Runs the security template's tool set (cargo-audit / gitleaks /
trivy fs / semgrep) inside the mission's team container and
materializes each finding as a mission_task keyed on the tool's
canonical id. The subsequent coding phase picks up the tasks and
applies remediations; the committer closes them by emitting
`COMPLETED: <external_id>` (Slice 5's task-card parser handles it).
Rust surface:
- cm_api::security_scan::run(mission_id, phase_id)
- Per-tool runners with JSON output parsing:
cargo audit --json → vulnerabilities[].advisory.id
gitleaks detect --report-format=json → [{ Fingerprint, RuleID }]
trivy fs --format=json → Results[].Vulnerabilities[].VulnerabilityID
semgrep --config=auto --json → results[] w/ rule+path+line fingerprint
- Tool errors surface as a `warning` task instead of failing the
scan — operator sees which need installing/fixing without a
silent no-op.
- Findings map to mission_tasks with external_id = "<tool>:<id>"
(e.g. cargo_audit:RUSTSEC-2024-0001, gitleaks:<sha>,
trivy_fs:CVE-2024-1234, semgrep:<rule>@<file>:<line>).
API:
- POST /api/missions/{id}/security-scan { phase_id }
→ { findings, tasks[] } — full task list after upsert so the
canvas can render immediately.
Frontend:
- triggerSecurityScan helper in lib/api/missions.ts. Findings
show up in the existing Tasks tab (Slice 5's UPSERT path).
Container requirements (opt-in):
- Runs inside the team container via `docker exec`, so the tools
must be present in that image. Missing = warning task, not fail.
- `-w /workspace/repo` so scanners see the mounted repo. Reads
teams.zeroclaw_container (populated on first phase run).
Follow-ups:
- MCP bundle wrapping the same tools as agent-callable functions
(currently agents scan by shelling out to `cargo audit` etc.
directly; a typed MCP wrap lands with clean audit trail).
- Auto-fire from the security_hardening workflow template on
phase transition (currently manual via API trigger).
- Bundle the four tools into the runtime image (or a dedicated
security-tools image) so operators don't have to install them.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Executes a benchmark harness inside the mission's team container
and records the resulting metrics as a benchmark_snapshots row keyed
on (phase_id, iteration). Baseline pass (iteration=0) captures
before_metrics; each post-iteration call captures after_metrics +
computes delta vs baseline.
Rust surface:
- cm_db::repo::missions::upsert_benchmark_snapshot / benchmark_snapshots_for
- cm_api::benchmark_runner::{baseline, after_iteration, run}
- Harness enum: Auto | Criterion | CargoBench | VitestBench |
PytestBench | Shell (each with a command() vector)
- Auto detection peeks at the repo layout inside the container
(Cargo.toml → CargoBench, package.json → VitestBench, pyproject
→ PytestBench). Falls back to a Shell echo when nothing
identifiable.
- Bencher-format line parser extracts (name, ns_per_iter,
plusminus) so criterion + `cargo bench` output become structured
samples the canvas can diff.
- compute_delta pairs samples by name, emits {before_ns, after_ns,
delta_pct, direction: improved|regressed}.
API:
- POST /api/missions/{id}/benchmark { phase_id, slot, iteration? }
triggers baseline or after run and returns the mission's full
snapshot list.
- GET /api/missions/{id} now includes `benchmarks[]` in the detail
payload.
Frontend:
- New Benchmarks tab on MissionCanvas with iteration + driver
header, plus a 4-column grid (bench / before / after / Δ%) when
delta samples are present. Improved deltas render green,
regressions red.
- TS types + triggerBenchmark() helper in lib/api/missions.ts.
Wiring notes:
- team_container_for_mission reads teams.zeroclaw_container — that's
populated by topology_worker::try_team_gateway_url on first run,
so trigger baseline AFTER the mission's first phase spawns the
container.
- Not auto-fired yet by phase execution; that's the "template phase
executor" work that spans Slices 4-8. Manual API trigger works
today; automated hook is a follow-up.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Watches mission_artifacts for MD entries with render_pdf_status='pending'
and turns them into styled PDFs via:
1. Read source MD from <mission_root>/<path>
2. Call configured LLM (default gemini-2.5-flash) with a document-
typesetter system prompt that constrains style to a self-contained
HTML doc with inline CSS + our color palette
3. Print to PDF via `chromium --headless=new --print-to-pdf`
4. Save alongside source MD (foo.md → foo.pdf) + update
mission_artifacts.rendered_pdf_path + render_pdf_status='done'
Graceful degradation: GEMINI_API_KEY unset OR chromium missing =
row marked failed with a descriptive error, worker keeps ticking.
The frontend's "Open PDF" affordance (Slice 2) light up automatically
when render succeeds.
Boot ordering: PDF worker spawns after task_card_worker. Poll every
30s over up to MAX_PARALLEL=2 rows at a time — respects LLM rate
limits and keeps chromium's peak RAM under control.
Env knobs:
GEMINI_API_KEY — required for LLM step
CLAWMATES_PDF_RENDERER_MODEL — model id, default gemini-2.5-flash
CHROMIUM_BIN — chromium binary, default `chromium`
CLAWMATES_MISSIONS_ROOT — artifact dir root, default /var/lib/clawmates-missions
Dockerfile now installs chromium + fonts-liberation and sets
CHROMIUM_BIN=/usr/bin/chromium so the container image has everything
the renderer needs.
Also bumps workspace tokio deps to include the `process` feature
(required for tokio::process::Command).
Follow-ups:
- Anthropic + OpenAI provider variants (only Gemini in this slice)
- SSE stream on /api/missions/{id}/artifacts for the "PDF ready"
notification instead of poll-via-mission-GET
- Per-template PDF style overrides (currently one house style
for all missions)
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Watches topology_runs' event stream for the INT-XX marker protocol
(see skills/foundation/int-xx-marker-protocol.md) and materializes
mission_tasks rows with typed status so the canvas Tasks tab renders
a live timeline instead of raw agent chatter.
Migration 0051 adds mission_id + mission_phase_id columns to
topology_runs (nullable) so runs enqueued by a mission phase can be
attributed. Populated by future phase executors; NULL for legacy
research/loops runs (parser skips them cleanly).
New Rust surface:
- task_card_parser::parse(text) — line-scanner over TASK/WORK/
HANDOFF/TEST_PASS/TEST_FAIL/REVIEW_APPROVE/REVIEW_BLOCK/COMPLETED
markers. Strict: exact kind + colon + INT- prefix, no in-prose
matches, no bold/code-fence wrappers.
- task_card_parser::apply_for_run(pool, run_id) — reads the run's
mission binding, walks its event payloads, extracts text/output/
content/message string fields (matching every ZeroClaw event
shape we see), parses markers, UPSERTs mission_tasks via the
(phase_id, external_id) unique key from Slice 1.
- task_card_worker::spawn — 15s poller over runs updated in the
last 5 minutes. Idempotent + generous window survives server
restarts + task-scheduling jitter.
Boot wires the worker after the content loaders. Silent no-op when
mission wiring isn't populated yet.
MarkerKind → status mapping (monotonic-forward):
TASK → created
WORK → working
HANDOFF → validating
TEST_PASS → validating
TEST_FAIL → failed
REVIEW_APPROVE → validating
REVIEW_BLOCK → failed
COMPLETED → complete
Follow-ups:
- Wire phase executor to populate topology_runs.mission_id +
mission_phase_id (Slice 6/7/8 work)
- Assign assigned_agent_id via the event's producing agent alias
(currently always None)
- SSE stream on /api/missions/{id}/tasks for live canvas updates
(currently the canvas polls via mission GET)
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Two things land together:
1. Ships the 5 workflow recipes as TOML files under
templates/workflows/*.toml:
- research_only (hub_spoke research → MD + PDF)
- research_and_code (research → coding loop until INT-XX drained)
- security_hardening (scan → research patches → coding with
reviewer approval + full MCP bundle)
- refactor (single-pass coding with dep audit
preamble + before/after benchmarks)
- benchmark (author + baseline benchmarks per stack)
Each declares phases[], per-phase config, default_team_template.
Loaded read-only into an in-memory registry (workflow_registry)
via OnceLock — no DB row per recipe.
2. Ships the mission-launch orchestrator that closes the loop from
Slice 3.5d's mechanics. When a mission transitions draft→running,
`mission_orchestrator::on_launch`:
- Reads mission.team_template_id (skips if unset)
- Loads the team template detail (roles + skills bindings)
- Builds a topology graph from role slots via cm_topology::build
- Inserts the teams row + stamps template_id/version/risk_profile/mcp_bundles
- For each role: agent insert, model binding, runtime provision
(opt-in via RuntimeProvisioner::from_env), brain_seed::ingest
(Slice 3.5d), agent_template_link::upsert (Slice 3.5d),
team_members bind, audit trail
- UPDATE missions SET team_id = ...
Wired into routes::missions::set_status when prior.status='draft'
and new='running'. Failures log + are non-fatal (mission still
flips to running so the user can inspect + retry).
With this, Slice 3.5d's brain-seed + link machinery actually gets
populated, and the MCP skills server's template-defaults-merge path
(Slice 3.5b/d) starts serving real bindings to real agents.
Follow-ups (Slice 5-8):
- Task-card parser watches run events for TASK/COMPLETED markers
→ mission_tasks rows
- PDF renderer worker turns MD artifacts into PDFs
- Before/after benchmark runner honors phases[].config.benchmark
- Security scan MCP bundle exposes cargo-audit/gitleaks/trivy/semgrep
- Level-up endpoints diff learned-vs-seeded via agent_template_link
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Ships the lineage layer that ties agents back to their team template
and wires the MCP skills server to actually merge template default
skills with per-agent overrides.
Migration 0050 adds `agent_template_link` (agent_id PK, template_id,
template_version, role_slot, seeded_at, created_at + indexes for
template/role lookups). Populated at agent-materialization time by
Slice 4's mission-launch orchestrator; read here by the skills MCP
server and by future level-up (Slice 8.5).
New Rust surface:
- cm_db::repo::agent_template_link (upsert / get / mark_seeded /
agents_for_template — the last is what level-up's "prompt upgrade
on template N+1" query needs)
- cm_api::brain_seed::ingest(claw_id, seed_md, identity_prompt)
opens cm_brain::ClawBrain on spawn_blocking, sets system_prompt
on first touch, writes seed as agent_md, commits. Idempotent —
skips when agent_md already populated.
- cm_api::mcp_skills::mcp_skills tools/call now resolves the caller
agent's template + role via agent_template_link and merges
template default skills with per-agent overrides (was overrides-
only in Slice 3.5b).
- cm_api::team_template_loader now binds template_role_skills after
upserting each template — looks up each declared skill by name,
attaches with pin_in_context=true for foundation skills and the
first two role skills. Missing skills log + skip.
- Boot ordering: skills load BEFORE team templates so the binding
lookup resolves.
Follow-up (Slice 4): mission-launch orchestrator calls brain_seed::ingest
+ agent_template_link::upsert when minting a team from a template.
Until that lands, the link is populated only by manual writes; the
MCP merge is silent-no-op for agents without a link (falls through
to overrides-only), which matches the pre-3.5d behavior.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Exposes the skills catalog as MCP resources so agents can discover
+ read skill markdown on demand — the delivery half of the "skills
teach how to think, MCP gives ability to act" model.
New endpoint: POST /mcp/skills (parallel to the existing /mcp door).
Protocols supported:
- initialize — handshake, advertises resources + tools
- resources/list — one entry per skill visible to the caller's
workspace. URI scheme:
skill:global/<name>
skill:workspace/<ws>/<name>
description carries the skill's description
+ when_to_use so the LLM can decide when
to reach for it.
- resources/read {uri} — returns body as text/markdown. Enforces
workspace scope on workspace-authored
skills.
- tools/list — one entry: skills__pinned_bundle
- tools/call — skills__pinned_bundle concatenates every
skill pinned for the calling agent (via
X-ZeroClaw-Agent header) with H1 headers.
Cheaper than N resources/read at turn start.
Adds the `clawmates_skills` bundle to the runtime template config
alongside `clawmates_door`, and teaches the MCP bearer rewriter
(prewrite_daemon_config_with_risk) to inject the workspace-owner
service session bearer on both `clawmates` and `clawmates_skills`
servers.
Follow-ups:
- Slice 3.5c: seed ~40-60 builtin skills across the 6 stacks
- Slice 3.5d: agent_template_link lineage — until it lands, the
pinned_bundle tool can only surface per-agent overrides, not
template defaults (documented inline)
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Introduce the skills catalog: the second half of the two-layer agent
model (skills teach agents HOW to think about a problem; MCP servers
give them the ABILITY to act). Delivery via MCP resources lands in
Slice 3.5b; this slice ships the data model + API surface.
Migration 0049 extends the legacy `skills` table (from 0001_init.sql,
originally a workspace catalog of markdown snippets) with the richer
typing we need — name, when_to_use, tags, source_kind, current_version
— rather than duplicating tables. Also adds:
- skill_versions (version history for level-up promotions +
rollback; back-pointer via promoted_from
JSONB records agent_id / research artifact /
brain memory that produced it)
- template_role_skills (m2m binding skills to team-template roles
with pin_in_context + order_idx)
- agent_skills_ext (per-agent overlay: include=true adds a skill
to the bundle; include=false prunes a
template default for this specific agent)
Rust surface:
- cm_db::repo::skills_catalog with typed Skill/SkillVersion/
AgentSkillBinding structs + upsert_builtin (idempotent — bumps
version + appends to skill_versions ONLY when body changes) +
list_visible/get/get_by_name reads + template + agent binding
helpers + effective_for_agent (merges template defaults with
agent overrides, applies exclude precedence, batch-fetches skill
bodies)
- cm_api::routes::skills_catalog with:
GET /api/skills — list visible
GET /api/skills/{id} — detail
GET /api/claws/{id}/skills — effective binding (accepts
template_id + role_slot as query args to merge in template
defaults)
Follow-ups:
- Slice 3.5b: clawmates_skills MCP server exposes catalog as MCP
resources, honoring pin_in_context for auto-injection
- Slice 3.5c: seed ~40-60 builtin skills across the 6 stacks
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Team templates are the canonical rosters + tool bundles that mint
concrete teams for a mission. Every builtin ships as a TOML recipe
under templates/teams/*.toml, loaded into the DB at server boot.
Migration 0048 adds:
- team_templates (id, key, name, stack, default_topology,
risk_profile, mcp_bundles, version, source,
workspace_id)
- template_roles (m2m: template_id + slot; system_prompt,
skills[], brain_seed)
- teams gets template_id + template_version for level-up lineage
Ships 6 builtins:
- rust_sdlc — planner/coder/tester/reviewer/committer for Rust
- backend — api_designer/db_engineer/coder/tester/committer
(Postgres, DuckDB, graph DBs, wire protocols)
- frontend — designer/coder/tester/committer (React + Tailwind + ShadCN)
- mobile — designer/coder/tester/committer (Expo, RN, iOS, Android)
- gpu — arch_analyst/kernel_author/bench_engineer/coder/committer
(CUDA, Metal, ROCm from Rust)
- threejs — scene_designer/coder/shader_author/perf_engineer/
committer (three.js, WebGL, WebGPU)
Each role has a versioned system_prompt + skill list + brain_seed
markdown. Skills column is a name array today; Slice 3.5a promotes it
to a typed m2m join with the real skills catalog.
Server boot:
- team_template_loader::load_builtins reads TOML from
/etc/clawmates/templates/teams (container) or templates/teams (dev),
upserts idempotently. Deterministic uuid per template key (sha256
of a fixed namespace + key) so ids are stable across boots.
- Dockerfile copies templates/ to /etc/clawmates/templates.
Read API:
- GET /api/team-templates — list all
- GET /api/team-templates/{id} — detail with roles
Wizard:
- Step 3 rewired from a raw team_id text field to a template picker
with "LLM auto-provision" as the default option + one card per
builtin, showing stack, topology, risk profile, and description.
- Mission create now passes team_template_id (not team_id) so phase
execution knows which template to mint from.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Introduce the unified `missions` tier that will replace the current
research_topics + loops split. This slice ships the data model +
backfill + skeleton REST surface; the old wizards keep working in
parallel until Slice 9's big-bang cutover.
Migration 0047 adds:
- missions (top-level workflow: template_kind + team +
schedule + status + config)
- mission_phases (ordered {research|coding|benchmark|
security_scan} phases per mission)
- mission_tasks (typed units of work, e.g. INT-XX cards,
UPSERT-keyed on (phase_id, external_id))
- mission_artifacts (MD/PDF/benchmark/security/diff files with
a pending queue for the PDF renderer worker)
- benchmark_snapshots (before/after pairs per iteration)
Backfill copies existing research_topics + loops rows into the new
tables as one-shot missions with the appropriate template_kind, so
Slice 2's UI can render the full history immediately.
New Rust surface:
- cm_domain: MissionId, MissionPhaseId, MissionTaskId, MissionArtifactId
- cm_db::repo::missions: Mission/MissionPhase/MissionTask/
MissionArtifact structs + insert (txn-wrapped)/get/list/set_status/
phases_for/set_phase_status/upsert_task/tasks_for/register_artifact/
artifacts_for/next_pdf_pending/set_pdf_result
- cm_api::routes::missions: skeleton list/create/get/set_status
routes registered at /api/missions/*
Follow-up slices layer richer behavior (template dispatch, phase
execution, task parsing, artifact rendering) on this foundation.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Coding loops with team_id set MUST run inside their team container so
agents have /workspace/repo bind-mounted. When try_team_gateway_url
silently returned None on error (mkdir perm denied, spawn_team failed,
etc.), the executor fell through to the shared runtime — which has no
repo mount — and the coding agents narrated for 6 minutes without
touching a file. Runs completed "green" with zero commits, hiding real
infra breakage.
Change try_team_gateway_url from Option<String> to Result<Option<String>, String>:
- Ok(Some) — team spawned/reattached; drive it.
- Ok(None) — no team binding on this run; existing per-topic/per-loop
fallback resolvers still apply.
- Err — team was expected but spawn failed; caller fails the run
with a descriptive error instead of silently degrading.
Each failure path in try_team_gateway_url now formats a specific
diagnostic string (docker connect, spawn_team, missing repo_workspace_path,
etc.) that surfaces into topology_runs.error.
The MCP-bearer mint failure is deliberately kept as a warning + best-
effort: some tools will 401 but the container still boots. Only failures
that would prevent code from being touched escalate to Err.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
The log SSE endpoint was always resolving the container name from a
research topic id (research-<topic_id>-team). For paired coding loops
that own a team_id, the actual container the topology worker spawns is
team-<team_id>-container (spawn_team) — not the research topic's one.
That mismatch produced a stream of 404s from Docker:
Docker responded with status code 404: No such container:
research-<topic_id>-team
Mirror topology_worker::try_team_gateway_url's precedence:
1. run's loop has team_id → team-<team_id>-container
2. run has research_topic_id → research-<topic_id>-team
3. loop.source_research_topic_id (legacy paired flow) → same as 2
4. else → clear error, no more 404 spam
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Two UX cleanups on the research canvas:
1. Agent cards were showing "(missing agent)" for every slot after an
in-wizard auto-provision because the Dashboard's `claws` prop is SSR-
rendered and doesn't include agents created during the client session.
Refetch /api/team/claws on canvas mount + refreshKey change, merge
with the prop (fresh wins) so newly-provisioned agents resolve
correctly without a page reload.
2. The Description block was always fully expanded. Wrap it in <details
open> so the user can collapse it once they've read it, matching the
existing "Original prompt" pattern.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
The wizard was hard-failing (500) when clawstor was unreachable —
env unset, network error, non-JSON HTML response from a fallback
proxy, or non-2xx status all mapped to ApiError::Internal, which
blocked the wizard from advancing.
Clawstor fan-out is a warmup optimization, not a prerequisite.
Real fleet materialization happens later at spawn time. When the
aggregator is absent, return a skipped FanoutReply (all_ok=true,
empty peers) so the wizard proceeds, and log the reason server-side.
Unblocks: picking clawhdf5 in the ResearchWizard when the tank/
architect clawstor daemons are running but the HTTP aggregator
(`claw-store serve`) isn't deployed yet.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
PATCH /api/teams/{id}/runtime-config existed since the team-wizard work
but had no UI — you needed curl to swap a team's risk_profile or add
gitea_forge to its bundles. Add compact pickers to TeamRunsModal above
"Run now": a Risk profile <select> and a Bundle checkbox list.
Fetches current settings from GET /api/teams/{id} on open and PATCHes
inline on every change. No save button — the debounce is the user's
next click. Optimistic state; next-open resync corrects any drift.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
The LoopsWizard hard-blocked on an empty roster via NoAgentsGate — new
users had to bounce to the Agents page first. Match ResearchWizard's
flow: remove the top-level gate, add an auto-provision panel to the
staffing step (6) that derives 3-5 roles from the loop's task via
Claude Sonnet 5 and preselects the returned agents into
selectedAgents so the existing submit path publishes them onto the
loop with zero extra clicks.
Existing rosters still work — the hand-pick panel now sits below the
auto-provision card and only renders when the workspace has agents and
no team was auto-provisioned this session.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Per-team runtimes had their MCP bearer swap wired in the prior slice,
but per-topic (research_container::spawn) and per-loop (spawn_loop)
containers still baked the stale template bearer and 401'd every
tools/list. Same fix, extended: mint a workspace-owner service session
via runtime_provision::mint_workspace_service_token and inject via
prewrite_daemon_config_with_risk.
Move mint_workspace_service_token from topology_worker into
runtime_provision so all three spawn call sites share the helper.
Callers updated: routes/research.rs (start_topic), routes/research_setup.rs
(prepare_topic_runtime), routes/loops.rs (ensure_loop_container).
Co-Authored-By: Claude Opus 4.7 <[email protected]>
CI's fmt check runs on stable toolchain that rejects let chains in
if conditions. Nest the `if let` inside the block instead.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
The runtime template's static clawmates_door bearer is rejected by
cm_auth::authenticate() (needs an auth_sessions row). Every per-team
agent was getting `unauthorized: missing or invalid bearer token` and
`0 tool(s) registered from 0 server(s)`.
Add AuthService::mint_service_session + users::owner_of_workspace and
mint a 30d service session in try_team_gateway_url; inject it into the
freshly-spawned team container's config.toml [[mcp.servers]] clawmates
Authorization header via prewrite_daemon_config_with_risk (bearer arg).
Follow-up: apply the same pattern to research::spawn (per-topic) and
per-loop spawn paths.
Co-Authored-By: Claude Opus 4.7 <[email protected]>
Auto-provision (and every other build_team caller) hit
'dangling_reference: claude_cli is not a known provider family'
because provider_alias_for still returned v0.7.x aliases —
claude_cli.default / claude_cli.glm / claude_cli.glm5 /
kimi_cli.default — all deleted upstream when providers.models
schema was restructured.
Now the mapping resolves to real configured aliases:
- 'claude'* prefix → anthropic.default
- 'gemini'* prefix → gemini.default
- 'llama'* / 'groq' → groq.default
- glm* + kimi* → anthropic.default (fallback until glm.default /
moonshot.default provider tables land in the runtime template)
- unknown → anthropic.default
Covers the model picker's full roster (claude-sonnet-5 / opus-4-8 /
haiku-4-5 / sonnet-4-6 / glm-4.6 / glm-5.2 / kimi-k2 /
gemini-2.0-flash / llama-3.3-70b-versatile) plus every legacy
shorthand.
Tests updated to assert the new mappings including the model
picker's ids.
The '+ new topic' button (commit 47a4242 unlocked it when the
workspace roster was empty) is a tiny 34x34 corner icon that
disappears against the header on a truly empty page. Users kept
asking why they can't start a research topic when in fact they
could — the target was just invisible.
Replace the 'Hit the + button to launch the wizard' hint with a
proper primary CTA: coral pill 'Start a research topic' with the
Plus icon, centered in the empty sidebar. Same treatment for
LoopsList → 'Start a loop'.
The wizard flow's auto-provisioning behavior means the empty-
workspace path is now the happy path — one click and you get
everything (topic, team, agents, container). The empty state
should invite that click, not require a hunt.
The '● <model>' text on the per-agent Computer slide-out was
read-only — swapping a claw's model required curl. Now it's a
button that opens a small dropdown of the curated fleet models:
- Sonnet 5 / Opus 4.8 / Haiku 4.5 / Sonnet 4.6 (Anthropic)
- GLM 4.6 / 5.2 (Z.AI)
- Kimi K2 (Moonshot)
- Gemini 2.0 Flash (Google)
- Llama 3.3 70B (Groq)
Click a model → PATCH /api/claws/{id}/model → picker closes, the
button relabels to the new selection. The endpoint persists the DB
binding + best-effort re-provisions the runtime; the swap applies
on the claw's next turn. Long-tail models still work via curl with
any string.
Adds an optional onModelChanged callback so callers (Dashboard's
runtime-config enrich cache) can refresh their state without a
full re-render.
Auto-provisioned agents (via the research + loops team wizard) show
up on the Agents page (same agents::insert → agents::roster path),
and PATCH /api/claws/{id} already handled name/job_title/system_prompt/
avatar/accent/wallpaper. The one thing that was NOT reachable from the
Agents page: swapping the model.
Add a dedicated endpoint:
- PATCH /api/claws/{id}/model { model: string }
- Persists via agents::set_model_binding (DB)
- Best-effort runtime rebind via RuntimeProvisioner::provision_claw
(idempotent — overwrites agents.<alias>.model_provider on the
shared ZeroClaw config)
- Audit-logged as 'agent.model_changed' with the new model in payload
Now an operator can open the Agents page, click a claw that was
auto-provisioned by the team wizard, and swap its model
(claude-sonnet-5 → glm-5.2 → whatever) without recreating the team.
Same DB row, same claw_id, same brain — just a new provider on the
next turn.
Frontend affordance not shipped in this commit — the endpoint is
usable via curl/psql/scripts today; a UI 'Model' picker on the claw
detail card can land in the next Agents-page pass.
Two bundled changes:
── LiveRunLogs prettification ──────────────────────────────────
The Steps + Container tabs were plain mono lines with a single
color per event. Now they get structured layout:
Steps:
- Color-hashed actor pill (stable palette so [Distiller] and
[Novelty Analyst] each get their own hue across the session).
- Phase pill (plan=cyan, work=green, synth=amber, aggregate=purple).
- Token count pill formatted 1.2k / 14.3k / etc.
- Gated-action warning pill in amber when > 0.
- Left-border color strip keyed to the actor for at-a-glance
visual grouping.
- Long outputs collapse to their first 300 chars with a '+ N more'
toggle to expand the full text.
- 'done' events get a green (or red for error) border strip +
pill instead of blending into the stream.
Container:
- Splits '[actor] action (outcome) · msg' into colored spans —
actor pill (deterministic color), action in dim, outcome pill
green/red/dim by state.
- Non-line events (info/error/done) get their own left-border
strip so bash echoes and stack traces don't drown in the daemon
chatter.
- Timestamps switch to HH:MM:SS.mmm — dense but scannable.
Small palette (LOG constants) keeps the color budget bounded — no
new UI vocabulary, just cleaner reads of what was already there.
── Team-wizard governance parity ───────────────────────────────
build_team_with_lifecycle now matches POST /api/claws' governance:
- enforce_new_agent quota check per member (previously bypassed
workspace agent quotas entirely for team/auto-provision paths).
- audit::append('agent.created', ..., {source: 'team_wizard'}) per
member so team-created claws appear in the same audit trail as
individually-created ones. Adding a 'source' key distinguishes
provenance without changing consumers.
.brain (h5) handling was already consistent between the two paths —
both use the lazy on-first-access load_brain hook seeded from
agents.system_prompt. No change there.
Step 5 of ResearchWizard was 'assign agents from workspace roster'.
When the roster was empty, the wizard body was hard-swapped for
NoAgentsGate — you couldn't reach step 5 at all.
Now step 5 shows a 'Team' panel:
- Big cyan card: 'Auto-provision team from this topic'. One click
runs an LLM plan pass, gets 3-5 role slots + system prompts back,
materializes claws via the existing build_team pipeline, stamps
runtime posture, returns a shape that drops straight into the
submit body's agents[]. Card flips green with the derived roster.
- Below that: the classic roster picker, but only when the workspace
actually has ≥1 claw AND auto-provision hasn't landed. Otherwise
hidden — no dead empty-state affordance.
Every gate that required agents.length > 0 to render the wizard body
or the footer is gone. canNext gains a step-5 clause: allow Next when
EITHER auto-team is ready OR the user handpicked from a non-empty
roster.
Backend
- POST /api/teams/auto-provision — accepts {title, description,
outcome_kind, topology_kind?, model?, risk_profile?, mcp_bundles?}.
Derives topology from outcome_kind (integrations → pipeline; else
hub_spoke). LLM plan pass yields a JSON roster of 3-5 roles
(role_slot, name, system_prompt). Materializes team + claws via
build_team, stamps risk_profile (default research_web_readonly) +
mcp_bundles (default [clawmates_door, gitea_forge]). Response
carries team_id + agents[] in the shape /api/research already
expects.
- Every provisioned claw runs on claude-sonnet-5 by default;
overridable via the model field.
Follow-ups (not in this slice):
- Same picker in LoopsWizard (slice C — parallel change, same API).
- Post-create 'Team' section on ResearchCanvas / LoopsCanvas so
users can rebind after the fact (slice D).
- Full Teams tier UI + Agents-page deprecation (slice E).
The 'no agents → button disabled' guard hard-locked the wizard
behind an already-populated roster, forcing users to detour to the
Agents page and come back. NoAgentsGate already handles the empty
state gracefully inside the wizard body; the button just needed to
open it. Applied to both ResearchList and LoopsList.
Follow-up (design in progress): let the wizard auto-provision a
team from the topic/loop itself so users never have to leave to
create agents.
Previously the Agents header wrapped a 'N ORGS · N CO · N TEAMS ·
N AGENTS' small-caps caption above the title, with the toolbar
(select/history/brain) hanging off the right. Dense, noisy, and the
World tier already surfaces those counts at higher fidelity.
Now: single-line header — 'Agents' title on the left, toolbar flush
right, both center-aligned. Comment left in place noting where the
caption used to live in case we ever want it back.
