omnius 1.0.851 → 1.0.853

package/docs/DISCOVERY.json

@@ -33370,6 +33370,78 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-evidence-telegram-completion-review-live-20261013",
+      "kind": "guide",
+      "title": "Telegram Completion Review Live 20261013",
+      "summary": "Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-completion-review-live-20261013.json.",
+      "keywords": [
+        "work",
+        "orders",
+        "evidence",
+        "telegram",
+        "completion",
+        "review",
+        "live",
+        "20261013",
+        "json"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/evidence/telegram-completion-review-live-20261013.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/evidence/telegram-completion-review-live-20261013.json",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
+    {
+      "id": "guide.work-orders-evidence-telegram-native-planning-live-20261013",
+      "kind": "guide",
+      "title": "Telegram Native Planning Live 20261013",
+      "summary": "Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-native-planning-live-20261013.json.",
+      "keywords": [
+        "work",
+        "orders",
+        "evidence",
+        "telegram",
+        "native",
+        "planning",
+        "live",
+        "20261013",
+        "json"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/evidence/telegram-native-planning-live-20261013.json"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/evidence/telegram-native-planning-live-20261013.json",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-evidence-terminal-review-contract-probe-20261012",
       "kind": "guide",
@@ -38188,6 +38260,41 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-wo-completion-review-recovery-20261013-uppercase",
+      "kind": "guide",
+      "title": "Completion review recovery and Telegram liveness",
+      "summary": "Status: active. Follow-up to the operator's live completion-block and typing indicator report on installed Omnius 1.0.852, PID 2845019, telegramtest.",
+      "keywords": [
+        "work",
+        "orders",
+        "WO",
+        "completion",
+        "review",
+        "recovery",
+        "20261013",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/WO-completion-review-recovery-20261013.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/WO-completion-review-recovery-20261013.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-wo-fallback-quality-order-20261012-uppercase",
       "kind": "guide",
@@ -38327,6 +38434,43 @@
         }
       ]
     },
+    {
+      "id": "guide.work-orders-wo-live-native-cascade-ui-freeze-20261013-uppercase",
+      "kind": "guide",
+      "title": "Live native-planning cascade and TUI responsiveness",
+      "summary": "Status: implementation and live packaged acceptance complete. The operator reported publication in progress; runtime restart/activation is not yet verified. Follow-up to the live 1.0.851 report after the built-in free-model integration; do not substitute another ping-only check.",
+      "keywords": [
+        "work",
+        "orders",
+        "WO",
+        "live",
+        "native",
+        "cascade",
+        "ui",
+        "freeze",
+        "20261013",
+        "md"
+      ],
+      "maturity": "internal",
+      "audiences": [
+        "maintainer",
+        "large-context-agent"
+      ],
+      "layer": "documentation",
+      "interfaces": [
+        {
+          "type": "file",
+          "target": "docs/work-orders/WO-live-native-cascade-ui-freeze-20261013.md"
+        }
+      ],
+      "references": [
+        {
+          "type": "documentation",
+          "target": "docs/work-orders/WO-live-native-cascade-ui-freeze-20261013.md",
+          "relation": "canonical-artifact"
+        }
+      ]
+    },
     {
       "id": "guide.work-orders-wo-native-transport-fresh-install-20261012-uppercase",
       "kind": "guide",

package/docs/DISCOVERY.md

@@ -544,6 +544,8 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-evidence-public-review-after-20261012` | Public Review After 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/public-review-after-20261012.json. |
 | `guide.work-orders-evidence-public-review-before-20261012` | Public Review Before 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/public-review-before-20261012.json. |
 | `guide.work-orders-evidence-telegram-all-free-live-20261013` | Telegram All Free Live 20261013 | Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-all-free-live-20261013.json. |
+| `guide.work-orders-evidence-telegram-completion-review-live-20261013` | Telegram Completion Review Live 20261013 | Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-completion-review-live-20261013.json. |
+| `guide.work-orders-evidence-telegram-native-planning-live-20261013` | Telegram Native Planning Live 20261013 | Bundled Omnius documentation artifact: docs/work-orders/evidence/telegram-native-planning-live-20261013.json. |
 | `guide.work-orders-evidence-terminal-review-contract-probe-20261012` | Terminal Review Contract Probe 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/terminal-review-contract-probe-20261012.json. |
 | `guide.work-orders-evidence-terminal-review-error-probe-20261012` | Terminal Review Error Probe 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/terminal-review-error-probe-20261012.json. |
 | `guide.work-orders-evidence-terminal-review-schema-repair-probe-20261012` | Terminal Review Schema Repair Probe 20261012 | Bundled Omnius documentation artifact: docs/work-orders/evidence/terminal-review-schema-repair-probe-20261012.json. |
@@ -671,10 +673,12 @@ Daemon equivalents are `GET /v1/discovery/bootstrap`, `GET /v1/discovery?q=<inte
 | `guide.work-orders-wo-active-inference-route-and-telegram-review-20261012-uppercase` | Active inference route and Telegram completion review | Status: implementation complete and verified. Publication remains with the user. |
 | `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-wo-built-in-free-model-startup-20261012-uppercase` | Built-in free inference and clean Telegram settlement | Status: implemented, tested and committed. Live service limits are recorded below rather than claimed as model availability. Publication and bot restart remain operator-owned. |
+| `guide.work-orders-wo-completion-review-recovery-20261013-uppercase` | Completion review recovery and Telegram liveness | Status: active. Follow-up to the operator's live completion-block and typing indicator report on installed Omnius 1.0.852, PID 2845019, telegramtest. |
 | `guide.work-orders-wo-fallback-quality-order-20261012-uppercase` | Benchmark-informed fallback cascade | Status: implemented and verified. Publication and active runtime replacement remain with the user. Telegram progress presentation stays deferred. |
 | `guide.work-orders-wo-fallback-reply-contracts-20261012-uppercase` | Fallback reply contracts and live Telegram regressions | Status: implemented and verified in source and the freshly installed package. Publishing and restarting the active bot remain user-owned. The subsequent OpenCode-first capability ordering is tracked in its work order; Telegram progress presentation remains explicitly deferred. |
 | `guide.work-orders-wo-inference-fallback-20261012-uppercase` | Local inference outage fallback | Status: source implementation complete and verified. Installed-runtime activation is separate; the running daemon has not been upgraded or restarted. |
 | `guide.work-orders-wo-keyless-fallback-coverage-20261012-uppercase` | Keyless automatic fallback coverage and compatibility | Status: implemented and verified. Publication and replacement of the running bot remain user-owned; the running bot has not been restarted by this work. |
+| `guide.work-orders-wo-live-native-cascade-ui-freeze-20261013-uppercase` | Live native-planning cascade and TUI responsiveness | Status: implementation and live packaged acceptance complete. The operator reported publication in progress; runtime restart/activation is not yet verified. Follow-up to the live 1.0.851 report after the built-in free-model integration; do not substitute another ping-only check. |
 | `guide.work-orders-wo-native-transport-fresh-install-20261012-uppercase` | Native transport failure in the fresh npm installation gate | Status: implemented and verified. Publication remains with the user. |
 | `guide.work-orders-wo-opencode-all-free-models-20261012-uppercase` | All OpenCode free models in the fallback cascade | Status: implemented and verified. Publication and runtime replacement remain with the user. The subsequent live-reply fixes are tracked separately in fallback reply contracts. The original preferred-first/provider-fairness ordering recorded below has been superseded by benchmark-informed priority at the user's subsequent request. |
 | `guide.work-orders-wo-opencode-production-compatibility-20261012-uppercase` | OpenCode production request compatibility | Status: implemented and verified. Telegram presentation is also completed. Publication and active-runtime restart remain with the operator. Step's native attention-format compatibility remains unverified after a provider limit; the working cascade can continue to other compatible models. |

package/docs/work-orders/WO-completion-review-recovery-20261013.md

@@ -0,0 +1,89 @@
+# Completion review recovery and Telegram liveness
+
+Status: active. Follow-up to the operator's live completion-block and typing
+indicator report on installed Omnius 1.0.852, PID 2845019, `telegram_test`.
+
+## Live anchors
+
+- The request explicitly replies to an earlier source message and asks the
+  bot to tackle it. Interrogatory drafting was requested; no stale greeting
+  takeover is established. Private source text is not copied into this order.
+- The initial inline completion review reports two requirements supported and
+  a third dependent on missing referenced source material. That is a genuine
+  evidence gap, distinct from subsequent verifier availability failures.
+- `artifact-review`: Muse times out after about 45 seconds; Step then reaches
+  the aggregate deadline. The error tells the actor to revise the document.
+- `claim-review`: Muse repairs `uniqueItems`, then gets an unclassified HTTP400;
+  Ling times out. A later retry eventually succeeds on Step, after which the
+  terminal/native pipeline runs again. Exact unknown400 diagnosis is pending.
+- A failed semantic review is cached by exact bytes/context and consumes the
+  three-revision budget even when the verifier was unavailable. Retrying the
+  same valid bytes therefore produces an instruction to modify the artifact.
+- Inline artifact-only review adds instructions contradicting its base policy
+  to review every factual assertion against artifact receipts. Ordinary source
+  answer facts can be required to cite an unrelated artifact receipt.
+- Typing refreshes every three seconds but a request can occupy its sole
+  in-flight slot for 30 seconds, exceeding Telegram's action lifetime. Flood
+  retries can also retain stale disposable heartbeats.
+
+## Ordered work
+
+1. Reproduce the claim critic's exact production schema and Telegram transport
+   with real remote inference and synthetic fixtures. Never send private source
+   text, Telegram Bot API messages or local inference in the harness.
+2. Repair only evidenced wire incompatibilities, keeping original host schemas,
+   exact reply spans/hashes, evidence kinds, authority and delivery receipts.
+3. Give artifact-only claim review an explicit, consistent policy/schema scope.
+   Ordinary source facts belong to the source/objective gates; unsupported
+   artifact review or attachment claims still fail.
+4. Distinguish verifier transport unavailability from semantic rejection. Do
+   not poison the revision cache or consume the revision budget for outages.
+   Retain the exact current owned candidate and provide a guarded review-only
+   resume path. Stop, changed input, source or artifact invalidates its authority.
+5. Apply the bounded default stream allowance to the evidenced artifact/claim
+   review phases. Explicit limits, ordinary chat/unary/local paths and aggregate
+   deadlines remain authoritative.
+6. Make typing heartbeats disposable with a short queue/transport deadline and
+   no stale flood replay. Preserve governor limits, thread destination, current
+   work ownership and Stop; leave durable delivery timeouts intact.
+7. Run focused regressions and real installed-package review acceptance, then
+   make scoped commits and push. Preserve unrelated dirty changes. Publication
+   and runtime restart remain operator-owned.
+
+Do not remove completion evidence gates, fabricate successful reviews, promote
+summary into a reply, weaken required delivery or rewrite missing source facts
+to obtain a passing test. Availability pending is not completed work.
+
+## Context disconnect classification
+
+| Boundary | Observed disconnect | Repair |
+| --- | --- | --- |
+| Provider grammar | Muse rejects nested `oneOf` after `uniqueItems` is repaired. | Recognize the exact static rejection, lower only the native wire copy to `anyOf`, retain exclusive host validation. |
+| Reviewer evidence scope | Artifact-only review asks ordinary source facts for artifact receipts. | Explicit artifact-assertions policy and schema; source/objective gates retain factual responsibility. |
+| Review availability | Timeout becomes semantic rejection, revision-cache poison and generic repair/plateau bookkeeping. | Typed pending availability, frozen exact candidate, review-only resume and control-bookkeeping propagation. |
+| Terminal handoff | Runner commits an explicit incomplete reply, but the legacy Bridge drops its `declared_incomplete` authority. Terminal review sees an empty candidate and starts another workspace. | Receipt-bound incomplete delivery lane; actual ACK leaves goal open, removes obsolete continuation authority, and does not repeat drafting. |
+| Telegram liveness | A disposable heartbeat occupies one in-flight slot for 30 seconds or waits to replay after a flood. | 2.5-second queue/request lifetime, no stale flood replay, scoped coalescing and owner cancellation. |
+
+The first run's archived workboard and committed finalization explicitly say
+`incomplete`; its terminal review then reports no candidate visible reply and
+asks the next run to read the prior workspace's draft. The next workspace
+correctly refuses that foreign artifact path. The capability guard is working;
+the lost terminal candidate and unnecessary object-work replay cause the loop.
+The original missing source requirement remains a genuine unresolved fact.
+
+## Verified coherent deliveries
+
+- `0b58fd57`: shared exact `oneOf` rejection recovery. 208 focused adapter,
+  normalizer and actual-backend fixture checks passed, including overlap values
+  still rejected by the original exclusive host schema. Real Muse claim-review
+  accepted exact reply hash, mixed claim and matching receipt kinds in ~8seconds.
+- `1a14d955` / `ba291791`: typing transport regression and implementation.
+  26 typing/governor checks and CLI TypeScript passed. One old route-shape
+  fixture fails identically on isolated `3d8dff50` source, before this repair.
+
+The compiled inline-source scenario also passed real Muse review with zero
+artifact claims despite an optional local draft. No inference reply or catalog
+metadata response in these live runs was mocked. [Safe receipts](evidence/telegram-completion-review-live-20261013.json)
+retain only synthetic-fixture diagnostics and output hashes.
+
+Architecture decision: [separate review, delivery and objective states](../../.aiwg/architecture/adr-completion-review-delivery-states-20261013.md).

package/docs/work-orders/WO-live-native-cascade-ui-freeze-20261013.md

@@ -0,0 +1,154 @@
+# Live native-planning cascade and TUI responsiveness
+
+Status: implementation and live packaged acceptance complete. The operator
+reported publication in progress; runtime restart/activation is not yet
+verified. Follow-up to the live 1.0.851 report after the built-in free-model
+integration; do not substitute another ping-only check.
+
+## Actual live anchors
+
+- PID 338848, working directory `telegram_test`, version 1.0.851, bundle SHA256
+  `93c9f8bae03b447f603c3245a796b32b7ee51da12389a99929489dcb2335ca27`.
+  This matches the previously validated installed candidate: stale deployment
+  does not explain the discrepancy.
+- Public input 1002 in the operator’s Case Theory chat entered processing at
+  2026-10-13T08:38:34.455Z. The next input 1003 entered processing at
+  08:44:23.071Z and produced a valid observer/no-reply decision at 08:44:39.619Z.
+- Read-only inspection of the live terminal’s expanded inference block found
+  `router-native-requirements`, 272 retained control rows, 4m37s duration:
+  local HTTP503 → Muse HTTP400 twice → Step upstream-unavailable HTTP429 →
+  Ling upstream-unavailable HTTP429 → MiMo, with first output reported at 277.2s.
+  The display reported successful completion with 1207 tokens. Provider HTTP400 bodies
+  were not retained in the existing durable logs.
+- The separate 16s router block supplied by the operator is a successful
+  Muse schema repair, followed by a valid no-reply decision. It is not the
+  failing native cascade.
+- At inspection, TUI stdout/stderr are only `/dev/pts/6`; current provider-phase
+  diagnostics are not persisted. Existing root crash/session logs predate
+  this restart. Broker access logs show 422/503 local chat failures without
+  model/request correlation, insufficient to classify those refusals.
+- Process sampled at ~1GB RSS and ~12 minutes CPU in 20 minutes of uptime; current
+  updates and accepted replies show it is not permanently deadlocked.
+  A 3.3GB deferred-memory spool exists, but inspected append/maintenance paths
+  do not read it wholesale; do not attribute the freeze to it without proof.
+
+## Ordered repairs and acceptance
+
+1. Reproduce the actual native-requirement producer and independent critic
+   through the installed bundle using invented source text and active tasks.
+   Keep the full original host schema/owner/scope validator and prohibit
+   local inference, native action dispatch and Telegram API sends. Capture
+   bounded safe upstream failure diagnostics for these synthetic requests.
+2. Repair evidenced native grammar/request incompatibilities at the shared
+   phase boundary. Preserve host semantic validation, capability/authority,
+   provenance and original contract coupling. Validate real responses; no
+   mocked availability claim and no unconditional HTTP400/422 bypass.
+3. Remove repeated formatting of unchanged retained inference transcripts
+   during TUI repaint. Preserve full read mode, resize, thinking visibility,
+   title time/blink, retention bounds, phase reuse and input handling. Test
+   repeated repaint work with large completed native transcripts.
+4. Add safe durable phase/route diagnostics so future live failures can be
+   traced without extracting terminal rows. Do not persist credentials,
+   endpoint keys, raw user prompts or private generated transcripts. Optional
+   display observers must not fail/replay an inference request.
+5. Run relevant regressions, real native proposal/critic acceptance, rebuild
+   and make scoped verified commits to the tracked branch. Preserve all
+   unrelated dirty changes. Publication/restart remains operator-owned.
+
+The previous all-model ping harness established attention/reply/review behavior
+at healthy moments; it did not cover native task projection/planning. This
+follow-up closes that coverage gap rather than reasserting the ping results.
+
+## Reproduced causes and repairs
+
+The installed native producer reproduced `uniqueItems` rejection, then root
+`anyOf` rejection twice. The optional-field repair exposed the next exact
+upstream error: every property must be required (`activeScopeId` was named).
+The host contract deliberately permits omitted fields; making them required
+would alter its semantics. Recovery now learns that precise incompatibility
+per model/endpoint/API, omits only native schema framing, and preserves the
+original full host schema, parser, tool arguments and independent critic.
+An adaptation must change the previous wire schema before it can justify
+another retry. Recovery remains bounded by three distinct restrictions.
+
+A controlled prompt-only request also exposed true raw-stream inactivity:
+HTTP200 followed by the backend's 45-second idle watchdog. It was incorrectly
+reported as generic transport failure. Native planning/review streams now
+allow 90 seconds under the default policy, capped by caller/aggregate deadlines;
+explicit timeout settings and ordinary chat/unary/local paths retain their
+limits. Exact watchdog failures report `timeout`. No undocumented reasoning
+flags were added.
+
+The controlled 90-second diagnostic accepted a real 7-obligation/two-method
+proposal through the original parser and admitted an independent critic.
+This diagnostic intentionally omitted native framing at the wire; it is
+recorded separately from automatic production-adapter acceptance.
+
+[Safe live receipts](evidence/telegram-native-planning-live-20261013.json)
+contain hashes/metadata for invented fixtures, not private chat transcripts.
+
+## Delivered coherent repairs
+
+- `e65ed677`: cache unchanged TUI inference transcript rows; 61 focused checks
+  and CLI build passed. This removes repeated formatting work; it does not
+  establish that repaint was the sole cause of the reported freeze.
+- `04b4c5e7`: private bounded route traces at
+  `.omnius/telegram-inference/routes.jsonl` and isolated optional observers.
+  Files use 0600, the directory 0700, pending observations 128 and files 5 MiB
+  with one rotated archive. Trace failure cannot fail/replay the request.
+  Backend observer 14, trace 20, Bridge integration 22 checks passed; the
+  combined focused CLI run passed 105 checks. Stop/custody fences remain.
+- `42419cd2`: precise optional-schema recovery, ineffective-retry prevention,
+  scoped default native stream allowance and correct timeout classification.
+  Automatic compiled-workspace live acceptance passed both native phases:
+  three distinct HTTP400 capability errors repaired on Muse, then original
+  proposal validation and independent critic acceptance, without model failover.
+  Final focused verification passed 531 orchestrator + 112 CLI = 643 checks.
+  Full workspace rebuild, artifact audit and compiler-free fresh npm install
+  passed. At verification, PID 338848 still uses the old `93c9f8...`
+  bundle; this pass has neither published nor restarted it.
+
+## Broader regression limits
+
+The expanded run found four transport-fixture and two native-intake guard
+failures. An isolated source archive of `e65ed677`, with the original Runner
+rather than dirty/compiled workspace output, reproduced all six failures.
+Three transport fixtures omit the previously required
+`observationSourceMessageIds`; one ambiguity expectation predates the
+advisory-policy change. The two intake guard cases have an existing objective
+contract retention discrepancy. They are recorded as baseline failures and
+were not silently changed to claim a green full suite.
+
+## Final installed-package acceptance
+
+The freshly installed tarball used bundle SHA256
+`36c6a7172915a3edc9dc2a355ee9628f64a2d865e8e0cc3547b10e88d37a45e2`.
+A fresh process automatically recovered three distinct schema HTTP400s on Muse
+and retained the selected model throughout. The native proposal took 69.1 seconds,
+parsed five obligations/two methods with new-task continuity; the independent
+critic took 103.9 seconds overall, including 64.6 seconds before HTTP headers,
+and was admitted with method verdict `accept`. Both phases retained the
+original host schemas. Five actual generation POSTs were made; no model or
+metadata reply was mocked, and no local inference, native tools or Telegram
+API sends were performed. This validates production inference/validation
+boundaries, not a fresh Telegram delivery ACK or cross-application task.
+
+Reproduce against a fresh isolated installation:
+
+```sh
+node scripts/live-telegram-native-requirements-harness.mjs --run \
+  --bundle /path/to/isolated/install/lib/node_modules/omnius/dist/index.js \
+  --output /tmp/omnius-native-planning-live.json
+```
+
+The default harness pins Muse and denies alternative models, local inference,
+Telegram API calls and native action dispatch. `--inspect-only` makes no
+network requests. Optional diagnostic flags are recorded separately and are
+not substituted for the automatic installed-package acceptance above.
+
+The operator reported npm publication in progress after installed-package
+acceptance. A second rebuild, intended to refresh packaged documentation,
+was stopped in workspace compilation before it could replace `publish/`.
+The earlier complete build/audit/install/live validation remains the evidence
+for the code bundle above. No further publish-directory mutations were made
+by this pass while the operator published.