What IronClaw actually ships to Trace Commons under each consent posture.
These are REAL envelopes produced by IronClaw's redaction pipeline
(ironclaw-reborn traces preview, ironclaw main @ 2026-07-10), all from the
same synthetic recorded conversation (01-recorded-trace-input.json) — an
agent asked to email a budget file, deliberately salted with PII: a private
email address, a local file path, a phone number, and a SendGrid bearer token.
| File | Flags | What ships |
Status: roadmap / planning. No implementation. V1 remains exactly as launched — Aave-only, human-approved, click-based. Everything below the V1 boundary is future, gated work tracked as separate issues/cards; nothing here enables autonomous or live agent execution.
The product direction after V1 is **observe and recommend first; execute later,
Status: conceptual foundation. This document defines the core mental model behind Agentic Somm. It is evergreen and audience-neutral — the V1, roadmap, and policy specs cite it rather than restate it.
In legacy Somm, the unit of composition was the strategist. A strategist composed an arbitrary set of positions into a single synthetic position that
| name | parallel-pr-review |
|---|---|
| description | Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting. |
Review many open PRs at once by fanning out one read-only review subagent per PR (or per stack), each producing a structured verdict, then synthesizing a cross-PR summary and posting reviews. The reviewer (you) stays in the loop holding conclusions; subagents absorb the per-diff reading.
| # Zebra #5709 — request-trace capture (exp/5709-instrument-request) | |
| # | |
| # Config: download_concurrency_limit=50, stall_restart_timeout=0s (stall detector OFF) | |
| # Build: zmanian/zebra@exp/5709-instrument-request (full fix stack + REQUEST-entry logging) | |
| # State at capture: verified_height=1,732,187, continuous_height=1,732,187, next_height=1,732,190 (gap=3) | |
| # | |
| # Stuck blocks (per blockchair canonical): | |
| # 1,732,188 hash=000000000192c57103c7f8d821b000e8637870b7408af3ae9b624483095a05a7 | |
| # 1,732,189 hash=000000000109efac976b4cca733d50b222aa6eca5eef5f1555f2f6c519ffb037 | |
| # |
| # Zebra issue #5709 — instrumented binary capture | |
| # | |
| # Build: zmanian/zebra@exp/5709-instrument-lifecycle (info-level dbg5709 lifecycle) | |
| # Host: GCP c4-standard-24, mainnet, network_upgrade=Nu5 (sandblasting era) | |
| # State at capture: verified_height=1732115, continuous_height=1732116, processing_next=1732115 | |
| # | |
| # Critical finding: block 1,732,117 NEVER appears in any dbg5709 event | |
| # - Not in: downloaded | |
| # - Not in: queue_block (neither accepted nor rejected) | |
| # - Not in: verifier |
| 16:20:25 cont=1732124 verified=1732115 next=1732115 max=1733509 slots=845 waiting=1247 inflight=272 downloaded=1247 | dropped: alreadyq=9 noheight= minh= maxh= cancelV=1005 | |
| 16:20:55 cont=1732124 verified=1732115 next=1732115 max=1733509 slots=891 waiting=1418 inflight=369 downloaded=1418 | dropped: alreadyq=9 noheight= minh= maxh= cancelV=1005 | |
| 16:21:25 cont=1732124 verified=1732115 next=1732115 max=1733509 slots=891 waiting=1418 inflight=369 downloaded=1418 | dropped: alreadyq=9 noheight= minh= maxh= cancelV=1005 | |
| 16:21:55 cont=1732124 verified=1732115 next=1732115 max=1733509 slots=891 waiting=1418 inflight=261 downloaded=1418 | dropped: alreadyq=11 noheight= minh= maxh= cancelV=1005 | |
| 16:22:25 cont=1732124 verified=1732115 next=1732115 max=1733509 slots=891 waiting=1418 inflight=261 downloaded=1418 | dropped: alreadyq=11 noheight= minh= maxh= cancelV=1005 | |
| 16:22:55 cont=1732124 verified=1732115 next=1732115 max=1733509 slots=891 waiting=1418 inflight=261 downloaded=1418 | dropped: alreadyq=11 noheight= minh= ma |
This is a write-up of debugging a zebrad mainnet initial sync that wedged repeatedly at ~42% on otherwise perfectly-spec'd hardware. The summary up front: it's a real upstream bug ([ZcashFoundation/zebra#5709][issue]) and the ZEBRA_SYNC__CHECKPOINT_VERIFY_CONCURRENCY_LIMIT knob (NOT the two knobs the name implies you'd reach for) is the fix that actually moves the needle.
If you're hitting the same symptom, scroll to "What actually worked." If you want the diagnostic walk, read on.
| // -*- mode: Bluespec; -*- | |
| module CrosslinkBaselineStableModel { | |
| /* | |
| Baseline Crosslink fixes the current/sticky Tenderlink behavior: | |
| - sigma is fixed outside this focused model; | |
| - proposals sample the current PoW stream; | |
| - a nil-precommit quorum advances the round but does not resample or unlock | |
| same-round Tendermint state. |
name: notion-repo-report description: Generate a Notion activity report for a git repo covering a time period (default 24h). Includes a human-friendly summary, detailed workstream breakdown with GitHub links, open PR activity, and stats. Optionally publish under a specified Notion parent page. triggers: