ROUND 360 — CorpPilot seeded artifacts, traffic and dry-run boundary
Captured: 2026-09-06T09:23:44.004738+00:00

RESULT
CorpPilot supplies orchestration source and real-provider adapters, but the inspected demo can produce project artifacts, test-success markers and token accounting without a model run. No actual full-team run archive was found. Classify as a Chinese-language implementation lead, not 46 verified working agents.

PRIMARY SOURCE
https://github.com/xiaoyangtx996/CorpPilot
Pin: 6b5e7041d236c6dcfe25b44e0e9c627c2c18805e
Complete recursive tree: 164 entries, not truncated.
Its author linked it from https://linux.do/t/topic/2636562?page=6 (post102). That is distinct from the company pipeline in the same thread and from the following commenter's personal three-agent attempt.
README says 46 agents in 13 departments. The actual tree has 13 department SOUL.md files and 34 role files, totaling 47 definition files. These definitions are not a runtime roster; the discrepancy need not mean fraud. The README's install example still uses your-org placeholders and references install.sh, absent from this pinned tree. Runtime data directories contain .gitkeep files rather than a published task/event corpus.

DEMO PROVENANCE
scripts/demo_greenfield.py explicitly seeds:
- a short idea brief and PRD;
- fixed HTML mockup/design selection and implementation HTML;
- a minimal app.py;
- .tests_passed containing ok, written directly by the seed function.
Thus this marker in a demo artifact is not evidence that tests ran. The script can auto-approve gates when requested. It is an explicitly labeled demonstration, not evidence of fabricated real results.
scripts/traffic_seed.py contains six fixed records with agent/department/step/model labels, token counts and latencies. It computes costs from a hardcoded price table and timestamps entries two minutes apart starting one hour before seeding. The optional --seed-traffic path writes these to traffic_logs.jsonl. These are synthetic accounting data; neither their model names nor costs prove provider activity or current prices.

REAL CAPABILITY AND DRY RUN ARE DISTINCT
scripts/runtime/execution_backends.py:
- Default backend selection is agent_loop, which delegates to an AgentManager.
- ClaudeCodeBackend can invoke an installed CLI and save stdout/stderr.
- If CORPPILOT_CLAUDE_DRY_RUN is enabled, it writes a dry-run prompt artifact and returns success without invoking the CLI.
scripts/demo_claude_code.py enables that dry-run mode by default; --real explicitly selects a CLI call. Its JSON labels dry_run, so there is no need to infer real execution from a success boolean alone.
scripts/runtime/llm_client.py includes actual OpenAI-compatible and Anthropic request paths. We did not call them. Presence of callable machinery is meaningful implementation evidence, but no retained live output was supplied by these files.

DEVELOPMENT REPORT / EXTERNAL SEARCH
.codex/verification-report.md self-dates March18 and claims compilation, 11 tests and a health check after text-encoding cleanup. It is a developer verification summary with self-assigned scores, not a multi-agent work transcript. We did not rerun its checks.
GitHub all-state issues endpoint returned an empty array. Targeted search found the known author's forum link and unrelated namesakes, not a new operator trace. This is a scoped negative, not proof nobody uses the project.

NEXT
Close this source-only branch unless public task logs or a concrete operator incident emerges. VOKO remains the next independent lead. No connection established to Edict, XZ, or any lab merely from Chinese corporate-role vocabulary or common dashboard conventions.

METHOD / RETENTION
360-private retains pin/tree, README, selected demo/runtime source, verification report and empty issue result. Files read as data only: no target code, skill, model, test, registration or message executed. Raw captures remain private; report is sanitized. No new infrastructure required.
Previous goal turn: progress through Clowder incident provenance audit. Current: resolved another candidate and identified exact synthetic-output fingerprints. Goal remains active; zero confirmed escaped actors unchanged.