# Eve SOTA closure baseline — September 2026
**Status:** point-in-time baseline for closure task `0.2`
**Source
checkout:** `778b9c874163fe9f958cfb44b54b23ab2b444eff` (`C0`)
**Local
observation window:** `2026-09-01T15:06:40Z` through `2026-09-01T15:09:53Z`
(`L1`–`L5`)
**Machine-readable record:**
[`eve-sota-closure-baseline/2026-09-01.json`](eve-sota-closure-baseline/2026-09-01.json)
This is a baseline, not a readiness verdict. Source facts mean “present in the
named checkout”; historical measurements mean “recorded by the named committed
artifact”; local observations mean only this developer host in the observation
window. No production or staging system was queried. A command identifier in the
Evidence column resolves to the exact command and commit in the command catalog
below and in the machine-readable record.
## Planes, seams, tools, and views
The prompt inventory is a union of every definition that can be offered under
some valid scope. It is deliberately **not** the size of any one turn's served
toolset: family routing, release scope, client capabilities, builder tier, and
deployment bindings reduce the definitions a particular turn receives.
| Plane or seam | Count | What the count means | Evidence |
| ------------------------ | ----------------------------------: | ------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| Member plane | 43 definitions | 39 base member definitions, 3 audit definitions, and 1 deferred-family router definition | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Builder plane | 46 definitions | 15 admin-operation, 23 intent-workbench, 2 Hathor content-bridge, and 6 workbench-kit definitions | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Prompt-protected union | 89 definitions | Member and builder groups above, with no duplicate definition name | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Agent plane | 6 MCP tools | Queue, lease, brief, report, shipped, and verify tools; this catalog is separate from the prompt-protected union | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff`; historical run commit `44733109326b09bddc7a1113cfb1b3dd1d877ce1` |
| Quality plane | 0 separate model-facing definitions | Quality signs through deterministic evaluation and artifact verification; it has no additional conversational tool catalog in the inventory | residual of `C1`'s exhaustive 89-definition grouping @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Workbench-kit read seam | 1 generic read tool | One authenticated router spans the registered views below | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff`; historical run commit `44733109326b09bddc7a1113cfb1b3dd1d877ce1` |
| Workbench-kit write seam | 5 mutation tools | Each mutation is card-gated; these are included in the builder-plane count | `C1`, `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Registered workbench | Views | Evidence |
| --------------------------- | --------------------------------: | ------------------------------------------------------------------------------------------------------------------- |
| Tara workbench | 10 | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Launch-readiness governance | 2 | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Hathor | 4 | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Isis | 15 | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| **Total** | **31 views across 4 workbenches** | `C4` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff`; historical run commit `44733109326b09bddc7a1113cfb1b3dd1d877ce1` |
## Stable prompt boundary
The hash covers stable conduct variants, exact served skill text, and complete
offerable tool definitions. It excludes dynamic engine, persona, daypart,
memory, page, and live tour-catalog bytes. Component byte counts therefore do
not claim to be the total size of a live request.
| Component | Baseline | Evidence |
| ------------------------- | -----------------------------------------------------------------: | ------------------------------------------------- |
| SHA-256 | `cad7c1cb4098c319112dae202dce495dbc2c27b1143957105a3b1e9b94939b8b` | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Core conduct | 845 bytes | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Toolless conduct | 335 bytes | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Tool descriptions | 36,462 bytes over 89 definitions | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Complete tool definitions | 61,551 bytes over 89 definitions | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Skills | 3,945 bytes over 7 registered skills | `C1` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
## Evaluation cases, runs, and floors
The baseline family floor is case-level `pass^k`, with `k = 3`; it is not a
Wilson interval. The builder reliability table is a different statistic: the
lower endpoint of a pooled run-level Wilson 95% interval. Keeping those columns
separate prevents a stronger-looking number from silently changing the unit of
analysis.
| Family | Cases | Baseline runs | Case-level `pass^3` floor | Evidence |
| -------------------- | ------: | ------------: | ------------------------: | ------------------------------------------------- |
| Audit | 7 | 21 | 0.7142 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Capability/smalltalk | 19 | 57 | 0.8421 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Docs | 7 | 21 | 0.2857 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| General | 9 | 27 | 0.8888 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Member data | 48 | 144 | 0.7500 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Navigate | 10 | 30 | 0.9000 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Safety | 3 | 9 | 1.0000 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Tour | 7 | 21 | 1.0000 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Workbench read | 9 | 27 | 0.2222 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Workbench write | 2 | 6 | 0.5000 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| **Total** | **121** | **363** | — | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Builder family | Cases | Pooled runs | Passed runs | Wilson 95% lower floor | Evidence |
| --------------- | ----: | ----------: | ----------: | ---------------------: | ------------------------------------------------- |
| Docs | 5 | 50 | 49 | 0.8950 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Workbench read | 24 | 240 | 220 | 0.8747 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Workbench write | 25 | 250 | 229 | 0.8750 | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
The baseline arm used `363` billed runs and cost `$0.1109`; its ratchet record
does not retain a cache-read rate or median latency, so those fields are
explicitly null in the machine-readable record (`C2` @
`778b9c874163fe9f958cfb44b54b23ab2b444eff`).
## Cost, cache, and latency observations
These are different dated samples and must not be pooled. The targeted Phase 11
checks did not constitute a full-deck rerun.
| Sample | Cases / runs | Result | Billed cost | Median total latency | Cache-read rate | Evidence |
| ---------------------- | ------------ | ----------------------- | ----------: | -------------------: | ---------------------------: | ------------------------------------------------------------------------------------------------------------------- |
| Baseline family deck | 121 / 363 | Family floors above | $0.1109 | not retained | not retained | `C2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Curated-tour check | 1 / 10 | 10/10 passed | $0.0063 | 3.7 s | 47.2% over 8 reporting runs | `C3` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff`; historical run commit `2352ee93c5391e7d8c18ecaf87fd3225380228d0` |
| Release-blocked checks | 7 / 70 | 59/70 classified passed | $0.0295 | 8.1 s | 83.6% over 63 reporting runs | `C3` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff`; historical run commit `2352ee93c5391e7d8c18ecaf87fd3225380228d0` |
The telemetry cache floor is `70%` (`C2` @
`778b9c874163fe9f958cfb44b54b23ab2b444eff`). The first post-initiative weekly
observation recorded `3,233` turns, only `246` with reported cost, `$0.000727`
per reporting turn, and a `26.5%` cache rate; the same-day fixed battery then
measured `92%` across `150` runs after serving-route pinning (`C3` @
`778b9c874163fe9f958cfb44b54b23ab2b444eff`; weekly evidence commit
`cb5d630822f85933ab63b228d5336be3b8b0a6b2`). That is a historical drift and
remedy observation, not the current host's live assistant telemetry.
## Queue and lease state
The current observation is the local `oshun_dev` Postgres database. It is not
production or staging state, and the aggregate query intentionally records no
titles, identifiers, or holder names.
| Local durable state | Observation | Evidence |
| ------------------------------------- | ------------: | ----------------------------------------------------------------------------------- |
| Work items | 4 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Draft | 2 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Ready / queue-eligible | 1 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Verified | 1 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Leased or in progress | 0 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Lease rows / live / expired / holders | 0 / 0 / 0 / 0 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
## Operator-memory posture
Source posture is default-on **only when a database URL is bound**. Absence of a
database intentionally becomes session-only memory; a false-valued kill switch
disables the durable slice. The slice rejects member identifiers and
email-shaped values, stores confirmed text verbatim, and has bounded categories.
| Memory fact | Baseline | Evidence |
| --------------------------------------------------- | ---------: | ----------------------------------------------------------------------------------- |
| Categories | 3 | `C8` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Preference slots | 12 maximum | `C8` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Standing-initiative slots | 1 maximum | `C8` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Pinned-context slots | 8 maximum | `C8` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Local table rows / operators / populated categories | 0 / 0 / 0 | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
The current shell had neither accepted database URL set and no explicit memory
kill switch (`L1` at `2026-09-01T15:09:53Z`, checkout
`778b9c874163fe9f958cfb44b54b23ab2b444eff`). Therefore, a BFF launched from that
unchanged shell would be session-only even though the local Postgres service and
empty memory table are reachable. This does not make a claim about an
already-running deployment.
## Invocation, tour, voice, and selection surfaces
| Surface | Count and scope | Evidence |
| --------------------- | ----------------------------------------------------------------------------------------------------------- | ------------------------------------------------- |
| Assistant invocation | 12 registered points across 25 source sites: customer web 9 points / 22 sites; admin web 3 points / 3 sites | `C5` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Reviewed tours | 7 plans and 17 steps: customer 3, studio 1, admin 3 | `C6` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Voice controls | 4 controls across 2 web shells: input and playback in customer web, input and playback in admin web | `C9` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Selection-to-ask | 2 registered invocation points, customer and admin | `C5` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Admin selection scope | 3 labels (`crashes`, `incidents`, `review`) across 4 source components | `C9` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
All `3` customer tours are member-visible; the `1` studio plan appears only at
builder tier; all `3` admin plans use the admin player (`C6` @
`778b9c874163fe9f958cfb44b54b23ab2b444eff`). Provider-backed voice credentials
were configured for `0` of the `4` checked voice providers in the restricted
local secret file, while browser speech fallbacks remain implemented (`L5`, `C9`
@ `778b9c874163fe9f958cfb44b54b23ab2b444eff`). This is name-only availability;
no credential value was printed or copied.
## Model legs
The registry contains `4` legs: `3` bound and `1` explicitly unbound (`C7` @
`778b9c874163fe9f958cfb44b54b23ab2b444eff`). Prices are dated snapshots in USD
per million tokens, not live quotes.
| Leg | State and dated pin | Input / output price snapshot | Evidence |
| ---------- | ------------------------------------------------------------------------------------------- | --------------------------------: | ------------------------------------------------- |
| Turn | bound: `deepseek/deepseek-v4-flash-0731`; 3 measured fp8 endpoints in the serving allowlist | $0.04494 / $0.08988 on 2026-08-30 | `C7` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Escalation | bound: `deepseek/deepseek-v4-pro-0813` | $1.218 / $2.436 on 2026-08-17 | `C7` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Judge | bound provisionally to `deepseek/deepseek-v4-pro-0813` | $1.218 / $2.436 on 2026-08-17 | `C7` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Embedding | unbound; current docs retrieval is lexical BM25 | no price | `C7` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
The restricted local secret file was mode `0600`; OpenRouter was set and the
four checked provider-backed voice keys were unset (`L5` at
`2026-09-01T15:06:41Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff`).
This proves only local configuration presence, not provider health or
authorization.
## Dependency and runtime availability
| Dependency | Local observation | Evidence |
| --------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- |
| Node / pnpm | available: 24.15.0 / 10.25.0 | `L3` at `2026-09-01T15:07:00Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| PostgreSQL / pgvector | reachable: PostgreSQL 16.14; vector extension 0.8.2 installed | `L1` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Redis | healthy container on port 6379; `PONG`; image tag `redis:7-alpine` | `L2` at `2026-09-01T15:07:00Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Object storage | MinIO healthy on ports 9000–9001; image uses the mutable `latest` tag | `L2` at `2026-09-01T15:07:00Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Qdrant | no container and port 6333 unreachable; local vector capability is pgvector instead | `L1`, `L2` @ `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Browser automation | Playwright 1.60.0; 3 installed engines with executable Chromium, Firefox, and WebKit paths | `L3` at `2026-09-01T15:07:00Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Mobile automation | ADB 1.0.41 / platform tools 34.0.4 and Maestro 2.5.1 installed; 0 attached devices | `L3` at `2026-09-01T15:07:00Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Blender | executable available, version 4.0.2 | `L3` at `2026-09-01T15:07:00Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Unreal Engine | required path executable; reports 5.5.4 as `ueagent`; version probe exits 1 after initialization because Vulkan/display is unavailable | `L4` at `2026-09-01T15:07:15Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
| Coding-agent CLIs | Codex 0.152.0 and Claude Code 2.1.247 available | `L3` at `2026-09-01T15:09:53Z`, checkout `778b9c874163fe9f958cfb44b54b23ab2b444eff` |
The mutable MinIO tag, absent Qdrant process, unattached mobile device, and
Unreal graphics failure are recorded as limitations, not passes. Task `0.7` owns
the expiring capability record and will re-probe these plus native desktop
permissions and external channel credentials; this baseline intentionally does
not pre-approve or infer those capabilities.
## Claim boundary and open baseline gaps
- No full-deck model run was performed for this document. Family floors remain
the committed ratchet values.
- The baseline deck has no retained cache or latency statistic. Null is the only
honest value.
- Queue and lease counts describe one local development database only.
- Credential checks establish presence by variable name only; they do not test
provider reachability, quota, account policy, or data residency.
- Dependency observations do not expire themselves. Task `0.7` must replace them
with stale-expiring probes before later runtime admission relies on them.
- The current model registry has no bound embedding leg. That is an explicit
architecture choice for lexical docs retrieval, not evidence that retrieval
quality is sufficient. **Superseded 2026-09-05 by task 3.2 — see "Declared
drift since capture" below. The sentence above remains the fact as captured on
2026-09-01 and is not rewritten.**
## Declared drift since capture
This record is a dated capture and its verifier asserts that current source
still matches it. Those two things collide the moment a later task changes
something the baseline recorded, and rewriting the capture to make the check
pass would destroy the "before" picture Phase 18 compares against. So the
capture stays frozen and drift is DECLARED in `documentedDrift`: each entry
names the section, the task that moved it, the value as captured, and the value
now. Undeclared drift still fails the verifier.
Drift is listed as prose rather than a table on purpose: every numeric table row
in this record's narrative must cite the capture's own command id and source
checkout, and drift is by definition a fact from a later checkout.
- **`modelRegistry`, tasks `3.2` and `15.1`** — the embedding leg moved from
`unbound` to `perplexity/pplx-embed-v1-0.6b`, priced at four thousandths of a
dollar per million input tokens; then the vocabulary widened from four legs to
nine, so the capture's `unbound` status no longer exists and the chat legs
carry re-measured prices. Reproduce the current state with the same command
the capture used, `C7`.
Task 3.2 priced the whole enumerated field from billed calls
(`docs/audits/EVE_SOTA_EMBEDDING_PRICING_2026-09.md`). The binding rests on
price and data posture; retrieval relevance is still unmeasured and is owned by
task 3.5, which may re-bind.
Task 15.1 gave every leg a capability contract, including the legs Eve does not
have (`docs/audits/EVE_SOTA_MODEL_LEG_CONTRACT_2026-09.md`): two
operator-configured speech legs and three not-admitted ones joined the four
bound legs. Re-pricing the chat legs from the endpoint feed under unchanged pins
also measured real auction drift since capture — the turn leg's input price rose
11.2% and the escalation ladder's output price rose 36.6% while its input price
fell 9.0%, the floor moving from GMICloud to Novita. Those are the auction
moving, not a re-bind.
## Reproduction command catalog
Run all commands from the repository root at checkout
`778b9c874163fe9f958cfb44b54b23ab2b444eff`. Historical evidence commits are
named beside the affected tables above. Live commands observe mutable local
state and therefore reproduce the query, not necessarily the captured output.
### `C0` — checkout identity
```bash
git rev-parse HEAD
```
### `C1` — tool grouping and prompt bytes
```bash
jq '{promptBytesHash,promptBytesComponents}' docs/audits/eve-smx-ratchet.json
jq -r '.entries[] | select(.kind=="tool-definition") | .source.file' \
docs/audits/EVE_BUILDER_PROMPT_INVENTORY_2026-08.json \
| sort | uniq -c | sort -nr
```
### `C2` — family and Wilson floors
```bash
jq '{familyFloors,familyFloorsSource,builderWilsonFloors,builderWilsonFloorsComment,telemetryFloors}' \
docs/audits/eve-smx-ratchet.json
```
Baseline family runs are reproducibly derived as `cases * 3`, where the
ratchet's `familyFloorsSource` names `k=3`; summing the derived runs gives the
recorded deck total.
### `C3` — cost, cache, and latency evidence
```bash
jq '{generatedAt,baseCommit,liveModelVerification,weeklyEvidenceLifecycle}' \
docs/audits/eve-phase-11/2026-08-30-run.json
jq '{capturedDate,sourceCommit,costReport,sameDayRouteCalibration,remedy,decision}' \
docs/audits/eve-smx-weekly/2026-08-23-follow-up.json
```
### `C4` — workbench views and agent MCP
```bash
jq '{generatedAt,baseCommit,registry,phase7StrictBrowserBattery,phase8}' \
docs/audits/eve-phase-7-8/2026-08-30-run.json
```
### `C5` — invocation inventory
```bash
jq '{schemaVersion,contentHash,siteCount,pointCount:(.points|length),bySurface:(.points|group_by(.id|split(".")[0])|map({surface:.[0].id|split(".")[0],points:length,sites:map(.files|length)|add}))}' \
apps/oshun/bff/src/assistant/generated/assistant-invocation-inventory.json
```
### `C6` — tour catalog
```bash
pnpm --dir libs/oshun/shell-assistant exec tsx -e \
"import {CURATED_ASSISTANT_TOURS as t} from './src/tour-plans.ts'; console.log(JSON.stringify({total:t.length,byAudience:Object.fromEntries(['customer','studio','admin'].map(a=>[a,t.filter(x=>x.audience===a).length])),steps:t.reduce((n,x)=>n+x.steps.length,0)}))"
```
### `C7` — model registry
```bash
pnpm --dir apps/oshun/bff exec tsx -e \
"import {ASSISTANT_MODEL_REGISTRY as r} from './src/assistant/model-registry.ts'; console.log(JSON.stringify({total:r.length,bound:r.filter(x=>x.status==='bound').length,unbound:r.filter(x=>x.status==='unbound').length,entries:r}))"
```
### `C8` — memory posture
```bash
rg -n 'OPERATOR_MEMORY_CATEGORIES|SLOT_CEILINGS|resolveOperatorMemoryEnabled|operatorMemoryEnabled|assistant_operator_memory' \
apps/oshun/bff/src/assistant/operator-memory.ts
```
### `C9` — voice and selection source surfaces
```bash
rg -l 'data-admin-selection-scope=' apps/oshun/admin/src/components --glob '*.tsx'
rg -n 'data-admin-selection-scope=|Start voice input|Enable voice output|Dictate a message|Play this reply aloud' \
apps/oshun/web/src/components/assistant/AssistantPanel.tsx \
apps/oshun/admin/src/components
```
### `L1` — local queue, leases, memory, and pgvector
```bash
docker exec oshun-dev-postgres psql -U oshun -d oshun_dev -X -v ON_ERROR_STOP=1 -Atc \
"WITH s AS (SELECT status, count(*)::int n FROM work_item GROUP BY status) SELECT jsonb_build_object('workItems', COALESCE(sum(n),0), 'byStatus', COALESCE(jsonb_object_agg(status,n), '{}'::jsonb), 'queueEligible', COALESCE(sum(n) FILTER (WHERE status='ready'),0), 'leasedOrInProgress', COALESCE(sum(n) FILTER (WHERE status IN ('leased','in-progress')),0)) FROM s;"
docker exec oshun-dev-postgres psql -U oshun -d oshun_dev -X -v ON_ERROR_STOP=1 -Atc \
"SELECT jsonb_build_object('leaseRows', count(*), 'live', count(*) FILTER (WHERE (lease->>'expiresAt')::timestamptz > clock_timestamp()), 'expired', count(*) FILTER (WHERE (lease->>'expiresAt')::timestamptz <= clock_timestamp()), 'holders', count(DISTINCT lease->>'agentId')) FROM work_item WHERE lease IS NOT NULL AND status IN ('leased','in-progress');"
docker exec oshun-dev-postgres psql -U oshun -d oshun_dev -X -v ON_ERROR_STOP=1 -Atc \
"SELECT jsonb_build_object('memoryRows', (SELECT count(*) FROM assistant_operator_memory), 'operators', (SELECT count(DISTINCT operator_sub) FROM assistant_operator_memory), 'categories', (SELECT count(DISTINCT category) FROM assistant_operator_memory), 'vectorVersion', (SELECT extversion FROM pg_extension WHERE extname='vector'));"
for eve_runtime_name in OSHUN_ADMIN_DATABASE_URL OSHUN_V1_DATABASE_URL OSHUN_ASSISTANT_OPERATOR_MEMORY; do
if printenv "$eve_runtime_name" >/dev/null; then
echo "$eve_runtime_name=set"
else
echo "$eve_runtime_name=unset"
fi
done
```
### `L2` — local services
```bash
docker ps --format '{{.Names}}|{{.Image}}|{{.Status}}|{{.Ports}}'
for eve_probe_port in 6379 9000 9001 6333; do
if timeout 1 bash -c "/dev/null; then
echo "tcp:$eve_probe_port=reachable"
else
echo "tcp:$eve_probe_port=unreachable"
fi
done
docker exec oshun-dev-redis redis-cli ping
```
### `L3` — local executables and harnesses
```bash
node --version
pnpm --version
blender --version
adb --version
adb devices -l
maestro --version
codex --version
claude --version
pnpm --dir apps/oshun/web exec playwright --version
pnpm --dir apps/oshun/web exec node --input-type=module -e \
"import {chromium,firefox,webkit} from 'playwright'; import {existsSync} from 'node:fs'; console.log(JSON.stringify(Object.fromEntries(Object.entries({chromium,firefox,webkit}).map(([k,v])=>[k,{path:v.executablePath(),exists:existsSync(v.executablePath())}]))));"
```
### `L4` — required Unreal path
```bash
test -x /root/workspace/UnrealEngine-5.5/Engine/Binaries/Linux/UnrealEditor-Cmd
runuser -u ueagent -- \
/root/workspace/UnrealEngine-5.5/Engine/Binaries/Linux/UnrealEditor-Cmd -Version
```
The second command is expected to report the engine version and then exit red on
this host's missing Vulkan/display device; availability and runnable rendering
are deliberately separate facts.
### `L5` — name-only local provider configuration
```bash
stat -c '%a %n' /root/Desktop/workspace/drawer/env-master.env
(
set -a
. /root/Desktop/workspace/drawer/env-master.env
set +a
for eve_key_name in OPENROUTER_API_KEY DEEPGRAM_API_KEY OPENAI_API_KEY ELEVENLABS_API_KEY CARTESIA_API_KEY; do
if [ -n "${!eve_key_name:-}" ]; then
echo "$eve_key_name=set"
else
echo "$eve_key_name=unset"
fi
done
)
```
This command prints variable names and set/unset state only. It must never be
changed to print lengths, prefixes, hashes, or values into committed evidence.