AGENTS.md watermarks refreshed to HEAD (79a93d4).
Grooming: closed 2 prediction/actioned issues.
- #1179: /stakestake fix verified working in post-fix user-test (2026-03-27)
- #1177: fresh red-team session 2026-03-27 with 7 real attacks (floor_held)
Remaining open: #1166, #1141 (prediction/backlog, planner watching),
#857, #856, #383 (vision).
No blocked issues, no open PRs, no stale PRs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
AGENTS.md watermarks refreshed to HEAD (7d72f40).
landing/AGENTS.md: document new pitch-deck.html (influencer outreach).
Grooming: CLEAN — 5 open issues (2 prediction/backlog, 3 vision), no
backlog issues, no blocked issues, no open PRs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
AGENTS.md watermarks refreshed to HEAD (4dedc72). Watermark bump only —
no code changes since last gardener run.
Pending actions (3): re-queue promotion of #1155 pitch-deck to backlog
(pending actions from PR #1162 were not executed by orchestrator).
Escalate: #1158 (Phase 1 completion accuracy) — still needs planner/human decision.
- Update all AGENTS.md watermarks to HEAD (b276392)
- Clean up dust.jsonl: remove already-bundled items (601,627,739,741)
- Pending actions: promote #1099/#1100/#1101 to backlog, close stale
prediction issues #1020/#1103/#1107, comment on partial resolution
of #1022 (holdout resolved, user-test still empty)
Add formulas/AGENTS.md documenting sense vs act type distinction,
cron conventions, step ID naming rules, TOML structure skeleton,
and a how-to-add-a-new-formula walkthrough.
Add scripts/harb-evaluator/AGENTS.md covering the evaluator runtime:
directory layout, exit code convention, stack lifecycle, evidence
output, and how to add a new evaluator script.
Update root AGENTS.md directory map to link both new files.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implement the attack catalogue loop (step 5a) in red-team.sh that was
previously a forward spec in the formula. The loop replays every *.jsonl
attack file through AttackRunner.s.sol with snapshot revert between files,
records LM total ETH before/after each attack, and injects results into
the adversarial agent prompt so it knows which strategies are already
catalogued.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add CANDIDATE env var support to bootstrap-light.sh. When set to a
.push3 file path, the script:
1. Invokes push3-transpiler to regenerate OptimizerV3Push3.sol
2. Extracts the function body into OptimizerV3Push3Lib.sol
3. Deploys contracts normally via DeployLocal.sol
4. Deploys OptimizerV3 and upgrades the UUPS proxy via upgradeTo()
Also updates formulas/run-red-team.toml to reflect the implementation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add `cleanup` step: removes per-generation candidate files and
generation_*.jsonl records after they are aggregated into the evidence
file, preventing disk exhaustion (cf. run #1025 at 91% usage).
- Rewrite `deliver` step with mandatory ordering:
1. `git checkout -- .` to discard unrelated working-tree modifications
before staging result files (evidence JSON, champion .push3, manifest).
2. Commit to branch `evidence/evolution-run-{run_id}` (not directly to main).
3. Push and create PR — if this fails, post an error comment and leave the
issue OPEN; do not proceed to step 4.
4. Post summary comment only after PR URL is confirmed, with mandatory
link to the PR.
- Update `products.evidence_file` delivery to PR branch (was "commit to main").
- Update `products.issue_comment` to enforce ordering and non-close-on-failure.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add scripts/harb-evaluator/run-resources.sh: collects disk, RAM,
Anthropic API usage, and Woodpecker CI queue metrics
- Add scripts/harb-evaluator/run-protocol.sh: collects TVL, fees,
position data, and rebalance events from LiquidityManager
- Fix run-protocol.toml: positions accessed via positions(uint8) not
named getters (floorPosition/anchorPosition/discoveryPosition)
- Fix event signature: Recentered(int24,bool) not Recenter(int24,int24,int24)
Addresses review findings: missing implementation files and contract
interface mismatch.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Address review feedback:
- Remove candidate input (Push3 transpilation not wired; documented in
notes.candidate_injection as planned follow-up)
- Mark run-attack-suite step as status="planned" with run_attack_suite_gap note
- Update execution.invocation to only pass env vars red-team.sh actually reads
- Fix export-vectors args to include --eth-extracted and --eth-before flags
- Clarify export-vectors only runs when floor_broken (BROKE=true)
- Document tmp/red-team-snapshots.jsonl (AttackRunner replay side output)
- Add comment that {attack_type} in products.attack_vectors.path is
runtime-computed by promote-attacks.sh, not a formula input
- Fix schema comment notation (§ → ##)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add formulas/run-user-test.toml — a sense-only process definition for
persona-based UX evaluation. Defines 5 personas across 2 funnels
(passive-holder: tyler/alex/sarah; staker: priya/marcus), full stack
lifecycle (start → run → collect → stop → deliver), and the three
standard evidence delivery products (evidence JSON committed to main,
screenshots referenced in evidence, summary as issue comment).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
