Real bounded Tech/Dev Hermes pilot (experimental, NOT enabled)
Owned files only in infra/hermes-pilot; no existing core, module, tracer, profile or runtime config changed. No push/deploy/RELEASE_AUTHORIZE. Do not wire this into the existing tracer completion endpoint: that endpoint deliberately accepts only deterministic JSON.
Fixed task and boundaries
Task tech-dev-clamp-quantity-v1: produce one <=2048-byte Python clamp_quantity(quantity) implementation, integer range 0..99. No input/browser prompt is accepted. The model has zero tools, no shell/browser/Git/deploy credentials. Trusted code alone writes quantity.py, runs separate AST-allowlisted QA (9 boundary cases), and commits an isolated, remote-free fixture repository. This is real generated-code QA, not application QA. Source commit is recorded as provenance, not represented as the fixture's base commit.
infer.py uses installed run_agent.AIAgent, verified from the installed signature and agent/agent_init.py; enabled_toolsets=[] is additionally enforced by asserting empty agent.tools. Existing approved OPENAI_API_KEY is read in memory only; no messaging/API-server credentials/auth pools copied. Separate temporary HERMES_HOME, no memories/context/background review/fallback. Provider/model pinned to current canina-hermes custom, https://nr.parsaaghayi.ir/v1, Free; no provider installation or account changes. Existing configs remain untouched. Model output is untrusted and never directly shell-executed; QA rejects all syntax except the single nested min/max return expression before isolated Python execution.
Installed image identity: sha256:373ddd5e6649f525b17993e1c885cdf1352127f8e98fd329140a73237125e52f, install stamp commit 818c13be1dc4fd28987e1e881a9408224afd4535, v0.21.6. Discovery: /opt/hermes/hermes chat --help supports --oneshot, --max-turns, --run-budget; /opt/hermes/.venv/bin/python loads installed API. Official skills and https://hermes-agent.nousresearch.com/docs/llms.txt consulted. The initially guessed developer API docs URL returned404; installed source/signature is authoritative for this pinned build.
PREPARE mapping — parent integration required
executor.execute(lease, artifact_root, infer, heartbeat) only accepts a fresh staging, first-attempt, 20-cent, 40hex-source lease and exact lease fields; heartbeat failure aborts before inference and before QA/commit. Trusted adapter must obtain this lease via existing authenticated claim AFTER independent Gate1/READY, verify the explicitly allowlisted task identity/scope/criteria server-side, and supply heartbeat connected to the authenticated backend. A caller-created dict is NOT an authorization. Never expose this Python interface to browser requests.
Budget: one model inference, max_iterations1/max_tokens160, model run budget15s, process kill18s, QA3s; outer rehearsal kill28s. The18s kill is inside docker exec so killing its client cannot leave inference running. No retries. 20-cent core reservation MUST remain reserved for unknown billing; there is no measured-dollar guarantee from this provider, so live admission must remain disabled until provider-side pricing/cost cap is independently verified. Do not reconcile to0 or claim full end-to-end success. No Stage evidence/Gate2/release calls exist.
rehearse.py is explicitly disposable: synthetic lease IDs/heartbeat local deadline, never calls core, never claims real Gate1. Run from repository root: timeout 28s python3 infra/hermes-pilot/rehearse.py. This is NOT a supported live adapter. Parent must preserve lease fencing and heartbeat across any longer runner and implement trusted artifact ingestion/new report verification rather than bypass tracer validation.
Actual evidence and blockers
Evidence directory /opt/services/canina/validation/v4-real-pilot:
red.log: missing executor assertion failed before implementation.inference-private.log: actual installed Hermes/provider inference exit0 under75s diagnostic ceiling; generated source saved, not fabricated. This ceiling was ONLY diagnostic, not accepted as a PREPARE lease run.model-artifact/quantity.py: actual model artifact; independent QA passes9 cases, SHA2560125246b551896c5f9ee98fabeb02982a6690a9974c0eb24ef3ae676d46380d5; isolated Git commit95cb3d27d636ae817d6a778e8053e2f87b50e57b.actual.log: bounded full rehearsal failed with inner timeout exit137 at18s; no completion/QA success was assumed. Previous client-only timeout was corrected to inner process kill. Installed model/startup cannot currently complete reliably inside30s PREPARE lease without authenticated ongoing heartbeat. Do not extend lease locally or call the75s diagnostic a bounded lease success.
Contract tests: python3 infra/hermes-pilot/test_contract.py. Parent still owns backend integration, authenticated heartbeat orchestration, allowlist admission, billing caps, signed artifact transport and Stage CI. This commit is a real generation/independent-QA proof and fail-closed executor seam, not a live autonomous Tech department or released product.