kairos-chain 3.69.0 → 3.73.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4277c267574d3ac35dc096a5a6ce3371e074a89d6840a7274d5c3c81397cd643
-  data.tar.gz: 0a07d054c3f1c3266d63184bf35e29239b91fcfacbebe3a2bbc2290603aca200
+  metadata.gz: 4344b2bf968bbb0b650c672522c8abdee9ae34daea4f06899e60cfaf815fa489
+  data.tar.gz: e2a99d727e1ca7d404ecdd0945c29e9964220b1ec8aaca8be44f46c55b9a5e77
 SHA512:
-  metadata.gz: f40163bd119d1d39c20ac8c986e05fed26e38c445fe7454afb72d35c80f03df8282122674f50d2fc5183261cb8f5a87ec50b1ca71e5ed1a9711cd2a6a007e2c2
-  data.tar.gz: b12d79ed73d1bc51a00dc7910be24903b53fca4a5c6d6a1549e4c7cf5bb4b384552a0af7af284e40fa0d220cfdf94e879c433f91c418ffb357d8e890c96a4215
+  metadata.gz: 9d47b320473eb188dcc9f57655f11cd152ce0cee6e160c714396ebcd508156a5696c0c0db8eeb7ace61956cfc5e61467507a051ce6d200552d95ebe3a7f9ebf1
+  data.tar.gz: e38d3d417efb9be7c9e0274d9aca36ba7c1fd062f7ef0ecfc204536f86c99a9bbbbf025a52ee31525caab67b94a3dba88c41fcd3ab9d49313d6a609b10a2e0f8

data/CHANGELOG.md

@@ -4,6 +4,257 @@ All notable changes to the `kairos-chain` gem will be documented in this file.
 
 This project follows [Semantic Versioning](https://semver.org/).
 
+## [3.73.0] - 2026-08-17
+
+### Fixed
+
+- **Round 2 of the same review returned 0 APPROVE of 3 valid seats and thirteen
+  more blocking findings, three of them saying round 1's fixes did not hold. The
+  response was to subtract.** Two of the six guards round 1 added are removed
+  rather than repaired. The `-o` output path is deleted: guarding it by comparing
+  resolved paths failed three ways — a case-only difference on a case-insensitive
+  filesystem, a hardlink, and any read input the check did not enumerate, which
+  included every L2 context and `config/pm.yml` — and each failure destroyed the
+  memo while the run printed that nothing had been written to it. The page now
+  always goes to `<data dir>/log/pm_l2_report.html`, beside the data directory so a
+  relocated instance still finds it, and under a name the operator's own `.gitignore`
+  already knows how to handle. The carried `exclude` is
+  also removed: carrying it was itself a round-1 fix, and since an exclude term is
+  a substring of document names while an inferred term is usually the item's own
+  record name, it suppressed the item's own primary record. It still applies to
+  the authored terms it was written beside, and the row says when it was not
+  applied.
+- **The anti-flood cap bounds the row, not only each term.** Twelve terms each
+  under the twenty-document cap unioned to 124 of 1179 documents for one item, and
+  a note of the ordinary shape reached 23. A row over the cap is refused rather
+  than truncated, because truncation is silent and moves `last_activity` and the
+  headline figures with it; the row reports how many its terms reached.
+- **Paths are derived from the script's own location** instead of by appending a
+  literal `.kairos`, which had reported a populated instance as empty at exit 0 on
+  every session of a relocated data directory. **A row with no comparison names
+  which of five things is missing**, separating an unparseable L2 date from an
+  unparseable memo marker, because they blame different files and collapsing them
+  stated a false fact for the second time. **Nested store shapes are checked**, not
+  only their absence: a `projects` or `items` value that was truthy and not an
+  object reached `.values()` and raised.
+- **The test file is rewritten, not extended.** An audit applied 65 one-line
+  mutations to the round-1 suite and 36 survived — the whole of `main`'s wiring,
+  all cross-item aggregation, and the impossible-date guard the suite was named
+  for, whose fixture built a second document matching the same term so the valid
+  date sorted last and the impossible one never reached the parse point. 53 cases
+  now, and of the 30 mutations that map to a reported finding 29 are killed; the
+  survivor is equivalent. Four habits are stated in the file: exercise guards
+  through `main` in a subprocess, check that a fixture cannot satisfy its own
+  assertion, build several rows when testing aggregation, and assert messages and
+  exit codes by content. Nothing runs the suite automatically — `rake test`
+  collects Ruby files only.
+- **Accepted rather than fixed, and recorded where they happen.** A context
+  declaring a parseable but absurd date such as `9999-12-31` flattens the other lag
+  bars, which is what bars relative to the widest lag mean. And what the report
+  says still depends on which `python3` resolves, since `date.fromisoformat`
+  accepts basic format from 3.11. Separately, two stale `.pyc` files sit inside one
+  installed SkillSet from earlier runs, so its `content_hash` differs from a clean
+  tree's; nothing here removes them.
+- Live data after the change: 28 of 28 items comparable, 19 with L2 more recent,
+  median 29 days, widest 81 — identical to before, so nothing the subtraction
+  removed was carrying coverage.
+
+## [3.72.0] - 2026-08-17
+
+**Built and never published.** Its contents ship in 3.73.0, which carries the second round of fixes to the same feature; the entry is kept because the commits it describes are in the history.
+
+### Fixed
+
+- **Six defects in the session-start report below, all found by a pre-release
+  multi-LLM review and all demonstrated by running code rather than reasoning
+  about it.** The review returned 0 APPROVE of 3 counted seats. Two of the five
+  invariants the change declared were false as stated, which is why they are
+  listed here rather than deferred.
+  - *The read-only promise was prose.* `open(out, "w")` accepted any path, so
+    `-o <memo>` truncated `store.json` while the run printed that nothing had been
+    written to it. The output path is now refused if it resolves to the memo or
+    the mapping, via `realpath`, so a symlink cannot walk around it.
+  - *A read-only report changed the SkillSet's chain-recorded hash.*
+    `exec_module` writes bytecode, and `scripts/__pycache__/l2_scan.cpython-310.pyc`
+    landed inside the SkillSet directory — inside `Skillset#all_file_hashes`, hence
+    inside `content_hash`, hence inside what `skillset_manager` records as
+    `skillset_event` and verifies with `raise SecurityError`. The recorded hash was
+    a function of the local CPython build and of whether the report had run.
+    `sys.dont_write_bytecode` is now set around the import.
+  - *The anti-flood guard was capped on one tier only.* A document's name is
+    `name:` or `title:` or its basename, and 321 of 1177 contexts take it from a
+    free-text `title:`. One context titled `Review` made `review` a search term
+    reaching 351 records; titled `Context`, all 1178. Both tiers are now capped at
+    twenty documents, which costs nothing measurable: of 1125 distinct names none
+    reaches more than 20, and the two items that use inference return the same 2
+    and 17 records.
+  - *A non-string `touched_at` or `due` crashed the report.* `pm_item` writes both
+    through with no check beyond a JSON type and this SkillSet's own Ruby suite
+    writes the integer `20260701` to each, so slicing them raised `TypeError` — the
+    defect `lib/project_manager/parsed_time.rb` exists to prevent, re-acquired at a
+    fifth call site because the reader is in another language. Permanent once
+    triggered, since the value stays in the store.
+  - *One shape-valid impossible date took the whole run down.* `l2_scan` validates
+    that a declared date looks like a date, not that it exists, so `2026-02-30`
+    reached `date.fromisoformat` outside the `try` — the guard covered one end of
+    the interval only. Both ends now go through it.
+  - *An unreadable memo marker was reported as unreadable records.* An item with
+    seventeen perfectly datable records was described as "records found, none
+    datable", and it silently left the denominator: 28/28 matched with median 29
+    became 27/28 with median 28.5. The three causes — no terms, undatable records,
+    unreadable marker — are now counted and worded apart.
+- **Smaller fixes from the same review.** The authored `exclude` is carried into
+  the inference fallback rather than dropped, so a distinction the operator wrote
+  down is not undone by the fallback. A mapping whose `include` is a string rather
+  than a list no longer expands to single-character terms (one of which matched
+  1177 of 1177 documents, displayed as the operator's own authored mapping).
+  `store['projects']`, `mapping['items']` and dependency entries missing `kind` or
+  `ref` no longer raise. `--open` falls back to `xdg-open` and survives neither
+  binary existing, since the gem ships to Linux. The hook reads `KAIROS_DATA_DIR`
+  before `$CLAUDE_PROJECT_DIR/.kairos`, because the data directory is relocatable
+  and a relocated instance got a hook pointing at nothing. The hook no longer
+  discards stderr or forces a zero exit: doing both made every failure
+  indistinguishable from a session where nothing had drifted. Operator-facing text
+  no longer renders a Python list repr, and `--quiet` documents the two lines it
+  prints instead of three.
+- **`test/test_pm_l2_report.py`, 30 cases, 27 of them red against the version that
+  shipped before them.** Of those 27, nine exercise the old behaviour directly and
+  eighteen fail because the guard function did not exist — that distinction is
+  recorded rather than counted as thirty demonstrations. The remaining three cover
+  HTML escaping and a degenerate render, which were already correct and are held
+  as regression guards. The suite drives the real `l2_scan.match` rather than a
+  copy of it, so the two views cannot disagree about what a term matched.
+
+### Added
+
+- **The `project_manager` SkillSet (v0.6.0) reports the memo-versus-L2 drift once
+  per session, and no longer needs a human to author search terms first.** The
+  memo lags the context store and the lag is invisible from whichever side is
+  being read: on the development instance, 19 of 28 items have L2 activity more
+  recent than their last memo touch, median 29 days, widest 81. Derivation could
+  already measure that, but only when someone remembered to run it and only for
+  items a human had authored terms for. Two read-only additions.
+  `scripts/pm_l2_report.py` renders the comparison as one HTML page, and
+  `plugin/hooks.json` declares it as a `SessionStart` hook so the harness runs it
+  without anyone deciding to. `SessionStart` and not `Stop`: this is not a gate,
+  it decides nothing, and only Stop-family payloads carry the once-per-turn brake
+  `kairos_hook_projector`'s gates need. Delivery is by projection — `skillset
+  install` changes no host settings, and the MCP handshake projects on every host
+  start, so no core change was needed to reach the host. Whether the newly
+  written hook fires on that same start or the following one depends on when the
+  host reads its settings relative to the handshake; that ordering is not
+  measured, and `kairos-plugin-project` run by hand settles it. `skillset upgrade
+  --apply` is not a substitute: it projects only when it actually upgrades
+  something, and `project_manager` is not in the core set it upgrades. Measured
+  at 0.18s over 1172 contexts; the script writes exactly one file, its own
+  output, and the memo's hash is unchanged across a run.
+- **Search terms fall back to inference from the item's own title and notes**
+  when the authored mapping has no entry for an item, or its entry matched
+  nothing — so no item goes unreported and L2 is never asked to be relabelled.
+  Inference cannot replace the mapping and does not try: 43 of 53 hand-authored
+  terms appear nowhere in any item's title or notes, having been written from
+  knowledge of the work. What it can do is refuse to flood. Only a token that is
+  itself the name of an existing L2 document, or a compound identifier reaching
+  at most twenty documents, is accepted; a bare English word is refused however
+  rare it looks. Accepting bare words returned 51 and 82 records for the two
+  items that have almost none, because a defect is described with words like
+  store, write, config and yaml, and those match hundreds of unrelated names as
+  substrings. Refusing them, the same two return 2 and 17, and all 28 items
+  become comparable. The cost is misses — inference alone found 87 records across
+  the 24 mapped items where the mapping found 296 — and the trade is deliberate:
+  a miss shows up as a smaller count, a spurious record does not show up at all.
+  Unchanged by this release: nothing writes to the memo (derivation v0.12 §1),
+  and neither the digest's shape nor the secretary's grant moved.
+
+## [3.71.0] - 2026-08-17
+
+### Added
+
+- **The round dashboard ships with the L1 `multi_llm_review_workflow` entry**
+  (v3.10.2). `scripts/render_dashboard.rb` reads a round summary as JSON on
+  stdin, fills `assets/review_dashboard.html`, and writes a self-contained page.
+  These are the worked example `resource_render` names in its own description
+  and in its default output derivation (`render_dashboard.rb` →
+  `dashboard.html`), and neither was in the distribution — they existed on one
+  instance only. A fresh install therefore had a core tool whose documented
+  example pointed at files that were not on disk. `dashboard.html` itself is
+  deliberately not shipped: it is one June 2026 render of
+  `kairos_hook_projector_stage1_design_v0.1`, and the renderer recreates it.
+
+### Fixed
+
+- **An L1 entry's `assets/` and `scripts/` are deleted by an upgrade without
+  appearing in the report.** The 3.70.0 upgrade removed three files from this
+  instance's `multi_llm_review_workflow` entry (two dashboard pages and the
+  renderer, 30.9 KB, last touched 2026-06-02) while the L1 section of the report
+  said only `[UPDATED] multi_llm_review_workflow` and `Conflicts: 0`. Mechanism:
+  `UpgradeAnalyzer#analyze_knowledge` hashes `<name>.md` alone to decide
+  new / unchanged / updated / user_modified / conflict, and the apply step
+  replaces the whole entry directory, so any subdirectory content the
+  distribution does not carry is removed silently. The L0 section, by contrast,
+  reports `[KEPT] … (user-modified)`. Shipping the two files removes the
+  deletion for this entry; the general reporting gap is unfixed and recorded.
+  Note for anyone adding assets to a shipped entry: the `.md` must change in the
+  same release, or the entry is classified `:unchanged` and the new files never
+  install.
+- **The dashboard's gate stated a closing condition the project does not use.**
+  It required every blocking-pool seat to APPROVE *and* the displayed round's
+  entire (a)+(b) count to be zero. Findings may now carry `carryover: true`
+  (raised in an earlier round, still open; an absent flag means new), and the
+  panel reports a **freeze candidate** when new (a)+(b) is zero, showing the vote
+  tally beside it as a reference value. Driven through the real renderer and the
+  real gate function: a round with zero new and one carryover (a) at 1 of 2 seats
+  approving reports `GATE NOT PASSED` under the old rule and `FREEZE CANDIDATE`
+  under this one — and that is the state both 2026-08 review threads actually
+  closed in. A round with one new (a) and one carryover (a) at 2 of 2 approving
+  reports `NOT CLOSED — 1 new blocking P0 (a+b), 1 carryover`.
+- `Consensus.aggregate`'s `@return` line documented a `:convergence` key the
+  method no longer returns; the 3.70.0 rename matched bracket and definition
+  forms only. Comment only.
+
+## [3.70.0] - 2026-08-17
+
+### Changed
+
+- **The block of vote counts `multi_llm_review` returns is named `vote_tally`,
+  not `convergence`** (SkillSet v0.10.1). It holds `approve_count`,
+  `reject_count`, `skip_count`, `successful_count`, `threshold` and `rule` —
+  vote arithmetic. The closing condition the L1 workflow states is
+  "new (a)+(b) P0 = 0, carryover counted separately", which this SkillSet does
+  not compute and no returned field carries. INV-R2 had already demoted the
+  ratio to a recorded reference value in a comment at `consensus.rb:156` while
+  leaving the field's name intact, so every round handed the orchestrator a
+  block whose name claimed what its contents could not answer. Renamed rather
+  than given a new sibling field: with nothing in the payload called
+  convergence, the criterion has to be fetched from the findings, whereas a new
+  field would have left the misleading name in place. 62 sites across 8 files —
+  one definition, four production reads, 57 test assertions. One SkillSet
+  boundary is crossed: `agent`'s `agent_step.rb` reads this column and now reads
+  `vote_tally` with a fallback to `convergence`, following the pattern that file
+  already uses for the v0.7 `verdict` → `reference_verdict` rename, because
+  records written earlier still say `convergence`. Consumers outside this
+  repository that read the old key get nil. Falsified: with the three
+  production files reverted to the old name and the tests left renamed, the five
+  affected test files produce 44 errors; restored, the suite is 556 runs / 1809
+  assertions / 0 failures. Merged at the operator's instruction without
+  multi-LLM review.
+- **The L1 `multi_llm_review_workflow` pre-flight checklist states the closing
+  condition, not the ratio** (v3.10.1). The checklist line read "Convergence
+  rule: 3/5 APPROVE (full) or 3/4 APPROVE (after exclusion)", while
+  § Convergence Rules — 200 lines further down a 1578-line file — states that
+  the machine-side signal is "new (a)+(b) P0 = 0" and the ratio is auxiliary.
+  The checklist is what gets read before dispatch, so the ratio was the
+  operative rule in practice regardless of the prose. The line now leads with
+  the closing condition and keeps both ratios beside it as reference values. No
+  rule changed; the order in which a reader meets them did.
+
+### Known issue, recorded rather than fixed
+
+- `consensus[:vote_tally][:reason]` is read in two places
+  (`multi_llm_review.rb:548`, `multi_llm_review_collect.rb:431`) and is never
+  written, so the `|| 'quorum not met'` fallback is the only reachable value.
+  Changing it would alter an operator-facing message, which is a new claim.
+
 ## [3.69.0] - 2026-08-15
 
 ### Added

data/lib/kairos_mcp/version.rb

@@ -1,4 +1,4 @@
 module KairosMcp
-  VERSION = "3.69.0"
+  VERSION = "3.73.0"
   CHANGELOG_URL = "https://github.com/masaomi/KairosChain_2026/blob/main/CHANGELOG.md"
 end

data/templates/knowledge/multi_llm_review_workflow/assets/review_dashboard.html

@@ -0,0 +1,332 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Multi-LLM Review Dashboard</title>
+<style>
+  :root {
+    --bg: #0d1117; --surface: #161b22; --border: #30363d;
+    --text: #e6edf3; --text-muted: #8b949e;
+    --approve: #3fb950; --reject: #f85149; --revise: #d29922;
+    --advisory: #58a6ff; --font: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
+  }
+  * { margin: 0; padding: 0; box-sizing: border-box; }
+  body { font-family: var(--font); background: var(--bg); color: var(--text); padding: 24px; }
+  h1 { font-size: 1.4rem; margin-bottom: 4px; }
+  .subtitle { color: var(--text-muted); font-size: 0.85rem; margin-bottom: 24px; }
+  .grid { display: grid; grid-template-columns: repeat(auto-fit, minmax(280px, 1fr)); gap: 16px; margin-bottom: 24px; }
+  .card { background: var(--surface); border: 1px solid var(--border); border-radius: 8px; padding: 16px; }
+  .card h2 { font-size: 0.95rem; color: var(--text-muted); margin-bottom: 12px; text-transform: uppercase; letter-spacing: 0.05em; }
+  .verdict { display: inline-block; padding: 2px 10px; border-radius: 12px; font-size: 0.8rem; font-weight: 600; }
+  .verdict.approve { background: rgba(63,185,80,0.15); color: var(--approve); }
+  .verdict.reject { background: rgba(248,81,73,0.15); color: var(--reject); }
+  .verdict.revise { background: rgba(210,153,34,0.15); color: var(--revise); }
+  table { width: 100%; border-collapse: collapse; font-size: 0.85rem; }
+  th, td { text-align: left; padding: 8px 12px; border-bottom: 1px solid var(--border); }
+  th { color: var(--text-muted); font-weight: 500; }
+  .finding-tag { display: inline-block; padding: 1px 6px; border-radius: 4px; font-size: 0.75rem; font-weight: 600; margin-right: 4px; }
+  .finding-a { background: rgba(248,81,73,0.15); color: var(--reject); }
+  .finding-b { background: rgba(210,153,34,0.15); color: var(--revise); }
+  .finding-c { background: rgba(88,166,255,0.15); color: var(--advisory); }
+  .stat-number { font-size: 2rem; font-weight: 700; }
+  .stat-label { color: var(--text-muted); font-size: 0.8rem; }
+  .bar-row { display: flex; align-items: center; gap: 8px; margin-bottom: 6px; }
+  .bar-label { width: 120px; font-size: 0.8rem; color: var(--text-muted); text-align: right; }
+  .bar-track { flex: 1; height: 20px; background: var(--border); border-radius: 4px; overflow: hidden; display: flex; }
+  .bar-seg { height: 100%; transition: width 0.3s; }
+  .bar-seg.a { background: var(--reject); }
+  .bar-seg.b { background: var(--revise); }
+  .bar-seg.c { background: var(--advisory); }
+  .round-tabs { display: flex; gap: 8px; margin-bottom: 16px; }
+  .round-tab { padding: 6px 16px; border-radius: 6px; border: 1px solid var(--border); background: transparent;
+    color: var(--text-muted); cursor: pointer; font-size: 0.85rem; }
+  .round-tab.active { background: var(--surface); color: var(--text); border-color: var(--advisory); }
+  .legend { display: flex; gap: 16px; margin-bottom: 16px; font-size: 0.8rem; color: var(--text-muted); }
+  .legend-item { display: flex; align-items: center; gap: 4px; }
+  .legend-dot { width: 10px; height: 10px; border-radius: 2px; }
+  .instructions { background: var(--surface); border: 1px solid var(--border); border-radius: 8px;
+    padding: 16px; margin-bottom: 24px; font-size: 0.85rem; color: var(--text-muted); }
+  .instructions code { background: var(--border); padding: 2px 6px; border-radius: 4px; font-size: 0.8rem; color: var(--text); }
+  textarea { width: 100%; min-height: 120px; background: var(--bg); border: 1px solid var(--border);
+    border-radius: 6px; padding: 12px; color: var(--text); font-family: monospace; font-size: 0.8rem; resize: vertical; }
+  button { padding: 8px 16px; border-radius: 6px; border: 1px solid var(--border); background: var(--surface);
+    color: var(--text); cursor: pointer; font-size: 0.85rem; }
+  button:hover { border-color: var(--advisory); }
+  button.primary { background: rgba(88,166,255,0.15); border-color: var(--advisory); color: var(--advisory); }
+  .actions { display: flex; gap: 8px; margin-top: 12px; }
+  #json-error { color: var(--reject); font-size: 0.8rem; margin-top: 4px; min-height: 1.2em; }
+</style>
+</head>
+<body>
+
+<h1>Multi-LLM Review Dashboard</h1>
+<p class="subtitle">KairosChain L1: multi_llm_review_workflow — HTML resource (assets/)</p>
+
+<div class="instructions">
+  <strong>How to use:</strong> Paste a review result JSON into the editor below, or use the sample data to explore.
+  The JSON format follows the <code>(a)/(b)/(c)</code> finding classification from the multi-LLM review workflow.
+  After visualizing, use <strong>Copy as Prompt</strong> to feed the analysis back into Claude Code.
+</div>
+
+<div class="card" style="margin-bottom: 24px;">
+  <h2>Review Data Input</h2>
+  <textarea id="json-input" placeholder='Paste review JSON here...'></textarea>
+  <div id="json-error"></div>
+  <div class="actions">
+    <button class="primary" onclick="loadData()">Visualize</button>
+    <button onclick="loadSample()">Load Sample</button>
+    <button onclick="copyAsPrompt()">Copy as Prompt</button>
+  </div>
+</div>
+
+<div id="dashboard" style="display:none;">
+
+  <div class="round-tabs" id="round-tabs"></div>
+
+  <div class="legend">
+    <div class="legend-item"><div class="legend-dot" style="background:var(--reject)"></div> (a) deployment-grounded</div>
+    <div class="legend-item"><div class="legend-dot" style="background:var(--revise)"></div> (b) philosophy-aligned</div>
+    <div class="legend-item"><div class="legend-dot" style="background:var(--advisory)"></div> (c) value-divergent</div>
+  </div>
+
+  <div class="grid">
+    <div class="card">
+      <h2>Consensus</h2>
+      <div id="consensus-verdicts"></div>
+      <div style="margin-top:12px;">
+        <span class="stat-label">New blocking P0 (a+b): </span>
+        <span id="blocking-count" class="stat-number" style="font-size:1.4rem;"></span>
+        <span class="stat-label" style="margin-left:16px;">Carryover (a+b): </span>
+        <span id="carryover-count" class="stat-number" style="font-size:1.4rem;"></span>
+        <span class="stat-label" style="margin-left:16px;">Advisory (c): </span>
+        <span id="advisory-count" class="stat-number" style="font-size:1.4rem; color:var(--advisory);"></span>
+      </div>
+    </div>
+    <div class="card">
+      <h2>Gate Status</h2>
+      <div id="gate-status" style="font-size:1.1rem; margin-top:8px;"></div>
+    </div>
+  </div>
+
+  <div class="card" style="margin-bottom:16px;">
+    <h2>Finding Distribution by Reviewer</h2>
+    <div id="finding-bars"></div>
+  </div>
+
+  <div class="card">
+    <h2>All Findings</h2>
+    <table>
+      <thead><tr><th>Reviewer</th><th>Class</th><th>Finding</th><th>Severity</th></tr></thead>
+      <tbody id="findings-table"></tbody>
+    </table>
+  </div>
+</div>
+
+<script>
+const SAMPLE = {
+  artifact: "kairos_hook_projector_stage1_design_v0.1",
+  rounds: [
+    {
+      round: 1,
+      reviewers: [
+        {
+          id: "philosophy_persona",
+          label: "Philosophy Persona (4.7)",
+          pool: "blocking",
+          verdict: "APPROVE",
+          findings: [
+            { class: "b", text: "Inv-C2: substrate reference (plugin_projector) should be invariant, not named dependency", severity: "P0" },
+            { class: "c", text: "Consider adding explicit Prop 5 recording annotation", severity: "P2" }
+          ]
+        },
+        {
+          id: "engineering_persona",
+          label: "Engineering Persona (4.7)",
+          pool: "blocking",
+          verdict: "REVISE",
+          findings: [
+            { class: "a", text: "Inv-2 vs Inv-5 timestamp semantics contradict each other", severity: "P0" },
+            { class: "a", text: "Orphaned compile record lifecycle not specified", severity: "P0" },
+            { class: "b", text: "Inv-O1 declaration-order is mechanism dressed as invariant", severity: "P0" },
+            { class: "c", text: "Prefer explicit error types over string matching", severity: "P2" }
+          ]
+        },
+        {
+          id: "claude_cli_4.6",
+          label: "Claude CLI (Opus 4.6)",
+          pool: "blocking",
+          verdict: "REVISE",
+          findings: [
+            { class: "b", text: "Substrate-as-invariant: compiler must not name plugin_projector", severity: "P0" },
+            { class: "a", text: "mode_name binding integrity across recompile not guaranteed", severity: "P0" },
+            { class: "c", text: "Section ordering could improve readability", severity: "P2" }
+          ]
+        },
+        {
+          id: "codex_gpt5.4",
+          label: "Codex (GPT-5.4)",
+          pool: "advisory",
+          verdict: "REJECT",
+          findings: [
+            { class: "c", text: "Exhaustiveness of Inv-C3 not formally verifiable", severity: "P0" },
+            { class: "c", text: "Missing rollback procedure specification", severity: "P0" },
+            { class: "a", text: "Race condition possible if two compiles run concurrently", severity: "P1" }
+          ]
+        },
+        {
+          id: "cursor_composer2.5",
+          label: "Cursor (Composer 2.5)",
+          pool: "advisory",
+          verdict: "REJECT",
+          findings: [
+            { class: "c", text: "Design lacks complete error taxonomy", severity: "P0" },
+            { class: "c", text: "No performance benchmarks specified", severity: "P1" },
+            { class: "a", text: "File path validation insufficient for symlink traversal", severity: "P1" }
+          ]
+        }
+      ]
+    }
+  ]
+};
+
+let currentData = null;
+let currentRound = 0;
+
+function loadSample() {
+  document.getElementById('json-input').value = JSON.stringify(SAMPLE, null, 2);
+  loadData();
+}
+
+function loadData() {
+  const errEl = document.getElementById('json-error');
+  errEl.textContent = '';
+  try {
+    currentData = JSON.parse(document.getElementById('json-input').value);
+    currentRound = 0;
+    renderRoundTabs();
+    renderRound(0);
+    document.getElementById('dashboard').style.display = 'block';
+  } catch (e) {
+    errEl.textContent = 'JSON parse error: ' + e.message;
+  }
+}
+
+function renderRoundTabs() {
+  const tabs = document.getElementById('round-tabs');
+  tabs.innerHTML = '';
+  currentData.rounds.forEach((r, i) => {
+    const btn = document.createElement('button');
+    btn.className = 'round-tab' + (i === currentRound ? ' active' : '');
+    btn.textContent = 'Round ' + r.round;
+    btn.onclick = () => { currentRound = i; renderRoundTabs(); renderRound(i); };
+    tabs.appendChild(btn);
+  });
+}
+
+function renderRound(idx) {
+  const round = currentData.rounds[idx];
+  const reviewers = round.reviewers;
+
+  // Verdicts
+  const vEl = document.getElementById('consensus-verdicts');
+  vEl.innerHTML = reviewers.map(r =>
+    `<span style="margin-right:12px;">${r.label}: <span class="verdict ${r.verdict.toLowerCase()}">${r.verdict}</span></span>`
+  ).join('<br>');
+
+  // Counts. A finding carrying carryover: true was raised in an earlier round
+  // and is still open; it does not enter the closing condition. An absent flag
+  // means new, which is what the round-1 shape and every earlier input produce.
+  let blocking = 0, carryover = 0, advisory = 0;
+  reviewers.forEach(r => r.findings.forEach(f => {
+    if (f.class === 'a' || f.class === 'b') {
+      if (f.carryover) carryover++; else blocking++;
+    } else advisory++;
+  }));
+  document.getElementById('blocking-count').textContent = blocking;
+  document.getElementById('carryover-count').textContent = carryover;
+  document.getElementById('advisory-count').textContent = advisory;
+
+  // Gate. The closing condition is new (a)+(b) = 0 — CLAUDE.md § Aggregation
+  // rule, L1 multi_llm_review_workflow § Convergence Rules. The vote tally is a
+  // reference value, shown and not required: the roster ratio can be
+  // arithmetically unreachable, and the intended close is (a)+(b) exhaustion
+  // declared by the operator. This panel therefore reports a freeze candidate,
+  // never a passed gate.
+  const blockingReviewers = reviewers.filter(r => r.pool === 'blocking');
+  const approveCount = blockingReviewers.filter(r => r.verdict === 'APPROVE').length;
+  const gateEl = document.getElementById('gate-status');
+  const votes = `votes ${approveCount}/${blockingReviewers.length} APPROVE (reference)`;
+  gateEl.innerHTML = blocking === 0
+    ? `<span style="color:var(--approve);">&#10003; FREEZE CANDIDATE</span> — 0 new blocking P0, ${carryover} carryover still open — ${votes}`
+    : `<span style="color:var(--reject);">&#10007; NOT CLOSED</span> — ${blocking} new blocking P0 (a+b), ${carryover} carryover — ${votes}`;
+
+  // Bars
+  const barsEl = document.getElementById('finding-bars');
+  barsEl.innerHTML = '';
+  reviewers.forEach(r => {
+    const a = r.findings.filter(f => f.class === 'a').length;
+    const b = r.findings.filter(f => f.class === 'b').length;
+    const c = r.findings.filter(f => f.class === 'c').length;
+    const total = Math.max(a + b + c, 1);
+    const maxFindings = Math.max(...reviewers.map(rv => rv.findings.length), 1);
+    const scale = 100 / maxFindings;
+    barsEl.innerHTML += `<div class="bar-row">
+      <div class="bar-label">${r.id}</div>
+      <div class="bar-track">
+        <div class="bar-seg a" style="width:${a * scale}%" title="(a) ${a}"></div>
+        <div class="bar-seg b" style="width:${b * scale}%" title="(b) ${b}"></div>
+        <div class="bar-seg c" style="width:${c * scale}%" title="(c) ${c}"></div>
+      </div>
+      <span style="font-size:0.8rem;color:var(--text-muted);width:40px;">${a+b+c}</span>
+    </div>`;
+  });
+
+  // Table
+  const tbody = document.getElementById('findings-table');
+  tbody.innerHTML = '';
+  reviewers.forEach(r => {
+    r.findings.forEach(f => {
+      tbody.innerHTML += `<tr>
+        <td>${r.id}</td>
+        <td><span class="finding-tag finding-${f.class}">(${f.class})</span></td>
+        <td>${f.text}</td>
+        <td>${f.severity}</td>
+      </tr>`;
+    });
+  });
+}
+
+function copyAsPrompt() {
+  if (!currentData) return;
+  const round = currentData.rounds[currentRound];
+  let prompt = `## Multi-LLM Review Round ${round.round} Summary\n\n`;
+  prompt += `**Artifact:** ${currentData.artifact}\n\n`;
+
+  const blockingReviewers = round.reviewers.filter(r => r.pool === 'blocking');
+  const approves = blockingReviewers.filter(r => r.verdict === 'APPROVE').length;
+  prompt += `**Gate:** ${approves}/${blockingReviewers.length} blocking APPROVE\n\n`;
+
+  prompt += `### Blocking findings (a+b) — must address:\n\n`;
+  round.reviewers.forEach(r => {
+    r.findings.filter(f => f.class !== 'c').forEach(f => {
+      prompt += `- [${r.id}] (${f.class}) ${f.severity}: ${f.text}\n`;
+    });
+  });
+
+  prompt += `\n### Advisory findings (c) — reviewer preference:\n\n`;
+  round.reviewers.forEach(r => {
+    r.findings.filter(f => f.class === 'c').forEach(f => {
+      prompt += `- [${r.id}] (${f.class}) ${f.severity}: ${f.text}\n`;
+    });
+  });
+
+  navigator.clipboard.writeText(prompt).then(() => {
+    const btn = event.target;
+    btn.textContent = 'Copied!';
+    setTimeout(() => btn.textContent = 'Copy as Prompt', 1500);
+  });
+}
+</script>
+</body>
+</html>