Mushi-Mushi

Dispatch Mushi fix agent

dispatch_fix

Start an automated fix for a classified bug report: creates a branch and opens a signed draft PR, returning a fix ID for tracking. Use an idempotency key to retry safely.

Instructions

Start a Mushi fix agent for a classified report; it writes a branch and opens a signed draft PR. Set agent="cursor_cloud" to dispatch a Cursor Cloud Agent (default uses the in-repo worker). Requires GitHub connected + an LLM key (run diagnose_setup mode=dispatch first). Returns { fixId, status } (fixId is the dispatch id; get_fix_timeline accepts it immediately); poll get_fix_timeline for progress and merge_fix when CI is green. Write; pass the same idempotencyKey to retry safely — without it each call starts a new attempt. Report must be classified — run triage_issue if not.

Input Schema

TableJSON Schema

Name	Required	Description
`agent`	No	Which agent runs the fix. Omit for the project default (auto); cursor_cloud and github_cloud_agent dispatch a cloud agent.
`reportId`	Yes	Report UUID to fix (`report_id` is accepted too.)
`projectId`	No	Project UUID — defaults to the configured project. (`project_id` is accepted too.)
`idempotencyKey`	No	Optional RFC 4122 UUID. Resend the same key to safely retry without dispatching a duplicate fix job (Idempotency-Key IETF draft).
`inventoryActionNodeId`	No	Optional inventory Action node UUID for spec-traceability (§2.10). When provided, the fix-worker embeds the expected_outcome contract in the LLM prompt and runs validateAgainstSpec before opening the PR.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`fixId`	Yes
`status`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.1.12Sep 24, 2026

changedInput schema / properties / agent / description

Previous value: -"Override the agent adapter"New value: +"Which agent runs the fix. Omit for the project default (auto); cursor_cloud and github_cloud_agent dispatch a cloud agent."

changedInput schema / properties / agent / enum

Previous value: -[
-  "claude_code",
-  "codex",
-  "rest_worker",
-  "mcp"
-]New value: +[
+  "auto",
+  "claude_code",
+  "codex",
+  "cursor_cloud",
+  "github_cloud_agent",
+  "rest_worker",
+  "rest_fix_worker",
+  "llm",
+  "mcp"
+]

addedInput schema / properties / projectId

Added value: +{
+  "description": "Project UUID — defaults to the configured project. (`project_id` is accepted too.)",
+  "type": "string"
+}

changedInput schema / properties / reportId / description

Previous value: -"Report UUID to fix"New value: +"Report UUID to fix (`report_id` is accepted too.)"

Changed2 schema fields changedv0.1.10Sep 15, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed2 schema fields changedv0.1.1Jun 25, 2026

addedInput schema / properties / reportId / format
```
Added value: +"uuid"
```

addedInput schema / properties / reportId / pattern

Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"

First observedv0.1.0Jun 24, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses the real-world side effects (branch creation, signed draft PR), the non-idempotent behavior ('without it each call starts a new attempt'), and the prerequisite of GitHub + LLM key. These are consistent with readOnlyHint=false and idempotentHint=false, and they add detail the annotations alone cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every clause carries information: purpose, agent override, prerequisites, return contract, retry semantics, and classification precondition. It is front-loaded with the main action. The only minor blemish is the cryptic 'Write;' marker, which slightly obscures the retry note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a rich schema and output schema, the description covers everything an agent needs to invoke it correctly: when it is applicable, prerequisites, what it returns, how to monitor it, and how to complete the workflow. Nothing critical is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers all 5 parameters with descriptions (100% coverage). The description adds value by emphasizing that agent defaults to the in-repo worker and by framing idempotencyKey omission as a new attempt. This is a modest addition over the schema, which already explains the idempotency behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start a Mushi fix agent'), plus the concrete side effects ('writes a branch and opens a signed draft PR'). This clearly differentiates it from siblings like suggest_fix, which only produce suggestions, and submit_fix_result, which submits results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides direct context for when to dispatch: a report must be classified, with an explicit fallback ('run triage_issue if not'). It also names prerequisites and the post-dispatch workflow (poll get_fix_timeline, merge_fix when CI is green). It does not enumerate all alternative tools, but the key conditions and sequencing are explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.