Commit Graph
213 Commits
Author SHA1 Message Date
Kevin Veen-BirkenbachandClaude Opus 5.5 9f34768497 fix(kvb-check-gate): skip parent journal rows whose text cannot be encoded
A row with a lone surrogate in gate-parents.jsonl, which sandboxed agents can write, raised UnicodeEncodeError at the TEMP table insert and crashed every commit-msg, pre-push and pre-merge-commit hook and the hub gate view. opened() now keeps only rows whose repo, branch and parent encode; the test fails without the change.

🎯 Fix: 97 %
💥 Break: 2 %
💸 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>
2026-11-12 18:09:16 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 c8b2e586de fix(orchestrator): hub gate view reads recorded parents through gates.opened
W5 moved recorded parents into a journal that gates.opened() loads into a TEMP table; the W3 hub opened gates.db raw, so parents_of() raised and the gate view stayed empty. opened() and journal() take the kept directory explicitly (CLI: watch.KEPT, hub: its /kept mount), opened() closes the connection when setup raises, and the W3 tests use opened() plus a test for a parent from the kept journal.

🎯 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>
2026-11-12 18:07:17 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 39ffb1d45e Merge chore/skills-test-efficiency into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:28:11 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 8c5c0b118e Merge feature/kvb-git-pkgmgr-wrappers-replay into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:26:39 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 04715f89e3 Merge feature/kvb-code-clean/comments into unify/skills-20261112
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:26:39 +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 f7c585d56e Merge feature/workbench-w5-gates-receipts into unify/skills-20261112
Conflict in queue.py cmd_hold: kept the light-footprint aliases and per-kind stats, added W5's gated() call; W5's qualified() signature is gone and was unused below.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:23:19 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 6540e4e4f1 perf(kvb-check-security): cache findings and bound scan workers
security.py caches findings for 24 h, keyed by content, mode, the medusa binary, PATH and MEDUSA_ variables, in an owner-only directory, and runs medusa with min(files, 4) workers. Committed below the bar on the operator's word 2026-11-12 (one gate after the merge): test_security 14 green, the before-and-after measurement never ran; the GOMAXPROCS cap stays unstaged.

🎯 Fix: 70 %
💥 Break: 10 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 95 %
🏆 Score: 60
🚦 Gate: ⛔ fix 70 % < 90, break 10 % > 5; security 95 % < 100: ask the operator before the commit

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 16:18:08 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 59d9e29bcb fix(kvb-org-queue): book light jobs by their own footprint
Light single-file runs booked about 17 % RAM and 5 GB learned from heavy runs under a polluted signature. Each entry now stores its aliases, freezes its footprint at grant and learns per signature and kind; heavy kinds book at least the old pooled share, and a job keeps its own learned disk need when the old pool is empty. Hooks take the payload cwd and fall back to the old rule when it is unknown or malformed. Six skill docs now agree on what self-admits. test_queue 70, test_watch 46 and test_operator 30 green with negative controls; two independent reviews.

🎯 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>
2026-11-12 16:17:38 +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 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 7d1b8aef4d fix(kvb-git-branch-cleanup): trim description to fit the listing budget
The replayed pkgmgr wrapper skills put the description listing at 1501 of 1500 words; one word less brings it back to 1500.

🎯 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 11:30:22 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 7c0872ea68 fix(kvb-org-queue): reread the config on every poll of a waiting hold
A waiting hold kept the config.json it started with, so a raised RAM or slot limit only reached it after cancel and re-hold. wait() now calls fresh() each poll; a missing, unreadable or incomplete file keeps the last complete config, so a half-saved edit never ends a wait. The History and learning details move to learning.md, bringing SKILL.md from 605 to 540 of 600 words and clearing master's red test_lock.

🎯 Fix: 92 %
💥 Break: 3 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 11:25:24 +00:00
Kevin Veen-Birkenbach 7618492d66 feat(kvb-git): follow the pkgmgr merge flow of each worktree
pkgmgr worktree flow (pkgmgr 7fb2296, live after its release) records per worktree the refs merged in before a gate (pull) and the branches the finished branch merges into (push). The skills now act on it:

- hotfix.py sync merges, after origin/<default> and the register's base chain, every entry of the flow's pull list that is not merged already; an invalid flow file stops sync with exit 2 before any merge. pkgmgr starts only when <git-dir>/pkgmgr/flow.yml exists, so a sync without a flow, and the tests, never run the system pkgmgr wrapper.
- kvb-org-split merges a finished sidetree into each push target of the flow in order, its upstream when none is set.
- kvb-git-commit-next names the push targets the branch flows into when it closes.

Word budgets kept (kvb-git-hotfix and kvb-org-split trimmed back under 600), skill text 2807 -> 2809 tokens. Tests: 38 hotfix tests OK, 3 new (pull list merged after the chain, invalid flow refused before any merge, no pkgmgr start without a flow file).

🎯 Fix: 93 %
💥 Break: 3 %
💸 Cost: 100 %
⏱️ Time: 99 %
🛡️ Security: 100 %
🏆 Score: 91
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 1e1fd0e79821ad9a8d4fea99b38ac59ecb02d7b2)
2026-11-12 10:40:49 +00:00
Kevin Veen-Birkenbach 7199e6bfba feat(kvb-cleanup): take the inventory from pkgmgr gc --report
The /tmp inventory starts from one read-only pkgmgr gc --report pass over /tmp and the write-scope dirs, du -sh only without pkgmgr. The worktree-orphans rule moves into worktrees.md, keeping SKILL.md under its 600-word cap at unchanged token cost.

🎯 Fix: 95 %
💥 Break: 2 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit ad2e97aae428fe23e3a4828776ff045766ff9722)
2026-11-12 10:38:54 +00:00
Kevin Veen-Birkenbach ebe7886654 feat(kvb-git): wrap the pkgmgr worktree and gc commands as skills
kvb-git-branch-gc becomes kvb-git-branch-cleanup and kvb-git-orphans-find becomes kvb-git-worktree-orphans, which drops its own orphans.py for pkgmgr's output. New wrappers: kvb-git-gc, kvb-git-worktree-cleanup and kvb-git-worktree-up. kvb-cleanup, kvb-dream, AGENTS.md and README.md point at the new names. Merges only after the pkgmgr release that ships these commands.

🎯 Fix: 90 %
💥 Break: 3 %
💸 Cost: new
⏱️ Time: new
🛡️ Security: 100 %
🏆 Score: 87
🚦 Gate: cost new, time new: cleared by the operator's commit word for the Skills wrappers (2026-11-07)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 18dade9a48a84761bf0c3a9b35584367ae0cb0e4)
2026-11-12 10:38:42 +00:00
Kevin Veen-Birkenbach fd8fc08603 Merge fix/kvb-check-security-accept-key-collision into unify/skills-20261111
🧪 Test / 🧪 Lock + lint (push) Canceled after 0s
2026-11-12 09:19:56 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 32591405ab fix(kvb-check-security): one acceptance never hides an identical line elsewhere
An acceptance was keyed by rule, path and the sha1 of the stripped line, so two identical flagged lines in one file shared it: Experiment accepted a false positive at utils/docker/registry.py:105 and the real B310 at :78, same text, vanished from the score (2026-11-12). A row without context now accepts a finding only while no other finding of the scan shares its rule, path and text; accept --line binds a row to the sha1 of the five surrounding lines and is required when the line's text occurs more than once in the file, and refuses a --sha1 that is not that line's. Existing rows keep working on unique lines; the new test fails on master (100 percent, 2 accepted) and passes here (50, then 75 percent).

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

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 09:19:45 +00:00
Kevin Veen-Birkenbach 37265fdb4e Merge fix/kvb-org-queue-light-kinds-skip-reservations into unify/skills-20261111 2026-11-12 08:48:17 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 151031ab4a fix(kvb-org-queue): light kinds meet only running and granted jobs, never a reservation
Every entry blocked by budget or disk added its share to the tally of all entries behind it, and a head the host load keeps out counted as granted while a job ran, so test-nostack jobs needing 0 GB and 11 % CPU waited behind 'CPU 170-242 % in use or reserved' (live queue 2026-11-12). Operator pick on the chair's ask: a light_kinds entry is now checked only against running and granted entries; reservations, a load-held head included, hold back heavy kinds alone. resources() returns what a job takes or reserves, so evaluate() keeps both tallies. Heavy-only queues give master's verdicts (skeptic probe: 0 of 40000 random cases differ); a stream of light jobs can delay a heavy head, as the docstring and SKILL.md now state. Tests kill the reviewer's three mutants and fail on master.

🎯 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>
2026-11-12 08:47:26 +00:00
Kevin Veen-Birkenbach 64bd13cecb Merge fix/kvb-org-organize-council-git-marker into fix/kvb-org-queue-load-held-reserves-nothing
🧪 Test / 🧪 Lock + lint (push) Canceled after 0s
2026-11-12 08:40:39 +00:00
Kevin Veen-Birkenbach 4df1c2e48c Merge master into unify/skills-20261111 2026-11-12 08:23:22 +00:00
Kevin Veen-Birkenbach 21a044b428 Merge fix/kvb-org-organize-council-git-marker into fix/kvb-org-queue-load-held-reserves-nothing 2026-11-12 08:15:40 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 256fe2c327 fix(kvb-org-queue): an idle queue no longer waits on a head the host load alone keeps out
evaluate() counted a non-hotfix entry that passed every queue check but was held back by the live host load as granted for every entry after it: its slot, the exclusive-kind drain and its CPU/RAM share. With RAM held outside the queue the head never started and nothing behind it did either (2026-11-12 03:50 UTC: 27 entries, no job active, host idle). While no queue job is active, such an entry now reserves nothing and holds nothing back; with jobs active it keeps its reservation, and a load-held hotfix still holds back every entry after it. Replayed on the live queue, the fix grants test-nostack-1035 at once.

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

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 08:08:40 +00:00
Kevin Veen-Birkenbach 6b75be39d5 Merge feature/operator-workbench into unify/skills-20261111 2026-11-11 22:51:51 +00:00
Kevin Veen-Birkenbach 45db829e45 Merge fix/kvb-check-gate-excluded-targets into unify/skills-20261111 2026-11-11 22:36:00 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 9f598a56ab fix(kvb-org-organize): count only real git markers in the council gate
An empty /tmp/.git (2026-11-11 19:47, owner unknown) made council.py gate treat all of /tmp as a git worktree: every unclaimed Edit or Write under /tmp was blocked and test_council turned every skills gate red. A parent now counts only when its .git is a directory holding HEAD or a regular file starting with gitdir:, as git itself requires, so normal repos, linked worktrees and submodules still block unclaimed edits. A FIFO named .git is never opened, so it cannot hang the hook. Root fix proposed by the chair Main.

🎯 Fix: 94 %
💥 Break: 3 %
💸 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>
2026-11-11 22:35:39 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 bcbcd9f9a2 fix(kvb-check-gate): exclude operator-listed targets from every gate
gate_excluded_targets in .claude/agents-council/config.json of the passwd home (never $HOME or the environment, so no caller swaps in its own list) names targets no gate requires or runs. status shows them excluded and keeps the gate green without them, naming the exclusion and the config in the green line; excluding every target keeps the gate open and skips the hotfix check. run refuses an excluded target with exit 2. Operator order 2026-11-11: no oracle tests in any gate.

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

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 22:34:47 +00:00
Kevin Veen-Birkenbach 4ab13b6e65 Merge fix/kvb-org-queue-footprint-noise into master
🧪 Test / 🧪 Lock + lint (push) Canceled after 0s
2026-11-11 21:31:48 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 c1a88c6556 fix(kvb-org-queue): learn CPU by median, path-free signatures, exclusive gate kinds
The CPU share learned the p90 of the host-wide peak minus before, which carries every neighbour's spike: 30 days of history give test-nostack a p90 of 73.8 against a median of 9.7, and rows that no other job overlaps learn the same p90, so concurrency is not the cause. signature() also kept the --repo value of a script as its operand, so every worktree's scan learned apart and fell back to the kind (130 of 301 test-nostack rows). The CPU share now learns the median while RAM keeps the p90, and an operand holding a path separator leaves the signature. New optional config keys exclusive_kinds and light_kinds: a job of an exclusive kind runs only beside light kinds, and an exclusive entry that only running jobs of other kinds keep out holds back every later non-light entry, so no lower-ranked job overtakes a waiting gate.

🎯 Fix: 91 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 87
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 20:39:19 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 ca54420f4d fix(kvb-org-queue): restart holders on stale queue code; link host skills into projects
Every holder judges the shared queue.json with its own loaded code, so the project copies from 2026-11-07 (no RAM/CPU budget) granted heavy jobs on the slot limit alone and overloaded the host at 18:24. Each entry now stamps a hash of queue.py and the sibling scripts it loads; a poll that finds other code installed in ~/.agents/skills leaves the queue ungranted and re-execs the same hold with the installed queue.py, on the realpath interpreter, with signals reset and a caught signal ending the hold instead. queue.py list prefixes entries on other or unstamped code. A project install now symlinks every skill the global install holds instead of copying it, so the project hooks and ../ references stay valid and one host runs one version.

🎯 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>
2026-11-11 20:33:54 +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-BirkenbachandClaude Opus 5.5 134b1d30f1 fix(kvb-org-queue): a hotfix held back by host load holds back the entries after it
The grant order ignored live load: a prio-1 hotfix that fit the budget but waited on RAM or CPU counted as granted for the entries after it, so CPU-light jobs behind it could start, keep the load up and starve it. Such a hotfix now holds back every entry after it until it starts (operator pick 2026-11-11 on Main's report). Each holder stores the reason of its last poll, and list shows it, so a job the load holds back no longer reads as granted, without list sampling the CPU.

🎯 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>
2026-11-11 16:34:37 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 5053c6a9be Merge fix/kvb-org-operator/executable-commands into master
🎯 Fix: 93 %
💥 Break: 4 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 16:13:06 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 928d50f600 Merge fix/kvb-check-security/file-level-fingerprint into master
🎯 Fix: 95 %
💥 Break: 2 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 16:13:03 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 87669ad138 Merge fix/skills/no-diff-in-chat into master
🎯 Fix: 92 %
💥 Break: 2 %
💸 Cost: 99 %
⏱️ 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>
2026-11-11 16:13:00 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 47ec0213e1 fix(kvb-org-operator): refuse operator commands no shell can run
operator.py add accepted prose, slash commands, aliases and <slot> commands as runnable rows, so the operator got bash blocks that do nothing or fail. A command must now start, after VAR=value words, with a program on PATH, a path to one or a shell builtin, and hold no <slot>; anything else is refused unless the row is a decision. Older rows of that kind stay in the table but get no bash block and are skipped by run. Ordered by the operator on 2026-11-11.

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

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 16:12:43 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 87426c0046 fix(kvb-check-security): accept a finding without a line by the sha1 of its file
A MEDUSA finding without a line number (a Dockerfile-level rule, for example) had no fingerprint, so security.py accept could never waive it and the score stayed below 100 after review. Such a finding is now keyed by the sha1 of the whole file; any edit of the file brings it back.

🎯 Fix: 95 %
💥 Break: 2 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 15:48:11 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 3ad111be0a fix(skills): show the diff stat, never the diff, in commit and essence skills
kvb-git-commit-no-verify, kvb-git-commit-next and kvb-skill-essence printed the full staged diff into the chat before every commit or batch write. The operator ordered on 2026-11-11 that the chat shows only the diff stat and the score table, to save tokens.

🎯 Fix: 92 %
💥 Break: 2 %
💸 Cost: 99 %
⏱️ 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>
2026-11-11 15:40:15 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 7043cdfd98 fix(kvb-org-queue): book a job at its own command's footprint
A command with 5+ runs is booked at its own p90 RAM and CPU share, an unlearned one at its kind's p90. The old rule took the larger of kind and command, and for an unlearned command the largest command of its kind: test-nostack-788 (docker build) sat 90 min at position 1, booked at 42.6 % RAM from a legacy gate.py hold row while test-nostack measures 5.6 %; skills make test (3.3 %) was booked at the test kind's 35 %.

🎯 Fix: 93 %
💥 Break: 5 %
💸 Cost: 99 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 12:07:13 +00:00
Kevin Veen-Birkenbach 45063dc71f Merge fix/kvb-org-queue/unclaimed-grant into master 2026-11-11 09:51:46 +00:00
Kevin Veen-Birkenbach b87fb4cc37 Merge fix/kvb-org-unify/listing-budget into master 2026-11-11 09:51:45 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 4df3945066 fix(kvb-org-queue): an unclaimed grant drops its reservation
evaluate counted every unblocked waiting entry as granted for the entries behind it, but only that entry's own wait() poll turns it active; a living holder that stopped polling kept its slot and share forever and wedged the queue. Every poll now stamps polled; a waiting entry silent for CLAIM_SECONDS (3 polls) reserves nothing and is listed last, and once it polls again it takes a fresh seq and enqueue time, so it rejoins at the back of its rank.

🎯 Fix: 92 %
💥 Break: 3 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 89
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:51:29 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 d59a234a8c fix(kvb-org-unify): fit the skill listing budget and drop the German trigger
The 33-word description pushed the listing to 1518 of 1500 words and its trigger phrase was German, so test_lock and test_english failed on master after the swarm/unify merge. The description now has 14 words; the listing holds 1499.

🎯 Fix: 97 %
💥 Break: 1 %
💸 Cost: 96 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 100
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:50:32 +00:00
Kevin Veen-Birkenbach 083fcb37e0 Merge fix/kvb-org-organize/cache-missing-root into master 2026-11-11 09:47:15 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 8f942ff071 fix(kvb-org-organize): skip a missing cache root in the cache trim
cache_files walked every cache_dirs entry with os.fwalk, which raises FileNotFoundError for a folder that does not exist (~/.cache/ms-playwright on this host), so cleanup --caches crashed and trim_caches never ran at disk stage warn. A root that cannot be walked is now skipped and the other roots are still trimmed.

🎯 Fix: 95 %
💥 Break: 2 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 93
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 09:44:40 +00:00
Kevin Veen-Birkenbach 275745ba1d Merge feature/kvb-org-swarm-unify into master 2026-11-11 08:45:47 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 68d3bc337a feat(skills): rename kvb-org-split to kvb-org-swarm, add kvb-org-unify
kvb-org-swarm keeps agent work in its own worktree until it meets 90/5; kvb-org-unify brings the swarm's branches back together. Every skill that named kvb-org-split now names kvb-org-swarm. Cost 111 % accepted by the operator on 2026-11-11.

🎯 Fix: 92 %
💥 Break: 3 %
💸 Cost: 111 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 80
🚦 Gate: ⚠️ cost 111 % > 100: ask the operator before the commit

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 08:44:58 +00:00
Kevin Veen-BirkenbachandClaude Opus 5.5 29d6afae72 style(kvb-org-operator): drop two trip-wire comments
🎯 Fix: 98 %
💥 Break: 1 %
💸 Cost: 100 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 97
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-11 08:41:26 +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