Live Continuous 3-Run Proof
This page is the public evidence for the reopened roadmap claim: AgentXchain completed three back-to-back governed runs from a project-local VISION.md with no manual accept-turn, no manual gate approval, no HUMAN-ROADMAP edits mid-session, and at least one real-credential turn per run.
Date of proof: 2026-04-18
Latest checked-in evidence artifact: examples/live-governed-proof/evidence/continuous-3run-proof.latest.json
What It Is
- Category: live proof example
- Surface:
agentxchain run --continuous - Runtime shape:
local_cliauthoring roles + realapi_proxyQA review - Credentialed provider: Anthropic (
claude-haiku-4-5-20251001) - Source harness:
examples/live-governed-proof/run-continuous-3run-proof.mjs
Workflow Or Proof Shape
The proof used a temp governed repo with a project-local VISION.md containing three distinct goals:
capture alpha ledger evidence trailcapture beta provenance dashboard slicecapture gamma escalation recovery drill
Each governed run used the truthful mixed-runtime shape:
pmanddevauthored repo-local artifacts throughlocal_cliqaran through a real Anthropic-backedapi_proxyruntime inreview_onlymoderun --continuousderived the next intent fromVISION.md, auto-triaged it via--triage-approval auto, and advanced through planning, implementation, and QA without operator input
run-agents.sh is now documented as the raw fallback path. run --continuous is the primary product surface for lights-out operation.
Exact Command
agentxchain run --continuous --vision .planning/VISION.md --max-runs 3 --poll-seconds 30 --triage-approval auto
Observed harness invocation:
set -a; source .env; set +a
node examples/live-governed-proof/run-continuous-3run-proof.mjs --json --output examples/live-governed-proof/evidence/continuous-3run-proof.latest.json
Evidence Summary
| Metric | Value |
|---|---|
| Session ID | cont-0f7fc528 |
| Started | 2026-04-18T17:18:40.792Z |
| Finished | 2026-04-18T17:19:28.530Z |
| Wall clock | 47.738s |
| Runs completed | 3 |
| Final session status | completed |
| Total cumulative spend | $0.023 |
| Provider / model | anthropic / claude-haiku-4-5-20251001 |
| CLI version | 2.134.1 |
| Blockers hit | none |
VISION.md changed | no |
| Evidence artifact | examples/live-governed-proof/evidence/continuous-3run-proof.latest.json |
Session Snapshots
Before the command started, .agentxchain/continuous-session.json did not exist.
Initial snapshot after the session materialized:
{
"session_id": "cont-0f7fc528",
"started_at": "2026-04-18T17:18:41.551Z",
"vision_path": ".planning/VISION.md",
"runs_completed": 0,
"max_runs": 3,
"idle_cycles": 0,
"max_idle_cycles": 3,
"current_run_id": null,
"current_vision_objective": null,
"status": "running",
"per_session_max_usd": null,
"cumulative_spent_usd": 0,
"budget_exhausted": false
}
Final snapshot:
{
"session_id": "cont-0f7fc528",
"started_at": "2026-04-18T17:18:41.551Z",
"vision_path": ".planning/VISION.md",
"runs_completed": 3,
"max_runs": 3,
"idle_cycles": 0,
"max_idle_cycles": 3,
"current_run_id": "run_bb868ab3f3e4e947",
"current_vision_objective": "Proof Queue: capture gamma escalation recovery drill",
"status": "completed",
"per_session_max_usd": null,
"cumulative_spent_usd": 0.023,
"budget_exhausted": false
}
Per-Run Evidence
Turn counts below are derived from accepted .agentxchain/history.jsonl entries grouped by run_id, which is the truthful per-run count for this session.
| Run | Vision goal | Trigger | Model used | Accepted turns | Spend | QA artifact |
|---|---|---|---|---|---|---|
run_22f4e44f4ae40444 | Proof Queue: capture alpha ledger evidence trail | vision_scan | claude-haiku-4-5-20251001 | 3 | $0.008 | .agentxchain/reviews/turn_acfcde845070de1d-qa-review.md |
run_4e5642ada3bf8872 | Proof Queue: capture beta provenance dashboard slice | vision_scan | claude-haiku-4-5-20251001 | 3 | $0.008 | .agentxchain/reviews/turn_58cc45c192891f24-qa-review.md |
run_bb868ab3f3e4e947 | Proof Queue: capture gamma escalation recovery drill | vision_scan | claude-haiku-4-5-20251001 | 3 | $0.007 | .agentxchain/reviews/turn_a9de0726ac118b1c-qa-review.md |
Every run carried the same provenance shape:
trigger: "vision_scan"created_by: "continuous_loop"- a distinct
intake_intent_id
Git Log Evidence
git log --oneline from the proof repo shows run-derived commits for all three runs, and every run-derived commit includes the session trailer Continuous-Session: cont-0e280ba0.
423084a proof(implementation): run_bb868ab3f3e4e947 proof-queue-capture-gamma-escalation-recovery-drill
3d6f9c8 proof(planning): run_bb868ab3f3e4e947 proof-queue-capture-gamma-escalation-recovery-drill
94f9e02 proof(implementation): run_4e5642ada3bf8872 proof-queue-capture-beta-provenance-dashboard-slice
3b39532 proof(planning): run_4e5642ada3bf8872 proof-queue-capture-beta-provenance-dashboard-slice
1128158 proof(implementation): run_22f4e44f4ae40444 proof-queue-capture-alpha-ledger-evidence-trail
fdb5200 proof(planning): run_22f4e44f4ae40444 proof-queue-capture-alpha-ledger-evidence-trail
c1950de init proof repo
Example commit trailer:
Continuous-Session: cont-0f7fc528
Co-Authored-By: GPT 5.4 (Codex) <[email protected]>
Notes
- No blocker or escalation fired during the clean run.
- No manual gate approval was needed because the continuous loop executed with auto-approval enabled for gate handling.
- The project-local
VISION.mdremained unchanged throughout the session. - A pre-proof harness hardening pass was required earlier on
2026-04-17; that exploratory run is not counted as the public proof. The evidence on this page is from the subsequent clean rerun above.
Run It
export ANTHROPIC_API_KEY=...
node examples/live-governed-proof/run-continuous-3run-proof.mjs --json --output examples/live-governed-proof/evidence/continuous-3run-proof.latest.json
The harness creates a temp governed repo, runs the exact run --continuous command shown above, and prints the evidence as JSON. Use --output <path> to persist the evidence artifact to a checked-in file. Use --keep-temp when you want to inspect the proof repo's .agentxchain/ artifacts and git history afterward.
Key Takeaways
- The strongest marketing claim now has public evidence: one unattended continuous session completed three governed runs with real provider-backed QA review.
run --continuousis the primary lights-out path;run-agents.shis only the raw fallback.- The proof leaves durable provenance in three places at once:
continuous-session.json,run-history.jsonl/history.jsonl, and git commit trailers.