fix(validation): resolve F-007 artifact validator CAS-hash conflation

ArtifactPayloadValidator passed the logical slot name into the
content-hash-keyed CAS store, crashing every workflow with a typed
produces slot. Validator now reads payloads from a content map threaded
through ValidationContext (populated from the orchestrator's per-session
artifact cache across all stages) and no longer depends on ArtifactStore.

Also records the slot->CAS-hash mapping as a new ArtifactContentStoredEvent
(registered for serialization), emitted at both CAS write sites, so
artifact content is recoverable from CAS by hash after a cold start.
This commit is contained in:
2026-06-08 17:26:34 +04:00
parent 3f59faaa08
commit d518400b5f
7 changed files with 206 additions and 13 deletions
@@ -225,7 +225,7 @@ fun main() {
inferenceRouter = inferenceRouter,
validationPipeline = ValidationPipeline(
validators = listOf(
ArtifactPayloadValidator(artifactStore),
ArtifactPayloadValidator(),
SemanticValidator(
rules = listOf(
CycleExitRule(requirePolicyForCycles = false),
@@ -30,3 +30,12 @@ data class ArtifactCreatedEvent(
val stageId: StageId,
val schemaVersion: Int,
) : EventPayload
@Serializable
@SerialName("ArtifactContentStored")
data class ArtifactContentStoredEvent(
val artifactId: ArtifactId,
val contentHash: ArtifactId, // CAS content hash returned by ArtifactStore.put(...)
val sessionId: SessionId,
val stageId: StageId,
) : EventPayload
@@ -4,6 +4,7 @@ import com.correx.core.events.events.ApprovalDecisionResolvedEvent
import com.correx.core.events.events.ApprovalGrantCreatedEvent
import com.correx.core.events.events.ApprovalGrantExpiredEvent
import com.correx.core.events.events.ApprovalRequestedEvent
import com.correx.core.events.events.ArtifactContentStoredEvent
import com.correx.core.events.events.ArtifactCreatedEvent
import com.correx.core.events.events.ArtifactValidatedEvent
import com.correx.core.events.events.ArtifactValidatingEvent
@@ -70,6 +71,7 @@ val eventModule = SerializersModule {
subclass(ApprovalDecisionResolvedEvent::class)
subclass(ApprovalGrantCreatedEvent::class)
subclass(ApprovalGrantExpiredEvent::class)
subclass(ArtifactContentStoredEvent::class)
subclass(ArtifactCreatedEvent::class)
subclass(ArtifactValidatingEvent::class)
subclass(ArtifactValidatedEvent::class)
@@ -22,6 +22,7 @@ import com.correx.core.context.model.TokenBudget
import com.correx.core.context.model.EntryRole
import com.correx.core.events.events.ApprovalDecisionResolvedEvent
import com.correx.core.events.events.ApprovalRequestedEvent
import com.correx.core.events.events.ArtifactContentStoredEvent
import com.correx.core.events.events.ArtifactCreatedEvent
import com.correx.core.events.events.ContextTruncatedEvent
import com.correx.core.events.events.ToolCallAssessedEvent
@@ -418,11 +419,25 @@ abstract class SessionOrchestrator(
llmEmittedSlots.firstOrNull()?.let { slot ->
artifactContentCache["${sessionId.value}:${slot.name.value}"] =
inferenceResult.response.text
inferenceResult.responseArtifactId?.let { hash ->
emit(
sessionId,
ArtifactContentStoredEvent(
artifactId = slot.name,
contentHash = hash,
sessionId = sessionId,
stageId = stageId,
),
)
}
}
val validationCtx = ValidationContext(
graph = graph,
sessionState = session.state,
availableTools = effectives.registry?.all()?.map { it.name }?.toSet()
availableTools = effectives.registry?.all()?.map { it.name }?.toSet(),
producedArtifactContent = graph.stages.values.flatMap { it.produces }.mapNotNull { slot ->
artifactContentCache["${sessionId.value}:${slot.name.value}"]?.let { slot.name.value to it }
}.toMap(),
)
when (val outcome = mapValidationOutcome(sessionId, stageId, validationCtx)) {
is StageExecutionResult.Success -> {
@@ -702,8 +717,17 @@ abstract class SessionOrchestrator(
)
}
val jsonContent = Json.encodeToString(ProcessResultArtifact.serializer(), processResult)
artifactStore.put(jsonContent.toByteArray())
val storedHash = artifactStore.put(jsonContent.toByteArray())
artifactContentCache["${sessionId.value}:${slot.name.value}"] = jsonContent
emit(
sessionId,
ArtifactContentStoredEvent(
artifactId = slot.name,
contentHash = storedHash,
sessionId = sessionId,
stageId = stageId,
),
)
}
val sourceId = toolCall.id ?: invocationId.value
@@ -1073,7 +1097,7 @@ abstract class SessionOrchestrator(
),
)
InferenceResult.Success(response)
InferenceResult.Success(response, responseArtifactId)
} catch (e: TimeoutCancellationException) {
emit(
sessionId,
@@ -1456,7 +1480,7 @@ private fun buildDiffString(path: String, existingContent: String?, proposedCont
}
internal sealed interface InferenceResult {
data class Success(val response: InferenceResponse) : InferenceResult
data class Success(val response: InferenceResponse, val responseArtifactId: ArtifactId? = null) : InferenceResult
data class Failed(val reason: String) : InferenceResult
data object Cancelled : InferenceResult
}
@@ -3,7 +3,6 @@ package com.correx.core.validation.artifact
import com.correx.core.artifacts.kind.FileWrittenArtifact
import com.correx.core.artifacts.kind.ProcessResultArtifact
import com.correx.core.artifacts.kind.TypedArtifactSlot
import com.correx.core.artifactstore.ArtifactStore
import com.correx.core.events.types.ArtifactId
import com.correx.core.validation.model.ValidationContext
import com.correx.core.validation.model.ValidationIssue
@@ -13,16 +12,14 @@ import com.correx.core.validation.pipeline.Validator
import kotlinx.serialization.json.Json
import java.nio.file.Path
class ArtifactPayloadValidator(
private val artifactStore: ArtifactStore,
) : Validator {
class ArtifactPayloadValidator : Validator {
override suspend fun validate(context: ValidationContext): ValidationSection {
val issues = mutableListOf<ValidationIssue>()
for ((_, stageConfig) in context.graph.stages) {
for (slot in stageConfig.produces) {
validateSlot(slot, issues)
validateSlot(slot, context.producedArtifactContent, issues)
}
}
@@ -31,11 +28,10 @@ class ArtifactPayloadValidator(
private suspend fun validateSlot(
slot: TypedArtifactSlot,
artifactContent: Map<String, String>,
issues: MutableList<ValidationIssue>,
) {
val bytes = artifactStore.get(slot.name) ?: return
val payloadStr = bytes.toString(Charsets.UTF_8)
val payloadStr = artifactContent[slot.name.value] ?: return
when (slot.kind.id) {
"file_written" ->
@@ -11,4 +11,5 @@ data class ValidationContext(
val cyclePolicies: Set<CyclePolicyBinding> = emptySet(),
val sessionState: SessionState? = null,
val availableTools: Set<String>? = null,
val producedArtifactContent: Map<String, String> = emptyMap(),
)
+161
View File
@@ -0,0 +1,161 @@
# correx QA / Audit Report — 2026-06-08
Live operator session (Phase 3). Provider: local llama-server via env-var fallback
(`llama-cpp:default` @ 127.0.0.1:10000). Target: `qa/sample-repo/` (tag `clean`).
## Run context / repro prompt
Workflow: `role_pipeline` (analyst→architect→planner→implementer⇄reviewer).
Target workspace (TUI `Hello` workingDir): `/home/kami/Programs/correx/qa/sample-repo`
(reset between runs with `git -C qa/sample-repo reset --hard clean`).
Provider: env-var fallback `llama-cpp:default` @ 127.0.0.1:10000 (start llama-server first).
Operator prompt used for every run so far:
```
Fix the failing test in this repository. Running `python3 -m pytest` shows
tests/test_calc.py::test_average_empty failing: calc.average([]) raises
ZeroDivisionError, but it should return 0.0 for an empty list. Diagnose the
cause in src/sampleapp/calc.py, implement the fix, and verify all tests pass.
```
Patches applied this session (rebuild + restart server to load):
- F-001: `LlamaCppInferenceProvider.kt` — drop grammar when tools present.
- F-005: `FileReadConfig`/`Main` workspace builder/`FileReadTool` — workingDir-relative
path resolution.
- F-007: validator content-map (drops CAS dep) + `ArtifactContentStoredEvent` slot→hash
recording. No server restart needed for validation correctness.
## Findings
### F-001 — grammar + tools sent together → llama.cpp 400, every tool+artifact stage dies
- **invariant/contract:** functional (workflows run end-to-end) / #7 path (artifact constraint)
- **subsystem:** infrastructure/inference (llama_cpp)
- **severity:** blocker
- **evidence:** `logs/current.log` analyst stage: `llama-server returned 400 Bad Request:
"Cannot use custom grammar constraints with tools."`. Request body carries both
`"grammar": "root ::= ..."` and `"tools":[file_read, stage_complete]`.
- **repro:** `correx run role_pipeline` (any prompt) against sample-repo. Analyst declares
`allowed_tools=[file_read, ShellTool]` AND `produces=[analysis]`. Fails immediately.
- **root cause:** `LlamaCppInferenceProvider.kt:103-104` sets `grammar` and `tools`
unconditionally. llama.cpp's server forbids the combination. ANY stage that both has
tools and a JSON `responseFormat` is unrunnable on llama.cpp. role_pipeline analyst +
implementer both do → pipeline cannot start.
- **fix direction:** when tools are present, drop the GBNF grammar and rely on
post-hoc schema validation + retry (invariant #7 still holds — output is validated);
OR gate the artifact emission into a separate tool-free final inference turn.
- **status:** PATCHED (workaround) — `LlamaCppInferenceProvider.kt`: grammar suppressed
when tools are present; artifact now constrained by validation+retry only. Requires
server restart to take effect. Proper fix tracked below.
- **follow-up TODO (proper fix):** add a first-class artifact-emission tool — the LLM
calls `emit_artifact(path, content, description)` like it calls file_read/file_write,
making artifact production an explicit schema-checked tool call instead of a grammar
constraint that can't coexist with tools. TODO left in code at the patch site.
### F-002 — non-retryable 400 is retried to exhaustion
- **invariant/contract:** functional (retry accounting)
- **subsystem:** core/kernel (orchestration retry policy)
- **severity:** minor
- **evidence:** orchestrator marks the 400 `retryable=true`; retries 1/3, 2/3, 3/3 all
identical 400s within ~80ms, then `WorkflowFailedEvent retryExhausted=true`.
- **suspected cause:** retry classifier treats all provider failures as retryable. A 400
`invalid_request_error` is deterministic request-construction failure → should be terminal.
- **status:** confirmed
### F-003 — `~` not expanded in default_system prompt path
- **subsystem:** core/kernel (prompt loading) / core/config
- **severity:** minor
- **evidence:** `failed to load prompt '~/.config/correx/prompts/default_system.md':
Prompt not found (searched: .../prompts/~/.config/correx/prompts/default_system.md)` —
tilde concatenated literally onto the config dir. Logged ERROR on every attempt.
Non-fatal (run proceeds) but noisy + the default system prompt is silently absent.
- **status:** confirmed
### F-005 — file_read jails relative paths against process cwd, not the workspace
- **invariant/contract:** functional (tool jailing) / two-plane consistency (#9)
- **subsystem:** infrastructure/tools/filesystem (FileReadTool) + apps/server wiring
- **severity:** major (blocks any file_read of a relative path unless server launched
from inside the workspace)
- **evidence:** `logs/current.log` session c0eab7ba: analyst emitted
`file_read(path=tests/test_calc.py)`. Plane-2 PATH_CONTAINMENT PROCEEDed
(`resolved=.../qa/sample-repo/tests/test_calc.py, inWorkspace=true`), but the tool's own
`validateRequest` rejected it: `Path 'tests/test_calc.py' is not in the allowed list`
→ stage produced no artifact → surfaced as the misleading `no transition condition
matched from stage analyst`.
- **root cause:** `FileReadTool` resolved the relative path via `Paths.get(p).toAbsolutePath()`
= JVM process cwd (the correx repo root, where the server was launched), not the bound
workspace. `FileReadConfig` had no `workingDir` field at all, unlike FileWrite/FileEdit
which carry `workingDir` and call `resolvePath()`. So the two file-access planes anchored
relative paths to different roots.
- **status:** PATCHED — added `workingDir` to `FileReadConfig`, wired
`workspace.workingDir` in Main's per-workspace tool builder, and gave `FileReadTool` a
`resolvePath()` mirroring FileWriteTool. Requires server restart.
- **note:** the operator-facing failure reason (`no transition condition matched`) masked
the real cause (tool denial). See F-004 family — failure-reason surfacing is lossy.
### F-007 — ArtifactPayloadValidator conflates slot name with CAS content-hash → crash
- **invariant/contract:** functional (artifacts validate) / #7 (LLM output untrusted
until validated — the validation step itself is broken)
- **subsystem:** core/validation + core/artifacts-store contract vs infrastructure CAS
- **severity:** BLOCKER (every workflow with a typed `produces` slot crashes at the first
post-stage validation against the real CAS store)
- **evidence:** `logs/current.log` session 28c818c1: analyst COMPLETED
(responseArtifactId=82da21d5…, a real blake3 hash), then
`runSession ... failed: hex string must have even length` —
`CasArtifactStore.hexToBytes` at `CasArtifactStore.kt:102`, called from
`ArtifactPayloadValidator.validateSlot:36`.
- **root cause:** `ArtifactPayloadValidator.validateSlot` calls
`artifactStore.get(slot.name)`. `slot.name` is the LOGICAL slot id ("analysis"), but
`CasArtifactStore.get` requires `ArtifactId.value` to be a hex content-hash
(`id.value.hexToBytes()`). "analysis" → odd-length → `require` throws. The validator has
no slot-name→content-hash mapping: `ValidationContext` carries only the static graph +
`SessionState`, and `SessionState` holds NO produced-artifact map. So the validator
cannot locate the bytes it is supposed to validate.
- **deeper implication:** this path has apparently never been exercised end-to-end against
the real content-addressed CAS — it only "works" if the ArtifactStore is keyed by literal
slot name (an in-memory test double). The `ArtifactStore.get(ArtifactId)` contract is
ambiguous: the validator treats ArtifactId as a logical name, the CAS treats it as a hash.
- **fix direction (NOT a one-liner):** the run's produced-artifact mapping
(slot name → ArtifactId(hash)) must be derived from the event log (an ArtifactProduced-type
event projection per invariant #1) and threaded into `ValidationContext`, so the validator
resolves slot.name → stored hash before `get`. Cross-module change
(events → projection → context builder → validator). Audit-only: NOT patched.
- **status:** FIXED.
- **fix applied:** two changes (validation crash + durable mapping).
1. *Validator no longer touches the CAS.* `ValidationContext` gained
`producedArtifactContent: Map<String,String>` (slot.name.value → payload). The
orchestrator populates it from the in-memory `artifactContentCache` for every produced
slot across `graph.stages` (scoped to the session). `ArtifactPayloadValidator` reads
from that map and **dropped its `ArtifactStore` dependency entirely** — the slot-name
vs content-hash conflation is gone. `Main.kt` wiring updated. Validation stays live-only
(never runs during replay) so invariant #8 is unaffected.
2. *Slot→CAS-hash mapping now recorded as an event* (invariant #9 — env observation
recorded at the moment it runs). New `ArtifactContentStoredEvent(artifactId=logical
slot, contentHash=CAS blake3 hash, sessionId, stageId)`, registered in
`Serialization.kt`, emitted at both CAS write sites (LLM-emitted slot path + tool/
process_result path; the tool path previously discarded the `put()` return value). This
is the durable record that lets content be recovered from CAS by hash after a cold start.
- **remaining follow-up (not in this fix):** the validator/`needs`-rehydration still read the
*in-memory* `artifactContentCache`, which is lost on restart (the F-001 rehydration-gap
suspect). Closing that means resolving slot→hash→CAS from the new
`ArtifactContentStoredEvent` on cold start / re-validation. Foundation is now in place.
### F-006 — TUI input pane render glitch
- **subsystem:** apps/tui-go
- **severity:** minor (cosmetic)
- **evidence:** operator screenshot 16:07 — a garbled/smeared rectangular artifact in the
bottom-right of the input pane (uncleared region / stale cell buffer) while the prompt
text rendered normally on the left.
- **repro:** operator confirms it appears **only on multi-line paste** into the input box;
single-line / typed input renders clean. Likely the input widget doesn't repaint the full
region when a pasted block changes line count.
- **status:** confirmed, repro narrowed (multi-line paste only)
### F-004 — InferenceFailedEvent / RetryAttemptedEvent unmapped to TUI bridge
- **invariant/contract:** functional (operator observability)
- **subsystem:** apps/server (DomainEventMapper)
- **severity:** minor
- **evidence:** `DomainEventMapper: unmapped payload type=InferenceFailedEvent` and
`=RetryAttemptedEvent` repeated. Operator sees failure only via router narration, not a
structured failure/retry surface in the TUI.
- **status:** confirmed