Committed serial items: e2e files split to <= 500 lines (d8b1c95) and the scoped right-click context menu (ded7c9a). Tests run once after the install, by the operator's order 2026-11-15.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every palette item carries a scope (general, a tab, or an element kind); right-click and the Menu key or Shift+F10 open one menu with the element's items, then the tab's, then the general ones. Shift+right-click and text fields keep the browser menu; the diff feedback becomes one provider; any other key closes the menu instead of reaching the global shortcuts.
🎯 Fix: 85 %
💥 Break: 6 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 80
🚦 Gate: ⛔ fix 85 % < 90, break 6 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Probe sandboxes gain the channels, quietBubbles and known.now the merged branches added; the hub view keeps queue_jobs apart from the job list; the image ships sandbox_paths.py; kvb-match writes pages into the council root pages folder; the install test scaffolds the council parts and agent roots; skill texts move detail into their side files to stay under the word caps.
🎯 Fix: 88 %
💥 Break: 4 %
💸 Tokens: 98 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 86
🚦 Gate: ⛔ fix 88 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The approval hook binds a hub approval to a plain git commit of the staged index only; commits that add files from the working tree, amend, take a pathspec, run in a chain or inside a shell wrapper fall back to the normal dialog. Every git call of the hook runs with an environment allowlist. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 93 %
💥 Break: 3 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 90
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 013 and its implementation: page-mic.js puts a microphone on every textarea and text input, records with MediaRecorder and inserts the transcript at the cursor; Escape cancels. /api/stt transcribes with the local whisper.cpp model ggml-small-q8_0 (pinned to commit 5359861c and its sha256) in a per-request temp dir, capped at 60 s and 5 MiB, and returns German or English only, retranscribing a clip detected as another language in both and keeping the surer one. Without a model the button is disabled and names the install row. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 72 %
💥 Break: 12 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 63
🚦 Gate: ⛔ fix 72 % < 90, break 12 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 012 plus its first two phases: the kvb-match skill (match.py add, list, show) feeds the existing review queue, /api/match serves the cards and local-only stale and snapshot posts, and payload files are read only as regular files under /tmp within the sandbox view and 64 KiB. The card at #tasks/match shows face, name, age in days, repository, branch, worktree and files that open while scrolling; right-click or long press marks a line, stale cards cannot be accepted. Accept, reject and the passkey release follow in phase C after the screenshot feedback. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 75 %
💥 Break: 8 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 95 %
🏆 Score: 66
🚦 Gate: ⛔ fix 75 % < 90, break 8 % > 5; security 95 % < 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
rates.py folds the token, commit and score journals into per-hour and per-day rates for the header chips and the rates page; /api/rates drops from about 1950 ms to 380-830 ms on a year of data. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 75 %
💥 Break: 10 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 95 %
🏆 Score: 64
🚦 Gate: ⛔ fix 75 % < 90, break 10 % > 5; security 95 % < 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
queue_order.py parses queue.py list --json into positions and reasons; the Tasks board overlays each card with its queue position, wait and reason, and falls back to Order only when the queue cannot be read. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 80 %
💥 Break: 10 %
💸 Tokens: 20 %
⏱️ Velocity: 20 %
🛡️ Security: 100 %
🏆 Score: 100
🚦 Gate: ⛔ fix 80 % < 90, break 10 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
glossary.js is the single source of the gate, branch and rule terms; ancestry, tree, artifacts, offices and rules render text chips from it with the explanation on hover, focus and Enter. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 80 %
💥 Break: 8 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 74
🚦 Gate: ⛔ fix 80 % < 90, break 8 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The agents hierarchy gains a matrix org chart: agents as columns, chairs as rows, so one agent with several chairs shows every one of them; a Home tile can pin it. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 82 %
💥 Break: 8 %
💸 Tokens: 90 %
⏱️ Velocity: 90 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ⛔ fix 82 % < 90, break 8 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One rule table replaces the two lists: each allow, ask and deny rule shows its hits from the extracted dry-run matcher, ask patterns the matcher never grants read never granted instead of unused, and the table scrolls in its own container below 600 px. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 10 %
💸 Tokens: 100 %
⏱️ Velocity: 103 %
🛡️ Security: 100 %
🏆 Score: 74
🚦 Gate: ⛔ fix 85 % < 90, break 10 % > 5; velocity 103 % > 100: ask the operator before the commit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Settings store the notification channels (browser, sound, speech) instead of one notify flag, migrating the old flag to the browser channel; alerts and speech follow the chosen channels. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 8 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 78
🚦 Gate: ⛔ fix 85 % < 90, break 8 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The radio shows the device card on the left and the speak and history cards on the right from 45 to 61 rem of height, stacking below that; only the history scrolls. History rows get stable keys (sent-row id, else time, sender and occurrence), and focus moves to the nearest row when the focused one disappears. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 12 %
💸 Tokens: 60 %
⏱️ Velocity: 45 %
🛡️ Security: 100 %
🏆 Score: 100
🚦 Gate: ⛔ fix 85 % < 90, break 12 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each Home tile header gets an open button that jumps to the screen, panel or item the tile shows, restoring its scroll and selection. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 10 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 77
🚦 Gate: ⛔ fix 85 % < 90, break 10 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
speakRows queues all speech rows of a poll before the single redraw, so a MAYDAY behind other rows is never lost, and a draw that throws shows a toast instead of stopping the pump. Late and stale rows both bubble. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 80 %
💥 Break: 5 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 76
🚦 Gate: ⛔ fix 80 % < 90
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The cleanup runs pkgmgr branch cleanup --local and offers deletion only for ancestry-merged branches; squash or PR merges stay a dry-run preview. A signed branch whose ref vanished without a pkgmgr delete becomes gone (deleted outside this run, or after an interrupted apply) and is shown apart from deleted and failed; an Unknown --branch answer for a vanished ref repeats the run once without it. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 88 %
💥 Break: 6 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 83
🚦 Gate: ⛔ fix 88 % < 90, break 6 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A 404 on Run, Close, a passkey signature or a rule accept closes the card with the notice "already done or removed elsewhere" instead of a lasting error; a selection reloads /api/state once and closes only the cards that are gone, other failures keep the old error. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 90 %
💥 Break: 3 %
💸 Tokens: –
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 87
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
councilroot.py resolves one durable council root for every script and migrates the old /tmp root under the held locks: a preflight conflict moves nothing, each legacy file is renamed to a staging name before it is copied so a late writer is merged by the catch-up, id-less journals merge by line multiset, a differing whole file is kept beside its namesake, and a crash marker makes install copy the skills and report. One settings-file list, managed drop-ins included, serves councilroot.py and queue.py. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 88 %
💥 Break: 7 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 82
🚦 Gate: ⛔ fix 88 % < 90, break 7 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
watch.py admits heavy work only while PSI, swap-out rate and RAM forecast stay under the configured limits; config.default.json is the single default the install writes once (mode 600, no clobber) and every hook, admit and queue command falls back to. Browser runners and package-manager script forms count as heavy, preflight derives its probes from the light and heavy tool lists, and the shipped default carries no prune command, buildx path or host-specific key. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14).
🎯 Fix: 85 %
💥 Break: 8 %
💸 Tokens: 99 %
⏱️ Velocity: –
🛡️ Security: 100 %
🏆 Score: 79
🚦 Gate: ⛔ fix 85 % < 90, break 8 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Stars now pin each resources chart (hardware, tokens, combined overlay) with its chip selection, the artifacts tree and single artifacts, Agent priority, Waits on Operator and a single agent card as live Home tiles. A long artifact id pins as <kind>#<digest>, the view store keys selections by digest, refuses pins it cannot keep and Home shows a gone tile with unpin. Fixtures use synthetic operator-example-01 paths; requirement 008 lists the new pins.
🎯 Fix: 91 %
💥 Break: 4 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 87
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
voicePace and readingPace set each row's floor, span and duration in one place: the spoken rest reveals the unread words over the speech audio, a procedure word reveals none, a burst and silent reading reveal the rest at reading pace, and wordsRead never goes below the floor. A sound that fails or is dropped still ends cleared. Requirement 003 W6 states it; probes cover quiet, burst, fallback, cut, auto, check, silent, rejected and faulty rows.
🎯 Fix: 92 %
💥 Break: 4 %
💸 Tokens: 100 %
⏱️ Velocity: 100 %
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, tokens and velocity <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The 008 star row took about 26 px from the stage cards: the tasks/3d canvas fell under 80 px, where zoomToFit's 40 px padding gave a negative field of view and froze the camera, and the agents/orbit card pushed the page past 844 px with the radio spot open, against 001's no-scrollbar rule. The chart legend is now the panel's star slot (style-home.css places it at the end of the last key line under 640 px), and the 3D fit clamps its padding to a quarter of the canvas height and skips a canvas of height 0. The Firefox radio probe waits for paused with src cleared, since Firefox pauses the element before the product's 3 s fade ends.
🎯 Fix: 92 %
💥 Break: 4 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The vendored 3d-force-graph appends three empty style elements to head while it loads and fills them with its own CSS; the page CSP allows styles by nonce only, so it blocks them and Firefox logs six style-src-elem errors, which failed the W3 artifacts e2e once 594d185 opened the 3D view there. page-graph3d.js now intercepts head.appendChild only while that script runs (document.currentScript is its tag), skips style elements from it and removes the interception on load or error. The CSP and the pinned library stay unchanged; the page already styles the classes those blocks targeted.
🎯 Fix: 95 %
💥 Break: 3 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 92
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
passkey.py accepted an RS256 public key of any modulus size. It now refuses a modulus under 2048 bits at registration and at every verification, before either signature backend, with a fixed error asking for a new passkey; the library backend checks key_size again and the openssl backend's key_type requires the same size. The SubjectPublicKeyInfo is read as strict DER (no negative or padded INTEGERs, minimal lengths, no unused bits, no trailing data) and the rsaEncryption identifier must match exactly. ES256 and EdDSA are unchanged. An already pinned weak key is refused on every use until a new passkey is pinned. Accepted MEDUSA findings: AIC-EXFIL-005 and PRIV-SCAN-762 at tests/hub_support.py:151 (public half of a throwaway test key) and PQC001 at passkey.py:236 (WebAuthn offers no post-quantum algorithm yet).
🎯 Fix: 95 %
💥 Break: 3 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 92
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 006 marked the burn chart box with data-panel="burndown", which the Home registry of requirement 008 never registered, so test_hub_home found an unregistered panel once both landed on unify. Nothing reads that id; the chart stays pinnable as the registered tasks/burn panel and the overlay styles select .burn-box.
🎯 Fix: 95 %
💥 Break: 2 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: ~100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 001 S6: the hub gets a Firewall view of the Claude Code permission and sandbox settings. The operator signs each change with the passkey; a host settings writer (systemd path unit) applies only exact, signed changes to allowlisted settings files through O_NOFOLLOW directory and file descriptors, and a timer refreshes the view. Every signed text and every page sink refuses or marks hidden characters: Cc, Cf, Zl, Zp, every space but U+0020 and the Default_Ignorable set, with U+FE0E/U+FE0F allowed only after one of the 359 non-ASCII emoji bases of Unicode 16 (shared table, validated at import, the same pair rule on the page). Removal of a deny, ask or denyRead entry is exempt only as an exact single remove. The permission hook prints the hub's refusal reason, cleaned of hidden characters. Accepted MEDUSA false positives (independent review, operator pick): 38 this round, mainly the Unicode defence tables read as attack patterns, generic MM-SCAN-058 heuristics, WEB-FLASK-004 at view.py:213 (ints from the validated table via tojson), EXF26-TOOL-004 on the non-secret WebAuthn challenge, PRIV-SCAN-060 on the office-action shape check and PQC007 on a picker key.
🎯 Fix: 95 %
💥 Break: 3 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 92
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 005: every radio message in the Stream and the radio log shows the avatars of the agents that read it, with read time and an ack badge where a receipt exists; receipt rows no longer appear as entries of their own, and the sender shows once. Read times come from seen marks, stamped only after a fresh presence pass no older than two sighting intervals; a stored time before its row is refused. An operator message links to its relay row through the ts radio.py prints first on stdout right after store(), checked against an exact row (sender Operator, relay text, targets, no to_sessions); a ts shared by two rows shows no readers. radio.py clips printed addresses; the hub keeps the first stdout line whole. Accepted MEDUSA false positives: MM-SCAN-058 at server.py:73, JB-SCAN-641 and JB-SCAN-616 at radio.py:389 (clip, the output sanitizer), FLA-SCAN-055 at radio.py:109. Committed below the 90/5 bar on the operator's word; the receipts e2e runs through the queue.
🎯 Fix: 89 %
💥 Break: 6 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 84
🚦 Gate: ⛔ fix 89 % < 90, break 6 % > 5
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Requirement 001 S8: the hub can use a shared OpenAI-style speech service (KVB_ORCHESTRATOR_SPEECH_URL, key from a mounted file) instead of the local piper and whisper engines, and the image takes its pinned artefacts through an optional INFINITO_ARTEFACT_BASE cache. A new transport serves speech and the LLM: one wall-clock deadline over DNS, connect, TLS handshake and body, certificate and hostname always verified, no redirect followed. A key travels only over https or to loopback; both the speech and the LLM start refuse it otherwise. Key files are capped at 4096 bytes. Streamed WAV answers with placeholder sizes are accepted only when the data chunk runs to the end, and are rewritten before caching. Accepted MEDUSA false positives (41, independent review, operator pick): raw client socket patterns in transport.py, AIC-EXFIL-005 on the sealed key path, JB-SCAN-2237 on the hub's own system prompt, STG009 on the RIFF pad byte and LLM01 at language.py:111, where agent-written titles reach the NL prompt but the model only proposes a plan the operator confirms.
🎯 Fix: 93 %
💥 Break: 4 %
💸 Cost: –
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>