feat(guardrails): steering channel + shell-in-file rule + capability-gap detector

Bundles three operator-reliability guardrails (Vikunja #28/#29/#30) plus the
in-flight branch WIP they were built on top of (reasoning_content capture,
operator/project profile editor, write-jail workspaceRoot fix) — the tree is
interdependent (SessionOrchestrator references reasoningArtifactId from the WIP)
and does not compile as separable subsets, so it lands as one commit.

Guardrails:
- #28 mid-stage steering: ClientMessage.SteerSession -> GlobalStreamHandler ->
  orchestrator.submitSteering, reusing SteeringNoteAddedEvent + existing context
  fold (advisory, non-authoritative; invariants #3/#7). Closes the gap where
  steering typed off an approval gate was silently dropped.
- #29 shell-in-file guardrail: ShellInFileContentRule (core:toolintent) blocks a
  file_write whose content is a bare shell command (e.g. "mkdir -p ..."); FileWriteTool
  description now advertises auto-mkdir of parent dirs. Basename-allowlist so the
  extensionless case is caught; scripts/Makefiles/multiline exempt.
- #30 pt1 capability-gap detector: deterministic CapabilityGapDetector maps stage
  intent -> implied ToolCapability, compares to granted tools, emits advisory
  CapabilityGapDetectedEvent in FreestyleDriver.lockAndRun. Recorded, never fails
  the gate and never auto-grants (invariants #3/#4/#5). Reflection rung is pt2.

Verified: ./gradlew check green (whole tree).
This commit is contained in:
2026-07-07 13:27:59 +04:00
parent 879672a47d
commit 41ed6414c6
43 changed files with 1592 additions and 94 deletions
@@ -20,6 +20,7 @@ import com.correx.core.events.events.OrchestrationResumedEvent
import com.correx.core.events.events.RefinementIterationEvent
import com.correx.core.events.events.RetrySalvageDecidedEvent
import com.correx.core.events.events.SalvageDecision
import com.correx.core.events.events.SteeringNoteAddedEvent
import com.correx.core.events.events.StoredEvent
import com.correx.core.events.events.TransitionExecutedEvent
import com.correx.core.events.orchestration.OrchestrationState
@@ -469,6 +470,30 @@ class DefaultSessionOrchestrator(
emit(sessionId, OrchestrationResumedEvent(sessionId, stageId))
}
/**
* Records free-form operator steering for a session that is mid-stage — independent of any
* approval gate. Unlike [submitApprovalDecision]/[submitClarification] this never completes a
* pending deferred: the running stage is not paused waiting on it. It only appends a
* [com.correx.core.events.events.SteeringNoteAddedEvent], which [buildSteeringNoteEntries] folds
* into context as an advisory `steeringNote` entry on the *next* context turn (invariants #3/#7 —
* advisory only, never a state mutation). Reuses the existing SteeringNoteAddedEvent/fold rather
* than a parallel event type, since that mechanism already implements exactly this semantics
* (see TalkieFacade's STEERING chat mode, which emits the same event).
*/
suspend fun submitSteering(sessionId: SessionId, text: String) {
if (text.isBlank()) return
val currentStageId = runCatching { orchestrationRepository.getState(sessionId).currentStageId }
.getOrNull()
emit(
sessionId,
SteeringNoteAddedEvent(
sessionId = sessionId,
content = text,
stageId = currentStageId,
),
)
}
private suspend fun executeMove(
ctx: EnrichedExecutionContext,
decision: TransitionDecision.Move,