omnius 1.0.696 → 1.0.698

package/dist/update-worker.js

@@ -292930,6 +292930,9 @@ var DECAY_TAU2 = {
 var DEFAULT_INLINE_KG_MAX_BYTES = 512 * 1024 * 1024;
 var DEFAULT_INLINE_EPISODES_MAX_BYTES = 1024 * 1024 * 1024;
 
+// packages/execution/dist/tools/diagnostic.js
+init_process_async();
+
 // packages/execution/dist/tools/background-task.js
 init_process_kill();
 init_process_lifecycle();

package/docs/DISCOVERY.json

@@ -29472,6 +29472,40 @@
         }
       ]
     },
+    {
+      "id": "guide.guides-long-horizon-feature-workflow",
+      "kind": "guide",
+      "title": "Long-horizon feature work",
+      "summary": "Implementation, acceptance cases and delivery records are tracked in WO-01.",
+      "keywords": [
+        "guides",
+        "long",
+        "horizon",
+        "feature",
+        "workflow",
+        "md"
+      ],
+      "maturity": "stable",
+      "audiences": [
+        "user",
+        "integrator",
+        "coding-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/guides/long-horizon-feature-workflow.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/guides/long-horizon-feature-workflow.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.guides-media-generation",
       "kind": "guide",
@@ -30543,6 +30577,40 @@
         }
       ]
     },
+    {
+      "id": "guide.research-aiwg-long-horizon-feature-workflow",
+      "kind": "guide",
+      "title": "AIWG research teams and long-horizon feature delivery",
+      "summary": "Date: 2026-09-05. Status: design research for consolidation; no runtime implementation in this note.",
+      "keywords": [
+        "research",
+        "aiwg",
+        "long",
+        "horizon",
+        "feature",
+        "workflow",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/research/aiwg-long-horizon-feature-workflow.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/research/aiwg-long-horizon-feature-workflow.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.research-archived-context-window-attention-model",
       "kind": "guide",
@@ -32434,6 +32502,46 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-long-horizon-feature-delivery-wo-01-native-research-feature-workflow-uppercase",
+      "kind": "guide",
+      "title": "WO-01 — Native research-to-feature workflow",
+      "summary": "Status: complete — repository implementation, twelve-scenario acceptance and scoped Git delivery. Authorized by the user request to bring the AIWG research-team mechanism into Omnius. Publication and live acceptance remain with the user.",
+      "keywords": [
+        "work",
+        "orders",
+        "long",
+        "horizon",
+        "feature",
+        "delivery",
+        "WO",
+        "01",
+        "native",
+        "research",
+        "feature",
+        "workflow",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/long-horizon-feature-delivery/WO-01-native-research-feature-workflow.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/long-horizon-feature-delivery/WO-01-native-research-feature-workflow.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-omnius-context-engineering-behavior-fixes",
       "kind": "guide",
@@ -32770,6 +32878,46 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-live-telegram-log-review-2026-09-05-uppercase",
+      "kind": "guide",
+      "title": "Telegram field review after publication — September 5, 2026",
+      "summary": "Scope: read-only review requested after the user observed improvement. Runtime package is 1.0.697. The launcher started at 01:05 PDT; its current runtime child and Telegram poll owner is PID 4160370, started at 13:33 PDT. Two processes are the launcher/child relationship, not evidence of competing pollers.",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "LIVE",
+        "TELEGRAM",
+        "LOG",
+        "REVIEW",
+        "2026",
+        "09",
+        "05",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/LIVE-TELEGRAM-LOG-REVIEW-2026-09-05.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/LIVE-TELEGRAM-LOG-REVIEW-2026-09-05.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-runtime-health-remediation-readme-uppercase",
       "kind": "guide",
@@ -34790,6 +34938,237 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-43-telegram-router-progress-boundary-uppercase",
+      "kind": "guide",
+      "title": "WO-43: Keep router failures out of Telegram progress and repair routing contracts",
+      "summary": "Status: complete in repository; verified for user publication Priority: P1 Reported: September 5, 2026, after publication of 1.0.696 Source baseline: d8e6e2ed on origin/main",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "43",
+        "telegram",
+        "router",
+        "progress",
+        "boundary",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-43-telegram-router-progress-boundary.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-43-telegram-router-progress-boundary.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-44-evidence-backed-terminal-results-uppercase",
+      "kind": "guide",
+      "title": "WO-44: Deliver an evidence-backed final result in Telegram",
+      "summary": "Status: complete in repository; publication and live acceptance remain with the user Priority: P1 Source baseline: 44fa69cc Observed runtime: 1.0.696, sibling telegramtest; read-only inspection",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "44",
+        "evidence",
+        "backed",
+        "terminal",
+        "results",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-44-evidence-backed-terminal-results.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-44-evidence-backed-terminal-results.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-45-native-ollama-tool-contract-uppercase",
+      "kind": "guide",
+      "title": "WO-45: Preserve tools across the native Ollama transport",
+      "summary": "Status: complete — implementation, mocked transport verification and scoped Git delivery Priority: P1 for callers selecting native Ollama chat with tools Source baseline: af6fb8eb",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "45",
+        "native",
+        "ollama",
+        "tool",
+        "contract",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-45-native-ollama-tool-contract.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-45-native-ollama-tool-contract.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-46-shell-result-authority-uppercase",
+      "kind": "guide",
+      "title": "WO-46: Preserve process authority for shell observations",
+      "summary": "Status: repository repair complete and delivered to origin/main. Publication and live validation remain with the user.",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "46",
+        "shell",
+        "result",
+        "authority",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-46-shell-result-authority.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-46-shell-result-authority.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-47-diagnostic-execution-contract-uppercase",
+      "kind": "guide",
+      "title": "WO-47: Validate and execute diagnostics without blocking the agent",
+      "summary": "Status: repository repair complete and delivered to origin/main. Publication and live validation remain with the user.",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "47",
+        "diagnostic",
+        "execution",
+        "contract",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-47-diagnostic-execution-contract.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-47-diagnostic-execution-contract.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-runtime-health-remediation-wo-48-conversation-result-evidence-uppercase",
+      "kind": "guide",
+      "title": "WO-48: Retain command evidence in conversation results",
+      "summary": "Status: repository repair complete and delivered to origin/main. Publication and live validation remain with the user.",
+      "keywords": [
+        "work",
+        "orders",
+        "runtime",
+        "health",
+        "remediation",
+        "WO",
+        "48",
+        "conversation",
+        "result",
+        "evidence",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/runtime-health-remediation/WO-48-conversation-result-evidence.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/runtime-health-remediation/WO-48-conversation-result-evidence.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-telegram-dmn-wo-22-dmn-outreach-and-learning-uppercase",
       "kind": "guide",

package/docs/DISCOVERY.md

@@ -434,6 +434,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.guides-agent-integration` | Agent And Service Integration | An integration should discover Omnius at runtime instead of encoding a partial provider or tool list. |
 | `guide.guides-bring-your-own-inference` | Bring Your Own Inference | Omnius routes local and hosted models through an explicit provider descriptor. The descriptor determines the wire protocol, URL paths, authentication headers, and supported operations. It is the source of truth used by setup, model discovery, TUI runs, REST chat, summaries, voice, Telegram, sponsors, and endpoint probes. |
 | `guide.guides-dashboard` | Web Dashboard | The Omnius daemon serves a zero-build, self-contained dashboard from the same origin as the REST API. Start it with omnius serve, then open http://127.0.0.1:11435/. The interface uses Omnius's compact NOCLIP-derived style kit and shared responsive observability-card grids; the route registry in packages/cli/src/api/web-ui.ts is the source of truth for pages  |
+| `guide.guides-long-horizon-feature-workflow` | Long-horizon feature work | Implementation, acceptance cases and delivery records are tracked in WO-01. |
 | `guide.guides-media-generation` | Media Generation | Omnius exposes media generation through TUI commands, tools, Telegram creative workflows, and sponsor media endpoints. |
 | `guide.guides-osint-research` | Categorized OSINT research | Omnius ships a local, searchable snapshot of the OSINT4ALL Start.me page. It uses the same compact discovery pattern as AIWG skills: |
 | `guide.guides-realtime` | Realtime Conversations | Realtime mode is for short, natural, back-and-forth spoken conversation behind ASR and TTS. |
@@ -467,6 +468,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.reference-configuration` | Configuration Reference | Configuration is layered from environment, global user settings, project settings, and active TUI state. |
 | `guide.reference-rest-api` | REST API Reference | This is the maintained human inventory for the supported Omnius daemon API. The machine contract is generated by packages/cli/src/api/openapi.ts and served at /openapi.json; every operation in that contract must appear here, and the generated REST block in the root README must match this file byte-for-byte after heading normalization. Browser HTML routes and |
 | `guide.reference-slash-commands` | Slash Commands | This file is generated from packages/cli/src/tui/command-registry.ts. |
+| `guide.research-aiwg-long-horizon-feature-workflow` | AIWG research teams and long-horizon feature delivery | Date: 2026-09-05. Status: design research for consolidation; no runtime implementation in this note. |
 | `guide.research-archived-context-window-attention-model` | Context Window Attention Model | Bundled Omnius documentation artifact: docs/research/_archived/context_window_attention_model.py. |
 | `guide.research-archived-context-window-attention-spec` | Context Window Attention-Weighted Optimization Spec | The context window treats all items (system prompt, memory cards, chat history, voice transcriptions, reflection notes) at roughly equal attention weight (~1.0). This causes: |
 | `guide.research-archived-context-window-attention-weights` | Context Window Attention Weights | Bundled Omnius documentation artifact: docs/research/_archived/context_window_attention_weights.json. |
@@ -522,6 +524,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-hermes-architecture-deltas-08-completion-critic-reconciliation-ledger-index-uppercase` | Completion Critic Reconciliation Ledger Index | Bundled Omnius documentation artifact: docs/work-orders/hermes-architecture-deltas/08-completion-critic-reconciliation-ledger/INDEX.md. |
 | `guide.work-orders-hermes-architecture-deltas-08-completion-critic-reconciliation-ledger-workorder-uppercase` | Workorder: Completion Critic Reconciliation Ledger | Convert completion verification into a durable claim/evidence ledger. The critic must receive: |
 | `guide.work-orders-hermes-architecture-deltas-index-uppercase` | Hermes Architecture Deltas Workorder Index | Status: ready for implementation planning. These documents are workorders only; they do not claim the features are implemented. |
+| `guide.work-orders-long-horizon-feature-delivery-wo-01-native-research-feature-workflow-uppercase` | WO-01 — Native research-to-feature workflow | Status: complete — repository implementation, twelve-scenario acceptance and scoped Git delivery. Authorized by the user request to bring the AIWG research-team mechanism into Omnius. Publication and live acceptance remain with the user. |
 | `guide.work-orders-omnius-context-engineering-behavior-fixes` | Omnius Context Engineering Behavior Fixes | Source observation: current Omnius behavior while supervising a noclip/earth sidebar cleanup task. The observed run mixed internal cognitive-agent artifacts with user-task artifacts, repeated stale edit attempts after the file had changed, and overclaimed completion despite stale or missing verification. |
 | `guide.work-orders-runtime-health-remediation-audit-uppercase` | Runtime Health Remediation Audit Log | Session: RHR-2026-09-02 Host user: roko Program root: /home/roko/Documents/Projects/Adjacent/omnius/omnius |
 | `guide.work-orders-runtime-health-remediation-cli-current-main-suite-evidence-uppercase` | Current-main CLI suite reconciliation evidence | This tranche reconciles the complete CLI suite except the protected generated discovery outputs and packages/cli/tests/update-service.test.ts, as directed. It does not edit publish/, the shared runtime-health tracker or audit, or the protected discovery files. |
@@ -531,6 +534,7 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-runtime-health-remediation-h1-h2-h7-telegram-continuity-evidence-uppercase` | H1, H2, and H7 Telegram continuity evidence | Scope: deterministic Telegram stream ownership, immutable task-local routing, exact-once text delivery evidence, bounded long-poll client replacement, bridge restart authority, and task-local delegated-agent runtime ownership. |
 | `guide.work-orders-runtime-health-remediation-h6-main-tui-wo-05-confirmation-evidence-uppercase` | H6 Main-TUI and WO-05 Confirmation Evidence | This closure wires the top-level TUI FullSubAgentTool to live parent-context headroom and the exact owning task cancellation signal. It also confirms the WO-05 completion authority after the interruption, safe-media, workboard, and canonical-context changes. |
 | `guide.work-orders-runtime-health-remediation-live-telegram-log-review-2026-09-03-uppercase` | Live Telegram Log Review, 2026-09-03 | This review is read-only. It examines the persisted Telegram conversation and intake lifecycle records in /home/roko/Documents/Projects/Adjacent/telegramtest/.omnius. The running global Omnius package reports version 1.0.687. This means the observations describe the deployed pre-publication runtime, not the newer source commits on this repository's main bran |
+| `guide.work-orders-runtime-health-remediation-live-telegram-log-review-2026-09-05-uppercase` | Telegram field review after publication — September 5, 2026 | Scope: read-only review requested after the user observed improvement. Runtime package is 1.0.697. The launcher started at 01:05 PDT; its current runtime child and Telegram poll owner is PID 4160370, started at 13:33 PDT. Two processes are the launcher/child relationship, not evidence of competing pollers. |
 | `guide.work-orders-runtime-health-remediation-readme-uppercase` | Runtime Health Remediation Program | Program ID: RHR-2026-09-02 Status: active, implementation authorized Owner: Omnius runtime, orchestration, execution, memory, and Telegram packages External dependency: /home/roko/Desktop/ollama-unify Last reconciled: 2026-09-03 |
 | `guide.work-orders-runtime-health-remediation-telegram-longhaul-2026-09-04-uppercase` | September 4 Telegram long-haul remediation | Status: complete; all five root repairs verified and delivered to origin/main Baseline: Omnius main 69c4a160; installed package 1.0.694 Incident run: telegram-64ac9937dc7647a8-1788572475259-1 Observation window: 2026-09-04 18:41–20:43 PDT Owner: repository repair; user owns publication and subsequent live testing |
 | `guide.work-orders-runtime-health-remediation-tool-quality-2026-09-05-uppercase` | September 5 tool-quality and live-behavior follow-up | Status: WO-30 through WO-42 complete in repository; full verification passed; delivered to origin/main for user publication Repository baseline: 501e8394 on origin/main Verified source head: 7005aa41; subsequent closure changes are documentation only Observed running package: 1.0.695, verified from its actual executable/package path User scope: monitor live  |
@@ -584,6 +588,12 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-runtime-health-remediation-wo-40-web-content-and-crawl-receipts-uppercase` | WO-40: Preserve retrieved content and validate crawler responses | Status: complete in repository; verified for user publication Priority: P1 Date: 2026-09-05 |
 | `guide.work-orders-runtime-health-remediation-wo-41-completion-evidence-consistency-uppercase` | WO-41: Expose verification coverage and preserve typed completion authority | Status: complete in repository; verified for user publication Priority: P1 Program: September 5 follow-up |
 | `guide.work-orders-runtime-health-remediation-wo-42-media-execution-and-configuration-uppercase` | WO-42: Media execution and configuration boundaries | Status: complete in repository; verified for user publication Priority: P1 |
+| `guide.work-orders-runtime-health-remediation-wo-43-telegram-router-progress-boundary-uppercase` | WO-43: Keep router failures out of Telegram progress and repair routing contracts | Status: complete in repository; verified for user publication Priority: P1 Reported: September 5, 2026, after publication of 1.0.696 Source baseline: d8e6e2ed on origin/main |
+| `guide.work-orders-runtime-health-remediation-wo-44-evidence-backed-terminal-results-uppercase` | WO-44: Deliver an evidence-backed final result in Telegram | Status: complete in repository; publication and live acceptance remain with the user Priority: P1 Source baseline: 44fa69cc Observed runtime: 1.0.696, sibling telegramtest; read-only inspection |
+| `guide.work-orders-runtime-health-remediation-wo-45-native-ollama-tool-contract-uppercase` | WO-45: Preserve tools across the native Ollama transport | Status: complete — implementation, mocked transport verification and scoped Git delivery Priority: P1 for callers selecting native Ollama chat with tools Source baseline: af6fb8eb |
+| `guide.work-orders-runtime-health-remediation-wo-46-shell-result-authority-uppercase` | WO-46: Preserve process authority for shell observations | Status: repository repair complete and delivered to origin/main. Publication and live validation remain with the user. |
+| `guide.work-orders-runtime-health-remediation-wo-47-diagnostic-execution-contract-uppercase` | WO-47: Validate and execute diagnostics without blocking the agent | Status: repository repair complete and delivered to origin/main. Publication and live validation remain with the user. |
+| `guide.work-orders-runtime-health-remediation-wo-48-conversation-result-evidence-uppercase` | WO-48: Retain command evidence in conversation results | Status: repository repair complete and delivered to origin/main. Publication and live validation remain with the user. |
 | `guide.work-orders-telegram-dmn-wo-22-dmn-outreach-and-learning-uppercase` | WO-22: DMN outreach, DM sharing, and outcome learning | On 2026-09-03 at 17:07 PDT the bot posted in the OMNIUS group without being addressed. The operator asked whether this was self-induced reflection. |
 | `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 |

package/docs/guides/long-horizon-feature-workflow.md

@@ -0,0 +1,42 @@
+# Long-horizon feature work
+
+Implementation, acceptance cases and delivery records are tracked in [WO-01](../work-orders/long-horizon-feature-delivery/WO-01-native-research-feature-workflow.md).
+
+Use a feature workflow when one objective needs sustained research, a reviewed specification, several dependent changes, integration and explicit acceptance checks. Give Omnius the objective, constraints and observable acceptance criteria. For example:
+
+> Use the native feature workflow to add resumable imports. Research the current import and storage paths, write a specification, have a separate read-only worker review it, implement the parser and persistence changes, integrate them, and test interruption and duplicate-record recovery. Preserve accepted work across restarts. Report unresolved questions and failed checks before claiming completion.
+
+The runner exposes `feature_workflow` to create or revise the plan, inspect readiness, reopen scoped repair work after a recorded failure, and select an exact prior program to resume. Work still runs through the ordinary file, terminal and child-agent tools. A workflow does not grant permission to publish, deploy or contact other people.
+
+## What carries the work forward
+
+| Phase | Required result |
+| --- | --- |
+| Research | Bounded findings and durable source/artifact references; missing streams remain visible. |
+| Specification | An exact specification artifact and a separate review of that version, including findings and unresolved questions. |
+| Implementation | Changes owned by individual tasks, with their prerequisite evidence and output artifacts. |
+| Integration | The combined source state and an integration artifact identifying it. |
+| Acceptance | Declared commands executed against that combined state, with actual command receipts. |
+| Handoff | The result, remaining limitations and evidence needed to continue or publish. |
+
+A worker completing its run is not sufficient to approve its own specification. An approval is tied to the reviewed artifact version. A later edit makes an older review stale. Similarly, a passing check on an individual change does not verify a different integrated source state.
+
+When acceptance fails, the workflow retains accepted research and other unaffected work. Remaining tasks and stale checks stay open. A later source mutation invalidates checks on the preceding integrated state.
+
+Omnius rebuilds the current plan identity, ready tasks, required artifact references and unresolved obligations from durable records for each request. That compact state survives context reduction; older artifact bodies can be reopened by their exact references. Insufficient capacity for required current state leaves inference admission blocked with a reason.
+
+## Continuing after interruption
+
+Keep the objective ID, accepted plan reference and owning run identity shown by the workflow. Resume selects that exact durable program. It does not reconstruct authority from a conversational summary or the latest unrelated handoff.
+
+The recovered program must validate its artifact references, operation receipts and ownership before allowing dependent work. Work whose external effects are uncertain needs reconciliation before it can be repeated. A normal continuation may enter a new runner epoch; its adoption record preserves the original evidence identities.
+
+Replacing the objective retires the old program. Delayed child results cannot reopen it. Adding a constraint to the same objective should preserve accepted work that remains valid and expose any newly required work.
+
+## Reading the result
+
+Telegram can display a report derived from the committed task evidence when a run has no separately authored final reply. It includes recorded changes, command outcomes, evidence gaps and next actions. The Evidence view retains additional detail when the visible result must be shortened.
+
+The report distinguishes successful verification from an observation command that merely exited successfully. Failed, timed-out or stale checks remain visible. A missing final report is reported as a delivery problem with a reconstruction step, so a retry does not silently repeat completed changes.
+
+The design was adapted from [AIWG's research and delivery mechanisms](../research/aiwg-long-horizon-feature-workflow.md). It uses Omnius's existing workboard, completion authority, immutable artifact storage and interruption lifecycle.