Dai Ha
1ce0aba7fc
Workers now land in their own herdr tab inside a dedicated, shared "worker
space" (workspace.create → tab.create → agent.start{tab_id} → close seed shell
→ rename), instead of splitting the user's currently-focused tab. Placement is
configurable (worker.placement tab|pane, worker.workspace, worker.tabLabel);
a future per-session space is just a distinct label.
New: Workspace/Tab records, WorkspaceControl over workspace.*/tab.*,
AgentControl.start tab_id overload, Agent.tabId.
Lifecycle carefulness:
- ensureWorkspace is a synchronized find-or-create (never double-creates)
- teardown closes the tab ONLY when the worker is its sole pane (never a
shared user tab), resolving the tab via pane.get before closing
- tolerance is precise: only *_not_found is swallowed; real failures surface
- spawn failure closes the orphan tab; post-start cosmetic steps can't orphan
a live worker or fail the spawn
- unique per-worker names (claude-<profile>-<nonce>-<seq>) with retry: herdr
rejects duplicate agent names, and the per-process nonce survives a restart
with lingering workers
herdr facts pinned: agent.start honors tab_id; agent name must be unique;
kind/status are detected from terminal output, not the name.
Reviewed at high effort (multi-agent); all findings addressed. 34 tests green
(29 unit/acceptance + 5 contract vs live herdr 0.7.0). Also bumps wiki.
34 lines
1.4 KiB
YAML
34 lines
1.4 KiB
YAML
# bridged configuration (example). Copy to bridged.yaml and adjust.
|
|
#
|
|
# bridged is the sole gateway between primary/worker Claude sessions and herdr.
|
|
# It is NOT a Claude process and must never carry ANTHROPIC_BASE_URL.
|
|
|
|
# REST + MCP listen address. Keep it on loopback — bridged is same-host in Stage-1.
|
|
bind:
|
|
host: 127.0.0.1
|
|
port: 8080
|
|
|
|
# herdr Unix socket. Omit to use the client default
|
|
# (${HERDR_SOCKET_PATH:-~/.config/herdr/herdr.sock}).
|
|
herdrSocket: ~/.config/herdr/herdr.sock
|
|
|
|
# How a worker session is spawned. Stage-1 uses the existing ccs `ltms-local`
|
|
# profile, whose .claude.json routes to the gx00 vLLM below.
|
|
worker:
|
|
profile: ltms-local
|
|
baseUrl: http://gx00.gw:8000 # the gx00 vLLM (models: coder / deepseek-v4-flash)
|
|
model: coder
|
|
# Placement: each worker lands in its OWN tab inside a dedicated worker space, so it
|
|
# never splits or clutters your real work spaces. Use `pane` for the legacy behaviour
|
|
# (split the currently-focused tab).
|
|
placement: tab # tab | pane
|
|
workspace: bridged-workers # the dedicated worker space (found-or-created, shared)
|
|
tabLabel: "worker: {profile} #{n}" # {profile}/{model}/{n} substituted; {n} keeps sibling tabs distinct
|
|
|
|
# Subscription boundary. A worker's base_url host MUST be one of these; the primary
|
|
# must carry none. Grounded in ltms-local's real endpoints.
|
|
guard:
|
|
offSubscriptionHosts:
|
|
- gx00.gw
|
|
- ollama.ltms.dev
|