Cli/Program.cs:69, 33ca80a8a10a)
• PR test coverage is focused: The patch adds unit coverage for the tools/list body, argument parsing, usage text, RunAsync list-mode behavior, and capability-description drift against concrete capability command lists. (tests/OpenClaw.WinNode.Cli.Tests/RunAsyncTests.cs:86, 33ca80a8a10a)
• Real behavior proof missing: The PR body lists validation commands, but it does not include terminal output, logs, a screenshot, recording, or other after-fix proof showing winnode --list-tools against a real tray MCP server. (33ca80a8a10a)

Likely related people:

• shanselman: Current-main blame shows Scott Hanselman introduced the CLI runner and MCP bridge surfaces this PR extends, and later adjusted MCP capability gating. (role: recent area contributor; confidence: high; commits: 0b5260bf9b4f, 0b31e210a421, 6711591b5c14; files: src/OpenClaw.WinNode.Cli/Program.cs, src/OpenClaw.Shared/Mcp/McpToolBridge.cs, src/OpenClaw.Tray.WinUI/Services/NodeService.cs)
• Ranjesh: Recent current-main history added MCP runtime toggling and AppCapability MCP-only separation, which affects the live capability set returned by tools/list. (role: recent adjacent contributor; confidence: medium; commits: d7d7661ac28c; files: src/OpenClaw.Tray.WinUI/Services/NodeService.cs, src/OpenClaw.Tray.WinUI/App.xaml.cs)

Codex review notes: model gpt-5.5, reasoning high; reviewed against b41fe8243cc3.

• The egg game starts only after the PR passes the real-behavior proof check.
• Before that, no creature or rarity is rolled. The treat waits for real proof.
• This is still just collectible flavor: proof affects review readiness, not creature quality.