Render stage clarification questions as an AskUserQuestion-style form:
header chip, prompt, selectable option chips, and a free-text custom slot.
Arrow/hjkl nav, space to select, e for custom, enter to submit. Submit
guards on all-answered and sends ClarificationResponse; the parked stage
re-runs with the answers in context.
Surfaces the clarification loop over the wire: ServerMessage.ClarificationRequired
(clarification.required, carrying the structured questions) is mapped from
ClarificationRequestedEvent; ClientMessage.ClarificationResponse carries the
operator's answers and is routed to orchestrator.submitClarification on both
the global and session streams. Reuses the core ClarificationQuestion/Answer
types as the wire shape. Round-trip tests for both directions.
Makes the research feature runnable end-to-end, off by default.
- config: [tools.research] (enabled, searxng_url, max_results, max_fetch_bytes).
- registration: web_search/web_fetch are built into BOTH the default and per-workspace
tool registries when research.enabled, sharing one HTTP client threaded from Main
(none built on the static path). Egress stays harness-enforced: web_fetch is T2
(operator-approved) and the existing NetworkHostRule still applies.
- workflow: examples/workflows/research.toml — decompose → gather → report, with the
three artifact schemas and prompts. Fan-out (search per sub-question, fetch per source)
runs as repeated tool calls inside the gather stage (Correx has no parallel agents);
per-source synthesis into the dossier is the compression step, so the report stage
consumes summaries, never raw pages. ResearchWorkflowTest validates the graph contract.
To run: set [tools.research].enabled, register the 3 [[artifacts]], copy research.toml +
prompts + schemas into the workflows dir, start SearXNG. Launch like any workflow (the
T2 fetch approval surfaces as an approval card; the report opens in the artifact viewer).
Follow-ups (noted, not blocking): batch fetch-approval at the source-list level (§3),
a dedicated SourceFetched/LowQualityExtraction event (quality + content hash are already
in tool-result metadata), dynamic per-session egress allowlist, and the web approval client (§6).
Health states are events. A HealthMonitor polls registered HealthProbes on an
interval and appends HealthDegraded/HealthRestored only on a status transition
(hysteresis), so health is observable, replayable, and renderable like every
other fact in the log. The probe reads nondeterministic environment state and
records it at observe-time (Invariant #9); HealthProjection rebuilds current
health by replay, never re-probing (Invariant #8). Monitor is live-only, started
in ServerModule.start alongside narration; seeded from the projection so a
restart does not re-emit a degraded the log already records.
First concrete probe: DiskWatermarkProbe — event-log + CAS size and growth rate,
warning before the 2am surprise. Read surface mirrors `correx stats`:
GET /health/checks replays the system session and `correx health` renders it.
Health events ride the reserved __system__ session, filtered from operator
session listings.
LLAMA_SERVER (liveness + tokens/sec trend) and EVENT_STORE (append/fsync latency)
probes plug into the same HealthProbe framework as follow-ups.
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.
Layer 1 of tui-requirements §5: a no-LLM analyzer that shell-lexes a
proposed command, classifies binaries against a known-command table, and
mechanically flags the constructs that widen blast radius — sudo/doas,
recursive delete, pipe-to-shell (skipping wrappers so `| sudo sh` counts),
redirects outside the workspace, network binaries, base64/eval, and
unparseable input (itself a red flag). Pure + replay-stable: same preview
+ workspaceRoot → same analysis, no environment reads.
The approval band renders command approvals as a card — worst-first flag
chips over the reconstructed command line, each token colored by severity
(T0–T4 ramp). ^x opens a scrollable fullscreen view so a long command is
never truncated. Diff and plain-preview paths are unchanged.
Server: computeToolPreview now renders the shell tool's argv as a full,
shell-quoted command line instead of the 200-char JSON-args fallback,
honouring §3's "full untruncated command". The TUI parser accepts both
the rendered line and the older `{"argv":[...]}` shape for replay.
Layer 2 (model annotation) deliberately deferred per the spec.
The TUI overflowed and became unreadable on narrow terminals: the status bar and
footer spilled far past the edge (justify never truncated), the two-column main
split shrank the events panel to ~20 cols, and the stats overlay wrapped mid-word.
- justify is now width-safe: shrinks the left segment first (the right holds the
high-signal connection clock / active spinner), clamps the right only as a last
resort, ANSI-aware so it never slices escape codes. No line can exceed the width.
- Main area collapses below narrowWidth (96): single full-width session list when
idle; output stacked over the live event strip in-session (the strip is too
valuable to drop — the constraint is width, not height).
- Compact chrome when slim: status drops workspace/gauge/provider-suffix and uses a
short clock ("◷ 3s") + bare spinner; footer uses a reduced hint set and drops the
"Soft·blue" badge; approval action row tightens its gaps so decision keys stay
visible.
- Overlays get near-full-width on slim terminals; stats pane uses compact formats +
per-line clipping so it never wraps.
Tests: no rendered line exceeds the terminal width at 40–160 cols (incl. the stats
overlay); narrow in-session main stacks output+events.
Implements the load-bearing TUI-requirements §2 hard requirements:
- Last-event clock: "last event Ns ago" always visible in the status bar while
in-session, updating every frame tick. Turns warn-colored when an active session
has gone quiet past the stale threshold — the "thinking vs hung" tell. The
WebSocket connection indicator (●/◌/○) already covers immediate drop visibility.
- Unknown-event raw fallback: applyServer now surfaces any unrecognized,
session-scoped event type as a raw row in the event stream instead of silently
dropping it (the frontend must not lie by omission). Recognized-but-unrendered
types (router.response, protocol_error) get an explicit no-op so the default
branch means genuinely unknown.
Tests: agoLabel formatting, unknown-event surfaces-as-row, known-ignored
no-spurious-row. Preview "session" frame exercises the clock.
Deferred: the full Go↔Kotlin per-event-type render matrix (§2 last bullet) — a
larger fixture effort than the core behaviors landed here.
Implements observability-spec §2 + §3-tier-1: metrics as a pure fold over the
event log, no third pillar, no OTel. Every metric is replayable over the full
historical log because it derives from events other contexts already emit — no
new EventPayload subclasses, so no serialization registry change.
- MetricsProjection: Projection<MetricsState> folding inference/tool/approval/
stage/workflow events into raw sums; approval request→decision latency is
correlated in-fold via a transient pending-request map.
- MetricsInspectionService: rebuilds via DefaultEventReplayer, derives read-side
ratios (token throughput, avg approval wait, session wall-time accounting split
into inference / tool / approval-wait / other) into MetricsReport.
- GET /sessions/{id}/metrics route, mirroring the replay endpoint.
- `correx stats <sessionId>` CLI client (--json passthrough), mirroring replay.
- Tests: seeded-event fold correctness with controlled timestamps (7) + CLI
render smoke tests (4).
Implement T1 of observability epic: every server log line carries sessionId
(and stageId where known) via SLF4J MDC, propagated across coroutine
suspension points.
Changes:
- Create com.correx.apps.server.logging.Correlation: withSessionContext()
helper that sets MDC (sessionId, stageId), wraps block in MDCContext(),
and restores prior values on exit; supports safe nesting
- Wrap launchSessionRun() orchestrator loop in withSessionContext(sessionId)
so all session logs carry the sessionId
- Wrap GlobalStreamHandler ChatInput and StartChatSession onUserInput call
sites in withSessionContext(sessionId)
- Wrap SessionStreamHandler ChatInput onUserInput in withSessionContext(sessionId)
- Update log4j2.properties patterns: append
%notEmpty{ [%X{sessionId}]}%notEmpty{ [%X{stageId}]} before %msg
on both console and file appenders
- Add kotlinx-coroutines-slf4j:1.9.0 dependency for MDCContext
Test (6 tests):
- withSessionContext sets/restores sessionId ✓
- withSessionContext sets/restores stageId ✓
- Nested contexts stack and restore correctly ✓
- MDC cleared when stageId not provided ✓
- Propagation across coroutine boundaries via MDCContext ✓
- Cleanup after block exit ✓
Acceptance:
- Zero behavior change; no core module touched ✓
- All imports verified as used ✓
- No bare try-catch; try/finally used correctly ✓
- Detekt-compliant ✓
- Full test suite passes (120 tests, 119 passed, 1 skipped) ✓
A stale RUNNING session skipped by resumeAbandoned stayed RUNNING in
every projection — the TUI showed a phantom running workflow that no
process was executing, and each boot re-logged the same skip. Parking
now emits OrchestrationPaused(reason=ABANDONED_STALE): status becomes
PAUSED (truthful — not executing, resumable via POST /resume) and
subsequent boots skip it on status alone.
#2: approval pauses narrate from ApprovalRequestedEvent (carries
tool/tier/preview/stage directly) instead of OrchestrationPaused +
a pending-approvals map the next event had not yet populated — the
narrator always lost that race and produced generic text.
#3: NarrationTrigger now carries the triggering event's stageId; the
narration status line and RouterNarrationEvent.stageId use it instead
of the router projection's currentStageId, which terminal events have
already cleared ('Stage: none').
#9: ExecutionPlanLocked -> plan.locked and ArtifactValidated ->
artifact.validated mapped to the TUI (Go: feed lines, plan shows the
compiled stage chain); ArtifactValidating explicitly dropped.
#10: blank router turn guard — a length-finish with empty text now
emits an explanatory turn naming the max_tokens budget instead of a
silent blank; blank steering responses no longer emit steering notes.
#12: resumeAbandoned only auto-resumes sessions whose last event is
within orchestration.resume_abandoned_max_age_minutes (default 24h,
0 disables); staler sessions stay parked for POST /resume. Knob is
TUI-editable and persisted.
launchSessionRun and launchSessionResumeWithRehydrate each inlined their
own copy of the freestyle phase-2 handoff with different guard sets — the
run path had none, so a failed planning run still called lockAndRun and
emitted a spurious ExecutionPlanRejected. Both now call one handoff that
checks graph id, planning result, and an existing plan lock before
locking and running phase 2.
resumeAbandonedSessions (boot pickup of RUNNING sessions) and the
restart-while-approval-pending subscription still used the bare
launchSessionResume: no artifact-cache rehydrate and no freestyle
plan-lock handoff. A freestyle session killed mid-planning was grabbed
by the boot path before the operator could POST /resume, completed the
planning graph, and stranded — WorkflowCompleted but never locked
(live repro: session b36b0e45, 2026-06-12).
Both paths now use launchSessionResumeWithRehydrate; the bare launcher
is deleted.
Three gaps found by live QA (kill between planning-complete and plan lock):
- launchSessionResumeWithRehydrate never handed off to FreestyleDriver, so a
resumed freestyle session stranded at planning-complete with no plan lock
and no phase 2; now locks+runs when planning completed and no
ExecutionPlanLockedEvent exists yet.
- resume route 400'd on phase-2 sessions (workflowId freestyle-<sid> is
compiled, never registered); now recompiles the locked plan after
rehydrating the artifact cache.
- orchestrator.resume threw when currentStageId was terminal ('done') or
unknown to the graph; now returns WorkflowResult.Completed.
Chat sessions never emitted ProjectProfileBoundEvent — only the workflow
path did — so router triage always saw a null profile and could not cite
conventions or commands. Extract the binding from launchSessionRun into
ServerModule.bindProjectProfile and call it from handleStartChatSession.
h1-h3 headings become the file's symbols, so design docs and GDDs are
embedded and retrievable alongside code. .md files now also participate in
workspace fingerprinting (INDEXED_EXTENSIONS derives from pattern keys).
Adds 'gd' to SYMBOL_PATTERNS (func/class_name/class/signal/enum at column 0,
optional static prefix). Because INDEXED_EXTENSIONS derives from the pattern
keys, .gd files now also participate in WorkspaceStateProbe fingerprinting,
making fp: state keys content-sensitive for Godot repos.
- Add existsByTurnIdPrefix(prefix) to L3MemoryStore interface; implemented in
InMemoryL3MemoryStore (mutex-guarded) and TurboVecL3MemoryStore (metadata map).
All test fakes (TrackingL3MemoryStore, CapturingStore) updated.
- Introduce RepoMapIndexerPort interface; RepoMapIndexer implements it. Allows
injection of test doubles without framework overhead.
- ProjectMemoryService.indexAndRecord: reads latest WorkspaceStateObservedEvent
from event store (invariant #9 — recorded fact, not re-probe); skips scan+embed
when L3 already holds entries for "repomap:<root>:<stateKey>"; passes stateKey
to RepoMapComputedEvent; embeds each scanned entry after append; per-entry
failures warn-logged (CancellationException rethrown).
- Tests: InMemoryL3MemoryStoreTest +2 cases; new ProjectMemoryServiceReuseTest
covers same-key skip, changed-key re-index, no-observation always-reindex,
and embedding turnId tag verification.
After a freestyle plan compiles successfully, requestPlanApproval is invoked
before ExecutionPlanLockedEvent is emitted. Rejection emits
ExecutionPlanRejectedEvent(source="operator") with no lock and no phase-2 run.
Adds public SessionOrchestrator.requestPlanApproval seam delegating to
requestStageApproval, wired in Main.kt. Two new tests cover the reject and
approve paths; existing tests stay green via the default passthrough param.
Both silent-failure branches in FreestyleDriver.lockAndRun now emit
ExecutionPlanRejectedEvent (source=compile or missing_content) before
returning, satisfying invariant #1. Event registered in eventModule for
correct polymorphic serialization.
qa_ping is a minimal single-stage file_write workflow used for live QA smoke
runs (writes 'pong' into the qa/ scratch repo). The qa/ workspace itself is a
nested git repo and stays untracked; the compiled tui-go binary is ignored.
Artifact content wider than the modal was silently cut off. Lines are now
hard-wrapped at rune boundaries to the modal content width, and scroll
clamping uses the wrapped line count so the last page stays reachable.
file_written artifacts store a JSON envelope ({path, contentHash, size, mode})
whose contentHash points at the real bytes in CAS. The viewer rendered the
envelope itself. StreamQueries now detects the envelope shape (string "path" +
"contentHash") and dereferences the inner hash, falling back to the raw string
when parsing fails or the inner hash is missing (WARN logged — likely evicted).
[router.narration] model_id selects which provider handles narration turns
instead of generic capability routing — lets a small/fast model own narration
while the main model keeps CHAT/STEERING.
- NarrationSettings.modelId parsed from TOML, threaded via RouterConfig
.narrationModelId into DefaultRouterFacade.narrate (3-arg route)
- DefaultInferenceRouter: exact-id match against healthy providers, with a
post-select health check; any miss logs WARN and falls back to capability
routing (never fails the narration turn)
- onUserInput unchanged — only narrate uses the pinned model (tested)
Follow-ups spotted while fixing the artifact-content bug:
- #1 robustness: listArtifacts resolves content via runCatching, degrading to null
instead of failing the whole listing on one bad CAS read (resolveContent helper)
- #2 eviction visibility: WARN when a referenced artifact hash resolves to null
(most likely evicted/compacted while still referenced by the event log)
- #3 ordering trap: document on ArtifactCreated/ArtifactContentStored that 'Created'
fires at validation, AFTER ContentStored at inference — the latent fold hazard
- #4 reopen gap: SessionSnapshot now carries workspaceRoot (derived from
SessionWorkspaceBound), so a reopened session restores its workspace label
- #5 orchestrator headroom: isBackEdge externalised to a top-level function so
DefaultSessionOrchestrator drops below the TooManyFunctions threshold (was at it)
#6 (orphaned empty F-010-era artifacts) needs no code change — empty content is
already normalised to null ('(no content stored)'); emission is prevented going
forward by the shipped F-010/F-018/F-020 fixes.
Root cause of empty artifact content (even for role_pipeline sessions with intact CAS
data): ArtifactContentStored is emitted at inference time, BEFORE ArtifactCreated (which
fires at validation). listArtifacts only applied the content hash via accs[id]?.let{} —
a no-op because the artifact wasn't in the map yet — so the hash was silently dropped and
every artifact showed blank.
Verified against the live store (session 4679ed1e): all 5 artifacts had hash=none before,
now resolve to their validated content (analysis 867B, design 1074B, impl_plan 966B,
patch 574B, review_report 369B).
- ArtifactContentStored now seeds the accumulator (getOrPut), order-independent
- fold extracted to pure StreamQueries.planArtifacts for unit testing
- regression test: content hash captured when ContentStored precedes Created
- inference-output fallback retained for genuinely content-less stages
Artifacts with no ArtifactContentStored mapping (older sessions, or stages where the
slot->hash link was lost) showed a blank pane. listArtifacts now falls back to the
stage's last InferenceCompleted output so the operator can still see what the stage
produced. Empty-string content is normalised to null so the viewer shows a clear
'(no content stored)' instead of a blank pane.
Verified: role_pipeline sessions already resolve content from CAS (index + segments
intact, store rooted at ~/.config/correx/artifacts); the previously-blank sessions are
healthcheck/degenerate runs whose inference output was genuinely empty.
Reopening a session after relaunch sent only a thin summary snapshot, so the output
panel was blank and the event list showed at most 7 entries (of a 100+ event run).
- SessionSnapshot now carries lastOutput/lastResponse, resolved from the last
InferenceCompleted artifact in CAS; tui-go onSnapshot restores the output panel
- recentEvents cap raised 7 -> 200 so a normal session's event list isn't truncated
- resolveLastOutput extracted as a helper
Note: artifact content is unaffected — verified intact and CAS-retrievable for
role_pipeline sessions (artread); content-less artifacts occur only in workflows that
record no ArtifactContentStored (e.g. healthcheck/process-result stages).
Implements the replay-safe half of preemptive redirect (graph re-routing). An
operator-confirmed PreemptRedirectEvent overrides the resolver's edge at the next
transition boundary; the pure resolver stays untouched.
- PreemptRedirectEvent / PreemptRedirectBlockedEvent (+ serialization registration)
- TransitionExecutedEvent + TransitionDecision.Move gain optional redirectId — the
durable 'consumed once' marker
- PreemptRedirect.decide: pure decision over the event log (override / block / none),
so replay reaches the identical outcome without re-classifying (invariant #8)
- override wired in DefaultSessionOrchestrator.step above resolveTransition; back-edge
jumps count against the existing maxRetries cap via executeMove
- blocks jumps to unknown stages or targets with unsatisfied needs
- DomainEventMapper: redirect events mapped to null (operator surface ships with the
LLM-proposal + approval-confirm front-half)
- tests: override+consume-once, block-on-needs, block-on-unknown, ignore-consumed
Front-half (LLM proposal -> approval-gate confirm -> emit PreemptRedirectEvent) is
deferred; needs live LLM verification. Until it ships no redirect event is emitted in
production, so the override is inert. Spec: docs/plans/2026-06-10-freestyle-graph-rerouting.md
A multi-line paste put raw newlines into the single-line input slot, overflowing
the fixed-height box and leaving a smeared/stale region. flattenForDisplay collapses
newlines (↵) and tabs for rendering only; the inputBuffer keeps real characters for
submission.
- generic SystemResourceProbe: owner-agnostic /proc/meminfo system RAM
overlaid on the vendor GPU probe, wired on both managed and static paths
so the VRAM/GPU/RAM gauge renders with an external llama-server (was dormant)
- F-002: classify provider 4xx (e.g. llama.cpp 400) as terminal, not retryable
(except 408/429); stops retrying deterministic request failures to exhaustion
- F-003: FileSystemPromptLoader expands leading ~ / ~/ to user home
- F-004: map InferenceFailedEvent + RetryAttemptedEvent to new
ServerMessage.InferenceFailed / RetryAttempted, decoded+rendered in tui-go;
ArtifactContentStoredEvent explicitly mapped to null (internal, no warn)
- tests: tilde expansion, SystemResourceProbe (static/managed/fail-soft)
Two operator features over the existing WebSocket protocol, plus a tui-go nav fix.
Config editor (g / palette "config"):
- core:config gains a thin registry stack: OrchestrationKnobs ([orchestration]
block), CorrexConfigWriter (round-trip TOML serializer; parseToml(write(c))==c),
ConfigHolder (AtomicReference live config), and EditableConfig (allowlist of
editable fields + patch applier; security fields are absent so they can never
be patched).
- ConfigService validates -> persists (atomic temp+move) -> swaps the holder ->
rebuilds config-derived services. Live-apply is scoped to safe seams: stage
timeout, compaction threshold (now a supplier), router knobs (routerFacade
rebuild), and personalization/project toggles all take effect on the next
session/turn; in-flight sessions keep the config they started with.
server.host/port are persisted + badged "restart required", not hot-swapped.
- Protocol: GetConfig / UpdateConfig / ConfigSnapshot; TUI overlay with
type-aware editing (bool toggle, enum cycle, inline int/string edit) and save.
Artifact viewer (v / palette "artifacts"):
- Server assembles a session's artifacts from the event log and resolves bytes
from the CAS store (StreamQueries.listArtifacts) — a replay-neutral snapshot
read. TUI overlay lists artifacts and shows scrollable content.
tui-go fix: workflow failure no longer clears selectedID (which yanked the user
to the list); listNav lands on the first session when nothing is selected
instead of wrapping to a random one.
Config is not event-sourced (it lives in TOML); editing stays outside the log.
Live QA audit of role_pipeline against a sample repo surfaced and fixed a
chain of defects that prevented any tool+artifact workflow from running
end-to-end. The pipeline now completes cleanly with a real, validated,
reviewed file change.
- F-008 workflow: propagate stage token_budget -> generationConfig.maxTokens
(TomlWorkflowLoader) so large stages stop truncating at the 2048 default.
- F-009 tools/kernel: file_read missing-file is recoverable; recoverable tool
errors feed back into the loop instead of aborting the stage.
- F-010/F-018 kernel: reject premature stage_complete and nudge the model to
emit the owed artifact / invoke a write tool (bounded by MAX_TOOL_ROUNDS).
- F-011 schemas: list-typed artifact fields string -> array (analysis/design/
impl_plan) to match model output.
- F-012 kernel: strip an outer markdown code fence from LLM artifacts.
- F-013 validation: payload-validation failures are retryable; structural
failures stay terminal (wires the invariant-#7 reject+retry contract).
- F-014 tools: file_edit schema matches its real params; edits emit a diff.
- F-015 kernel: record tool-execution events + materialise a real file_written
artifact from the on-disk write; gate validation so a no-write stage cannot
be rubber-stamped (no more false-success runs).
- F-016 server: raise stageTimeoutMs 60s -> 180s for slow local models.
- F-019 artifacts/kernel: file_written artifact carries the unified diff so the
reviewer can verify the change (shared DiffUtil; file_write emits a diff too).
- F-020 tools: model-correctable file_edit failures are recoverable + steer
toward replace/file_write over the fragile patch op.
Full findings register (F-001..F-021, incl. open F-021 resume rehydrate bug)
in qa/audit-report-2026-06-08.md. All module tests green.
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.
Two fixes surfaced by the 2026-06-08 QA audit running role_pipeline on a local
llama-server.
F-001: LlamaCppInferenceProvider sent both a GBNF grammar and tools on the same
request; llama.cpp rejects the combination ("Cannot use custom grammar
constraints with tools"), failing every stage that has tools and produces a
schema-constrained artifact. Drop the grammar when tools are present and rely on
post-hoc schema validation + retry (invariant #7 still holds). TODO left for a
first-class emit_artifact tool as the proper fix.
F-005: FileReadTool resolved relative paths via toAbsolutePath() against the JVM
process cwd instead of the bound workspace, so the file-read jail anchored to the
wrong root and disagreed with the Plane-2 PATH_CONTAINMENT check. Add workingDir
to FileReadConfig, wire workspace.workingDir in the per-workspace tool builder,
and give FileReadTool a resolvePath() mirroring FileWriteTool/FileEditTool.
kami