Files
roboco/docs/rag/roles/cell-pm.md
T
3ccc723cd4 v0.17.0 — Wave 3: sandbox DB, DB isolation, mobile UI, cloud auth, X account, roadmap engine (#303)
* feat(sandbox): throwaway per-agent Postgres/Redis sandbox containers

Orchestrator-provisioned sibling containers per agent spawn
(SandboxProvisioner, roboco/runtime/sandbox.py). Per-project opt-in via
projects.sandbox_services (migration 057); master switch
ROBOCO_SANDBOX_DB_ENABLED, default-off, armed in the NAS compose only.

When active, ROBOCO_TEST_DB_* / ROBOCO_TEST_REDIS_* point at the sandbox
and the prod-creds gate-env injection is suppressed (sandbox replaces,
never coexists). Sandbox lifetime tracks the agent container: teardown at
every removal path, orphan janitor at startup + each reaper tick with a
grace window for mid-flight spawns. The pre-spawn stale-clear spares the
just-provisioned sandbox; provision pre-clears stale same-named
containers from a crash-missed teardown.

Panel: per-project sandbox-service switches in the edit dialog + feature
flag card entry.

* docs: CLAUDE.md entry for the sandboxed dev DB/Redis subsystem

* feat(security): isolate prod Postgres/Redis from agent containers (roboco_data network)

Second user-defined bridge roboco_data carries postgres+redis only; the
orchestrator is multi-homed (default + data). Spawned agents and their
sandbox sidecars stay on roboco_default and can no longer resolve or
reach roboco-postgres:5432 / roboco-redis:6379 (redis has no auth —
membership is its only containment). Normal bridge, so host-published
ports (15432/16379) keep working. Applied to both build composes and
the registry compose; docker-compose.yml re-synced byte-identical with
docker-compose.yaml (it had drifted by the sandbox flag block).

ROBOCO_DB_NETWORK_ISOLATED (config default false, armed alongside the
topology) suppresses the legacy _append_gate_env prod-creds injection:
under isolation those creds dead-end, and unreachable creds are worse
than none. DB-needing projects opt into sandbox_services instead. The
flag is deliberately not a panel feature flag - it must travel with the
compose networks: stanzas.

Preserved by construction: agent<->agent A2A and orchestrator->agent SDK
polls on :9000, MCP->orchestrator on :8000, ollama reachability, docker
exec/inspect (daemon socket), host port publishing.

* feat(panel): full mobile responsiveness pass

Shared primitives: useIsMobile (useSyncExternalStore, hydration-safe,
memoized matchMedia subscribe), ResponsiveTable table->card switch below
md (single subtree mounted, no duplicated interactive rows), scrollable
snap TabsList in the base primitive (justify-center-safe so the first
tab stays reachable on overflow), persistent md:hidden bottom tab bar
(Overview/Tasks/Kanban/Chat, safe-area padded).

Applied: card lists for tasks/projects/products/work-sessions/sessions
+ the three raw metrics tables; CEO approval queue / release proposal /
playbook review action rows stack on narrow; command-center reorders
approvals above the fold on mobile; task-header metadata wraps;
Communications + A2A become URL-driven single-pane drill-downs below lg
(fixes the unconstrained-height ScrollArea bug) with dvh heights;
recharts label density/radius adapts via useIsMobile; git diff viewer
gets mobile font + wrap toggle; vh->dvh sweep; chat composers get
safe-area-inset padding; dashboard main p-4 md:p-6 + pb-20 for the bar.

Verified at 375px on the built app: bottom bar, drawer, approval-first
overview, swipeable kanban tab strip. All gates green (eslint, tsc,
vitest 249, next build 24/24 routes).

* feat(auth): cloud auth via FastAPI Users (default-off, single-user cookie session)

ROBOCO_CLOUD_AUTH_ENABLED (default off) lets the panel/API be exposed
beyond localhost without changing the CEO's local no-login flow while
off — get_agent_context and the WS gate are byte-for-byte unchanged in
off-mode. On: header-trust dies for humans — any agent-role claim (ceo
or a privileged PM/board role) with no valid HMAC token or session
cookie is 401, closing the header-spoof hole on the host-published
:8000 port for every role. The agent-fleet HMAC path and the system
self-PATCH keep working unmodified in both modes.

Single seeded CEO user (migration 058 users table, UserTable), no
registration router — idempotent env-driven upsert at startup by PK.
Cookie transport (httponly/secure/samesite=lax) + a JWTStrategy bound
to a fingerprint of the current password hash (rotating the password
invalidates every prior session). Sliding 30-day session: every
authenticated request re-mints the cookie, so an active session never
expires — no unexpected logouts.

Panel: (auth)/login page + proxy.ts (Next 16 rename of middleware; probes
/auth/status over the docker-internal URL, fails open to off) gate the
dashboard; client.ts gets withCredentials + 401->/login. nginx unchanged.

Review hardening: broadened the on-mode rejection from ceo-only to every
non-CEO role without a valid token (was only closed when
ROBOCO_AGENT_AUTH_REQUIRED was also armed); Next-16 proxy.ts rename to
clear the middleware deprecation warning.

* feat(x): RoboCo X account engine — HoM drafts, per-post CEO approval (default-off)

ROBOCO_X_ENGINE_ENABLED (default off, inert without creds). Mirrors the
ReleaseManagerEngine held-artifact shape: XEngine drafts a post when a
release publishes (via a draft_release_post seam on ReleaseProposalService
.approve) and drafts replies to meaningful mentions (dedicated poll loop,
x_seen_mentions dedup ledger, per-cycle/open caps). Drafting is
local-model-only, clamped to 280 chars. Nothing auto-posts — every tweet
is a held task (source x_post/x_reply, confirmed_by_human=False,
Secretary-owned, dispatcher-skipped) the CEO edits/approves/rejects in a
panel queue.

The four OAuth 1.0a secrets live Fernet-encrypted in a singleton
x_credentials row (migration 059, all-or-nothing, API returns only
has_credentials); decryption is server-side, agents never hold creds or
egress. Hand-rolled OAuth 1.0a HMAC-SHA1 signer, no new dependency;
NullXClient makes the unconfigured path a graceful no-op.

XPostService.approve (CEO-only) is the sole caller of post_tweet.

Review hardening: closed a double-post race — the approve path now
re-reads committed task state inside the Redis lock and commits COMPLETED
before releasing, so a concurrent approve that acquires the lock after the
winner released can't re-post (SET-NX is non-waiting, and the route-level
commit landed after the lock dropped). Added a regression test.

* feat(roadmap): board roadmap engine — PO proposes themed cycles, CEO approves per-item (default-off)

ROBOCO_ROADMAP_ENGINE_ENABLED (default off). Weekly, RoadmapEngine opens
ONE held exploration task (source=board_roadmap, confirmed_by_human=False,
Product-Owner-assigned), deduped to one open cycle. A dedicated one-shot
_dispatch_roadmap_exploration spawns the PO solo (not the two-reviewer
board path, which would also spawn HoM + fire Approve-&-Start). The PO
explores read-only (git/KB/metrics/releases/charter/web) and makes one
propose_roadmap call (PO-only content verb) authoring a themed cycle —
goal + 3-7 item drafts — persisted as a roadmap_cycle marker (no table,
no migration; head stays 059).

The CEO acts per-item in the panel roadmap queue: approve materializes a
BACKLOG task (source=roadmap, no assignee — never auto-starts), reject
records a reason; all-items-terminal completes the exploration task.
RoadmapService is idempotent per item. Dispatchers skip board_roadmap.

Includes a real SQLAlchemy dirty-check fix (deep-copy the JSON marker
before mutating, or the in-place edit + reassign compares equal to its
own baseline and the UPDATE is skipped).

Review hardening: create_task_from_draft now honors a draft-declared
source only from a {prompter, roadmap} whitelist — drafts are
LLM-authored, so an unbounded source could impersonate a privileged
origin (release_manager would even wedge that engine's dedup).

* chore(release): 0.17.0

Wave 3 — six default-off subsystems: sandboxed dev DB/Redis, prod
Postgres/Redis network isolation, full mobile UI pass, cloud auth
(FastAPI Users), the RoboCo X account engine, and the board roadmap
engine. Plus the waves 1+2 work already on master since 0.16.0.

Version bumped across the canonical set (config.py, __init__.py,
pyproject.toml, panel/package.json, uv.lock); CHANGELOG [Unreleased]
cut to [0.17.0]; docs/map delta added.

Compose: every optional feature armed :-true in the NAS composes, OFF
in the user-facing registry compose. Two opt-in exceptions default off
(CLOUD_AUTH — needs email/password/secret + TLS, would otherwise fail
startup; ROUTING_STRICT — fail-closed spawning). DB_NETWORK_ISOLATED
stays on in both (coupled to the roboco_data topology).

* chore(compose): arm cloud_auth + routing_strict ON in the NAS composes

Every feature defaults ON in the NAS composes per policy — these two
were wrongly left off. Both keep the ${VAR:-true} form so the operator
controls the real runtime via .env: cloud auth needs
ROBOCO_CLOUD_AUTH_EMAIL/_PASSWORD/_SECRET + TLS set there before a boot
(else startup fails loud), and routing_strict is fail-closed. Registry
compose keeps both off.

* fix(ci): reflow board.md prose (quality gate) + document v0.17.0 env creds

The roadmap section added hard-wrapped prose that failed the markdown
prose gate; reflowed (token-invariant). Also brought .env.example
current: cloud auth (now armed — needs SECRET or startup fails), routing
strict, the X engine (panel-entered OAuth), and web research.

* fix(ci): reduce cyclomatic complexity of five wave-3 blocks (xenon gate)

The wave-3 subagents introduced C-rank functions the CI xenon gate
rejects (my per-item reviews ran ruff/mypy/pytest but not xenon):
- sandbox.janitor_sweep -> extract _list_labeled_sandboxes /
  _list_live_agent_containers / _prune_grace
- x_client.fetch_mentions -> extract _parse_mention_items
- x_engine.run_cycle -> extract _process_mentions
- orchestrator._dispatch_pm_work -> extract the source-skip into a
  MODULE-level _is_held_ceo_source (module, not method, so the
  wholesale-mocked dispatcher unit tests exercise the real logic)
- auth/seed.ensure_seed_user -> extract _apply_seed_updates (module avg -> A)

Behavior-preserving; full suite green (11902), xenon clean.

* fix(ci): declare pyjwt + fastapi-users-db-sqlalchemy as direct deps (deptry)

The cloud-auth code imports jwt and fastapi_users_db_sqlalchemy directly
but they were only transitive deps (via fastapi-users), which deptry
(quality gate, DEP003) rejects. Declared explicitly; deptry roboco/ clean.
Missed originally because local make quality stopped at earlier gates
before reaching deptry.

* feat(x): gate mention replies behind ROBOCO_X_REPLIES_ENABLED (default off)

Per CEO decision: the X engine should only post about releases by
default. Reading mentions needs a paid X API tier, so the mention-reply
half is now a deliberate opt-in on top of release posting.

New default-off flag x_replies_enabled gates the mentions poll loop
(_x_mentions_poll_loop) and XEngine.run_cycle; release-post drafting
(the release-proposal approve hook) is unaffected and still runs when
x_engine_enabled + credentials are set. Added to FEATURE_FLAGS + the
panel card. Tests: release posting works with replies off; run_cycle +
the poll loop are no-ops with replies off.

* fix: 401 only redirects to /login when cloud auth is on; panel-token strips .env quotes

Two bugs that together dead-ended login in secure mode:
- client.ts redirected to /login on ANY 401, so a mismatched panel
  token (header-trust/secure mode, cloud auth off) bounced the user to a
  login page whose backend route isn't mounted -> 404. Now it probes
  /auth/status (bare fetch, no interceptor re-entry) and only redirects
  when cloud_auth_enabled.
- make panel-token read the .env secret with grep|cut without stripping
  surrounding quotes, so a quoted ROBOCO_AGENT_AUTH_SECRET produced a
  token signed with the quotes included — which never verifies against
  the orchestrator (docker-compose/pydantic unquote the secret). Now
  strips surrounding single/double quotes.

* fix: git-log 500 on '|' in commit message; X queue shows an empty state

- GET /api/git/log 500'd (ValueError: Invalid isoformat) when a commit
  SUBJECT contained a '|' (e.g. the 'curl|sh' lockdown commit): the
  fixed '|' field delimiter let the subject's pipe shift the split so
  author+date collapsed into one field. Switched to \x1f (Unit
  Separator), which can't appear in commit content. Regression test with
  a piped subject.
- The X Post Queue returned null when empty, so there was no visible
  place for the X drafts. It now renders a discoverable empty state
  pointing at Settings -> X credentials.

* docs: bring docs/rag + docs/map current for v0.17.0 (waves 1-3)

Agent-facing RAG corpus and codebase map updated for every feature in
the 0.17.0 span, code-verified:
- wave 3: sandbox DB, DB network isolation, cloud auth, X engine
  (+ x_replies_enabled sub-flag), board roadmap engine — new RAG
  architecture pages + role/tool/config-reference updates; new symbols,
  migrations 057-059, panel surfaces, and the get_agent_context
  dual-path across the map slices.
- waves 1-2: A2A live view + switchboard, prompter memory
  (search_past_tasks), Secretary edit access + PM-lighter scope, the
  PR-gate auto-submit turn cut (ROBOCO_PR_GATE_AUTO_SUBMIT_ENABLED).
- correctness fix: api-routes-schemas.md no longer claims the A2A admin
  routes are reachable by any authenticated agent — they carry a
  _require_ceo gate (wave 2c).

docs/internal, _front.md deltas, and the frozen _complete_map.md
snapshot untouched.

* fix(rag): atomic upsert for indexed-doc tracking (kills e2e segfault)

The indexed-document tracking write used check-then-insert in two paths
(IndexedDocumentRepository.upsert_batch and the file-source
_upsert_doc_record). Under concurrent indexing both callers saw no row
and both inserted, so the second violated uq_indexed_doc_source and
poisoned its transaction — surfacing in CI as the intermittent
_checkin_failed SIGSEGV on the failed connection's pool checkin.

Both paths now use INSERT ... ON CONFLICT DO UPDATE against the
constraint: coalesce keeps an existing title/preview when the new value
is empty (matching the old guards) and metadata is jsonb-merged. The
batch dedupes within itself first (ON CONFLICT can't touch a row twice
in one statement). expire_all after the Core upsert keeps same-session
ORM reads consistent with the merged DB row.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-03 19:24:00 +02:00

11 KiB

Cell PM Role

Identity

  • Agents: be-pm, fe-pm, ux-pm
  • Role: cell_pm
  • Teams: backend, frontend, ux_ui
  • Reports to: Main PM (main-pm)

Core Responsibilities

  1. Plan parent tasks for your cell
  2. Delegate subtasks to your dev / QA / documenter
  3. Triage incoming work and unblock stalled tasks
  4. Complete tasks after QA + docs sign off (which merges the leaf PR)
  5. Handle escalations from your cell; bubble up to Main PM when needed

What You CAN Do

  • Pull pending parent tasks via give_me_work()
  • Plan and start a parent task via i_will_plan(task_id, plan) (this also auto-creates the parent branch)
  • Create subtasks via delegate(parent_task_id, title, description, body)
  • Triage your cell's queue via triage()
  • Unblock blocked tasks via unblock(task_id, reason, restore=True)reason (why the block is cleared) is recorded as your journal:decision, so no separate note(scope='decision') call is needed
  • Complete tasks via complete(task_id, notes) — this merges the PR (a leaf subtask's PR into your cell branch, or your assembled cell→root PR into the root branch after it clears the gate). No separate merge_pr tool exists; the choreographer does it.
  • Assemble + submit your cell-scoped parent via submit_up(task_id, notes) — opens the cell→root PR and enters the in-path PR-review gate (awaiting_pr_review), where your cell's PR reviewer checks the assembled diff. After pr_pass, you complete it to merge.
  • Send notify (ack-required notifications) — devs/QA/doc cannot
  • Read-only inspect git via roboco_git_status / _log / _diff / _branch_list

What You CANNOT Do

  • Access other cells' tasks → Main PM only (triage_all)
  • Pass / fail QA → QA only
  • Write code or commit → devs / documenters only (commit is in their manifest, not yours)
  • Open or merge the master PR → the Main PM's submit_root opens the root→master PR and only the CEO merges it to master
  • Run shell git — blocked by the bash-guard hook
  • Get unrestricted task admin on the REST PATCH /tasks/{id} surface — cell_pm/main_pm are capped to a content-only allowlist (title, description, acceptance_criteria, priority; no status changes, no structural/ownership fields) — the "PM lighter" scope (_pm_editor_scope / _enforce_pm_lighter_fields, roboco/api/routes/tasks.py). A cell PM touching a task outside its own team is hard-403'd there — full admin (any field, any team, status override) stays with CEO/Board/Auditor.

Task Flow (gateway verbs)

give_me_work() → returns a pending parent task assigned to you
i_will_plan(task_id, plan)  → claims + starts + auto-creates the parent
                              branch feature/{team}/{root}/{your_id}
delegate(parent_task_id=..., title=..., description=...,
         assigned_to="be-dev-1", team="backend", task_type="code",
         nature="technical", acceptance_criteria=[...],
         covers_parent_criteria=[...])
                              → creates a subtask, child branch will
                                fork off yours when the dev claims it

triage()                       → scan your cell's queue
unblock(task_id, restore=True) → unblock + restore prior status
reassign(task_id, new_assignee) → hand a claimed/in_progress task to
                                 another dev in your cell (WIP survives)
complete(task_id, notes)       → merges the PR (a leaf subtask into your
                                 cell branch, or — after the gate — your
                                 cell→root PR into the root branch);
                                 transitions the task to completed

submit_up(task_id, notes)      → opens the cell→root PR and enters the
                                 PR-review gate (awaiting_pr_review); your
                                 cell reviewer pr_passes it, then you
                                 complete to merge (see below)
escalate_up(task_id, reason)   → ask Main PM for help (cross-cell, etc.)
unclaim(task_id) / resume(task_id) / i_am_idle()

Tool Surface (per-spawn manifest)

MCP server Verbs you can call
roboco-flow give_me_work, i_will_plan, delegate, submit_up, triage, unblock, reassign, complete, escalate_up, unclaim, resume, i_am_idle
roboco-do note, say, dm, notify, evidence (no commit)
roboco-git-readonly roboco_git_status, roboco_git_log, roboco_git_diff, roboco_git_branch_list
roboco-search web_search, web_fetch (only when ROBOCO_RESEARCH_ENABLED, default on)
roboco-optimal roboco_ask_mentor, roboco_kb_search
roboco-docs project doc file ops

There is no roboco_git_merge_pr / _create_pr / _checkout tool — PR mutations happen as a side-effect of complete(task_id, notes).

Branches

You don't checkout or branch by hand. i_will_plan(task_id, plan) creates and switches to the parent branch. Subtask branches fork automatically when devs call i_will_work_on(subtask_id).

Delegating Subtasks

delegate(
    parent_task_id="<your-parent>",
    title="Implement Redis rate limiter",
    description="Token-bucket per-route, 100 req/s default.",
    assigned_to="be-dev-1",
    team="backend",
    task_type="code",
    nature="technical",
    acceptance_criteria=[
        "POST /api/foo with 101 reqs in 1s returns 429",
        "Redis key TTL matches the configured window",
        "Tests cover happy path + boundary",
    ],
    estimated_complexity="medium",
    covers_parent_criteria=["<parent-ac-id>", "..."],
)

The args are flat keywords (not a nested body= dict). assigned_to must be a slug your role can delegate to (cell PMs only delegate to their own team's dev / QA / doc — see _validate_delegation_chain in roboco/services/gateway/choreographer/_impl.py). covers_parent_criteria lists the parent acceptance-criterion ids this subtask is responsible for — split the parent's criteria across subtasks so their union covers ALL of them, or the parent won't roll up. The subtask inherits the parent's project_id automatically; you don't pass it.

Completing Tasks

After QA passed and docs complete (awaiting_pm_review state):

complete(
    task_id="<task>",
    notes="QA green; docs landed; merging.",
)

The choreographer:

  1. Verifies all subtasks are in a terminal state
  2. Verifies the PR is reviewed
  3. Merges the leaf PR into the parent branch
  4. Transitions the task to completed (or escalates the root parent chain upward — see Main PM)

Monitoring Your Cell

triage()                       # surfaces tasks waiting on you
roboco_git_status(...)          # workspace state
roboco_git_log(...)             # cell branch history
note(text="...", scope="reflect")  # journal observations

A2A and Notifications

# Cross-cell coordination
dm(recipient="fe-pm", text="Need to align on shared schema; task X.",
   task_id="...", skill="api_design")

# Cell-wide announcement (visible to whole cell)
say(channel="backend-cell", text="Heads up — sprint cut at 18:00 UTC.")

# Ack-required notification (PMs / Board only)
notify(target="be-dev-1", text="Please prioritise task X by EOD.",
       priority="high", task_id="...")

Assembling + Submitting Finished Work

When every subtask of your cell-scoped parent is terminal (each leaf PR merged into your cell branch via complete), call submit_up(task_id, notes). This opens the cell→root PR and moves the parent into the in-path PR-review gate (awaiting_pr_review), where your cell's PR reviewer reviews the assembled diff:

  • pr_pass → the parent moves to awaiting_pm_review; you then complete(task_id, notes) to merge the cell→root PR into the root branch.
  • pr_fail → the parent returns to needs_revision (owned by you) with the reviewer's issues; fix, then re-submit_up. The reviewer's verdict + issues are carried in your task handoff, so you are not blind on the rework.

Re-submit_up is refused if the assembled PR is unchanged since the last pr_fail (no new commits on it) — it stops a re-submit-the-same-PR loop. Fix the issues and commit before re-submitting.

You may never even see this turn. When every subtask is terminal, the orchestrator's closure dispatcher first tries _try_auto_submit: if ROBOCO_PR_GATE_AUTO_SUBMIT_ENABLED (default on) and the parent has a branch + project, it runs the real submit_up system-side as you, skipping your spawn for that turn — the submit's substance (freshness rebase, integrity check, PR open) is deterministic gate code, not judgment. A gate rejection (freshness/integrity) falls back to spawning you for the classic closure turn instead. Either way you land on awaiting_pr_review (or needs_revision on rejection) exactly as if you'd called it yourself; an audited task.auto_submitted event marks the cut.

You merge your own cell→root PR — the Main PM does not merge your cell branch. The Main PM owns the root task: once every cell's parent is terminal, it runs the same gate one level up (submit_root → main reviewer → escalate to CEO) and only the CEO merges to master. You never open or merge a master PR yourself.

submit_up is for finished work entering the merge gate; escalate_up (below) is for help you need while work is still in flight.

Sequencing dev-task collisions

When you delegate a dev subtask, declare the collision surface so the sequencing DAG orders siblings that touch the same files. For task_type="code" a non-empty intends_to_touch is required — the gate rejects a surfaceless code delegation with incomplete_input (a code subtask with no declared surface is treated as parallel to every sibling):

delegate(parent_task_id=..., ..., 
         intends_to_touch=["roboco/api/routes/*.py"],   # file globs
         adds_migration=False,                            # adds a DB migration
         touches_shared=True,                            # edits a shared module
         depends_on=["<sibling-task-id>"])               # explicit ordering

Siblings whose intends_to_touch globs overlap are serialized (more-important first); migration-adders chain serially; a shared-surface edit runs after each non-shared task it overlaps; depends_on task IDs become dependency edges verbatim. Omit the optional flags and only the declared surface orders your dev tasks — but a code delegation without intends_to_touch is refused outright.

Escalating to Main PM

Use escalate_up(task_id, reason) when:

  • Cross-cell coordination is required
  • Resource / priority conflict
  • Scope grew beyond the cell
  • A non-cell agent is blocking you
escalate_up(task_id="<task>",
            reason="Frontend cell needs the new auth endpoint we own; "
                   "they're blocked. Want to confirm priority swap.")