Commit Graph
57 Commits
Author SHA1 Message Date
Kevin Veen-BirkenbachandClaude Opus 5.5 23b6d8579c fix(orchestrator): mark a branch done only when pkgmgr deleted it
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>
2026-11-14 21:22:28 +00:00
Kevin Veen-Birkenbach d364cfe55f Merge branch 'feature/orchestrator-firewall' into unify/skills-20261112-night
# Conflicts:
#	orchestrator/Dockerfile
#	orchestrator/kvb_orchestrator/view.py
#	orchestrator/templates/index.html.j2
#	orchestrator/templates/page-cleanup.js
#	scripts/orchestrator.sh
2026-11-13 18:18:54 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 9742884308 feat(orchestrator): firewall view with signed settings changes (001 S6)
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>
2026-11-13 18:14:17 +00:00
Kevin Veen-Birkenbach 5b65fb5284 Merge branch 'feature/radio-receipts-hub' into unify/skills-20261112-night
# Conflicts:
#	orchestrator/kvb_orchestrator/hub.py
#	orchestrator/server.py
#	orchestrator/templates/page-stream.js
#	skills/kvb-org-radio/scripts/radio.py
2026-11-13 17:56:36 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 30b2a32095 feat(orchestrator): radio receipts inline (005 phase B)
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>
2026-11-13 17:19:39 +00:00
Kevin Veen-Birkenbach 9fd9625570 Merge branch 'feature/orchestrator-s8-shared-cache' into unify/skills-20261112-night 2026-11-13 16:57:54 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 6d2bca77f7 feat(orchestrator): S8 shared speech service and sealed model transport
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>
2026-11-13 16:57:52 +00:00
Kevin Veen-Birkenbach ca9cd96442 Merge branch 'documentation/requirements-005-008-hub-views' into unify/skills-20261112-night 2026-11-13 15:32:17 +00:00
Kevin Veen-Birkenbach 370da99829 Merge branch 'documentation/requirements-001-003-cleanup' into unify/skills-20261112-night 2026-11-13 15:32:10 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 374fcaa864 test(kvb-check-score): let requirement documents name the former labels
006's label test scanned docs/requirements too, but the 006 requirement has to name Cost and Time to describe their rename, so the test failed once the requirement and the code met on the unify branch. The test now skips docs/requirements, and the 006 acceptance line says so.

🎯 Fix: 96 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 95
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:32:02 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 ebd67d5abf docs(requirements): pin PATCH with expect and 409 in 007 and 008
007 now names the view store's PATCH body with set and expected values and its 409 on a stale expectation, and 008's integration box requires that 409 for the pins, so two tabs never overwrite each other's layout.

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:29:56 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 4cf35872b2 docs(requirements): strike superseded 001/003 boxes and amend D21 and D59
Strikes nine 001 acceptance boxes that later decisions replaced, each with the decision that replaced it, rewords three boxes on the operator's picks (worktree-held branches skipped, the radio log replacing the sent list, icon labels allowed), and adds dated operator amendments to decision 21 (the signed delete removes only the local branch) and decision 59 (the radio spot shows the 004 radio log with its Sent tab).

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:28:53 +00:00
Kevin Veen-Birkenbach 679ebe5dc4 Merge branch 'feature/radio-set-panel' into unify/skills-20261112-night 2026-11-13 10:48:27 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 acf39255fc feat(orchestrator): radio set with CPU-gated speech, noise burst, modes and log (requirement 004)
The hub gates uncached /api/tts renders on the latest W4 host CPU sample (503 busy or unknown, cached lines always served, signed speech.threshold 30 to 90 in steps of 10, speech.gate in /api/state). The page plays a WebAudio squelch-tail burst when no speech plays, offers Auto, Quiet and Silence per browser, and always sounds the MAYDAY, PAN-PAN and SECURITE procedure word. The radio panel becomes a minimalist VHF faceplate with display line, mode buttons, knobs, PTT send and the internet station; the settings dialog loses its radio section. The log gets Sent, Received and All tabs with class, sender, recipient and agent chips plus text search. Decisions 3 and 10 of 004 now state that the procedure word still sounds in Silence.

Security: MEDUSA-MEX-SCAN-1167 at orchestrator/kvb_orchestrator/hub.py:126 accepted as a false positive after the round 5 skeptic review and the operator pick of 2026-11-13 (regex hit on rce inside RESOURCES; CpuGate reads host CPU samples, no model).

Break risk 6 % is above the 5 % bar; committed and merged on the operator pick of 2026-11-13 for this bundle.

🎯 Fix: 92 %
💥 Break: 6 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 86
🚦 Gate: ⛔ break 6 % > 5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 10:48:13 +00:00
Kevin Veen-Birkenbach b4a38f02d5 Merge branch 'chore/requirement-test-gaps' into unify/skills-20261112-night 2026-11-13 09:32:47 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 b202e021c7 test(orchestrator): close the 001 and 003 acceptance gaps with named tests
Ticks in 001 and 003 now name a test that passes on the final code: a 21-screen sweep in Chromium and Firefox at 1920, 1366 and 390 (no page scroll, every scroller reaches its last child, nothing clipped), the sessions timer check, the pkgmgr branch tree file, the forecast scope, the resources charts, bubble schedule, assets, stop and reading time, and the kanban and cleanup executors. Scrolling screens move into a pane so only main scrolls. The cleanup sheet keeps its dry-run note as visible text, now pinned by a test. The W6 fade check stamps removal from a MutationObserver against a timer started on the same mutation. Boxes whose final browser run is still owed stay unticked.

🎯 Fix: 95 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 91
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 09:32:39 +00:00
Kevin Veen-Birkenbach 7ceaf8f08c Merge branch 'documentation/requirements-005-008-hub-views' into unify/skills-20261112-night 2026-11-13 08:53:24 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 7ed142032b docs(requirements): add 005 to 008 for hub receipts, score overlays, resources view and home dashboard
005 shows readers and acks under every radio row instead of receipt rows. 006 renames the score labels to Tokens and Velocity, journals every score block, backfills it deterministically and draws each metric as a burndown overlay. 007 merges the hardware load into one chart, adds an accumulated tokens chart, a combined overlay mode and the unsigned /api/view store. 008 adds a Home tab with stars on every panel and item and a 12-column grid. All decisions operator-confirmed 2026-11-13.

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:51:25 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 43e8dac26b docs(requirements): 002 cosmos takes the sky only (decision 9)
Operator-confirmed 2026-11-12: the orchestrator keeps its generated music and its orbit and 3D scene, no <cosmos-graph> exists, and the orchestrator vendors the cosmos file set (cosmos.js, LICENSE, NOTICE.md). The acceptance criteria follow the revised scope.

🎯 Fix: 99 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 98
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 23:11:26 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 70844f3471 docs(requirements): keep 003 in English at the per-push waiver
test_english flagged the German waiver phrase at 003-operator-workbench.md:283.

🎯 Fix: 99 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 98
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 18:12:35 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 c4b67bb639 Merge feature/radio-set into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:28:13 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 e349198b7f Merge chore/requirement-001-audit into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:28:12 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 515fe61009 Merge feature/workbench-w4-resources into unify/skills-20261112
Conflicts combined W1 (Inbox leaves the Stream for Tasks, Waits on Operator) with W4 (Resources tab): five tabs with Resources, Stream keeps only the Firewall, the inbox hash keeps its redirect; index.html.j2 includes both diffs.js and resources.js.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:26:29 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 f5b2352f19 Merge feature/workbench-w3-artifacts into unify/skills-20261112
Conflicts kept both sides: runner.py docstring (W2 board changes and W3 gate changes), signing.py constants (W2 STATUSES and W3 GATE_*), index.html.j2 styles (W1 diff and W3 ancestry).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:24:59 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 9d6b3d26bf Merge feature/workbench-w2-kanban-forecast into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:23:41 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 eb4a335984 Merge feature/workbench-w1-operator-tasks into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:23:36 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 8711c23a39 docs(requirements): add 004 radio set
The Agent Orchestrator radio as a minimalist marine VHF set: a server CPU gate for speech, a WebAudio noise burst, modes Auto, Quiet and Silence, procedure words that always sound, every radio setting in the panel and a log with Sent, Received and All plus filters. Operator decisions 2026-11-12.

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:19:16 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 95337d9d54 docs(requirements): audit 001 against the shipped orchestrator
Ticks the 001 acceptance criteria the shipped code proves and rewords the ones whose mechanism changed.

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:18:50 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 8a44d504b5 feat(kvb-check-gate): W5 gate receipts, hooks and queue after-wait
gates.py installs hooks that check the merge level before a push without writing git config, writes receipts from green queue gates, and the queue gains the after-wait and rank. Requirement 003 strikes the hook-enforcement criterion: agents keep --no-verify, hooks bind humans and CI. Committed below the bar on the operator's word 2026-11-12 (one gate after the merge): test_gates 15, test_queue 63 and test_watch 46 green, security 100 %, break risk 6 % for the live queue and hook change.

🎯 Fix: 90 %
💥 Break: 6 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 85
🚦 Gate: ⛔ break 6 % > 5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:16:22 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 35c270e120 feat(orchestrator): W4 resources view and host samples
A resources timer samples host CPU, RAM, swap and per-session tokens into samples.jsonl; the hub serves them and a Resources view charts them. Committed below the bar on the operator's word 2026-11-12 (no further per-bundle tests, one gate after the merge): the W4 e2e never ran in a real browser.

🎯 Fix: 92 %
💥 Break: 6 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 86
🚦 Gate: ⛔ break 6 % > 5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:15:43 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 f7a59d43a5 feat(orchestrator): W3 artifacts tree, ancestry, gates and token-free cleanup
Artifacts show the branch tree with ancestry and gate marks. The cleanup runner calls pkgmgr branch cleanup with its real argv and parses its repos[*].items output, refuses any plan with a remote-branch action, marks an item done only when pkgmgr reports it done, and offers no delete for a branch a worktree holds. Every text states what the pkgmgr command does to volumes. Committed below the bar on the operator's word 2026-11-12 (no further per-bundle tests, one gate after the merge): the W3 e2e never ran; the client switches to --local once pkgmgr ships it.

🎯 Fix: 90 %
💥 Break: 6 %
💸 Cost: 30 %
⏱️ Time: 40 %
🛡️ Security: 100 %
🏆 Score: 100
🚦 Gate: ⛔ break 6 % > 5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:15:14 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 8e63b21e21 feat(orchestrator): W2 Kanban board with swimlanes and forecast
Tasks gain a Kanban board: columns Waiting, Running and Done, swimlanes P1 to P4+ and Unpinned by WSJF, after-dependency arrows and the dashed queue line; drag and drop stages status, pin and dependency moves that apply with one passkey. The burn chart gets the trend and a forecast. Committed below the bar on the operator's word 2026-11-12 (no further per-bundle tests, one gate after the merge): the W2 e2e never ran.

🎯 Fix: 80 %
💥 Break: 10 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 72
🚦 Gate: ⛔ fix 80 % < 90, break 10 % > 5

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:14:36 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 d09ed61161 feat(orchestrator): W1 operator tasks, diff previews and bound commit asks
Operator tasks move from the Inbox into Tasks with the Waits on Operator filter. Review and commit asks carry the staged diff; a file whose old or new blob holds an armour line or a detection-pattern match, or every file when no pattern loads, ships only its path, status, mode and counts. The approval binds to the staged tree id from git write-tree, the encoded request body respects the hub limit, and the hub image ships every client module signed.py loads. Committed below the bar on the operator's word 2026-11-12 (no further per-bundle tests, one gate after the merge): the full hub suite and the W1 e2e never ran, two high MEDUSA rows (sandbox_paths.py FLOOR, permission_hook.py ask POST) wait for their acceptance.

🎯 Fix: 85 %
💥 Break: 12 %
💸 Cost: 30 %
⏱️ Time: 30 %
🛡️ Security: 50 %
🏆 Score: 100
🚦 Gate: ⛔ fix 85 % < 90, break 12 % > 5; security 50 % < 100: ask the operator before the commit

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:13:58 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 07099c42ab docs(requirements): 003 W6 speech bubbles
Decision 17 and work package W6: a toolbar toggle shows speech bubbles at the agents in every view; the speaking agent's bubble grows and reveals its text word by word in Comic Neue at reading pace, waiting agents queue as small bubbles sized by order, and a bubble fades once read.

🎯 Fix: 92 %
💥 Break: 2 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 90
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:51:37 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 1bcc8c135f feat(workbench): requirement 003 with the gates and register contracts
Requirement 003 Operator Workbench (operator-confirmed 2026-11-11) and the contracts its work packages build on: gates.py keeps gate rules, branch parents and gate receipts in ~/.local/state/agents-council/gates.db (resolve takes the branch's own level, else the strictest of all parents; derive records the nearest ancestor tips; tree hashes everything a worktree holds through a temporary index). rasci.py gains --unpin, stamps every changed row with updated, and ranks a task after its after-dependencies.

🎯 Fix: 95 %
💥 Break: 3 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 92
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 18:13:24 +00:00
Kevin Veen-Birkenbach c3ab6b7e18 Merge feature/orchestrator/s52-night-per-agent into master
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	docs/requirements/001-agent-orchestrator.md
#	orchestrator/kvb_orchestrator/view.py
#	orchestrator/templates/page-board.js
#	tests/test_hub_state.py
2026-11-11 07:53:40 +00:00
Kevin Veen-Birkenbach afebf24703 Merge feature/orchestrator/s53-agent-presence into master
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	docs/requirements/001-agent-orchestrator.md
#	orchestrator/templates/page-board.js
#	tests/e2e/test_orchestrator_e2e.py
2026-11-11 07:48:48 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 995c7cb214 feat(orchestrator): S5.2 drain, suspend and resume chosen agents
The Day/Night menu lists every claimed agent with a checkbox and an All box; Drain, Suspend and Resume act on the ticked agents only, are disabled when none is ticked, and the agent popup carries the same three buttons for that one agent. Each action is passkey-signed with its agent list, night.py takes --target per session and keeps a per-agent part, and each chosen agent gets a call naming the action and its skill. The night skills say how to read a per-agent night.

🎯 Fix: 90 %
💥 Break: 5 %
💸 Cost: 106 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 81
🚦 Gate: ⚠️ cost 106 % > 100: operator approved the commit

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 07:45:49 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 fdf8722fc1 feat(orchestrator): S5.3 agent states, Status menu and 3D faces
Every Agents view marks each agent as working, alive, sleeping, suspending, unreachable or dead with an animated symbol; a Status menu hides states and switches the 3D faces, kept through a reload. The hub's container sees neither ~/.claude/sessions nor host processes, so the host timer kvb-orchestrator-sessions.timer runs client/sessions.py every 15 seconds while the page polls: it reads the session records without following symlinks, only regular files up to 64 KiB, keeps name, status and statusUpdatedAt within type and length bounds, checks the pid's process start, and writes agent-sessions.json atomically. The hub ignores a snapshot that is missing, malformed, older than five minutes or dated in the future. make orchestrator-install enables the timer and orchestrator-check reports it.

🎯 Fix: 90 %
💥 Break: 5 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 86
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 07:44:02 +00:00
Kevin Veen-Birkenbach 9123e05cd1 Merge feature/orchestrator-radio-numbers into master
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	docs/requirements/001-agent-orchestrator.md
2026-11-10 22:12:34 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 5dbf8d5f51 feat(orchestrator): speak radio numbers, times and paths the ICAO way
pronounced() rewrites a radio text for speech in four passes: paths become file or folder with name and parent (/tmp as temp, ~/ as home), dates with or without a clock become a date-time group converted to Zulu, times become four ICAO digits with Zulu for UTC, and hex runs, version numbers and the remaining digits are spelled in NATO and ICAO words with Decimal between digits. Invalid dates and times stay as written; the displayed text is unchanged.

🎯 Fix: 90 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 86
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 22:11:02 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 78f3d953e7 feat(orchestrator): radio icon in the header opens the radio spot on every tab
The header radio button opens the radio spot above the main area of the current tab. The Send button, the toolbar radio button and the Radio tab are gone, the mayday clears inside the spot without a Cancel mayday label, and the radio station probe waits for a visible row.

🎯 Fix: 92 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 21:10:20 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 57ab29eb0d feat(orchestrator): S5.1 radio spot, compact menus, trend, ETA and Tasks 3D
🧪 Test / 🧪 Lock + lint (push) Canceled after 0s
Requirement 001 decisions 52 to 58 (operator 2026-11-09):

- Radio spot: the Agents toolbar radio button expands inline with the one
  composer (every channel, post and call recipients, Record, Send), a gear
  with the radio settings (tones, squelch, read aloud, moved out of the
  general settings) and Cancel mayday, which leaves the toolbar; the Radio
  tab keeps speakers, stations and the log plus a jump to the spot.
- Day/Night menu: the badge and Drain, Suspend and Resume only; each
  explanation is the button's tooltip.
- Tasks toolbar: views, filter, estimation, sort and business value in one
  wrapping row with a Request choices dropdown; the status chips stay the
  second row.
- Burndown and burnup: a trend selector (off, linear regression, velocity
  over N days) stored in the hub settings, the trend lines and the forecast
  date on the chart, and a tooltip per point with the work packages that
  started, ended or joined there.
- ETA: every list row shows its ETA (end when done, else start or now plus
  the forecast length behind its predecessors), sharing one predecessor
  walk with the Gantt.
- Tasks 3D: a sixth view on the 3D engine with the dependency edges in the
  Gantt colours, layouts Force and Time.
- Steady 3D camera: the view fits once per graph build, refreshes keep the
  operator's camera.
- e2e: Firefox runs with its profile as cwd, so its crashreporter no longer
  drops core dumps into the repository.
- A forecast beyond the last second a Date can hold is no forecast, so a
  nearly flat regression no longer aborts the Tasks render.

Evidence: make test Ran 717 OK, ruff clean, markdownlint 0 errors; e2e 30 of
30 OK in Chromium and Firefox at 1920, 1366 and 390 px; MEDUSA 0 findings
after one skeptic-accepted lexical EXA006.

🎯 Fix: 93 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 08:10:51 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 d9eb121d12 feat(orchestrator): S5 Tasks with choices, Gantt, estimates and burn charts
Requirement 001 phase 6, S5:

- Tasks tab: every pending ask, rule request, operator row and choice
  card shows under "waits on Operator"; a choice request goes out on a
  fixed channel button, post and call with an agent multi-select, and a
  click on an option sends a passkey-signed answer the agent checks with
  operator_message. The unsigned /api/decisions/<id>/choose route is
  gone, and a decision, choice answer or choice recipient whose name
  holds "*" is refused, so a signed answer never reaches every agent.
- Gantt view: one bar per task from start to end (running to now), one
  arrow per explicit, branch-base and queue-order edge, hatched forecast
  bars (always, points only, real only) from the median duration or
  points times median hours per point.
- rasci.py set --after/--drop-after stores task dependencies and refuses
  unknown tasks and cycles.
- Estimation toggle (No estimate default, Story points) is stored in the
  hub settings; burndown and burnup per whole register, list filter or
  one agent or line, counting tasks or summing complexity with the
  unestimated tasks as their own line.
- New skill kvb-org-queue-estimate: "Request estimates" (story points
  mode, passkey-signed board action) or the skill sends exactly one
  newsletter listing every unestimated task with its RASCI parties; a
  party name that is no plain name shows as "unnamed party".
- Business value per task or in bulk is stored only with a verified
  passkey assertion over the exact ids and values; WSJF uses it instead
  of the median. The task list sorts by every decision-50 mode both ways.
- e2e: the walk's pending ask lives an hour instead of 60 s, and the
  CDP and BiDi drivers retry removing the browser profile while the
  browser exits (ENOTEMPTY).

Evidence: make test 709 OK, ruff and markdownlint clean
(/tmp/s5-make-test-fix-2.log); e2e 26 OK in Chromium and Firefox
(/tmp/s5-e2e-fix-2.log); MEDUSA 50 files, an independent skeptic
rejected four holes (unsigned choose route, unsigned estimates request,
free-text party names, "*" recipients incl. normalizer bypasses), all
fixed and re-verified, the 8 remaining pattern hits accepted, rescan 0
open.

🎯 Fix: 92 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 88
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 06:53:55 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 5c8b69d53d feat(skills)!: S4 night commands become drain, suspend and resume
Requirement 001 phase 6, S4 (decision 29):

- Skills renamed: kvb-org-evening -> kvb-org-drain, kvb-org-sunset ->
  kvb-org-suspend, kvb-org-sunrise -> kvb-org-resume, kvb-agent-relax
  -> kvb-agent-drain, kvb-agent-sleep -> kvb-agent-suspend,
  kvb-agent-wakeup -> kvb-agent-resume; their text uses the new verbs and
  every reference in skills, README, orchestrator and tests follows.
- night.py takes drain, suspend, resume, resume --alone and status. A
  state file written before the rename keeps working: mode evening reads
  as drain, sunset as suspend, the awake list as resumed and is rewritten
  on the next save; the hub's council.night_mode maps the same values.
  mode: day and handover_night_<session>.md keep their names.
- Orchestrator: the Day/Night menu shows Drain, Suspend and Resume, each
  confirmed, signed through /api/board/sign with the passkey and run as
  the existing argv job; the old action names are refused.
- kvb-skill-cleanup: git rates two renames at 44 and 50 % similarity,
  under its default threshold, so legacy.py detects renames from 40 %.
- tests/test_night_names.py fails on any old name in the tree outside a
  rename record "old ->".

BREAKING CHANGE: the six old skill names and night.py's clear and wake
are gone. Run make install (it reinstalls the orchestrator too), then
kvb-skill-cleanup to remove the old installed copies; until the install,
the running hub calls the old night.py path.

Evidence: make test 679 OK, ruff and markdownlint clean
(/tmp/s4-make-test-1.log); e2e 22 OK in Chromium and Firefox
(/tmp/s4-e2e-3.log); MEDUSA 23 files, the 2 findings are the
byte-identical atomic state write that moved with night.py, already
accepted after a skeptic at its old path, rescan 0 open.

🎯 Fix: 93 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 23:18:18 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 4d88296e47 feat(orchestrator): S3 generated SVG faces whose mouths move while speaking
Requirement 001 phase 6, S3:

- faces.js derives a face from the agent's stable key (its session id,
  or name:<name> without a session), so a rename keeps the face: shape
  4, colour 7, eyes 5, brows 4, mouth 5, hair or headwear 6, accessory 5,
  84,000 combinations. It emits constant SVG tags and attributes only.
- The emoji avatar is gone: popup, Orbit and Chord nodes, the radio
  view, stream and palette draw the SVG face (the 3D views keep their
  marker).
- While the radio reads an agent's message, its faces carry the class
  speaking and the mouth runs the talk keyframes; a silent face does
  not move, and prefers-reduced-motion stops the mouth.

Evidence: make test 673 OK, ruff and markdownlint clean
(/tmp/s3-make-test-1.log); e2e 20 OK in Chromium and Firefox, none
skipped (/tmp/s3-e2e-3.log); screenshots
/tmp/orchestrator-phase4-shots/*-speaking.png; MEDUSA 13 files, 2
findings ("PLA" in "templates", the UI call openAgent) accepted after
an independent skeptic that found no markup sink or selector injection
in the face code.

🎯 Fix: 94 %
💥 Break: 3 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 91
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 22:06:31 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 d89fb616b8 feat(orchestrator): S2 agent and node popups with leader line, node search
Requirement 001 phase 6, S2:

- Agent popup: a click on an agent opens one fading <dialog> with face,
  name, earlier names, offices, tasks, claims, subagents, history and
  the composer; Escape or a click outside closes it. The agent drawer
  and the Details side panel are gone.
- Node popup: a click on a node in a graph view enlarges it and marks it
  red, and an SVG leader line ties it to the translucent popup; a click
  elsewhere restores the node. popup.js places the popup right, left,
  below or above the node, caps its height to the room there and
  returns the line.
- Search: in the 3D views a search field with suggestions replaces the
  list of every node, one chip per distinct label.
- Fit: body.fit now applies at every width; without the side panel the
  orbit view otherwise grew a page scrollbar at 390 px.
- Two page modules had silently shadowed each other's functions of the
  same name while this was built; test_no_two_page_modules_declare_the_same_function
  now guards that. Artifact ids carry NUL, which CSS.escape turns into
  U+FFFD, so the node lookup compares dataset values.

- Composer: a message goes to the agent whose popup it was written in.
  deliver() read the global ui.agent after awaiting the upload, so
  closing the popup or opening another agent during an upload sent the
  signed message to null or to the other agent (found by the security
  skeptic, present before, easier now that a backdrop click closes).

Limits: the 3D leader line is placed when the popup opens and does not
follow the camera while the layout settles; the search keeps the first
node per label, so a second repository's main branch is found in the
graph, not through the search.

Evidence: make test 667 OK, ruff and markdownlint clean
(/tmp/s2-make-test-1.log); e2e 19 OK in Chromium and Firefox at 1920,
1366 and 390 px, none skipped, rerun after the composer fix
(/tmp/s2-e2e-4.log); screenshots in /tmp/orchestrator-phase4-shots/;
MEDUSA 22 files, 6 findings (a "PLA" pattern in "templates", the UI
names openAgent and drawAgent) accepted after an independent skeptic
that also found no XSS or selector injection in the popup code.

🎯 Fix: 93 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 21:18:55 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 c035373518 feat(orchestrator)!: S0 English everywhere, Sécurité, NATO hashes, ICAO digits
Requirement 001 phase 6, S0:

- Speech: the security class shows as "Sécurité" and is spoken as in
  maritime radio, "say-cure-ee-tay" three times. A hex run of 7 or more
  characters with a letter and a digit (commit, session, message ids) is
  spelled in the NATO alphabet; every other digit is spoken on its own
  in ICAO pronunciation (42305: four two tree zero fife). The spelling
  runs inside clip() before the length cut, so a phrase still fits
  SPEECH_LIMIT; the displayed text keeps its digits and hashes.
- English: every orchestrator label, tooltip, message, error, script
  output, document and test string is English (Regeln -> Firewall,
  Hierarchie -> Hierarchy, Steuerung -> Controls, Ausführen -> Run, ...);
  the page declares lang="en" and formats dates as en-GB. Task filter
  ids are English. German stays only in the skill trigger phrases that
  quote the operator, and as identifiers: the view keys (view=) and the
  leitstand id.
- tests/test_english.py scans every tracked text file for umlauts and
  German words, with an allowlist of the quoted trigger phrases.

BREAKING CHANGE: the Stream search tokens art: and seit: are now kind:
and since:; an old art: or seit: token counts as a plain word.

Evidence: make test 657 OK, ruff and markdownlint clean
(/tmp/s0-make-test-1.log); e2e 17 OK, none skipped (/tmp/s0-e2e-1.log);
MEDUSA 86 files, 24 findings on reworded strings accepted after an
independent skeptic (21 path:line, 0 rejected, no behaviour change in
signing, approving, rules, denying, offices, events), rescan 0 open.

🎯 Fix: 93 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 17:26:51 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 a388c6ef77 fix(orchestrator): S1 fit, rename once, Deutschlandfunk e2e, squelch, tree cause
Requirement 001 phase 6, S1:

- Fit: Agents and Artifacts in a graph view fill the window from 861 px
  up (body.fit flex column); the e2e walk probes #agents/orbit at every
  width for a page no taller than the window.
- Rename once: a session seen under two names by one source (two claims)
  flipped its name on every state build, so the Stream logged a rename
  each poll. Names.observe keeps only the newest sighting per session
  and source, and the timeline emits each (session, before, after) pair
  once.
- Deutschlandfunk: root cause was the signed media-src, which never
  listed the redirect target f111.rndfnk.com that st01.sslstream.dlf.de
  answers with (fixed in ba97f7c). The e2e now replays that chain, a
  302 from one https origin to a second, in Chromium and Firefox, with
  self-signed throwaway certificates the drivers accept.
- Squelch: a settings slider 0..1 scales every tone; at 0 no beep plays,
  music on or off (Voice.beep skips a silent tone). Stored settings
  without the key load with 1.0.
- Tree: the missing tree file error names `pkgmgr branch tree` and the
  release and install step that makes the timer write it.

Evidence: make test 655 OK, ruff and markdownlint clean
(/tmp/s1-make-test-1.log); e2e 17 OK, none skipped (/tmp/s1-e2e-3.log);
MEDUSA 14 files, 0 findings.

🎯 Fix: 94 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 90
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 13:37:02 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 46382cee9a docs(requirements): add Gantt, estimates and burn charts to 001 S5
Records the operator's decisions 44 to 51 of 2026-11-08 for the Tasks
tab: a Gantt view with dependency arrows from an explicit rasci --after
field, the branch base and the queue order; a forecast selector; the
estimation modes No estimate (default) and Story points; burndown and
burnup with a scope selector; an estimate newsletter sent only on a
button click or /kvb-org-queue-estimate to every agent holding a RASCI
role; a passkey-signed operator business value, also as one bulk batch;
and sort modes for the task list. They join subtree S5.

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: –
🛡️ Security: 100 %
🏆 Score: 94
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 09:44:17 +00:00