- Plugin bootstrap: a failed npm install, a Node older than 22.5 or a failed UI
build is recorded in runtime/last-failure.json; the next SessionStart prints
it once as a systemMessage naming the log and /agenthub-doctor (a different
failure is reported again; a successful bootstrap clears it). The foreground
pass checks the Node version itself and spawns no worker on an old Node.
- ReDoc: the standalone bundle (redoc 2.5.4, MIT, licence files kept) is
vendored under server/vendor/redoc/ and the `redoc` dependency dropped —
a runtime install (npm ci --omit=dev --ignore-scripts) goes 126 MB -> 45 MB.
vendor/ is excluded from the header audit and prettier.
- git missing from PATH: lane git actions answer 503 EGITMISSING with the
install command instead of a bare ENOENT.
- package.json engines: node >=22.5.0 (node:sqlite), matching MIN_NODE.
- Docs: INSTALL.md is the one install/setup guide (SETUP.md merged in and now a
pointer); no VS Code extension claim, one client-install hint, no
windows-build-tools, better-sqlite3 notes scoped to checkouts, new
"Plugin bootstrap never comes up" troubleshooting entry.
- Chat view: an attached image's path is pasted on its own after the text
(promptForPane). claude turns a paste that is only an image path into
[Image #n], but left a Windows path inside a paste of text as a plain path.
Other files and @-mentions stay in the text as before.
- Plugin bootstrap: depsHash covers only what npm installs (no release
version), so a version bump no longer reinstalls runtime deps; the client's
installed tree is kept while its manifests are unchanged (no npm ci per
update); the user-side build runs vite only (tsc -b cost ~25 s / ~900 MB);
clientBuild is recorded only after a build that did not fail, so a failed
one is retried; npm output goes to runtime/npm-install.log.
- Server: a port held by another program ends with a clear message and exit 1
instead of an uncaught 'error' stack trace.
- Client: the onboarding wizard is lazy and rendered only before onboarding;
usePrefersReducedMotion moved to hooks/ so PetSettings no longer pulls the
Sagi chat/pane stack into the entry chunk (884 KB -> 431 KB, gzip 268 -> 133 KB).
- Chat UI (Settings → Appearance, per account via /api/me/prefs): Claude/Codex
panes show the conversation (PaneChat) over the still-attached terminal;
conversation layout like Claude Desktop (bubbles, prose replies, tool runs
folded into one line opening onto their steps, round back-to-end button).
- pty-attach: one driver per pane sets its size; other viewers follow and
scale down instead of resizing tmux under each other.
- Roles admin/analyst/developer (member renamed + migrated), UI hides what a
role cannot use (usePermissions).
- Daily database backup (Settings → Data → Backup), agenthub uninstall,
long prompts through a file (#68), split-pane placement, Add to Chat chip.
Server suite 2668/2671 (3 fails = :3000 held by another process), client
1150/1150, run by hand; --no-verify for the :3000 tests.
Usage panel (status bar):
- every account shows its plan (Claude subscriptionType, Codex
chatgpt_plan_type, Cursor membershipType, Grok subscriptionTier)
- new quota rows: Cursor CLI (cursor.com usage-summary), Antigravity
(`agy --print /usage`, two model pools; AGENTHUB_AGY_USAGE=0 never runs
agy), Grok Build, Kimi Code, OpenCode Go — each login read from the tool's
own file, sent only to its own host while valid, never refreshed
- in-flight quota reads are shared between tabs
AI Tools catalog: Grok Build (`grok`) and Kimi Code (`kimi`) added;
Gemini CLI, Hermes and OpenClaw removed.
Also: Quit AgentHub (#65, `agenthub stop`), status-area icon, Add to Chat
on an editor selection, Settings in three groups, JetBrains-style Changes
panel (ticked files/hunks, ignore, blame, file history), terminal font.
--no-verify: :3000 is taken by another dev server (lane-detect tests);
both suites run by hand — server 2636/2639 (the 3 are :3000), client
1131/1131.
- Windows panes: a WinGet tmux runs native programs and there is no `sh`, so
every pane's `sh -c` wrapper died at once ("Command failed: tmux set-option
… mouse on"). paneArgv runs the CLI itself on win32, and a Terminal gets
tmux's own default shell (newSession drops the `--` for an empty argv).
- Plugin UI build: client deps install with --ignore-scripts and tsc/vite run
by the running node instead of `npm run build`. On Windows esbuild's
postinstall went through cmd.exe with no `node` on the server's PATH, both
installs failed, and Update now kept the previous UI. A test keeps the two
build steps equal to client/package.json's build script.
- Update all: Atomics.wait instead of a `sleep` binary Windows lacks.
A Windows self-update failed at "bootstrap": 'npm.cmd' is not recognized.
The update chain runs with the dashboard server's environment, whose PATH
need not reach npm.cmd, and the bootstrap looked npm up through cmd.exe
(shell: true, which also printed DEP0190).
- npmCommand() in scripts/plugin-bootstrap.js runs the npm bundled with the
running node (npm-cli.js beside process.execPath, Windows and Unix
layouts) with no shell, and puts that node's directory first on PATH (kept
under the env's own Path/PATH key) so npm scripts find the same node; npm
on PATH only when that node ships none
- Used by the runtime install, the UI build (plugin-open.js) and the
doctor's npm row (plugin-doctor.js)
- Settings → About → "Start AgentHub automatically" (AutostartSettings.tsx,
GET/PUT /api/settings/autostart, server/lib/autostart.js). The switch is
the systemd --user unit's / LaunchAgent's enabled state: on writes a unit
for the running server when none exists and enables it, off disables it;
neither starts or stops the server. A foreign unit is never touched
(409 EFOREIGN)
- The plugin bootstrap no longer installs a unit on every install: it
installs or starts one only while the user has it enabled, and a rewrite
keeps the enabled state (writeUserService({ enable })). An install that
already had the unit enabled stays on. A stale-but-enabled unit beside a
live detached server is repointed, no longer started onto the bound port
- unitIsEnabled / setUnitEnabled in systemd-service.js and launchd-service.js
Also:
- fix(workspace): status bar no longer covers the chat box below md (#61)
Analytics parity phases 2–7 (docs/plans/analytics-parity/), built on
138e706 and ported onto v2.3.1:
- Cost by AI tool (?tool= on cost/analytics/stats/workflows, by_tool,
Codex fast/priority and flex tiers, agenthub_cost_usd_total{tool,model})
- Date ranges (from/to) on cost/analytics/workflows; Analytics range select
with Today / This week (Monday) / This month (1st) / 7d / 30d / 90d / All /
Custom; workflow filters carried into workflow-stats.js (read worker)
- Budgets and cost alerts as alert rule types (alert_rules rebuilt without
its rule_type CHECK), GET /api/budgets/status, rule preview, spend pace,
status-bar budget chip; rules stay editable in place
- Query Explorer (/query, allowlisted sort, CSV/JSON export) and scheduled
reports (report_definitions/report_runs, Settings → Reports)
- Session Replay tab and immutable snapshots (session_snapshots, /snapshot/:token)
- Remote Codex sync, push ingest with a hashed token, privacy redaction and
ignored folders (Settings → Data), Cursor sessions (no cost)
- Read-only MCP server, statusline, Grafana/Prometheus files
Also: resizable sidebar, pet run/wave animations, the workspace home keeps a
half-typed prompt, and the pre-commit hook runs only the related tests for a
small commit.
- /api/workspaces and `agenthub workspace(s)` / `--workspace` as aliases of
/api/lanes and `agenthub lanes` / `--lane`; old names print one stderr note.
REPL `help lanes|workspace|workspaces` resolves through the aliases.
- A workspace holds up to ten sessions (slots 0-9); every console tab is a
group of 1-4 split panes (PaneGroups, agenthub.workspace.paneLayout);
parseGroups keeps the stored active tab when an earlier one is dropped.
- Browse button beside path fields: POST /api/lanes/pick-path opens the OS
picker on the server's desktop — loopback only and no forwarding header
(EREMOTE), a display failure is ENODIALOG not a Cancel, the dialog is
killed when the request closes, a folder field falls back to the in-app
browser on any failure.
- Changes rail counts chip, image viewer (/git/raw), status bar session
counts and per-day cost (`date=` on /api/pricing/cost).
- /agenthub-open and /agenthub-doctor run from the INSTALLED build
(supersededBy), doctor offers fixes behind two confirmations; plugin-open
treats a locked bootstrap as non-fatal.
- New-terminal shell waits for the first attach (issue #55).
- repo-onboarding / debug-live-issue skills removed.
- OpenAPI: pick-path, lane/date on /pricing/cost, tool on /run/history,
/api/workspaces mount.
Workspace sessions (docs/plans/desktop-parity, phases 1-5 and 7):
- sessions.lane_id: a workspace lists only the sessions its panes held,
stamped by bindRunSession (first writer wins, nested `claude -p`
excluded); GET /api/sessions?lane=&archived=
- session row state dot, double-click rename, archive (sessions.archived_at,
hides only); the activity bar's duplicate Sessions tab removed
- Fork beside Resume (--fork-session, Claude only), Ctrl/Cmd+click a live
session opens it in a second pane, a diff line's comment is pasted into
the workspace's last-focused pane (lib/panePaste.ts)
dashboard_runs stability:
- a pane's previous run is archived as <pane>@<started_at> instead of being
overwritten by INSERT OR REPLACE
- a run is flagged abandoned only once its tmux session is gone, at boot and
on the run-heal beat (panes outlive a server restart)
UI:
- sidebar: no footer, language or theme block; small collapse button in the
brand corner; version + update check in the connection details modal, a
status-bar dot while a release is out; language in Settings -> General
- one Switch component for every switch, the themed Checkbox for every
checkbox (no native checkboxes)
Also: AI Tools catalog trimmed to 10 built-ins (custom-file prompt modes
tested through fixtures), and the workspace plans under docs/plans/ (the
multi-user server plan lives in the AgentHub-Server repo).
Copy-only rename (workspace redesign, phase 0). The word a user reads
changes — "Lane" → "Workspace", "Add lane" → "Add workspace" — in both
locales, in agenthub CLI prose and help, in the server's error messages
and in the docs. Every identifier stays: /api/lanes, `agenthub lanes`,
--lane, AGENTHUB_LANE_ID, error codes, tmux names, DB tables, file,
component and i18n key names. docs/LANES.md keeps its name, retitled
"Workspaces (lanes)".
A `claude plugin update` run from a terminal (or with only the Claude desktop
app open) unpacks the new build and starts nothing: no SessionStart fires, so
the dashboard kept running the old cache dir across reboots, and with the
forge unreachable the sidebar read "Up to date" (seen on a machine stuck at
1.8.10).
- pluginStatus asks supersededBy for its own root: a recorded sibling install
sets `installed_not_running: {root, version}` and `update_available`, with
no network needed
- the sidebar reads "<version> installed, not running"; the update modal keys
on it, so Update now is offered even with no release tag or sha
- plugin-update-helper hands over to the recorded install first, the newest
sibling dir only as a fallback
- a plugin install whose release lookup failed reads "Could not check for
updates" instead of "Up to date"
- docs/PLUGINS.md: the case and the manual hand-over command
Part B: Model Pricing, Hook Configuration and CLAUDE_HOME move from
Settings → Dashboard to the Claude Code tab's AgentHub sub-tab
(ClaudeAgentHubSettings.tsx); CODEX_HOME is editable in Codex → AgentHub.
A home that is or contains the OS home is refused (EBADHOME).
Settings persistence: dashboard-saved settings go to
~/.config/agenthub/settings.env (AGENTHUB_SETTINGS_FILE), outside the plugin
cache an update wipes. Load order: real env > the checkout's .env > that file.
The first CLAUDE_HOME change pins DASHBOARD_DATA_DIR so the DB stays put.
C1: codex-usage.js reads Codex rollout journals into sessions (new column
tool) and token_usage, tracked per file in codex_rollouts; forks deduped by
total vector, sub-agent threads folded into the root; pricing-sync also
prices OpenAI models; PricingSettings with a vendor filter.
C2: codex-hooks.js installs AgentHub's hooks into $CODEX_HOME/hooks.json on
a click, through a stable forwarder; Codex trust is never written. The hook
route creates tool='codex' sessions and folds sub-agent hooks into the root.
D: antigravity-usage.js reads agy's per-conversation SQLite files (tokens
from ModelUsageStats) into tool='antigravity' sessions; antigravity-hooks.js
installs the named hook `agenthub` (PreInvocation, PostToolUse, Stop — never
PreToolUse) into ~/.gemini/config/hooks.json; Settings → Antigravity tab;
Gemini pricing.
Whole-change review fixes: sameOriginGuard on both home PUTs, routers.missing
on a CLAUDE_HOME change, reset-pricing scope, GET /api/sessions?tool=,
clear-data covering the new tables, Codex child-thread events moving no
status, hooks owning status only while current, EFOREIGN for a forwarder
that is not ours, agy quiet window and turn rules, AGENTHUB_SETTINGS_FILE
honoured from .env.
Docs, OpenAPI and the CLAUDE.md marker updated. Server 2141, client 779.
The plugin stops shipping its workflow layer:
- skills/ship-feature and skills/ship-feature-lane, the 18 stage/ship slash
commands (plugin.json keeps agenthub-doctor/update/open), and all four
agents/ (qc-local, senior-gate-reviewer, backend-reviewer, frontend-reviewer).
- CLI `agenthub skills install`, `agenthub lanes agents install`,
`agenthub ship-full|ship-quick`; routes POST /api/skills/install and
POST /api/lanes/:id/agents/install; the Settings button, the lane Tools
menu item and the Add-lane setup step that called them.
- The Superpowers auto-install: server/lib/skill-plugins.js, the bootstrap's
autoInstallSkillPlugins / skillPluginsSettled gate and the doctor row.
Pipelines are kept but dormant: server/data/pipelines/ is deleted, so no
template ships. `default` resolves to EMPTY_PIPELINE (no nodes, progress 0),
createLane still accepts it, POST /api/lanes/:id/stage answers 400
ENOPIPELINE, and the Workspace hides the stage timer, pickers, PipelineMap
and strip stage chip for a lane with no nodes. A template dropped into
DASHBOARD_PIPELINES_DIR turns it all back on. The server suite loads its
templates from server/__tests__/fixtures/pipelines/.
Docs: CLAUDE.md (marker, retired rules), README(.vi), INSTALL, ARCHITECTURE,
docs/LANES|PLUGINS|CLI|API, agenthub-introduction.html.
- git (#50): stage-hunk/discard-hunk take an optional `block` — one run of
consecutive +/- lines inside an @@ hunk. `onlyBlock` (server/lib/git-diff.js)
cuts git's fresh hunk down to it, folding the other blocks into the side
being checked; LaneDiffView hangs one review bar per block (unified + split)
and its arrows walk blocks.
- git exclude: entries AgentHub writes for a lane go to the COMMON git dir with
the lane's path prefix (server/lib/git-exclude.js, used by router-apply and
lane-mcp) — a linked worktree's own info/exclude is never read by git, and a
subdir lane has no .git. MCP sync no longer fails with ENOTDIR on a worktree
lane or creates a stray .git in a non-repo lane.
- codex lanes carry no pipeline: codex-ingest mirrors only idle/running,
codex-nudge is removed, agents install writes nothing for codex, the
Workspace hides stage/pipeline/feature pickers/PipelineMap for them, and
every server start clears leftover codex stage data and the old AGENTS.md
stage block.
- Changes panel: a whole file opens for reading and enters the editor on a
click on its text (caret at the clicked line), not automatically.
- macOS: LaunchAgent start-at-login (scripts/launchd-service.js, picked by
scripts/service-manager.js).
- Adds the AgentHub introduction slides and their image-embedding script.
What broke (code audit, untested on a Mac):
- Without systemd the server is always spawned from inside a Claude Code
session, so it inherited CLAUDECODE, CLAUDE_CODE_SESSION_ID,
CLAUDE_PLUGIN_ROOT, ... and tmux handed them to every lane pane (a codex
pane even resolved as `claude` in `agenthub`'s harness check).
- The ~/.local/bin/agenthub launcher pinned a versioned node path that
`brew upgrade`/nvm deletes, leaving the CLI dead until the next bootstrap.
- A discovery entry left over from before a reboot could name a recycled pid,
so the bootstrap's fast path believed a dashboard was live and
stopDashboard could signal an unrelated process.
- Lanes were stored under the typed cwd; macOS reports /private/tmp and the
on-disk case, so sessions never bound to a /tmp or differently-cased lane.
What changed:
- server/index.js deletes a DENYLIST of parent-session variables at startup;
user config (CLAUDE_CONFIG_DIR, CLAUDE_CODE_USE_BEDROCK, ANTHROPIC_*) stays.
- linkCli's launcher falls back to `node` on PATH when the pinned one is gone.
- liveServers ignores entries whose startedAt predates this boot (60 s margin).
- createLane and POST /api/lanes/ensure store/look up fs.realpathSync.native
of an existing cwd; the liveness reaper also tries the realpath. Existing
rows are untouched.
- session-liveness gains an exec seam so the darwin ps+lsof branch is tested.
- plugin-doctor names ~/.zshrc on darwin; INSTALL.md gains a macOS section
with the Mac verification checklist, mirrored in both READMEs and PLUGINS.md.
No launchd, no macOptionIsMeta, engines stays >=20.
Closes#24.
**The review node ran nothing.** Both templates declared
`/superpowers:requesting-code-review` — the skill about how to HAND OVER a
review, not one that reviews anything — so `agenthub lanes node review`
performed no review at all. They now declare the bare `/code-review`, Claude
Code's own. It carries no `plugin:` prefix, so `requiredSkillPlugins` skips it
and the doctor's required-plugin row is unchanged (verified against the live
function: still exactly the five superpowers skills the templates name).
**The rest is the brainstorm → implement → review span, made cheaper to run and
harder to lose track of.** `ship-feature` gains four sections it never had:
- **Right-size the run.** The pipeline is not free — every dispatching phase
costs a model call and minutes, and the fix-loop pays it again each lap. A
typo does not enter the pipeline at all; a small single-layer change skips the
plan-debate, independent-test and gate agents and lets the user's acceptance
be the gate; medium/large runs everything. Sizing is a claim made out loud,
and a task that grows re-sizes upward.
- **Dispatching a judgement.** The fresh-context/FOREGROUND/never-`fork`/
hand-only-verifiable-artifacts/one-parseable-line contract, written once
instead of re-argued in three phases — plus the rule that was missing
entirely: never dispatch what a command answers. An agent is for judgement,
not for typing.
- **Resuming after a compaction.** Long runs outlive the context window; the
lane skill had this and this one did not. Re-derive position from the declared
stage and the diff, and treat a phase whose evidence you cannot find as one
that did not happen.
- **A `Leave when:` line on every phase.** Objective exit criteria are what stop
both the silent skip and the endless polish: intake leaves when the answers
are in hand, review leaves when the latest pass over the CURRENT diff is
clean, the gate leaves when verification really ran AND the user said yes.
And, narrower: intake asks only what the repo cannot answer (a question the code
could have answered spends the user's round and earns a worse answer);
implement works the approved plan task by task, re-checks each acceptance
criterion, heartbeats on long work, and treats a plan that turns out wrong as a
return to `plan` rather than a quiet substitution; tests runs the suite the diff
needs rather than both by reflex.
The `default` 8-node pipeline walked past its own intake: the node declared
`agenthub stage intake`, a stage report with no work attached, so "intake" was
a label the run passed through without ever asking a question. It now declares
`/superpowers:brainstorming` (and detects it — that rule moves off `plan`),
and both driving skills make the brainstorm mandatory, asked with
AskUserQuestion and waited on rather than answered on the user's behalf.
Three stops replace three silent slides:
- After the plan is written and adversarially challenged, it goes to the USER
for approval. Implementation does not start without it, and work that turns
out to need a different approach comes back for a fresh one.
- Review picks its reviewers from `git diff --name-only`: Claude Code's own
`code-review` always, a domain reviewer only for a layer the diff actually
touched, and — new — only once the change is big enough to have seams. Three
agents re-reading twenty lines buys one opinion at three times the tokens, on
every fix-loop lap. Review is also a loop now: it ends on a clean pass over
the current diff, not on one pass having happened.
- The gate asks the user to accept before anything is claimed done (and in the
lane pipeline, before the PR is published — publishing is outward-facing).
A NO-GO re-enters by SIZE: a defect goes back to implement, a wrong approach
back to plan. Nothing carries a NO-GO forward with a note about it.
Also here, from a real stall seen on a lane: `ship-feature` had no waiting rule
at all, and a session at the gate invented one with `ScheduleWakeup` — a
/loop-only primitive that paces nothing here and is refused outright when
`auto` mode cannot reach its safety classifier. The rule the lane skill already
had now exists in both.
Cost, measured in what each agent is actually for: the suite run leaves its
agent (nothing is judged, so nothing is delegated — an agent there buys a
second model's tokens to read output the session can read for free), and
`backend-reviewer` drops from opus to sonnet like its frontend twin; both read
a scoped diff against a fixed checklist, and the senior gate above them is
still opus.
Skill bugs found in the same sweep: doc-map told agents not to recreate the
removed translations and then, three lines later, to mirror every README change
into them; the docs mapping still carried `+VN+CN` and the punctuation left by
their removal; Procedure jumped 2 → 6; Verify required `scripts/doc-coverage.sh`,
which does not exist in this repo.
`claude plugin update` unpacks the new version into a new cache directory and
says "Restart to apply changes". A Claude Code process that was already running
does not: it keeps loading the OLD directory, hooks and all.
Every session such a process opened then ran the OLD plugin-bootstrap, which saw
a state.json naming a different root, concluded the server had to be replaced,
repointed agenthub.service at itself and restarted the dashboard onto the
version the user had just upgraded away from. The dashboard reported the old
version and offered the update again — once per session, forever, while
installed_plugins.json and the cache both said the new version was installed.
A /agenthub-update from that session "succeeded" and changed nothing.
- `supersededBy()` reads Claude Code's installed_plugins.json. When a SIBLING
cache directory is the recorded install, the bootstrap logs one line and
returns "superseded" — no deps, no unit, no server. `--force` does not
override it: the self-update chain forces from the NEW directory, which is
never superseded, so the only --force refused is a deliberate downgrade.
It cannot hand over either — the process it would replace is the one loading
it — so the log line says to restart Claude Code.
- Matched by sibling directory, not by the <plugin>@<marketplace> key: correct
without parsing a cache path or trusting a name. A phantom entry (installPath
that no longer exists) is ignored rather than wedging the bootstrap shut.
Also adds `pruneRetiredPluginRoots()`, since the same updates leave a full copy
of the repo — node_modules and all — per release; twelve of them measured 1.7 GB
on one machine. It runs after writeState, so a bad prune cannot cost the record
of a good bootstrap, and it protects four independent readings of "in use":
this build, every installPath Claude Code records, the directory
agenthub.service names (`unitRoot`, foreign unit included), and any directory
still named in the user's settings.json hooks — that last one is the un-restarted
process above, seen from the other side. Plus the 2 newest survivors as a
rollback cushion, and nothing at all outside ~/.claude/plugins/cache/.
The residue an interrupted update leaves behind is invisible: the server
runs, every doctor row reads OK, and the unit quietly still names a cache
directory Claude Code deleted during the update. Nothing surfaces it until
a reboot, when the dashboard does not come back and nothing recorded why.
- fastPathOk now rejects a stale unit, so the next SessionStart repairs it
instead of short-circuiting. `unitIsStale` is pure fs on purpose: that
path runs on every session and may not spawn a process.
- Repairing the unit is not restarting the server. A current, healthy
server keeps running and the corrected unit takes effect at the next
start (`pendingSystemdRestart = systemdOwned && needsServer`), and the
detached-spawn fallback is guarded by needsServer so a stale unit alone
cannot start a second server onto a bound port.
- systemdOwned now also requires the unit to be ACTIVE. Installed-but-
stopped owns nothing: skipping the stop there and asking systemd to start
would bind an occupied port and crash-loop under Restart=always.
- /agenthub-doctor gains a systemd row naming the consequence ("will NOT
come back after a reboot") and the fix. WARN, never FAIL — the dashboard
in front of you works, and having no unit at all is a normal setup.
The fast-path test pins the regression against an otherwise fully healthy
install, live server included; without a live server it would have passed
against the unfixed code either way.
A plugin self-update took the dashboard down and left it down. The chain
ran correctly up to the point where the bootstrap SIGTERMs the server it is
replacing — and that server was systemd-managed, with the bootstrap running
as its descendant, i.e. inside its cgroup. Two failures fired at once:
* the server exits 0, and `Restart=on-failure` reads a clean exit as
"meant to stop", so systemd did not bring it back;
* `KillMode=control-group` reaped the bootstrap itself, mid-run, before it
could repoint the unit at the new plugin root or write state.json.
Evidence from the incident: bootstrap.log ends at "stopped the server
started from the previous plugin version" with no systemd line after it,
.bootstrap.lock survived with a dead pid, state.json still named the
previous version, and the unit's ExecStart still pointed at the old cache
dir. The same truncation is visible on three earlier updates — those only
recovered because a later SessionStart bootstrapped again.
systemd-service.js now splits install into writeUserService (repoints the
unit, starts nothing) and restartUserService (--no-block). The bootstrap
skips the manual stop whenever a unit of ours owns the server, and defers
the restart past writeState and releaseLock, so being killed by its own
request costs nothing. The unit is Restart=always: a graceful SIGTERM from
anything must no longer read as "leave it stopped".
installUserService keeps its old semantics for `agenthub service install`,
which runs from a user's shell and is not in the cgroup.
The READMEs never said tmux was needed, so a fresh install only found out
when Start Run failed with nothing explaining why. Both doctors were silent
about it too.
- README/README.vi: a prerequisites table (node, npm, git, tmux, claude,
codex, gh, systemd) and per-OS tmux install + verify steps; the feature
list is regrouped into observe/drive/configure and now covers analytics,
alerts, import, remote sources, the config explorer and Update all.
- INSTALL: Step 0 for the system packages, plus a troubleshooting entry
separating "tmux missing" from "the server has a different PATH".
- SETUP/docs/README: the same troubleshooting entry and a pointer to Step 0.
- plugin-doctor: a tmux row, WARN and never FAIL - the run console and
`lanes shell` break without it, nothing else does. Reuses tmux.js's own
isTmuxAvailable().
- agenthub doctor: asks GET /api/run/tmux instead, because the PATH that
decides whether a run starts is the server's, not the caller's shell's.
After the 1.5.2 -> 1.5.3 self-update the server ran 1.5.3 while the dashboard
still served the 1.5.2 UI. The client build had failed, and `runtime/client-dist`
still held the previous version's bundle, so nothing looked broken — the only
signal was the Settings page's "UI build v1.5.2 (rebuild client to match)".
Cause: the whole client build toolchain (vite, typescript,
@vitejs/plugin-react, tailwindcss, @types/*) is a devDependency, and npm reads
NODE_ENV=production as --omit=dev (`NODE_ENV=production npm config get omit` ->
`dev`). The dashboard server runs with NODE_ENV=production, and every bootstrap
descended from it inherits that: the plugin-update chain, and any SessionStart
fired by a `claude` running in a tmux pane the server started. So `npm ci`
dropped vite, `tsc -b` died on missing type declarations, and buildClient
returned "failed" with the stale bundle left in place.
`--include=dev` on both install paths — a CLI flag outranks the env, which is
the point. Verified by running buildClient with NODE_ENV=production against the
installed plugin root: previously "failed", now "built", and the served bundle
carries 1.5.3.
Also: plugin-update-helper writes its verdict BEFORE the bootstrap handover as
well as after. That step retires the process tree the helper hangs off, and the
observed run reached the new server with no verdict file at all — the dashboard
reported `last_plugin_update: null` for an update that had actually succeeded.
The ten `agenthub-*` plugins were listed by the marketplace but could never be
installed — two schema mistakes present since the entries were first authored
(57dc915), both invisible until you actually run `claude plugin install`:
- marketplace entries used `"path": "plugins/<name>"`; the CLI only accepts
`"source"`, so every one failed with
`This plugin's marketplace entry is invalid: source: Invalid input`
- each `plugin.json` carried npm's `"repository": { "type", "url" }` object;
the schema wants a plain string, so the next attempt failed with
`Validation errors: repository: Invalid input`
Verified by installing all 11 entries into a throwaway CLAUDE_CONFIG_DIR:
1/11 before, 11/11 after. `plugins-marketplace.test.js` was asserting the
broken shape, which is why CI stayed green — it now asserts `source` and
rejects `path`.
Marketplace renamed `claude-code-agent-monitor-plugins` -> `agenthub`, so the
install line is `agenthub@agenthub`. ARCHITECTURE.md documented a marketplace
name (`smartgift-claude-code-monitor`) that never existed in any revision.
The documented `/plugin marketplace add Smartgift-AI/Claude-Code-Monitor` also
never worked: the `owner/repo` shorthand resolves to github.com only, and this
repo is self-hosted on Gitea. Confirmed the CLI rejects `host/owner/repo` and
ignores GH_HOST / GITHUB_HOST / CLAUDE_CODE_MARKETPLACE_URL, so the full
https:// clone URL is the only supported form. Same GitHub-habit class fixed
elsewhere: raw.githubusercontent.com icon URLs (404, and the repo ships
favicon.svg not favicon.ico — the client had the same dead /favicon.ico),
a smartgift.github.io docs link (404), and Gitea `/blob/<ref>/` paths that
must be `/src/branch/<ref>/`.
Repository renamed to Smartgift-AI/AgentHub throughout. Gitea 301-redirects
the old name, so these were stale rather than broken; `docs/superpowers/`
keeps the old name because those are dated decision records.
Adds `repo-links.test.js` to guard both classes (it runs under the existing
pre-commit gate) plus an openapi.yaml drift check — the committed spec had
silently fallen a minor version behind package.json. `generate-openapi-yaml.js`
now exports `render()` so the test compares against one definition of the dump
options instead of a second copy.
Two leftovers from the rebrand, done together because they touch the same
docs and manifests.
**Data directory.** `agent-dashboard` could not simply be renamed in the
source: it names a real directory holding the live SQLite database. Startup
now moves it once, via `migrateLegacyDataDir()` in `server/lib/claude-home.js`
— a same-filesystem rename, so it is instant even at multiple gigabytes and
cannot leave two divergent copies. `getDataDir()` stays PURE and resolves to
the legacy path until the move happens; the first version of this put the
rename inside the getter, which meant `npm run test:server` relocated the
developer's real database as a side effect. The call sits behind
`require.main === module` and ahead of the router requires, because those pull
in db.js, which opens SQLite at module load. A failed rename is silent and the
old directory keeps being used: an unfashionable directory name beats a blank
database beside an unreachable one. Same treatment for the port-discovery file
(`.agent-dashboard.json` → `.agenthub.json`, old one dropped on write).
Not renamed on purpose: the Sagi localStorage keys (renaming silently resets
everyone's prefs) and the PWA manifest `id` (changing it orphans an installed
app).
**MCP server.** 4 tool calls in 46 days across 577,132 events, against 4,556
lines of TypeScript, a 2 MB committed build artifact, and a pre-commit guard
that had already blocked commits twice. Deleted: `mcp/`, the maintainer skills
and `mcp-reviewer` agent, the build check, `plugins/agenthub/.mcp.json`,
`docs/MCP.md`, 12 npm scripts, 5 Makefile targets, and every doc section
describing it.
Kept, because they are unrelated things sharing the name: the Config
Explorer's MCP tab and its API, per-lane Playwright MCP, the agenthub-config
plugin's MCP audit, and the historical `mcp__plugin_agenthub_*` events that
analytics must keep attributing.
Verified: server 1432/1432, client 459/459, tsc clean, prettier clean. Both
directions of the migration proven — a sandbox-HOME test run leaves the legacy
directory untouched, and a real boot moves it with its contents intact.
Clean break, no compatibility alias. Renames the product name, the CLI
binary (`ccam` -> `agenthub`), the env var prefix (`CCAM_` ->
`AGENTHUB_`), the Prometheus metric namespace (`ccam_*` ->
`agenthub_*`), the tmux session prefix (`ccam-lane-<id>` ->
`agenthub-lane-<id>`), the per-repo runtime profile directory
(`.ccam/profile` -> `.agenthub/profile`), the lanes state root
(`~/.claude/ccam-lanes` -> `~/.claude/agenthub-lanes`), the bundled
plugins (`plugins/ccam*` -> `plugins/agenthub*`) and their slash
commands (`/ccam-doctor` -> `/agenthub-doctor`, `/ccam:*` ->
`/agenthub:*`).
Because there is no alias, an existing install has to be updated by
hand: rename its `.ccam/profile` directory and any `CCAM_*` variables,
and reinstall the plugin under its new name.
Two other name families are deliberately left alone here, since they are
not just strings: the `Claude-Code-Monitor` repository/marketplace name,
and the `agent-dashboard` npm package plus its `~/.claude/agent-dashboard`
runtime directory, which holds the live database and needs a migration
rather than a rename.
Verified: server 1406/1406, client 459/459, `grep -i ccam` clean across
tracked files, `openapi.yaml` regenerated (95 paths, unchanged count).
A pipeline was all-or-nothing: `ccam ship-full` / `ship-quick` hand the whole
thing to a skill, and a node's own `command` — added so the map would stop
hiding the driver behind its detect regexes — was display-only. Re-running just
the CI gate, or redoing the brainstorm, meant clicking copy on the node and
pasting the string into a session by hand.
`ccam lanes node [<id>] [extra…] [--print]` runs it, in the lane's own cwd. A
slash-command node spawns `claude` with it as the prompt (same shape as
`ccam ship-full`); anything else is spawned directly. No id lists every node
and its command, which is also what the two error paths print.
The node is matched by id OR alias, the same way `ccam stage` matches one:
`default` calls the step `implement` and `ship-feature` calls it `implementing`,
and one command name must not depend on which template the lane happens to be
on. That needs the template's `aliases`, which the lane payload's
`pipeline_nodes` does not carry — so the two are merged, template for the
definition, lane for the `current` marker.
Both shipped templates now fill EVERY node's `command`. The seven that were
empty are the nodes whose only work IS the declaration — a terminal `done`, a
gate another agent declares — so they get `ccam stage <id>`, which keeps all 16
(and all 8) runnable instead of leaving holes a caller has to know about.
Slash commands for the same thing, because a session should not shell out to a
nested `claude`: `/intake`, `/plan`, `/implement`, `/tests`, `/e2e`,
`/e2e-passed`, `/review`, `/qc-plan`, `/qc`, `/gate`, `/publishing`, `/pr-open`,
`/reported`, `/watching-pr`, `/merged`, `/done`, plus `/ship-full` and
`/ship-quick`. Each resolves its node through `ccam lanes node <id> --print` and
runs the result IN the current session — invoking the slash command itself when
that is what the node names, otherwise running the shell argv. Resolving at call
time rather than baking the string into the file is what stops the 18 command
files from drifting when a template changes.
Two limits are deliberate:
- The command is split on whitespace and spawned WITHOUT a shell. A template
is data — anyone can drop a file into DASHBOARD_PIPELINES_DIR — so its
`command` must never be interpreted as shell. A node needing a pipe names a
script that contains one.
- Running a node does not declare its stage. A command executing is not proof
the node passed, same boundary as the console never writing a lane's stage.
Verified: npm run test:server (1403, +3 covering alias matching, full command
coverage of both templates, and every command file being listed in the
manifest), npm run test:client (459), prettier and check-headers clean. Docs:
docs/LANES.md § Running ONE node, docs/PLUGINS.md commands table, README +
README.vi CLI blocks, CLAUDE.md marker.
The ship-feature pipelines drive `/superpowers:*` commands as their per-node
drivers, so a fresh install had a dependency it was only told about — the
`/ccam-doctor` WARN row and a line in the README.
`server/lib/skill-plugins.js` now carries the whole thing, shared by the
doctor (reports) and the bootstrap (installs) so the two cannot disagree
about what is missing. The bootstrap installs at the very end of its DETACHED
worker — the install clones from the network and nothing in the 10 s
SessionStart hook may wait on it — retrying once behind a `marketplace add`,
logging a failure with the manual command, and never throwing: the dashboard,
hooks, CLI and MCP all work without these plugins. The outcome is recorded as
`state.skillPluginsSettled`, which `fastPathOk()` now also requires, so the
check runs exactly once per install and `/ccam-update` is the retry.
`CCAM_AUTO_INSTALL_PLUGINS=0|false|off` opts out.
Reporting is derived, installing is allowlisted. Requirements come from the
loaded templates, which is right for a report; installing from that same
source would not be, because a template is a file anyone can drop into
`DASHBOARD_PIPELINES_DIR` — it would turn "edit a JSON file" into "run this
vendor's install command on the next session". Auto-install consults
`AUTO_INSTALLABLE`, a constant in code (`superpowers` today), and reports
every other requirement as skipped.
Tests inject a `run` seam so no case reaches a real `claude plugin install`,
and cover the refusal explicitly.
The ship-feature pipelines have always depended on the `superpowers`
plugin — skills/ship-feature/SKILL.md calls its skills by name, and the
node detect rules match `Skill` events named `brainstorming`,
`writing-plans`, `test-driven-development` — but no README, INSTALL,
manifest or SKILL.md said so, and /ccam-doctor did not check. Install the
`ccam` plugin without it and `/ccam:ship-feature-lane` runs partway, then
fails at the first skill call with no warning beforehand.
/ccam-doctor now derives the requirement from the loaded pipeline
templates rather than a hardcoded list: every `/plugin:skill` a template
names, as its own `skill` or as one node's `command`, has to come from an
installed and enabled plugin. Editing a template cannot leave the check
behind, and a custom template in DASHBOARD_PIPELINES_DIR naming some
other plugin is covered for free.
Three deliberate calls:
- WARN, never FAIL. The dashboard, hooks, CLI and MCP all work without
it; failing a doctor run over it would cry wolf.
- A plugin present but explicitly disabled counts as missing — Claude
Code will not resolve its skills either way.
- The skills sitting in ~/.claude/skills/ count as satisfied. That is a
legitimate hand-copied setup, and calling it broken is how a warning
row teaches its reader to ignore it.
Docs state the prerequisite where someone installing would look: README
and INSTALL requirements, plus docs/PLUGINS.md for how the row decides.
The install line is `superpowers@claude-plugins-official`, verified
present in that marketplace's manifest.
Verified: npm run test:server (1379, +6 covering all three calls above
plus the partially-satisfied case), npm run test:client (459), prettier
and check-headers clean. `node scripts/plugin-doctor.js` here reports
`OK Skill plugins superpowers available`; the WARN branches were checked
against a temp CLAUDE_HOME.
A plugin card showed "7 skills, 5 agents" and nothing more — the counts
were the whole story, so finding out WHICH skills a plugin ships meant
opening its install directory by hand. The contribution chips are now
buttons: clicking one expands a list naming each artifact with its
description, one surface open at a time. Commands render with their
slash. Hooks stay a plain chip — a plugin's hooks are matcher/command
pairs declared inline in plugin.json, not named artifacts.
`contributes.items` carries the four surfaces server-side; the existing
counts keep their type and are now derived from those lists, so a chip
reading "3 commands" can never sit beside a list holding two.
That also fixes a real blind spot. Each surface was read only from the
conventional install subdirectory, but plugin.json may declare its own
paths — this repo's own `ccam` lists three files under
plugins/ccam/commands/ and keeps commands/ empty, so it reported zero
commands. Both sources are now read and de-duplicated. A declared path
resolving outside the plugin's install directory is dropped: a manifest
is third-party data and must not turn the dashboard into an arbitrary
file reader.
Also pins the Refresh button's width: both labels share one grid cell so
the button is always as wide as "Refreshing…" / "Đang làm mới…" and no
longer resizes the toolbar when the state flips. Measuring the longest
real string beats a min-width that would be wrong in the next language.
Verified: npm run test:server (1370 tests, +6 for the new discovery),
npm run test:client (457, +3 for the expand behaviour), tsc --noEmit,
prettier and check-headers clean. Docs synced: docs/API.md, openapi.yaml
(new CcConfigPluginItem schema), ARCHITECTURE.md, docs/PLUGINS.md.
A codex session emits no hooks and rarely calls `ccam stage` on its own, so
its card sat at `idle` forever while the amber "detected" badge was the only
thing that ever moved. `codex-ingest.js` now advances the declared `stage`
from its own written detection — the one place in CCAM where an inference
moves the blue `current` ring, and only for `codex` lanes.
It stays honest: gated on `recordDetection` having written (so forward-only,
declared-wins and the detection TTL are inherited unchanged), passes NO
evidence (the node renders `passed-no-evidence` amber, never `done`), and no
template's last node carries detect rules, so a lane can never be
auto-declared `done`. `setStage` grows a `keepDetection` option — its sole
caller — so the detection columns survive the advance and the card keeps
showing which command moved it instead of looking like an agent's own claim.
Two levers then get the evidence auto-advance cannot supply:
- `codex-nudge.js` now nudges on a stage held 2+ min with no evidence,
instead of on a detection sitting ahead of the declared stage — after
auto-advance the old condition can never fire, since the two now match.
- `ccam lanes agents install` on a codex lane writes the marker-delimited
`<!-- ccam:stage:start -->` block into the lane's own AGENTS.md — the one
instruction channel Codex reads — instead of copying agent templates into
`.claude/agents/`, which it never loads. Appended, user prose preserved,
reinstall replaces exactly that block.
Verified with a real `codex exec` run: stage moved to `watching-pr` with
`evidence: null` and the detection signal intact. 1364 server tests pass.
Adds ccam service install/uninstall/status for checkout installs and wires
the same systemd --user unit into plugin-bootstrap.js, so plugin-installed
colleagues get boot persistence too instead of needing a Claude Code
session to (re)start the server after every reboot.
A plugin update applied mid-session (/plugin followed by /reload-plugins)
fires no SessionStart, so the bootstrap's version handover never runs and the
dashboard server keeps executing a cache directory Claude Code has already
discarded. /ccam-open then rebuilt the bundle from the new root against that
old server, and the new bundle called routes the old server never had:
/api/lanes/pipeline-stats fell through to /:id and rendered "lane not found",
/api/workflows/skill-usage fell through to the SPA catch-all and broke
JSON.parse on the returned HTML. Both Workflows panels showed an error while
the code they needed was sitting on disk.
plugin-open now re-runs bootstrap when the live server's recorded pluginRoot
differs from the current one, or when no server is live at all. Bootstrap
already owns the stop/start and the dependency install the new root may need,
so this only restores the trigger that a mid-session update skips.
The Claude Config page was read-only for these four surfaces. It can now:
- register a marketplace from a pasted GitHub `owner/repo`, http(s) URL or
absolute path, and install / enable / disable / update / uninstall plugins,
all delegated to the `claude plugin …` CLI so its registry stays consistent;
- edit hooks and settings.json keys in the user, project and project-local
layers.
Server:
- `server/lib/cc-plugin-cli.js` wraps the CLI with `execFile` and an explicit
argv array — never a shell string. Every argument is validated before the
spawn (shape allowlist per kind, no control characters, no leading `-`, no
`..`), `CLAUDE_CONFIG_DIR` is pinned to the dashboard's CLAUDE_HOME, stdin is
closed so a prompt errors instead of hanging, and mutating calls are
serialized in-process.
- `cc-mutate.patchSettings` merges individual dotted keys into one settings
layer. It re-reads the file unredacted, so keys the UI never displayed —
including secret-valued ones — survive byte-for-byte. A payload carrying the
`<redacted>` placeholder is refused (EREDACTED), as are `__proto__` /
`prototype` / `constructor` segments; a settings file that does not parse is
reported (EBADJSON) rather than clobbered. Backup first, then atomic write.
- Six additive routes on /api/cc-config; a non-zero CLI exit is a 422 carrying
the CLI's own message, a missing binary a 503.
Client: install/add bars, per-card plugin and marketplace actions behind a
two-click confirm, and edit modes for hooks and settings that send only the
keys that changed. New i18n keys in en + vi; the explainer banners that said
these surfaces were read-only now describe what the writes actually do.
Tests: 61 new server tests (CLI argv construction and validation, the settings
key-merge, and the six routes against a fake `claude` on PATH).
Move .claude/agents/ and server/data/agent-templates/ship-feature-lane/
into one agents/ at the repo root — which IS the plugin root, so all five
agents now ship with the ccam plugin as ccam:<name>, the same way skills
already do.
The two pipeline agents were byte-identical copies in both places; that
duplication is gone. `ccam lanes agents install` now reads them straight
from agents/, so the per-lane copy in <lane>/.claude/agents/ still gives
the bare `subagent_type: qc-local` the ship-feature-lane skill prefers.
Skill and docs record both names: bare inside a lane, ccam: as fallback.
The repo root already IS the `ccam` plugin root (`"source": "./"`), so the
conventional `skills/` dir at the root is the plugin's skills dir — while
`.claude/skills/` only loaded for a session whose cwd was inside this
checkout. That is useless for a lane working in another repo, which is why
`ccam skills install` existed at all.
Move all seven skills to `skills/`: they now reach every plugin user as
`/ccam:<name>` (bare `/<name>` as an alias). `ccam skills install` stays as
the fallback for a plain checkout without the plugin, sourcing from the new
path.
Agents deliberately do NOT move. A plugin agent is addressed as
`ccam:qc-local`, which would break the `subagent_type: qc-local` references
in ship-feature-lane; `ccam lanes agents install` keeps writing them into the
lane's own `.claude/agents/`, the highest-priority agent source. MCP was
already plugin-shipped via `plugins/ccam/.mcp.json`.
Mechanical fallout: ~115 source files carry a doc-comment pointer to
`.claude/skills/file-headers/`, repointed to `skills/file-headers/`. The
generic Claude Code config-surface examples in openapi/cc-config (`.claude/
skills/code-reviewer`) describe any user's layout and are left alone.
Also fixes the two file-headers scripts, whose `ROOT=` climbed four levels
from `.claude/skills/file-headers/scripts/` and would have escaped the repo
from the new depth — it scanned sibling projects until corrected to three.
npm run test:server (1160 pass), test:client (422 pass), mcp:typecheck,
mcp:build + mcp:check-build all green.
Docs and the command's own instructions previously implied /ccam-update
fetches new code; it only reinstalled deps and restarted the server
against whatever version was already resolved. It now also runs
`claude plugin marketplace update` + `claude plugin update ccam@<mp> -y`
first, and says plainly that /reload-plugins is still a manual step
(no CLI/script equivalent exists to apply it automatically).
Verified against a real claude plugin uninstall: it only drops the plugin
from the enabled list. The server keeps running, the cached source stays on
disk, and the hook entries claude plugin install wrote into settings.json
are left behind pointing at the now-uninstalled cache dir — silently fails
once Claude Code eventually GCs it. The previous instructions ("uninstall
removes the hooks and the cached source") were untested assumptions; this
adds the missing settings.json cleanup step.
claude plugin install materializes the plugin's inline hooks into
~/.claude/settings.json itself, with \${CLAUDE_PLUGIN_ROOT} resolved to the
actual cache path — confirmed by installing the plugin for real and
inspecting the file. Those entries also contain "hook-handler.js", so
isOurEntry()'s plain substring match could not tell a legitimate
plugin-installed hook from a leftover npm run install-hooks entry: every
SessionStart would have stripped the plugin's own working hooks right back
out. isCheckoutHookEntry() only removes entries whose command does NOT
resolve under ~/.claude/plugins/cache/. plugin-doctor.js's duplicate-hook
count uses the same predicate.
Adds a root `ccam` plugin (`.claude-plugin/plugin.json`, `"source": "./"`) so
`/plugin marketplace add` + `/plugin install ccam@...` is enough on a machine
with nothing but Claude Code: no clone, no npm run setup, no manual npm start.
- scripts/plugin-bootstrap.js: SessionStart hook. Fast-path exit, Node >=22.5
gate (node:sqlite), mkdir lock with stale reclaim, deps installed into
~/.claude/agent-dashboard/runtime/ (never the plugin cache), legacy
checkout-hook cleanup (backed up), ~/.local/bin/ccam launcher, eager UI
build so client routes like /run work immediately, detached server spawn.
- scripts/plugin-open.js, scripts/plugin-doctor.js: /ccam-open, /ccam-doctor.
- server/index.js: DASHBOARD_CLIENT_DIST override (plugin cache is read-only).
- mcp/build/ is committed (plugin MCP servers start before any bootstrap could
build them) and kept honest by scripts/check-mcp-build.js (content hash,
not mtime), enforced by pre-commit when mcp/src changes.
- plugins/ccam-dashboard/.mcp.json moved under plugins/ccam/ with a working
${CLAUDE_PLUGIN_ROOT} path (the old relative path never resolved from a
marketplace-cached subdir).
- Docs: README, INSTALL, SETUP, ARCHITECTURE, CLAUDE.md, docs/PLUGINS.md,
docs/MCP.md, docs/CLI.md, docs/HOOKS.md.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Internal SmartGift build of a Claude Code monitoring dashboard.
Lanes: a durable unit of parallel agent work, one per working directory,
tracked across session restarts. Managed lanes are git worktrees the
dashboard provisions and can reset or remove behind a three-check destroy
guard and a counted preflight; adopted lanes are directories you already
own and are never destroyable.
Pipelines: a lane moves through pipeline stages. A stage the agent declares
with evidence renders green; a stage inferred from the tool-event stream
renders dashed amber and never counts as done. Detection is forward-only
within a 30-minute window, and never writes the declared stage.
Workspace: one page at /run with a lane grid, the selected lane's pipeline,
and a full Claude console behind a disclosure.
nntrivi2001