omnius 1.0.688 → 1.0.690

package/docs/DISCOVERY.json

@@ -33786,6 +33786,84 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-20-exact-session-continuation-uppercase",
+      "kind": "guide",
+      "title": "WO-20: Exact session continuation across exit and restart",
+      "summary": "On 2026-09-03, the telegramtest TUI displayed the latest pentest task during startup, but the first restored model context combined a completed breach.py handoff with an unrelated, older page.tsx todo tree. The user then entered continue, and Omnius continued the stale tree instead of the task that was active before /quit.",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "20",
+        "exact",
+        "session",
+        "continuation",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-20-exact-session-continuation.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-20-exact-session-continuation.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-21-task-convergence-and-todo-scope-uppercase",
+      "kind": "guide",
+      "title": "WO-21: Task convergence and todo scope",
+      "summary": "On 2026-09-03, a user reported that Omnius remained at task 2/8 for about 40 turns. The report did not include a screenshot or run artifact, so the exact label remains unverified. Omnius has two similar counters:",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "21",
+        "task",
+        "convergence",
+        "and",
+        "todo",
+        "scope",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-21-task-convergence-and-todo-scope.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-21-task-convergence-and-todo-scope.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-telegram-dropbear-context-rca-workorder",
       "kind": "guide",

package/docs/DISCOVERY.md

@@ -558,6 +558,8 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-runtime-health-remediation-wo-18-interruption-evidence-uppercase` | WO-18 interruption lifecycle evidence | Scope: /pause, /resume, /stop, safe-boundary ownership, recovery, and stale-effect prevention. This record is independent of the shared remediation tracker and records only verified WO-18 implementation evidence. |
 | `guide.work-orders-runtime-health-remediation-wo-19-clean-build-evidence-uppercase` | WO-19 Clean Build Evidence | WO-19 is implemented in commit 5f253c05. |
 | `guide.work-orders-runtime-health-remediation-wo-19-clean-build-reproducibility-uppercase` | WO-19: Clean Build and Optional-Dependency Reproducibility | Status: deterministic acceptance complete Risk: medium Depends on: WO-00 |
+| `guide.work-orders-runtime-health-remediation-wo-20-exact-session-continuation-uppercase` | WO-20: Exact session continuation across exit and restart | On 2026-09-03, the telegramtest TUI displayed the latest pentest task during startup, but the first restored model context combined a completed breach.py handoff with an unrelated, older page.tsx todo tree. The user then entered continue, and Omnius continued the stale tree instead of the task that was active before /quit. |
+| `guide.work-orders-runtime-health-remediation-wo-21-task-convergence-and-todo-scope-uppercase` | WO-21: Task convergence and todo scope | On 2026-09-03, a user reported that Omnius remained at task 2/8 for about 40 turns. The report did not include a screenshot or run artifact, so the exact label remains unverified. Omnius has two similar counters: |
 | `guide.work-orders-telegram-dropbear-context-rca-workorder` | Telegram Dropbear Context Engineering RCA Work Order | Observed run: /home/roko/Documents/Projects/Adjacent/telegramtest/.omnius, run id 1782873796963-i5r7mv. |
 | `guide.work-orders-wo-am-gaps-uppercase` | Associative Memory Gap Work Orders | Generated: 2026-04-13 Source: Deep audit of multimodal associative memory systems Status: READY FOR IMPLEMENTATION |
 | `guide.work-orders-world-class-memory-compiler-readme-uppercase` | World-Class Memory Compiler Program | Status: active implementation program Owner: Omnius orchestration and memory packages Last updated: 2026-07-13 |

package/docs/work-orders/runtime-health-remediation/TRACKER.md

@@ -309,3 +309,17 @@ deterministically repaired P0 or P1 defect.
   accessibility, and mocked inference end-to-end tests.
 - [x] WO-18 pause, stop, and resume use one durable interruption lifecycle and
   pass cancellation, restart, ownership, external-effect, and isolation tests.
+- [x] WO-20 exit and restart preserve one exact typed task continuation. Generic
+  context restoration cannot mix or activate unrelated historical artifacts.
+- [x] WO-21 task convergence and todo scope prevent stale `tasks N/M` displays,
+  cross-runner todo leakage, and activity-only re-engagement.
+  - [x] Bind todo tools to immutable runner-owned sessions.
+  - [x] Clear the active persisted checklist at a fresh task boundary after
+    archival.
+  - [x] Count only typed authoritative advancement as progress.
+  - [x] Latch an advisory convergence review when the leaf frontier is static.
+  - [x] Make loop, reminder, budget, and workboard progress semantics truthful.
+  - [x] Pass deterministic race, stasis, display, typecheck, and build tests.
+- [x] A recovered pause no longer strands its session. Submitting a new task
+  retires the superseded generation instead of refusing every later prompt,
+  while unreconciled external effects still fence admission.

package/docs/work-orders/runtime-health-remediation/WO-20-exact-session-continuation.md

@@ -0,0 +1,88 @@
+# WO-20: Exact session continuation across exit and restart
+
+## Incident
+
+On 2026-09-03, the `telegram_test` TUI displayed the latest pentest task during
+startup, but the first restored model context combined a completed `breach.py`
+handoff with an unrelated, older `page.tsx` todo tree. The user then entered
+`continue`, and Omnius continued the stale tree instead of the task that was
+active before `/quit`.
+
+## Root causes
+
+- `/quit`, `/exit`, readline close, and fallback exit abort an active runner.
+  The explicit quit paths also delete `.omnius/history/pending-task.json`.
+- Startup selects handoff, completion ledger, todo state, context chronology,
+  and visual history independently. These projections need not identify the
+  same session or run.
+- Generic restore mutates the process-wide task session, even though the
+  restored transcript is historical orientation only.
+- The host interprets words such as `continue` with a regular expression and
+  uses that classification to reuse a restored task identity.
+- A resumed task is submitted as a generated wrapper. The wrapper can replace
+  the original user goal in new completion, workboard, and handoff records.
+- Pending-task consumption checks only phase and session. It does not prove the
+  recovered run, epoch, and owner generation.
+- Updating an existing session-context entry changes its timestamp in place,
+  but does not move it into chronological order. Tail readers can therefore
+  report an older task as latest.
+
+## Required invariants
+
+- [x] An active task receives a typed, atomic continuation checkpoint before a
+  resumable exit.
+- [x] `/quit`, `/exit`, readline close, and graceful process termination pause
+  and preserve the active run. Explicit `/stop`, Ctrl+C, and double-Esc remain
+  terminal and delete the pending checkpoint.
+- [x] A checkpoint identifies the project, original goal, session, run, task
+  epoch, owner generation, lifecycle phase, exit reason, and capture time.
+- [x] Manual startup automatically adopts a checkpoint explicitly marked for
+  restart, without requiring an updater environment variable.
+- [x] Exact continuation context is scoped to the checkpoint session and run.
+  A global handoff, ledger, todo tree, or transcript cannot replace it.
+- [x] Generic context restore is orientation only. It does not bind task/todo
+  identity or mutate `OMNIUS_SESSION_ID`.
+- [x] Continuation authority comes from typed lifecycle state or an explicit
+  command. It never comes from semantic keyword or regular-expression
+  classification of user prose.
+- [x] The resumed runner receives the exact original user goal. Progress and
+  historical orientation remain separate context.
+- [x] A pending checkpoint is consumed only after the runner proves the same
+  session, run, epoch, and owner generation in the running phase.
+- [x] Session-context entries remain ordered by their effective save time after
+  merge or replacement.
+- [x] Corrupt, cross-project, incomplete, or identity-mismatched checkpoints
+  fail closed and remain available for diagnosis unless explicitly stopped.
+
+## Deterministic verification
+
+- [x] Pending checkpoint round-trip and schema validation.
+- [x] Exact four-field adoption match and one-field-at-a-time mismatch table.
+- [x] Quit wiring has no abort/discard path for an active resumable run.
+- [x] Restart continuation remains exact in the presence of a newer handoff,
+  higher-scoring stale ledger, unrelated todos, and unrelated visual history.
+- [x] Generic restore cannot bind a subsequent fresh task to historical todos.
+- [x] A resumed run persists the original goal, not a synthetic continuation
+  wrapper.
+- [x] Session-context merge reorders the updated entry chronologically.
+- [x] Focused CLI typecheck/build and affected tests pass.
+
+## Delivery evidence
+
+Implemented in the CLI session directory, TUI lifecycle coordinator, command
+surface, and runner continuation gate. Verification on 2026-09-03:
+
+- Focused CLI interruption, restore, session-diary, and command suites: 52
+  passed.
+- Focused orchestrator context and interruption suites: 67 passed.
+- Complete orchestrator suite: 2,292 passed, 14 skipped.
+- Complete CLI suite: 2,425 passed. Two unrelated tests timed out while the CLI
+  and orchestrator suites ran concurrently; both passed alone, 35 of 35.
+- CLI and orchestrator typechecks passed.
+- CLI and orchestrator builds passed.
+- A two-process, no-inference harness wrote the checkpoint in one process and
+  recovered the exact `harness-session/harness-run/epoch-3` selection in a
+  second process.
+
+No live inference or service restart was required for this host-side
+state-machine repair.

package/docs/work-orders/runtime-health-remediation/WO-21-task-convergence-and-todo-scope.md

@@ -0,0 +1,115 @@
+# WO-21: Task convergence and todo scope
+
+## Incident
+
+On 2026-09-03, a user reported that Omnius remained at `task 2/8` for about
+40 turns. The report did not include a screenshot or run artifact, so the
+exact label remains unverified. Omnius has two similar counters:
+
+- `tasks 2/8` is the completed-leaf count in the pinned TUI checklist.
+- `Loop intervention 2/8` is the second repetition intervention in a
+  model-tier-specific series.
+
+The source audit found defects in both paths. These defects are sufficient to
+produce the reported symptom even though they do not prove which counter the
+reporter saw.
+
+## Root causes
+
+- A TUI process reuses one todo session across tasks. A fresh runner hides old
+  todo IDs in its private view but leaves the persisted checklist unchanged.
+  The TUI reads that unchanged file and can display a stale `tasks 2/8` row.
+- Todo tools fall back to one mutable process-global session ID. Concurrent
+  parent, Telegram, background, and child runners can redirect one another's
+  unscoped reads and writes.
+- Any unique non-noop tool result increments the counter used to permit turn
+  extension and brute-force re-engagement. Varying reads, searches, and error
+  text therefore masquerade as task advancement.
+- The repeated-loop counter resets after its maximum intervention even though
+  no task state changed. Its status says that user guidance was requested, but
+  it does not create a user-input boundary.
+- A failed `todo_write` advances the reminder clock. The visible checklist can
+  remain unchanged for ten more turns without a reminder.
+- Small-model budget text says that a todo update resets the phase budget, but
+  the implementation resets only after a context-tree phase transition.
+- Workboard `lastSubstantiveProgress` treats successful discovery reads as
+  progress. This conflicts with the task and completion ledgers, where a read
+  is evidence but not advancement.
+
+## Required invariants
+
+- [x] Every runner binds todo tools to its own immutable session scope.
+- [x] Model-supplied todo session IDs cannot override the host scope.
+- [x] Concurrent runners cannot redirect one another's todo reads or writes.
+- [x] A fresh task archives the prior checklist and clears the active persisted
+  projection so the TUI, runner, REST, and Telegram views agree.
+- [x] Only a confirmed mutation, todo transition, workboard transition,
+  assertive verifier receipt, or delivery receipt counts as authoritative task
+  progress.
+- [x] Reads, searches, runtime-authored blocks, no-ops, and changing errors do
+  not extend the run or re-arm brute-force execution. Entry into the first
+  re-engagement cycle is deliberately not gated on prior authoritative
+  progress: that cycle is the rescue attempt for a run that has only read.
+  If it also advances nothing, re-engagement stops at cycle 2.
+- [x] Repeated stasis creates one latched, model-visible convergence review.
+- [x] The convergence review remains advisory. It does not infer completion,
+  manufacture a blocker, or force a user question.
+- [x] The loop intervention maximum does not silently reset without
+  authoritative progress.
+- [x] Todo reminders advance only after a successful state-changing write.
+- [x] Budget exhaustion text describes the actual reset condition.
+- [x] Workboard progress metadata uses the same authoritative distinction.
+- [x] Todo stagnation compares completed leaves, matching the TUI counter.
+
+## Status
+
+Implemented and verified on 2026-09-03.
+
+| Invariant | Implementation | Test |
+| --- | --- | --- |
+| Immutable runner-owned todo scope | `packages/execution/src/tools/todo-write.ts` `bindExecutionScope` | `todo-store.test.ts` "binds todo tools to a host session that model arguments cannot replace" |
+| Concurrent runner isolation | `AgenticRunner` constructor resolves one immutable `_sessionId`; `registerTool` binds it | `todo-store.test.ts` "keeps concurrent runner-scoped todo writes isolated" |
+| Fresh task clears the active projection | `_hidePriorSessionTodosForFreshTask` writes an empty active checklist after archival | `fresh-task-todo-boundary.test.ts` |
+| Typed authoritative progress only | `packages/orchestrator/src/convergence-progress.ts` | `task-convergence-progress.test.ts` (8 cases) |
+| Latched advisory convergence review | `agenticRunner.ts` convergence review block | `task-convergence-progress.test.ts` "latches one advisory review and clears it only after typed progress" |
+| Loop intervention maximum stays latched | `Math.min(maxInterventions, loopInterventionCount + 1)` | `agenticRunner-context-behavior.test.ts` "latches the loop-intervention maximum instead of cycling it back to one" |
+| Workboard progress uses the same distinction | `recordWorkboardToolCall` returns a status-fingerprint transition | `workboard-run-continuity.test.ts` "does not record a successful discovery read as task advancement" |
+
+Full suites run green: `@omnius/execution` 1507 passed, `@omnius/orchestrator`
+2303 passed (200 files, 2 skipped), `omnius` CLI 2428 passed (258 files).
+Typecheck passes for all three packages and `pnpm -r build` completes.
+
+The reported counter was never attributed to a specific field run. The evidence
+request below stays open.
+
+One correction was made during verification. An earlier draft of this work also
+refused to enter brute-force cycle 1 whenever the primary run recorded no
+authoritative advancement. That inverted the purpose of re-engagement and broke
+eight existing brute-force tests, because a run that has only read is exactly
+the run that still needs one push to act. The cycle-2 gate already bounds the
+thrash this work order set out to stop, so the cycle-1 refusal was removed.
+
+## Deterministic verification
+
+- [x] Scoped todo tools ignore conflicting model-supplied session IDs.
+- [x] Concurrent scoped todo tools write isolated session files.
+- [x] A same-session fresh task clears the old visible todo projection after
+  archiving it.
+- [x] Forty distinct reads produce zero authoritative progress.
+- [x] Changing failures produce zero authoritative progress.
+- [x] Mutations, todo transitions, workboard transitions, assertive verifiers,
+  and delivery receipts produce typed progress.
+- [x] A convergence review latches after the configured unchanged frontier and
+  clears only after typed progress.
+- [x] The loop intervention maximum stays latched instead of cycling to one.
+- [x] Focused execution, orchestrator, and CLI tests pass.
+- [x] Affected package typechecks and builds pass.
+
+## Evidence request for exact field attribution
+
+If the original run is available, collect only a redacted structural slice:
+the exact counter line or screenshot, Omnius version, model/backend, launch
+surface, incident time and timezone, session/run IDs, five turns before the
+stall through ten turns after it, todo IDs/statuses/revisions, workboard card
+statuses, and completion-ledger statuses. Do not copy a complete `.omnius`
+directory because debug previews can contain user text and source fragments.

package/npm-shrinkwrap.json

@@ -1,12 +1,12 @@
 {
   "name": "omnius",
-  "version": "1.0.688",
+  "version": "1.0.690",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omnius",
-      "version": "1.0.688",
+      "version": "1.0.690",
       "bundleDependencies": [
         "image-to-ascii"
       ],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omnius",
-  "version": "1.0.688",
+  "version": "1.0.690",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/library.js",