feat(toolintent): stage write-manifest enforcement (role-reliability §2)

Scope creep — an implementer writing files it never declared — is the
dominant local-model failure that compiler/tests don't catch. A stage can
now declare a `writes` manifest (workspace-relative globs); a FILE_WRITE
that resolves inside the workspace but outside the declared set is raised
as PATH_OUTSIDE_MANIFEST → BLOCK, so the model gets the violation as tool
feedback and retries within scope (the §2 bounded-retry signal).

Implemented as a plane-2 rule beside PathContainmentRule (same effect-based
dispatch on FILE_WRITE, same symlink-safe WorldProbe resolution, same
recorded observations so replay reads them back — invariant #9). An empty
manifest is unrestricted; out-of-workspace targets stay PathContainmentRule's
concern, so the two rules don't double-flag.

- StageConfig.writeManifest + TomlWorkflowLoader `writes` parsing
- ToolCallAssessmentInput.writeManifest, threaded from the active stage via
  SessionOrchestrator.runPlane2Assessment
- new ManifestContainmentRule, registered in the server assessor
- shared candidatePathStrings extracted so both path rules judge the same
  target set
- role_pipeline.toml documents the option on the implementer stage

The dedicated ManifestViolationEvent the spec names is not added: the
violation is already recorded replayably in ToolCallAssessedEvent (issue +
observations + BLOCK) and surfaced in the TUI rationale band. A first-class
event is worth adding only once reconciliation consumes it.
This commit is contained in:
2026-06-13 16:05:39 +04:00
parent 894969d62b
commit 4e5e4e56ea
11 changed files with 233 additions and 16 deletions
@@ -41,6 +41,7 @@ private data class StageSection(
val produces: List<ProducesEntry> = emptyList(),
val needs: List<String> = emptyList(),
@param:JsonProperty("allowed_tools") val allowedTools: List<String> = emptyList(),
val writes: List<String> = emptyList(),
@param:JsonProperty("token_budget") val tokenBudget: Int = 4096,
@param:JsonProperty("max_retries") val maxRetries: Int = 3,
@param:JsonProperty("requires_approval") val requiresApproval: Boolean = false,
@@ -102,6 +103,7 @@ class TomlWorkflowLoader(
},
needs = s.needs.map { ArtifactId(it) }.toSet(),
allowedTools = s.allowedTools.toSet(),
writeManifest = s.writes,
tokenBudget = s.tokenBudget,
// Propagate the declared token budget to the inference completion cap.
// Without this the StageConfig default (maxTokens=2048) is used, truncating
@@ -135,4 +135,24 @@ class TomlWorkflowLoaderTest {
val path = Files.createTempFile("workflow", ".toml").also { it.writeText(validToml) }
assertEquals("", loader.loadMeta(path).description)
}
@Test
fun `writes maps to the stage write manifest`() {
val toml = validToml.replace(
"allowed_tools = [\"ShellTool\"]",
"allowed_tools = [\"ShellTool\"]\nwrites = [\"core/**\", \"docs/*.md\"]",
)
val path = Files.createTempFile("workflow", ".toml").also { it.writeText(toml) }
val graph = loader.load(path)
val collectStage = graph.stages[graph.start]!!
assertEquals(listOf("core/**", "docs/*.md"), collectStage.writeManifest)
}
@Test
fun `writes absent means an empty manifest`() {
val path = Files.createTempFile("workflow", ".toml").also { it.writeText(validToml) }
val graph = loader.load(path)
val collectStage = graph.stages[graph.start]!!
assertEquals(emptyList(), collectStage.writeManifest)
}
}