omnius 1.0.850 → 1.0.852

package/docs/work-orders/WO-built-in-free-model-startup-20261012.md

@@ -0,0 +1,137 @@
+# 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.
+
+## Ordered work
+
+1. Repair the public independent-review request. Real installed-bundle probes
+   reproduced sequential HTTP 400 rejections for `uniqueItems`, then top-level
+   `anyOf`. Keep the full host schema and public semantic-review gate. Permit a
+   bounded repair for each newly observed supported limitation on the same route.
+2. Exercise other eligible free models with real synthetic generations through
+   the actual production request builders/parsers. Cover public review as well
+   as simple replies. Record actual failures/quotas; never claim availability
+   from mocked inference or promise that external services never fail.
+3. Include the free models in the default model-selection list without requiring
+   credentials or endpoint configuration. Use model names and neutral free-model
+   presentation in the picker. Retain truthful transport identity in internal
+   diagnostics/provenance. Preserve existing configured model choices.
+4. Update first startup and lightweight setup to offer a working built-in free
+   route before asking for credentials or downloading/loading local models.
+   Account-based providers and local inference remain selectable options.
+5. Repair the live TUI's premature/duplicate completed states and later failed
+   state shown after a healthy `pong`; inspect the separate public conversation
+   failure and stalled continuation path. Separate inference-phase completion
+   from task settlement and preserve actual Telegram acknowledgement authority.
+6. Rebuild, run meaningful regression tests and live remote acceptance, verify
+   the packaged artifact, then make scoped commits and push the tracked branch.
+   Publication/restart remains operator-owned.
+
+## Current live anchors
+
+The running bot uses 1.0.850, bundle SHA256
+`d8636120a09b01e5510cb048c5cafcbb0598474653831174196e6e708de3c33e`.
+Read-only Telegram history confirms private `pong` (message 3368) and public
+`pong` (message 5805). Public generation succeeded; the independent
+`chat-fast-path-review` request then exercised an additional schema shape that
+the earlier attention/simple-reply live harness did not cover.
+
+Private admin input can use its explicitly admitted single-pass path and avoid
+that independent public review. Do not remove the public review to copy the
+private behavior. The earlier schema-only `review` probe used the producer’s nominal 1,300-token
+limit. The complete Telegram method applies its observable-request budget
+(16,384 tokens in these remote probes), so the new all-model harness invokes
+the actual attention, generation, independent-review methods and parsers.
+
+
+## Implementation and regression verification, 2026-10-13
+
+- Public and private generation share the same provider adapters. Public review
+  retains its independent original host schema and semantic acceptance gate.
+- Every remote JSON phase receives its full producer contract in the prompt,
+  including on models with unknown or supported native structured output.
+  Explicitly unsupported native formats use prompt-only generation with original
+  host validation, complete-response buffering and unchanged tool authority.
+- Big Pickle’s exact Chat identity has an observed native-format override:
+  native requests returned HTTP 400 `{"model":"big-pickle"}`; omitting only that
+  format gave HTTP 200 generation and review with host acceptance. Production
+  revalidation then passed attention, generation and review without the probe flag.
+- Cat Jam’s bounded diagnostics learn `uniqueItems` and a root conditional-union
+  restriction. Only the native grammar is lowered. Nested closed objects, identity,
+  authorized tools and coupled fulfillment/continuation checks remain unchanged.
+- Exact pinned-gateway HTTP 429 `Endpoint is unavailable` errors retain their
+  HTTP status but are classified as upstream outages, not quota exhaustion.
+  They cool that model without scheduling a quota retry. Genuine rate limits keep
+  their existing cooldown and retry policy.
+- Remote streaming keeps the backend’s 45-second raw-byte idle watchdog and
+  the 120-second aggregate absolute ceiling. Hidden reasoning and buffered JSON
+  no longer hit a second 45-second absolute timer. Shorter caller limits and Stop
+  still apply; unary requests retain their original absolute attempt bound.
+- Built-in selected models enter the same catalog, transport, schema adapters,
+  validation and lifecycle reporting used by fallback. Explicit selection is first;
+  automatic alternatives use the capability ordering. Manual mode asks before
+  alternatives; disabled fallback still permits the selected built-in model.
+- New installations use built-in free inference with no key or local download.
+  `/model`, Telegram’s isolated model picker and completion include the neutral
+  `Built-in free` category. Bundled choices remain visible offline with truthful
+  availability labels; live pricing/retirement still control admission.
+  Existing local/keyed profiles and explicit transport overrides remain intact.
+- Independent regression checks: 504 orchestrator, 254 CLI and 15 provider registry
+  tests passed. These use controlled network fixtures for invariants and are
+  separate from the live model evidence. Full workspace rebuild passed.
+- The compiler-free fresh npm install passed for the packaged candidate, including
+  SQLite and AIWG checks; artifact audit passed and the 566-entry tarball has no
+  sourcemaps. No version was published and the running bot was not restarted.
+
+The existing README generated REST inventory check fails at the unchanged REST
+block (the task’s README diff only updates setup/prerequisites). The independent
+REST source check passes; this pre-existing inventory drift is not included in
+this repair.
+
+Live coverage deliberately sends only invented messages through real Telegram
+methods and providers. It never calls the Telegram Bot API, dispatches a native
+host tool, reads private conversation history, or invokes local inference. Thus
+these receipts establish inference-path behavior, not a new delivery ACK or
+native cross-application action test. Delivery/settlement regressions are in
+`87cecd19`; the installed 1.0.850 bot remains the operator’s running version.
+
+
+## Live packaged results and delivery
+
+Implementation: `b94a6179` public review, `87cecd19` Telegram settlement,
+`273a7bdb` built-in free integration and common adapters, `65a15404` Step’s
+opaque complex-schema compatibility. Commits are delivered to `origin/main`.
+
+The [durable live receipt](evidence/telegram-all-free-live-20261013.json) records
+all nine eligible models, exact bundle/catalog hashes, phase outcomes, safe
+provider diagnostics, original host acceptance, and physical request counts.
+No inference reply or catalog response in these live runs was mocked.
+
+| Model | Live result through Telegram methods | Adapter or remaining limit |
+| --- | --- | --- |
+| Big Pickle | Attention, generation and independent review passed in installed sweep | Exact Chat native-format opt-out; original host contract retained |
+| Cat Jam | All three phases passed in installed sweep | Learned `uniqueItems` and root conditional-union restrictions |
+| Ling 3.1 Flash | Earlier attention/generation passed; final isolated probes returned endpoint-unavailable HTTP 429 | Declared native-format opt-out; complete installed Ling→Muse cascade passed |
+| LongCat 2.5 Preview | All three phases passed in installed sweep | Full original JSON guidance, native Chat transport |
+| MiMo V2.6 Flash | All three phases passed in installed sweep | Full original JSON guidance, native Chat transport |
+| Muse Spark 1.3 | All three phases passed in installed sweep | Responses auto-only tool choice and learned native schema restrictions |
+| Nemotron 3.5 Lightning | All three phases passed in installed sweep; attention took 61.9 seconds under default deadlines | Raw-byte idle watchdog plus aggregate absolute bound; no invented thinking flag |
+| Space Bunny | All three phases passed in installed sweep | Full original JSON guidance fixed the prior JSON-syntax failure |
+| Step 5 Preview | Initial attention passed; patched final installed generation and independent review both passed (HTTP 200/200) | Simple native schema works, complex schema returned opaque HTTP 400; exact Chat prompt-only policy preserves full host validation |
+
+Step’s final attention probe and Ling’s final probes also recorded intermittent
+endpoint-unavailable HTTP 429s. These are external availability limits. The final
+installed Step→Muse public cascade completed with HTTP 429→200→400→400→200:
+Step’s outage, Muse generation, then two bounded review-schema repairs and an
+accepted independent review. No unavailable-model quota retry or fabricated
+answer was used. Both selected-model isolation and real automatic cascade modes
+are available in `scripts/live-telegram-free-models-harness.mjs`.
+
+The final unpublished candidate bundle SHA256 is
+`93c9f8bae03b447f603c3245a796b32b7ee51da12389a99929489dcb2335ca27`.
+Its compiler-free fresh install, SQLite/AIWG checks, 566-entry tarball audit,
+README wiring and sourcemap exclusion passed. The staging version remains
+1.0.850; the operator’s publish workflow must choose the next release version.
+The running production bot was not replaced by these harness installs.

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

@@ -0,0 +1,146 @@
+# Live native-planning cascade and TUI responsiveness
+
+Status: implementation and live packaged acceptance complete; operator publication/restart pending. Follow-up to the operator’s 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. Provider400 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.
+- Current 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 show422/503 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. The currently running 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.

package/docs/work-orders/WO-public-review-schema-compatibility-20261012.md

@@ -0,0 +1,31 @@
+# Public reply-review schema compatibility
+
+Status: repaired and verified; broader built-in-model/startup/lifecycle work is
+tracked in `WO-built-in-free-model-startup-20261012.md`.
+
+The live 1.0.850 bot delivered both private and public `pong`. Public generation
+succeeded on Muse, but its separate independent review used a larger schema
+that the private single-pass path did not require. The previous live acceptance
+covered attention and simple replies, leaving this phase untested.
+
+Real probes against the active installed bundle reproduced two sequential
+HTTP 400 errors: unsupported `uniqueItems`, then a forbidden top-level `anyOf`.
+The fallback allowed only one schema-repair retry and therefore moved to Step
+and Mimo. See the safe [before receipt](evidence/public-review-before-20261012.json).
+
+The repair recognizes the exact observed second diagnostic, lowers only the
+root `anyOf` of a complete closed response object, preserves nested alternatives
+and tool schemas, and permits one bounded retry per newly learned supported
+limitation. The original full host schema, identity/evidence checks and semantic
+review remain authoritative; structured output stays buffered until valid.
+
+The [live after receipt](evidence/public-review-after-20261012.json) records
+Muse HTTP 400 -> 400 -> 200 on the same model, with valid public-review output at
+the production 1,300-token limit. No inference or metadata response was mocked;
+synthetic context only, no Telegram sends or tools. The harness now includes
+the production review schema, policy and parser; the full Telegram-method
+multi-model harness is tracked under the broader work order.
+
+187 focused orchestrator regressions and 21 new public-review boundary tests
+passed. Those invariant tests use explicit fixture networking and are separate
+from the live acceptance above. The workspace build passed.

package/docs/work-orders/WO-telegram-reply-lifecycle-20261013.md

@@ -0,0 +1,28 @@
+# Telegram reply lifecycle
+
+Status: implemented and verified. The built-in-model/startup and multi-model
+live acceptance work continues under `WO-built-in-free-model-startup-20261012.md`.
+
+Read-only live history and delivery receipts confirm that public ping 5804
+received acknowledged reply 5805. ESP32 input 5806 failed later and has no
+delivery receipt. The display reused one chat view across inputs and reported
+later chat failures through an already-completed attention view, mixing these
+separate outcomes. Generic exhausted-fallback errors also became unclassified
+quick-chat failures.
+
+Reply views are now bound to their exact input. Attention/reply labels identify
+the phase; later errors preserve earlier successful replies and do not overwrite
+completed attention. Terminal callbacks are idempotent. Exhausted remote fallback
+has a typed diagnosis, preserving its nonretryable policy.
+
+Provider acknowledgement is retained immediately. Optional memory/display/notes
+or latency observers cannot turn an acknowledged delivery into failure or cause
+regeneration. Observation failures are recorded as hashes in a local diagnostic
+archive. Durable intake writes and ambiguous send handling retain their existing
+authority and no-replay behavior. Manual fallback wording now distinguishes an
+unavailable local endpoint from a selected remote provider.
+
+53 lifecycle, recovery, telemetry and public routing regression tests passed;
+CLI TypeScript and whitespace checks passed. Transport acknowledgements in these
+tests are fixtures, not real Telegram sends. Live inference coverage is recorded
+separately in the multi-model work order.

package/docs/work-orders/evidence/public-review-after-20261012.json

@@ -0,0 +1,211 @@
+{
+  "schema": "omnius.live-opencode-acceptance.v1",
+  "startedAt": "2026-10-13T06:45:58.488Z",
+  "syntheticOnly": true,
+  "mockedReplies": 0,
+  "localRequests": 0,
+  "telegramMessages": 0,
+  "toolsExecuted": 0,
+  "contextBytes": 0,
+  "stream": true,
+  "mode": "production_remote_cascade",
+  "receipts": [
+    {
+      "model": "cascade",
+      "case": "review",
+      "apiShape": "chat",
+      "physicalCalls": 3,
+      "wires": [
+        {
+          "model": "muse-spark-1.3-contributor-free",
+          "apiShape": "responses",
+          "stream": true,
+          "toolChoice": "auto",
+          "toolNames": [
+            "read",
+            "shell"
+          ],
+          "schemaSha256": "a9ac7ee9ce3436361dee69396f9ee208745e1ab80c6d50eb5913f7dc8dced13d",
+          "bodySha256": "c0220b976bd7d4976faf5c9cd9a36e42a23099ae137980619c1f4cea2b4c169c",
+          "maxOutputTokens": 1300
+        },
+        {
+          "model": "muse-spark-1.3-contributor-free",
+          "apiShape": "responses",
+          "stream": true,
+          "toolChoice": "auto",
+          "toolNames": [
+            "read",
+            "shell"
+          ],
+          "schemaSha256": "c148de498ab3e3da5b05b8c55cdada00fb057ee5679024012cf9f1910d183f49",
+          "bodySha256": "0fb7f740aaf36c2716bb52e65822c1984f8a00b266faea04ec3b71a359407577",
+          "maxOutputTokens": 1300
+        },
+        {
+          "model": "muse-spark-1.3-contributor-free",
+          "apiShape": "responses",
+          "stream": true,
+          "toolChoice": "auto",
+          "toolNames": [
+            "read",
+            "shell"
+          ],
+          "schemaSha256": "6b25faf4155e56d73fae9a522f3a35d2e40bd734e879f5987f62a183692e6cb0",
+          "bodySha256": "0811cc2fbc57eb898bdadca7b386a739a73e2a2db6c61876373235f2bb13f0e5",
+          "maxOutputTokens": 1300
+        }
+      ],
+      "http": [
+        {
+          "status": 400,
+          "error": {
+            "bodySha256": "ff87146d8064d14b2548e804bb5560f63857ef4d36cf1da734369825bab20656",
+            "type": "invalid_request_error",
+            "code": null,
+            "param": "schema",
+            "message": "JSON schema keyword `uniqueItems` is not supported for structured outputs"
+          }
+        },
+        {
+          "status": 400,
+          "error": {
+            "bodySha256": "f962557c7c9e2f9a179a02637853d17348d5afb970d9a453433f21800bb5f53a",
+            "type": "invalid_request_error",
+            "code": null,
+            "param": "schema",
+            "message": "schema must have type 'object' and not have 'oneOf'/'anyOf'/'allOf'/'enum'/'not' at the top level."
+          }
+        },
+        {
+          "status": 200
+        }
+      ],
+      "routes": [
+        {
+          "location": "remote",
+          "phase": "selected",
+          "model": "muse-spark-1.3-contributor-free",
+          "providerId": "opencode",
+          "backendType": "vllm"
+        },
+        {
+          "location": "remote",
+          "phase": "failed",
+          "model": "muse-spark-1.3-contributor-free",
+          "providerId": "opencode",
+          "backendType": "vllm",
+          "failure": {
+            "category": "request_rejected",
+            "status": 400,
+            "validationReason": "unsupported_schema",
+            "expectedKind": "json_schema",
+            "schemaDigest": "501572b1beb85034999a0fbc264df0641583878832c24cca100516eba3851c12",
+            "apiShape": "responses"
+          }
+        },
+        {
+          "location": "remote",
+          "phase": "selected",
+          "model": "muse-spark-1.3-contributor-free",
+          "providerId": "opencode",
+          "backendType": "vllm",
+          "schemaAdapter": {
+            "omittedNativeKeywords": [
+              "uniqueItems"
+            ],
+            "hostValidation": "unchanged"
+          }
+        },
+        {
+          "location": "remote",
+          "phase": "failed",
+          "model": "muse-spark-1.3-contributor-free",
+          "providerId": "opencode",
+          "backendType": "vllm",
+          "schemaAdapter": {
+            "omittedNativeKeywords": [
+              "uniqueItems"
+            ],
+            "hostValidation": "unchanged"
+          },
+          "failure": {
+            "category": "request_rejected",
+            "status": 400,
+            "validationReason": "unsupported_schema",
+            "expectedKind": "json_schema",
+            "schemaDigest": "501572b1beb85034999a0fbc264df0641583878832c24cca100516eba3851c12",
+            "apiShape": "responses"
+          }
+        },
+        {
+          "location": "remote",
+          "phase": "selected",
+          "model": "muse-spark-1.3-contributor-free",
+          "providerId": "opencode",
+          "backendType": "vllm",
+          "schemaAdapter": {
+            "omittedNativeKeywords": [
+              "uniqueItems",
+              "rootAnyOf"
+            ],
+            "hostValidation": "unchanged"
+          }
+        },
+        {
+          "location": "remote",
+          "phase": "succeeded",
+          "model": "muse-spark-1.3-contributor-free",
+          "providerId": "opencode",
+          "backendType": "vllm",
+          "schemaAdapter": {
+            "omittedNativeKeywords": [
+              "uniqueItems",
+              "rootAnyOf"
+            ],
+            "hostValidation": "unchanged"
+          }
+        }
+      ],
+      "finished": true,
+      "selectedRoute": {
+        "providerId": "opencode",
+        "model": "muse-spark-1.3-contributor-free",
+        "kind": "keyless"
+      },
+      "outcome": {
+        "state": "passed",
+        "schemaValid": true,
+        "visibleChars": 186,
+        "toolCalls": 0,
+        "outputSha256": "9c1b1bf16b0e1f7d152009dbad5698176de2e06ca39c697b0bbec805e1758ddf"
+      },
+      "elapsedMs": 9949
+    }
+  ],
+  "catalogSha256": "24be782386c5cb701cfc0f074ff314f7f50d08fa9b05dc7cafba745772099f3e",
+  "availableSha256": "4821bf18034717dd138fc9ad8e8b2ad1db51e37419fb1f0b2292b9e0ec5ebd23",
+  "selectedModels": [
+    "big-pickle",
+    "cat-jam-free",
+    "ling-3.1-flash-free",
+    "longcat-2.5-preview-free",
+    "mimo-v2.6-flash-free",
+    "muse-spark-1.3-contributor-free",
+    "nemotron-3.5-lightning-free",
+    "space-bunny-free",
+    "step-5-preview-free"
+  ],
+  "bundleVersion": "1.0.850",
+  "sourceModules": {
+    "agenticRunner": "b4a0291effd917bae0fb710b3d0369f3ef0213f678de5b0c3293c4ffc1f10629",
+    "opencode-responses-compatibility": "c99cb4c324a966936050266f205427da3a64b6e7665a2190e166e64906c15afa",
+    "opencode-chat-compatibility": "aeed3f7bc98dc2fa817b3364ef874b95684ddcd21db38b102e9d3e5e491bac94",
+    "opencode-free-models": "d8fbc9a3d30c0ee298647be7f8a3b55402d08e821c3d35a937b1f0ad793eb3c1"
+  },
+  "attentionSchemaSha256": "15d827c6ec46a34d5edfe219dda0c382b8d7a28480d4952b3e0df14c7d48507a",
+  "reviewSchemaSha256": "a9ac7ee9ce3436361dee69396f9ee208745e1ab80c6d50eb5913f7dc8dced13d",
+  "finishedAt": "2026-10-13T06:46:09.629Z",
+  "physicalCalls": 3,
+  "passed": true
+}