Crosses pipeline x debate with 3 model casts (Claude, GLM-4.7, heterogeneous)
on a fixed decision task, judge-ranked 1-6. Central finding: the topology x
model interaction is real and non-monotone — debate amplifies the strongest
model (GLM-4.7: 2nd->1st) but degrades others (Claude: 3rd->last). The optimal
configuration is a joint choice over {topology x per-role model}, which neither
a topology-only nor model-only study can surface. 21 turns, sequential, within
subscription quota caps. Safety invariant holds across all cells.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Single-role drafter on a fixed concision-weighted brief, one turn per backend,
judge-ranked: GLM-4.7 > Claude > Kimi > GLM-5.2. Notable inversion — the
flagship GLM-5.2 ranked last by over-writing the 25-word brief, underscoring
that the best model is role/task/rubric-dependent. Adds the worker_glm5
(glm-5.2 Opus-class) tier to the example config. Gemini excluded this run
(Google June-19 API-key-restriction 403; infra, not model).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Adds the Phase C result: five backends (Claude/Kimi/GLM/Gemini/Groq) as
interchangeable role-agents, per-node model selection via node.attrs["agent"],
and a 3-config drafter->refiner sweep judged for quality. Heterogeneous
GLM->Gemini won over the all-Claude baseline — an existence proof of
"which model wins which role in which topology." Notes quota-bounded sweep
scope as future work.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
TurnRequest gains an optional `agent` sourced from the graph node's
attrs["agent"]. The ZeroClaw executor binds a node to that alias directly
when present, falling back to the role→alias map otherwise. This lets a
single POST /api/topologies/run specify a different model per role
(heterogeneous topologies) entirely in the graph JSON — no server
ZEROCLAW_AGENT_MAP change or recreate per configuration, which makes
quota-frugal model×role sweeps practical.
cm-orchestrator 13 + cm-api topology_exec 4 tests pass, clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Gemini via the built-in `gemini` API family (gemini-2.5-flash default,
gemini-3-pro-preview flagship) and Groq via `groq` — both wired as topology
worker aliases (worker_gemini, worker_groq), no image rebuild. Documents the
Phase C recipe: map semantic roles to per-model aliases via the server
ZEROCLAW_AGENT_MAP, then POST /api/topologies/run.
Five subscription/API backends now selectable per role: Claude, Kimi, GLM,
Gemini, Groq. Proven live on gw-04 — a 3-stage pipeline ran researcher=GLM-4.7
-> analyst=Kimi-K2 -> writer=Gemini-2.5-flash end-to-end (RunRecord persisted).
Quota-care notes added (5h/weekly caps, low concurrency -> prefer sequential
pipelines, short prompts).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
GLM Coding Plan has no CLI of its own and ToS-throttles raw SDK/API access
("1113 Insufficient Balance"); it is served only inside officially supported
tools, and Claude Code is the primary one. So GLM rides the existing
claude_cli provider with a z.ai env override (ANTHROPIC_BASE_URL=
api.z.ai/api/anthropic + ANTHROPIC_AUTH_TOKEN) — no new provider, no image
rebuild. Fresh HOME + CLAUDE_CODE_OAUTH_TOKEN="" so the container's cached
Claude subscription doesn't override the routing; key via $NAME indirection.
Deployed & verified on gw-04: worker_glm answers "I am GLM-4.7, built by
Zhipu AI" over /ws/chat. Three subscription models now co-reside on one
runtime — Claude (coordinator), Kimi (worker_kimi), GLM (worker_glm).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Runtime image now installs Node 22 (nodesource) + both agent CLIs —
@anthropic-ai/claude-code and @moonshot-ai/kimi-code — so the zeroclaw
daemon can spawn `kimi -p` for the new kimi_cli provider on a Kimi
membership, parallel to `claude -p` (claude_cli). Kimi needs Node >=22.19;
the image was on Node 18.
Documents the kimi_cli worker recipe in agent.config.example.toml (the
coding endpoint is User-Agent gated → drive Kimi through its own CLI, not a
raw OpenAI-compat client) and keeps GLM via the registry family.
Deployed & verified on gw-04: coordinator (claude_cli) answers "Anthropic
built me", worker_kimi (kimi_cli) answers "I am Kimi, built by Moonshot AI"
— heterogeneous Claude + Kimi on one runtime, over /ws/chat.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Phase A wiring (config-only): server registry kimi provider now targets the
Kimi Code coding endpoint (api.kimi.com/coding/v1, model kimi-for-coding,
subscription-billed via a Kimi Code Console key). Runtime example documents a
custom.kimi worker provider (OpenAI-compatible coding endpoint) + GLM, selectable
per topology role via ZEROCLAW_AGENT_MAP. Activates on KIMI_API_KEY; no rebuild.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
ZeroClaw already supports glm + moonshot (Kimi) as model providers; document the
pattern to run a topology worker on them (env model+key, agent on the alias,
role->alias via ZEROCLAW_AGENT_MAP).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Adds a multi-provider registry so judges and topology execution can run on
providers beyond the default. cm-config gains [[llm.providers]] (name, base_url,
api_key_env) — all OpenAI-compatible (GLM, Kimi/Moonshot). The server builds an
Arc<dyn LlmProvider> per entry (OpenAiCompatProvider) keyed by name; a missing
key is skipped with a warning, not a boot failure. cm-runtime RuntimeConfig
carries a ProviderRegistry; Runtime::resolve_provider("<name>:<model>") selects a
registry provider (else the default). The door governor (Runtime::judge) and the
topology compare endpoint both resolve through it, so CLAWMATES_JUDGE_MODEL and
CLAWMATES_TOPOLOGY_EXEC_MODEL accept "glm:glm-4.6" / "kimi:kimi-k2".
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Both LLM-as-judge sites — the door governor (Runtime::judge) and the topology
comparison scorer (JudgeScorer) — now use the judge model (default
claude-opus-4-8, override CLAWMATES_JUDGE_MODEL). Execution/reasoning turns keep
using the configured default model (claude-sonnet-4-6).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Adds Runtime::judge (the configured model returns ALLOW/DENY + reason,
fail-open) and wires it into the door policy behind CLAWMATES_DOOR_GOVERNOR: a
governor agent judges each outbound action and can veto exfiltration / spam /
secret-leakage, atop the deterministic rules. Realizes the self-governing-
topology path — authority decided by an agent, not a human, still audited.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Ran the comparison harness end-to-end against a production model with an
LLM-judge, deployed live: debate wins quality (0.840, ~3x tokens), pipeline is
best value (0.790, cheapest), swarm is strictly dominated. Efficient frontier
{debate, pipeline}; the ranking changes vs the offline proxy — confirming
topology is a measurable quality/cost lever with §5 authority-invariance intact.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
(c) policy_decide is now async with real governance: kill switch +
per-workspace hourly rate cap (audit_log count) + email recipient-domain
allowlist + a governor extension point. Still allow-all by default (autonomous).
(b) the door now supports broker-executed tools: for a broker tool it mints an
auto-approved approval + single-use grant (agent->session->run->approval->
decide), then executes via the runtime so the broker consumes the grant and
reveals the credential — the agent never holds it. Exposes slack_post.
cm-runtime gains tool_broker_executed + tool_preview accessors.
4 door unit tests + clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Adds the claude_cli.door provider pattern (mcp_config + allowed/disallowed
tools) so a subscription claude_cli agent reaches the Clawmates door via Claude
Code's own MCP client, with native tools locked out (door = only actuator).
Validated live on gw-04: subdoor agent (claude_cli, subscription) → door →
outbox + agent|door.executed audit, cost 0.0; shell command denied.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Set the tool-free risk profile to level="full" so ZeroClaw raises no in-channel
approval (the human is removed; the Clawmates door auto-governs). Document that
claude_cli is text-only (claude -p doesn't surface tool calls), so agents that
ACT through the door need a tool-capable provider (groq/anthropic) — with a
commented actor-agent example.
Validated live: a groq-brained actor agent at full autonomy emitted
clawmates__email_send with no approval prompt; the door executed it (outbox +
agent|door.executed audit). No human in the loop.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Tool-free ZeroClaw agents get one actuator: an MCP server (POST /mcp, JSON-RPC
2.0, protocol 2024-11-05) that fronts the existing §15 machinery. The human
approver is replaced by an automated policy (default allow-all → agents are
autonomous; CLAWMATES_DOOR_POLICY=deny is a kill switch), but the governed parts
stay: every action is journaled to the append-only audit log, actions execute
through the runtime's gated-tool path, and broker credential-custody is wired in
for v2 tools. Synchronous execution returns the real result inline.
- crates/cm-api/src/mcp_door.rs: initialize/tools.list/tools.call handler; auth
(bearer -> workspace), classify effects, policy auto-decide, execute, audit.
v1 exposes email_send (-> outbox); slack/pay (broker+grant chain) is next.
- crates/cm-runtime: Runtime::{tool_descriptor_json, tool_gate_category,
execute_door_tool} — door-facing entry that builds ToolContext and consumes a
grant for runtime-executed gated tools.
- deploy/clawmates-runtime: agents now carry mcp_bundles=["clawmates_door"];
[[mcp.servers]] points at the door (bearer injected at deploy, not committed).
Validated live on gw-04: tools/call email_send -> isError:false + outbox row +
"agent|door.executed" audit, no human. 4 door unit tests + clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Switch the per-tenant runtime to ZeroClaw's new native `claude_cli` model
provider (added in the zeroclaw repo): every agent turn spawns `claude -p`
headless, authed by CLAUDE_CODE_OAUTH_TOKEN — i.e. the Claude subscription, no
per-minute API TPM ceiling (the groq free tier 429'd multi-turn pipelines).
- Dockerfile: install the Claude Code CLI (@anthropic-ai/claude-code) into the
runtime image.
- agent.config.example.toml: role-cast on model_provider = "claude_cli.default".
NOTE: set the model via env (ZEROCLAW_providers__models__claude_cli__default__model)
not the TOML sub-table, else resolve_default_model() reads empty -> NEEDS_ONBOARDING.
- .gitignore: token.key (local Claude OAuth token, never committed).
Validated live on gw-04: a 2-node researcher->writer pipeline ran via the
deployed POST /api/topologies/run -> claude_cli -> real claude turns; 2-step
RunRecord, cost_usd 0.0 (subscription), no rate limiting.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
ZeroClaw pairing codes are single-use, so a static ZEROCLAW_PAIRING_CODE only
works for the first run. Add ZEROCLAW_TOKEN: pair once out-of-band, set the
durable bearer, and runs are repeatable. PAIRING_CODE stays as a fallback; one
of the two is required.
Validated live on gw-04: a single-node pipeline driven through the deployed
authed POST /api/topologies/run drove a real ZeroClaw role-agent over /ws/chat
and returned a RunRecord with real output + token metering, persisted to
topology_runs.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
cm-orchestrator owns the topology graph; each turn now drives a real ZeroClaw
role-agent in a container via the proven gateway drive recipe, instead of a
tool-free cm-llm call.
- crates/cm-api/src/topology_exec.rs: ZeroClawDriveExecutor impl TurnExecutor —
pair (POST /pair + X-Pairing-Code, token cached) -> ws /ws/chat?agent=<alias>
-> send {type:message,content} -> drain chunk/done/approval_request/error.
approval_request is recorded as a BLOCKED GatedAction, never auto-approved (§15).
Role->alias via ZEROCLAW_AGENT_MAP, fallback ZEROCLAW_DEFAULT_AGENT (scout).
- POST /api/topologies/run {task,graph} -> execute() -> RunRecord, persisted
best-effort to the existing topology_runs table (no migration). compare stays
tool-free. from_env() is read in-handler so cm-api still boots unset.
- deploy/clawmates-runtime: example config now declares a tool-free multi-agent
role-cast; README documents the ZEROCLAW_* knobs + run endpoint.
tokio-tungstenite 0.26 (already in lock) + dev axum `ws` for the hermetic test.
3 lib tests green, clippy clean, SQLX_OFFLINE build clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Save each comparison and let users reload past ones.
- migration 0008: topology_runs (workspace-scoped; full comparison as JSONB).
- cm-db repo::topology_runs (insert / list_recent / get) + regenerated .sqlx.
- cm-api: compare persists best-effort (never loses the LLM result on a DB
hiccup); GET /api/topology-runs (recent) + GET /api/topology-runs/{id}.
Integration test asserts persist → list → get.
- frontend: "Recent comparisons" list on the Compare tab; click to reload a
saved run. e2e p8 green (39 suite); offline build + clippy clean.
Server self-migrates at boot (cm_db::MIGRATOR), so 0008 applies on deploy.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Add a Compare tab to /topologies: pick a task + roles + topology kinds, build a
graph per kind, run POST /api/topologies/compare, and render a leaderboard table
+ a quality/cost Pareto scatter (SVG, no deps). Wrap Build + Compare in a tabbed
TopologyWorkbench. e2e p8 extended to run a comparison end-to-end (build×N →
compare → leaderboard + Pareto). Full suite 39 green; build + TS clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
New authed workspace page (/topologies, in the global nav) that browses the
topology catalog and builds + visualizes a topology from a kind + roles:
- lib/api/topology.ts: zod schemas + fetchTopologyCatalog (server, authed).
- TopologyGraphView: lightweight SVG renderer (no new deps), laid out per kind
(row for pipeline/ring, star for delegation kinds, circle otherwise).
- TopologyExplorer (client): catalog list + roles input → POST
/api/topologies/build via the /api proxy → render the graph.
- ShellNav: add the Topologies nav item.
- e2e (p8): sign in → nav → browse catalog → build a pipeline → graph renders.
Full suite green (38); npm build + TS clean. Goes live with the next server+
frontend deploy (compare/Pareto UI to follow).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Run a task across topologies via the API and return a leaderboard + quality/cost
Pareto front. The handler builds a ProviderExecutor + JudgeScorer over the
runtime's configured provider/model, then calls cm_orchestrator::compare.
- cm-runtime: expose provider()/model()/max_tokens() accessors on Runtime.
- cm-api: depend on cm-orchestrator (provider feature); add the compare route.
- Integration test runs a 2-topology comparison through the real server
(scripted provider) → 200 with results + leaderboard. 4 topology tests green;
offline build + clippy clean.
The topology endpoints (catalog/classify/build/compare) ship to gw-04 with the
upcoming ReactFlow UI in one server+frontend redeploy.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Stateless, auth-gated routes backing the topology builder UI:
- GET /api/topologies — catalog of the 12 kinds + descriptions + role mix
- POST /api/topologies/classify — infer a kind + metrics from a posted graph
- POST /api/topologies/build — build a canonical graph from {kind, roles}
Add Serialize to cm-topology Classification/GraphMetrics; add ApiError::BadRequest
(400) for invalid build input; add cm-topology dep. 3 integration tests
(catalog/build/auth) green against Postgres; offline build + clippy clean.
No DB or provider yet — running/comparing topologies is a later provider-backed
endpoint. Server redeploy will batch with the ReactFlow UI that consumes these.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
cm-topology::build(kind, roles) instantiates a canonical graph for any of the 12
kinds from a role list (the template catalog + the search generator).
cm-orchestrator::evolve searches a (kinds × team-size) grid using the comparison
machinery as fitness: build a candidate per cell, run the task, score it, and
keep a MAP-Elites-style archive of per-cell elites + a quality/cost Pareto front
and the global best. evolve_all() covers every kind at full size. This is the
bridge toward Autonomous Organizational Evolution on a safe substrate — every
candidate still executes via safe turns (§15 invariant holds).
Demoed in topology_bench (auto-picks the best topology + Pareto kinds).
cm-topology 20 tests; cm-orchestrator 17 (--features provider); clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Working draft consolidating the platform: thesis, related work (ADAS/Darwin-
Gödel/SwarmAgentic + Autonomous Organizational Evolution), the topology model +
classifier, the safe-execution result (authority is topology-invariant — the §15
contract holds across any topology because the orchestrator only sequences safe
turns), the comparison harness + Pareto + workflow-of-topologies, preliminary
offline results, limitations/future (real-model runs, evolution), and a
reproduction section. Empirical tables are offline/illustrative placeholders.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Milestone-A second capability: chain whole topology runs in sequence, threading
each stage's final output into the next stage's task (e.g. swarm brainstorm →
hierarchical execute → debate review). Each stage is a full safe topology run,
so §15 holds at every step. WorkflowRecord aggregates per-stage RunRecords +
totals. Demonstrated in the benchmark example. 14 tests; clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Every TopologyKind now runs, mapped to five execution patterns:
- hierarchical ← hub_spoke, star_moe, market
- pipeline ← ring
- swarm ← flat, holacratic
- mesh (new) ← blackboard (two peer-exchange rounds + aggregate)
- debate (new) (propose → critique → revise → judge)
execute()'s match is now exhaustive (adding a kind upstream forces an executor),
so the Unsupported error is gone. Benchmark spans all five distinct patterns.
14 tests with --features provider; clippy clean. Doc updated.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
`cargo run -p cm-orchestrator --example topology_bench --features provider`
runs one task across hierarchical/pipeline/swarm topologies and prints a
leaderboard + quality/cost Pareto front. Offline-deterministic via the scripted
provider; set ANTHROPIC_API_KEY to run against a real model. Demonstrates
milestone B end-to-end and seeds the reproducible paper harness.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Make Scorer async and add JudgeScorer (behind the `provider` feature): asks a
cm-llm model to rate a run's output 0-100 vs the task and normalizes to [0,1],
giving the comparison harness real quality numbers. Robust integer parsing
(handles "Score: 92/100", clamps >100); provider errors score 0.0.
11 tests with --features provider (judge incl. parse + scripted-provider score);
core stays 7. Clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
compare(graphs, task, executor, scorer) runs the same task across a set of
topologies on the same executor, scores each, and returns a Comparison:
- per-topology results (quality, tokens, turns, blocked approvals, output),
- a leaderboard (quality desc),
- a quality/cost Pareto front (on_pareto flags),
- best_quality and best_value (quality-per-token) picks.
This is the "which patterns yield better results" engine and the structured
output the paper's benchmark tables consume. Generic over TurnExecutor +
Scorer (pluggable LLM-judge later); pure core, no new deps. 9 tests, clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Add a real TurnExecutor (behind the `provider` feature) that runs each
topology turn as a single tool-free LLM call via any cm-llm provider
(Anthropic / OpenAI-compat / scripted). Topologies now execute real model
calls and produce real metrics (tokens), feeding the comparison harness.
- ProviderExecutor builds a per-role system prompt + threads upstream context
into the user message; collects TextDelta → output, Usage → tokens.
- Tool-free reasoning turns take no sandbox-leaving actions (gated = []); §15
remains satisfied. Tool-using turns will route through a cm-runtime adapter.
- Core crate stays dependency-light; cm-llm/futures are optional (feature).
- Tests: pipeline + hierarchical run over the deterministic scripted provider
(7 tests with --features provider). Clippy clean.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
A pure async control-flow engine that executes a task across a TopologyGraph
by sequencing safe agent turns. Safety by construction: the engine can only
invoke turns via a generic TurnExecutor — it performs no side effects itself,
so §15 gating (inside each turn) is inherited and switching topology cannot
escalate authority.
- TurnExecutor trait + TurnRequest/TurnOutcome (real impl will wrap
cm-runtime::Runtime; tests use a scripted Echo executor).
- Pure planners (plan.rs): hierarchical (delegate down / synthesize up),
pipeline (topo-ordered threading), swarm (parallel attempts + aggregate).
- RunRecord journal (per-step + RunMetrics: tokens, gated actions, approvals
granted/blocked, turns) — feeds the Phase 4 comparison harness/paper.
- Unsupported kinds return an error (no panic). 5 tests, clippy clean.
Next (Phase 2b): a real TurnExecutor adapter over cm-runtime::send_message.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Replace the floating rounded nav pill with an edge-to-edge sticky header:
solid bg, bottom border, square corners, content centered to max-w-[1392px].
Drop the hero's -mt-[98px] underlap so it sits below the solid bar. Refresh
the @visual baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Swap the clawmates-mark.png image in the nav (mobile + desktop) for a lucide
Waypoints icon in an ink chip beside the wordmark — reads as a network/mesh of
agents, matching the infrastructure theme. Refresh the @visual baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Page is now Hero → Hierarchy → Scale → Why → Use cases → FAQ → CTA → footer.
- Scale: per-tenant runtime / scale-to-zero / delegation hierarchy.
- WhyGoverned: humans-in-the-loop, single audit journal, delegation, no rogue access.
- UseCases: support / marketing / research / engineering / finance / data.
- FinalCta: dark ink band bookending the hero ("Build your agent company").
- Trim FAQ to 4 (keep the e2e-referenced Qs); repoint nav/footer anchors to
the live section ids. Refresh the @visual baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Completes 02cde39: remove the CrewStrip and Security functions, their consts,
and the now-unused AgentToken/lucide imports from Sections.tsx; render only
Hero → Hierarchy → FAQ in the marketing page; refresh the @visual baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Page is now Hero → Hierarchy → FAQ → footer. Delete the CrewStrip and
Security section functions + their consts (CREW, SECURITY), drop the now-
unused AgentToken component and the lucide imports. Refresh the @visual
baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Remove the Pitch, One-click, Works, Always-on and Skills sections and the
"Build your AI crew" footer CTA banner. Page is now Hero → CrewStrip →
Hierarchy → Security → FAQ → footer (dark tier kept). Prune the now-dead
section functions, consts, and imports (Image, skills icons). Repoint the
"marketing rendered" heading assertion (p0/p7/visual) from the removed
Pitch heading to the hero h1 (/agentic systems/); refresh the @visual baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Re-skins the playful/consumer feel into disciplined agent-infrastructure,
keeping the animated hero canvas (re-themed) and adding the hierarchy story.
- Palette: re-point coral→ember (#E0584A); add ink/surface/mist/slate-light/
azure/teal tokens. One accent per viewport; retire the black/coral split-
headline pattern across all 8 headings (single ink color).
- Typography: hero/section weights 800→~650-675, tighter tracking, smaller
hero size; uppercase eyebrow label.
- Hero: dark ink base with glowing azure/indigo + faint ember canvas blooms;
light copy; new positioning ("Build safe, scalable agentic systems" + the
single-agent-to-company subhead); ember primary CTA + ghost "Read the docs".
- Imagery overhaul (code-built, no mascots): AgentToken chips (CrewStrip,
OneClick card, footer), AlwaysOn rebuilt as a terminal/log with an approval
line, SkillsShowcase as duotone lucide cards on Mist, Security as a shield/
lock motif.
- New HierarchyDiagram section ("One agent, or a whole org chart"): SVG org
chart with an azure active path and teal human-approval checkpoints on
sandbox-leaving actions.
- Tests: dark-hero/terminal/eyebrow contrast fixed to AA; refreshed the
marketing @visual baseline (hero masked).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
- Headline → "Scale your Large World" (coral on "Large World").
- Subtext → "Building safe and scalable systems of claws for any domain of work."
- Drop the "Get started for free" hero button; keep "Book a demo".
- Remove the three hero trust pills (free credits / no card / self-hostable).
- Point the p7 hero CTA assertion at "Book a demo"; refresh the @visual baseline.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Port of crnacura/AmbientCanvasBackgrounds' shift effect: large circles drift
at random with hue driven by 3D simplex noise, drawn to an offscreen buffer
then blurred and composited onto the visible canvas. Re-tuned to a light brand
palette (pale periwinkle base; blue→violet→coral blooms) so the dark hero copy
stays readable. Self-contained (vendored simplex noise), scoped to the hero,
respects prefers-reduced-motion, and pauses when scrolled out of view / tab
hidden.
- Replace claws-at-desk.png with <HeroAmbient/>; add a soft fade into the
section below.
- Mask the animated hero region in the marketing @visual snapshot (keeps the
baseline deterministic) and refresh the baseline.
- Fix a latent AA contrast bug the old illustration was hiding: the CrewStrip
caption (#77879e on white, 3.65:1) → #647289 (4.87:1).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Sign-out only cleared the local cm_session cookie via DELETE /auth/session.
In Clerk mode the real session is Clerk's, so that left it intact and the
push to /login bounced the user straight back into the app (Clerk's <SignIn>
auto-redirects when a session exists). Detect clerk-js at runtime
(window.Clerk) and sign out through it; local/air-gapped builds have no
window.Clerk and keep the cookie flow (never loading the Clerk SDK).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
On a user's first login the authed shell fires several API calls at once;
each ran the JIT-provision path and raced to INSERT the same new user row,
tripping the partial unique index on auth_subject. The losing requests
500'd and the post-login SSR errored out. Use INSERT ... ON CONFLICT
(auth_subject) DO UPDATE ... RETURNING so concurrent callers converge on
the row the winner created. Regenerated the .sqlx offline query cache.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
The frontend is documented as a single image whose AUTH_MODE env var
selects local vs Clerk auth per deployment (docs/clerk.md). But the root
layout and /login read AUTH_MODE during render with no request-time
signal, so Next 16 statically prerendered them at build time in the
build host's mode (local). The deployed image then served the local
login form forever, ignoring AUTH_MODE=clerk at runtime — ClerkProvider
and <SignIn/> never appeared.
Add `await connection()` (the v16 way to read env at request time) in
the layout's IdentityProvider and in /login so both render per-request
and honor the runtime AUTH_MODE.
Also add a root .dockerignore: the repo had none, so every image build
shipped the 67GB Rust target/ dir as build context.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
Swapped the placeholder PawPrint icon for the new claw logo everywhere it
appears: the marketing nav (mobile + desktop), the footer, the login card,
and the app left rail. The supplied PNG was a red claw on a solid near-black
background, so I flood-filled the background to transparent (the dark-red
outline survives the black threshold) and exported a trimmed, optimized
public/images/clawmates-mark.png (321x256, 88KB from 1.7MB). It reads cleanly
on both light (nav/login) and dark (footer/rail) surfaces.
Also regenerated the favicon + PWA icons from the new mark:
- src/app/icon.png (Next uses it as the favicon; removed the old favicon.ico)
- public/icons/icon-192.png and icon-512.png (claw on #0a0a0a, maskable)
Roster-card avatars on the login panel stay as PawPrint (decorative, not the
brand). Regenerated all seven @visual baselines that contain the mark — the
swap is sub-threshold for maxDiffPixelRatio, so I deleted and recaptured them
rather than relying on update-snapshots.
typecheck/lint/build green · all @visual green · deployed and verified live
(mark, /icon.png, and PWA icons all 200).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
The live /sign-in is a Clerk-rendered SignInForm (SSR is just a spinner); the
rendered design is the email-first progressive form. Reworked our /login to
match it visually while keeping our real email+password auth underneath.
- Email step: "Sign up with Slack" (cosmetic), OR, Work Email / Phone Number
tabs, work-email field, "Continue with work email →", "Other SSO Options".
Slack / Phone / SSO are cosmetic placeholders we don't support yet.
- Password step: "Continue" reveals the password field + "Sign in" (our actual
POST to /auth/session). A Back link returns to the email step.
- Headline now mirrors WorkClaw ("Multiply your team's brainpower" / "Sign up
to get early access").
- Right panel is now the role-card roster grid (PawPrint avatars, our own
roles) + "The AI crew for your team" + the claws-at-desk art.
- Updated all eight E2E signIn helpers (and the load assertions) for the new
two-step flow: fill Email → Continue → fill Password → Sign in. Labels
(Email/Password) and the "Sign in" button name are preserved.
- A11y: bumped the inactive tab text to full slate (was 3.41:1).
typecheck/lint/build green · p0-shell (full sign-in) green · p6-a11y (login
clean) green · all six @visual baselines green (login regenerated) · deployed
and verified live.
Co-Authored-By: Claude Opus 4.8 <[email protected]>
