clawdie/colibri
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 30

style: restore main green — fmt + prettier drift (Sam & Claude)

Browse source
This commit is contained in:
Sam & Claude 2026-06-27 17:19:57 +02:00
parent c05ca3a7b7
commit 8a80ff8da5
9 changed files with 130 additions and 114 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
crates/colibri-daemon/src/daemon.rs
View file

@ -354,8 +354,10 @@ fn push_cost_to_mother(task_id: &str, tc: &colibri_store::TaskCost) {
let payload_line = serde_json::to_string(&payload).unwrap_or_default();
let mut child = match std::process::Command::new("ssh")
.args([
"-o", "BatchMode=yes",
"-o", "ConnectTimeout=5",
"-o",
"BatchMode=yes",
"-o",
"ConnectTimeout=5",
&mother_host,
"report-task-cost",
])

57
docs/wiki/a2a-complexity-audit.md
View file

@ -8,13 +8,13 @@
Colibri speaks 5 protocols today:
| Protocol | Where | Lines | Purpose |
|---|---|---|---|
| **Custom JSON wire** | `crates/colibri-daemon/src/socket.rs` + `crates/colibri-client/src/lib.rs` | 1,981 | Local daemon control (spawn, status, snapshot, tasks, skills) |
| **MCP JSON-RPC** | `crates/colibri-mcp/src/lib.rs` | 570 | Editor integration + external MCP host |
| **MCP-over-SSH** | `packaging/mother/` (3 files) | 437 | Mother hive entrypoint (forced-command allowlist + node register) |
| **JSONL** | `crates/colibri-glasspane/src/lib.rs` | 1,186 | Agent subprocess stdout events |
| **SQL** | `crates/colibri-store/src/lib.rs` + `crates/colibri-store/src/schema.rs` | 1,150 | Local coordination (tasks, agents, skills, tenants) |
| Protocol | Where | Lines | Purpose |
| -------------------- | -------------------------------------------------------------------------- | ----- | ----------------------------------------------------------------- |
| **Custom JSON wire** | `crates/colibri-daemon/src/socket.rs` + `crates/colibri-client/src/lib.rs` | 1,981 | Local daemon control (spawn, status, snapshot, tasks, skills) |
| **MCP JSON-RPC** | `crates/colibri-mcp/src/lib.rs` | 570 | Editor integration + external MCP host |
| **MCP-over-SSH** | `packaging/mother/` (3 files) | 437 | Mother hive entrypoint (forced-command allowlist + node register) |
| **JSONL** | `crates/colibri-glasspane/src/lib.rs` | 1,186 | Agent subprocess stdout events |
| **SQL** | `crates/colibri-store/src/lib.rs` + `crates/colibri-store/src/schema.rs` | 1,150 | Local coordination (tasks, agents, skills, tenants) |
**Total protocol surface: ~5,324 lines.**
@ -40,6 +40,7 @@ USB node → HTTPS → mother A2A endpoint → PostgreSQL
```
**Removed:**
- `colibri-mcp-ssh` (32 lines) — SSH forced-command allowlist wrapper
- `node-register-mcp` (88 lines) — Custom MCP tool with embedded psql
- SSH key management in `setup-mother.sh` (~40 lines of key distribution logic)
@ -47,6 +48,7 @@ USB node → HTTPS → mother A2A endpoint → PostgreSQL
**Removed total: ~160 lines.**
**Added:**
- A2A HTTP endpoint on mother (~200 lines)
- A2A client library integration on USB node (~150 lines)
- mTLS/TLS termination for auth (~30 lines)
@ -54,6 +56,7 @@ USB node → HTTPS → mother A2A endpoint → PostgreSQL
**Added total: ~380 lines.**
**Net delta: +220 lines.** Not a code reduction. But operational complexity drops significantly:
- No SSH key distribution to USB nodes (key lives on seed partition → no longer needed on mother)
- No forced-command allowlist to maintain
- Standard HTTPS is easier to firewall, audit, and monitor than SSH forced-command
@ -78,7 +81,7 @@ Today: external MCP registry config — manual JSON listing third-party MCP serv
With A2A: third-party tools that speak A2A (not MCP) publish an Agent Card. Colibri discovers them via the well-known Agent Card URL instead of manual JSON config files.
**Reality check:** No third-party tools speak A2A yet. The protocol was just announced (April 2025). MCP has ~2 years of ecosystem maturity. This is a *future* replacement, not a *current* one.
**Reality check:** No third-party tools speak A2A yet. The protocol was just announced (April 2025). MCP has ~2 years of ecosystem maturity. This is a _future_ replacement, not a _current_ one.
**Verdict:** A2A discovery doesn't reduce code today. External MCP stays for tool access.
@ -94,20 +97,20 @@ With A2A: cost data is a typed message part (`application/json+cost`). The forma
**Code savings:** ~10 lines (the info! log stays; the A2A part is new code).
**Verdict:** Negligible code impact. The value is *interop*, not complexity reduction.
**Verdict:** Negligible code impact. The value is _interop_, not complexity reduction.
---
## What A2A does NOT replace
| Component | Why A2A doesn't touch it | Lines saved |
|---|---|---|
| **Unix socket wire protocol** (`crates/colibri-daemon/src/socket.rs`) | A2A is cross-node HTTP. Local daemon control needs IPC — Unix socket is faster, auth-free (filesystem permissions), and doesn't need a network stack. | 0 |
| **Spawner** (`crates/colibri-daemon/src/spawner.rs`) | A2A routes tasks to existing agents. Colibri *creates* agents by spawning subprocesses. A2A has no process lifecycle concept. | 0 |
| **Glasspane** (`crates/colibri-glasspane/src/lib.rs`) | A2A doesn't watch subprocess stdout. Glasspane is a PTY observer — it reads JSONL from child processes. A2A operates one layer above. | 0 |
| **Store** (`crates/colibri-store/src/lib.rs`) | A2A doesn't replace local SQLite coordination. Each node needs local persistence for task board, agents, skills — A2A is the *transport*, not the *database*. | 0 |
| **MCP editor bridge** | A2A is agent-to-agent. MCP is human-to-tool. Different protocols for different directions. They coexist. | 0 |
| **Contracts schemas** (`crates/colibri-contracts/src/lib.rs`) | A2A uses JSON Schema for input validation. Colibri's contracts are already compatible — no change needed. | 0 |
| Component | Why A2A doesn't touch it | Lines saved |
| --------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
| **Unix socket wire protocol** (`crates/colibri-daemon/src/socket.rs`) | A2A is cross-node HTTP. Local daemon control needs IPC — Unix socket is faster, auth-free (filesystem permissions), and doesn't need a network stack. | 0 |
| **Spawner** (`crates/colibri-daemon/src/spawner.rs`) | A2A routes tasks to existing agents. Colibri _creates_ agents by spawning subprocesses. A2A has no process lifecycle concept. | 0 |
| **Glasspane** (`crates/colibri-glasspane/src/lib.rs`) | A2A doesn't watch subprocess stdout. Glasspane is a PTY observer — it reads JSONL from child processes. A2A operates one layer above. | 0 |
| **Store** (`crates/colibri-store/src/lib.rs`) | A2A doesn't replace local SQLite coordination. Each node needs local persistence for task board, agents, skills — A2A is the _transport_, not the _database_. | 0 |
| **MCP editor bridge** | A2A is agent-to-agent. MCP is human-to-tool. Different protocols for different directions. They coexist. | 0 |
| **Contracts schemas** (`crates/colibri-contracts/src/lib.rs`) | A2A uses JSON Schema for input validation. Colibri's contracts are already compatible — no change needed. | 0 |
**Total irreplaceable: ~5,000 lines.** A2A doesn't reduce this at all.
@ -138,16 +141,16 @@ TOTAL 5,524 5,467
A2A is not a complexity reduction play. It's an **interoperability and operational simplicity** play:
| Metric | MCP-over-SSH (current) | A2A (proposed) |
|---|---|---|
| **Lines of code** | ~5,524 (spread across 6 crates + 3 shell scripts) | ~5,467 (SSH scripts gone, A2A handler added) |
| **Protocol count** | 5 | 6 (A2A adds one) |
| **Operational complexity** | SSH keys × N nodes, forced-command allowlists, peer auth setup | One HTTPS endpoint, mTLS certs, well-known URL |
| **Discoverability** | Manual external MCP registry entries | Agent Card at well-known URL |
| **Interoperability** | Colibri-only | Any A2A client |
| **Debugability** | `ssh -v`, `psql`, `jq` | `curl`, browser devtools, standard HTTP tooling |
| **Ecosystem maturity** | N/A (Colibri-specific) | Protocol < 3 months old, zero adoption |
| **When it pays off** | Works today for 4 nodes | Pays off at 10+ nodes, or when 3rd-party tools ship A2A |
| Metric | MCP-over-SSH (current) | A2A (proposed) |
| -------------------------- | -------------------------------------------------------------- | ------------------------------------------------------- |
| **Lines of code** | ~5,524 (spread across 6 crates + 3 shell scripts) | ~5,467 (SSH scripts gone, A2A handler added) |
| **Protocol count** | 5 | 6 (A2A adds one) |
| **Operational complexity** | SSH keys × N nodes, forced-command allowlists, peer auth setup | One HTTPS endpoint, mTLS certs, well-known URL |
| **Discoverability** | Manual external MCP registry entries | Agent Card at well-known URL |
| **Interoperability** | Colibri-only | Any A2A client |
| **Debugability** | `ssh -v`, `psql`, `jq` | `curl`, browser devtools, standard HTTP tooling |
| **Ecosystem maturity** | N/A (Colibri-specific) | Protocol < 3 months old, zero adoption |
| **When it pays off** | Works today for 4 nodes | Pays off at 10+ nodes, or when 3rd-party tools ship A2A |
---

28
docs/wiki/hive-pane.md
View file

@ -161,13 +161,13 @@ as the wiki.
A2A tasks map directly to Colibri's task board:
| A2A state | Colibri equivalent |
| -------------- | ------------------ |
| `submitted` | `Pending` |
| `working` | `Started` |
| `completed` | `Done` |
| `failed` | `Error` |
| `canceled` | (not yet modeled) |
| A2A state | Colibri equivalent |
| ----------- | ------------------ |
| `submitted` | `Pending` |
| `working` | `Started` |
| `completed` | `Done` |
| `failed` | `Error` |
| `canceled` | (not yet modeled) |
Mother pushes a `node_register` task to a new USB node; the node executes it and
returns the result. The task carries cost data as a typed A2A part:
@ -187,13 +187,13 @@ returns the result. The task carries cost data as a typed A2A part:
### What A2A adds over the current MCP bridge
| Concern | Current (MCP + SSH) | A2A |
| -------------------- | ----------------------------- | -------------------------------- |
| Discovery | Manual external MCP registry entry | Well-known Agent Card URL |
| Interop | Colibri-only | Any A2A client |
| Cost data | Embedded in task completion | Typed `application/json+cost` |
| Push notifications | Polling (heartbeat) | Optional webhook/push |
| Versioning | Ad-hoc | Agent Card version + schema pins |
| Concern | Current (MCP + SSH) | A2A |
| ------------------ | ---------------------------------- | -------------------------------- |
| Discovery | Manual external MCP registry entry | Well-known Agent Card URL |
| Interop | Colibri-only | Any A2A client |
| Cost data | Embedded in task completion | Typed `application/json+cost` |
| Push notifications | Polling (heartbeat) | Optional webhook/push |
| Versioning | Ad-hoc | Agent Card version + schema pins |
A2A is not a replacement for the MCP bridge — it's the next layer. The MCP
bridge handles local daemon commands (status, snapshot, spawn). A2A handles

125
docs/wiki/hive-routing.md
View file

@ -10,15 +10,15 @@
## What Exists Today
| Component | State | Gap |
|---|---|---|
| `mother_schema.sql` | `hive_nodes` table with `hw_profile` + `capabilities` JSONB | No stable node UUID; hostname is the key |
| `derive_capabilities()` trigger | Auto-computes `has_gpu`, `gpu_vendor`, `can_run_local_llm`, `max_model` from hw_profile | Only GPU/VRAM heuristics — doesn't probe running services |
| `clawdie-hw-probe` | Collects GPU, RAM, CPU, disks, ZFS, WiFi, Vulkan, Colibri status | No ollama/llama.cpp probing |
| `node-register-mcp` | UPSERTs hw_profile into `hive_nodes` on join | No UUID generation at join time |
| `crates/colibri-daemon/src/scheduler.rs` | Cron/interval/one-shot jobs, capability matching stubs | No cost-aware routing, no hive awareness |
| `colibri-store` | Local SQLite `agents` table with UUID (v4 random) | UUID is session-local, not hive-stable |
| T1.5 cost tracking | Per-task cost captured in local SQLite | No hive-level cost aggregation |
| Component | State | Gap |
| ---------------------------------------- | --------------------------------------------------------------------------------------- | --------------------------------------------------------- |
| `mother_schema.sql` | `hive_nodes` table with `hw_profile` + `capabilities` JSONB | No stable node UUID; hostname is the key |
| `derive_capabilities()` trigger | Auto-computes `has_gpu`, `gpu_vendor`, `can_run_local_llm`, `max_model` from hw_profile | Only GPU/VRAM heuristics — doesn't probe running services |
| `clawdie-hw-probe` | Collects GPU, RAM, CPU, disks, ZFS, WiFi, Vulkan, Colibri status | No ollama/llama.cpp probing |
| `node-register-mcp` | UPSERTs hw_profile into `hive_nodes` on join | No UUID generation at join time |
| `crates/colibri-daemon/src/scheduler.rs` | Cron/interval/one-shot jobs, capability matching stubs | No cost-aware routing, no hive awareness |
| `colibri-store` | Local SQLite `agents` table with UUID (v4 random) | UUID is session-local, not hive-stable |
| T1.5 cost tracking | Per-task cost captured in local SQLite | No hive-level cost aggregation |
## Design Goals
@ -81,17 +81,19 @@ A 32-character hex UUID generated once, stored locally, included in every hw-pro
```
**Properties:**
- **Stable across reboots**: stored on disk, not tmpfs
- **Survives re-provisioning**: if the seed partition preserves `/var/db/machine-id`, the same physical machine keeps the same identity
- **Not a secret**: it's an ID, not a key
- **Verifiable**: mother can check "has node a1b2c3d4 ever joined?" — if yes, this is a rejoin, not a new node
**Alternatives considered:**
| Approach | Pros | Cons |
|---|---|---|
| SMBIOS UUID (`hw.uuid`) | Truly hardware-bound, survives OS reinstall | Not available on all platforms (VPS, ARM); can be spoofed |
| SSH host key fingerprint | Cryptographically strong | Changes on OS reinstall; key rotation breaks identity |
| Random UUID (this design) | Portable, simple, survives seed restore | Can be copied/cloned (but same machine, same ID — that's correct) |
| Approach | Pros | Cons |
| ------------------------- | ------------------------------------------- | ----------------------------------------------------------------- |
| SMBIOS UUID (`hw.uuid`) | Truly hardware-bound, survives OS reinstall | Not available on all platforms (VPS, ARM); can be spoofed |
| SSH host key fingerprint | Cryptographically strong | Changes on OS reinstall; key rotation breaks identity |
| Random UUID (this design) | Portable, simple, survives seed restore | Can be copied/cloned (but same machine, same ID — that's correct) |
**Recommendation:** Generate on first boot, store in `/var/db/machine-id`. The hw-probe includes it as `machine_id`. Mother's `hive_nodes` table gets a `UNIQUE` constraint on `machine_id`.
@ -112,18 +114,18 @@ The `node-register-mcp` UPSERT switches from `ON CONFLICT (hostname)` to `ON CON
Every capability is a boolean derived from hardware facts, not a self-declaration. The hw-probe collects hardware; the trigger derives capabilities.
| Capability | Derived from | Used for |
|---|---|---|
| `has_gpu` | GPU detected in pciconf | GPU-accelerated inference |
| `gpu_vendor` | amdgpu/nvidia driver | Model compatibility |
| `vulkan_compute` | vulkaninfo success | llama.cpp Vulkan backend |
| `can_run_local_llm` | RAM ≥ 16GB or has GPU | Eligibility for local task execution |
| `max_model` | RAM heuristic | Model size limit (3b, 7b-q4, 13b-q4, 34b-q4) |
| `cpu_only` | No GPU detected | Fallback only (slow) |
| `has_wifi` | wlan devices | Network capability |
| `has_zfs` | ZFS pools non-empty | Storage capability |
| `colibri_running` | service status | Agent host eligibility |
| `provider_api_keys` | MCP-reported (not hw probe) | Cloud provider availability |
| Capability | Derived from | Used for |
| ------------------- | --------------------------- | -------------------------------------------- |
| `has_gpu` | GPU detected in pciconf | GPU-accelerated inference |
| `gpu_vendor` | amdgpu/nvidia driver | Model compatibility |
| `vulkan_compute` | vulkaninfo success | llama.cpp Vulkan backend |
| `can_run_local_llm` | RAM ≥ 16GB or has GPU | Eligibility for local task execution |
| `max_model` | RAM heuristic | Model size limit (3b, 7b-q4, 13b-q4, 34b-q4) |
| `cpu_only` | No GPU detected | Fallback only (slow) |
| `has_wifi` | wlan devices | Network capability |
| `has_zfs` | ZFS pools non-empty | Storage capability |
| `colibri_running` | service status | Agent host eligibility |
| `provider_api_keys` | MCP-reported (not hw probe) | Cloud provider availability |
### Local LLM capabilities (NEW)
@ -143,14 +145,14 @@ Extend the hw-probe to detect running local LLM services and extend the trigger
**New derived capabilities:**
| Capability | Derivation |
|---|---|
| `ollama_available` | `ollama_running == true` |
| `ollama_models` | Array of model tags (from `ollama list`) |
| `llama_cpp_available` | Binary at `/usr/local/bin/llama-server` or similar |
| `llama_cpp_models` | GGUFs in `/var/db/models/` or `/usr/local/share/models/` |
| `can_embed_locally` | `nomic-embed-text` in ollama OR any embedding model loaded |
| `inference_tier` | `local-fast` (GPU ≥ 24GB), `local-slow` (CPU-only, RAM ≥ 16GB), `cloud-only` |
| Capability | Derivation |
| --------------------- | ---------------------------------------------------------------------------- |
| `ollama_available` | `ollama_running == true` |
| `ollama_models` | Array of model tags (from `ollama list`) |
| `llama_cpp_available` | Binary at `/usr/local/bin/llama-server` or similar |
| `llama_cpp_models` | GGUFs in `/var/db/models/` or `/usr/local/share/models/` |
| `can_embed_locally` | `nomic-embed-text` in ollama OR any embedding model loaded |
| `inference_tier` | `local-fast` (GPU ≥ 24GB), `local-slow` (CPU-only, RAM ≥ 16GB), `cloud-only` |
### Probe additions to `clawdie-hw-probe`
@ -181,12 +183,12 @@ cache_weight: 0.0–1.0 (warm cache → higher weight)
### Cost tiers
| Tier | Provider | Cost per 1M tokens | Latency | Used when |
|---|---|---|---|
| T0 (free) | Local ollama/llama.cpp | $0.00 | 5–60s | Non-urgent, capability match |
| T1 (cheap) | DeepSeek V3 | $0.27 / $1.10 | 2–5s | Default for most tasks |
| T2 (balanced) | Gemini Flash | $0.15 / $0.60 | 1–3s | High cache-hit tasks |
| T3 (premium) | Claude Sonnet 4 | $3.00 / $15.00 | 3–8s | Complex reasoning, only when needed |
| Tier | Provider | Cost per 1M tokens | Latency | Used when |
| ------------- | ---------------------- | ------------------ | ------- | ----------------------------------- |
| T0 (free) | Local ollama/llama.cpp | $0.00 | 5–60s | Non-urgent, capability match |
| T1 (cheap) | DeepSeek V3 | $0.27 / $1.10 | 2–5s | Default for most tasks |
| T2 (balanced) | Gemini Flash | $0.15 / $0.60 | 1–3s | High cache-hit tasks |
| T3 (premium) | Claude Sonnet 4 | $3.00 / $15.00 | 3–8s | Complex reasoning, only when needed |
### Local LLM routing rules
@ -257,6 +259,7 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
**What:** Mother is the brain. Nodes register, mother routes. No peer-to-peer.
**Implementation:**
1. Add `machine_id` to `hive_nodes` + hw-probe (1 day)
2. Extend `derive_capabilities()` for local LLM (1 day)
3. Add `routing_score()` function to mother's PostgreSQL (stored function — zero Rust changes)
@ -268,12 +271,14 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
**Total:** ~3.5 days.
**Pros:**
- Simple to reason about — one source of truth
- Lowest implementation risk
- Scheduler lives on mother (always-on)
- Existing MCP bridge handles all communication
**Cons:**
- Mother is single point of failure for routing (but not execution — once dispatched, the task runs independently)
- Latency: scheduler must query mother on every tick
- Doesn't scale to 100+ nodes (not a real concern for our use case)
@ -285,6 +290,7 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
**What:** Mother stores the matrix, but nodes can also route tasks they own to peers directly. Hybrid: central registry + distributed execution.
**Implementation:**
1. All of Option A (3.5 days)
2. Add `capabilities` API to `colibri-daemon`'s Unix socket (self-awareness) — 1 day
3. Add local peer discovery via mDNS or Tailscale whois — 1 day
@ -294,12 +300,14 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
**Total:** ~8.5 days.
**Pros:**
- Lower latency for local dispatch
- Survives mother downtime for peer-to-peer tasks
- Natural fit for local LLM use case (beefy node is on same LAN)
- Nodes that discover each other can route without phoning home
**Cons:**
- Complexity: two code paths (central + peer-to-peer)
- Security: peer-to-peer dispatch needs authentication (who can send tasks to my daemon?)
- Harder to audit: cost tracking must handle peer-dispatched vs mother-dispatched tasks differently
@ -312,6 +320,7 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
**What:** Don't build a routing engine at all. The capability matrix is exposed as an MCP tool that agents query. The agent itself decides where to route based on the matrix + its own reasoning. The matrix is advisory, not prescriptive.
**Implementation:**
1. All of Option A minus the routing_scoring function (2.5 days)
2. Add `colibri_query_hive_capabilities` MCP tool on mother — returns full online node matrix (0.5 day)
3. Add `colibri_dispatch_to_node` MCP tool — sends task to a specific node (1 day)
@ -320,6 +329,7 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
**Total:** ~4.5 days. **Zero scheduler changes.**
**Pros:**
- Exploits Colibri's architecture-as-differentiator: the agent IS the intelligence
- The routing decision is auditable in the conversation log (why did the agent pick this node?)
- Natural fit for local LLM — the agent can reason "this task is low priority, I'll try the beefy node first"
@ -327,6 +337,7 @@ When the task completes, the local daemon writes cost to its SQLite (T1.5). The
- The skill can be iterated without recompiling Colibri
**Cons:**
- Each routing decision costs tokens (the agent must reason about it)
- Agents make inscrutable routing choices (the LLM "just knows")
- No hard guarantees — an agent might route a $5 task to Claude when DeepSeek would do fine
@ -350,26 +361,26 @@ The capability matrix, stable UUIDs, and local LLM probes are the foundation —
### Phase 1 — Identity & Capability Foundation
| Deliverable | Where | Lines |
|---|---|---|
| `machine_id` generation in `clawdie-firstboot` | clawdie-iso | ~15 |
| `collect_machine_id()` in hw-probe | clawdie-iso | ~10 |
| `collect_ollama_status()` in hw-probe | clawdie-iso | ~30 |
| `collect_llama_cpp()` in hw-probe | clawdie-iso | ~20 |
| `collect_local_llm()` aggregator in hw-probe | clawdie-iso | ~25 |
| `machine_id` column + constraint in mother_schema.sql | colibri | ~5 |
| Extended `derive_capabilities()` for `ollama_available`, `llama_cpp_available`, `inference_tier` | colibri | ~40 |
| `node-register-mcp` handling of `machine_id` key + new local_llm fields | colibri | ~15 |
| This design doc (hive-routing.md) | This file | ~0 (done) |
| Deliverable | Where | Lines |
| ------------------------------------------------------------------------------------------------ | ----------- | --------- |
| `machine_id` generation in `clawdie-firstboot` | clawdie-iso | ~15 |
| `collect_machine_id()` in hw-probe | clawdie-iso | ~10 |
| `collect_ollama_status()` in hw-probe | clawdie-iso | ~30 |
| `collect_llama_cpp()` in hw-probe | clawdie-iso | ~20 |
| `collect_local_llm()` aggregator in hw-probe | clawdie-iso | ~25 |
| `machine_id` column + constraint in mother_schema.sql | colibri | ~5 |
| Extended `derive_capabilities()` for `ollama_available`, `llama_cpp_available`, `inference_tier` | colibri | ~40 |
| `node-register-mcp` handling of `machine_id` key + new local_llm fields | colibri | ~15 |
| This design doc (hive-routing.md) | This file | ~0 (done) |
### Phase 2 — Routing Engine
| Deliverable | Where |
|---|---|
| `colibri_query_hive_capabilities` MCP tool | colibri-mcp |
| `colibri_dispatch_to_node` MCP tool | colibri-mcp |
| `hive-routing` skill | `.agent/skills/` |
| `Task.routing` JSONB field in colibri-store | colibri-store |
| Deliverable | Where |
| -------------------------------------------------------------------------------------------------------------- | ----------------- |
| `colibri_query_hive_capabilities` MCP tool | colibri-mcp |
| `colibri_dispatch_to_node` MCP tool | colibri-mcp |
| `hive-routing` skill | `.agent/skills/` |
| `Task.routing` JSONB field in colibri-store | colibri-store |
| Mother-side routing score as PostgreSQL function (optional — only if agent-driven routing proves insufficient) | mother_schema.sql |
---

8
docs/wiki/index.md
View file

@ -53,21 +53,21 @@ warning.
| [headroom-sidecar](./headroom-sidecar.md) | Optional tool-result compression sidecar and its Unix-socket protocol |
| [jail-confinement](./jail-confinement.md) | Persistent vs ephemeral jails, priv-mode policy, reuse of spawner confinement for MCP servers |
| [mother-hive](./mother-hive.md) | Mother MCP architecture — forced-command SSH, single-home-in-colibri, peer auth, key-on-seed |
| [hive-routing](./hive-routing.md) | Hive member identity (machine UUID), capability matrix + local LLM probes, cost-aware task routing |
| [hive-routing](./hive-routing.md) | Hive member identity (machine UUID), capability matrix + local LLM probes, cost-aware task routing |
| [hive-pane](./hive-pane.md) | Glasspane for the hive — multi-node cost observability, A2A discovery, and operator board |
| [a2a-complexity-audit](./a2a-complexity-audit.md) | A2A code complexity impact — 6-protocol surface audit, when A2A pays off |
| [a2a-complexity-audit](./a2a-complexity-audit.md) | A2A code complexity impact — 6-protocol surface audit, when A2A pays off |
| [naming-decisions](./naming-decisions.md) | Ledger of harness-neutral / architecture renames — shipped and in-flight |
| [daemon-not-demon](./daemon-not-demon.md) | Why we say daemon (helper spirit) not demon (bad spirit) — English + Slovenian |
| [layered-soul](./layered-soul.md) | How Colibri consumes the layered-soul reviewed-context repo today vs planned |
| [task-board](./task-board.md) | Capability match scoring, cron scheduling, intake drain, SQLite backing |
| [quality-gates](./quality-gates.md) | `ci-checks.sh` as the pre-merge gate; why drift reached `main` before |
| [contracts](./contracts.md) | Stable JSON schemas (run-manifest, runtime-inventory, provider-test), golden tests |
| [contracts](./contracts.md) | Stable JSON schemas (run-manifest, runtime-inventory, provider-test), golden tests |
| [store-schema](./store-schema.md) | SQLite coordination schema and migration discipline |
| [external-mcp](./external-mcp.md) | MCP bridge for editors + external stdio MCP host; read/write/external-call gates |
| [operator-cli](./operator-cli.md) | The `colibri` CLI as a thin typed Unix-socket client over the daemon API |
| [tui](./tui.md) | Terminal dashboard client (colibri-tui) vs the colibri-glasspane state machine |
| [terminal](./terminal.md) | Terminal capability decision (Kitty, extended-key reporting, tmux passthrough, SSH terminfo) |
| [runtime-inventory](./runtime-inventory.md) | Host runtime inventory + watchdog status reader; additive, read-only integrations |
| [skills-catalog](./skills-catalog.md) | Read-only runtime consumer for reviewed skill artifacts |
| [skills-catalog](./skills-catalog.md) | Read-only runtime consumer for reviewed skill artifacts |
| [vault-provision](./vault-provision.md) | Vaultwarden-driven env-file provisioning into jails after agent spawn |
| [deployment](./deployment.md) | Host installer (clawdie): ZFS layout, rc.d/systemd service, dry-run safety |

2
docs/wiki/sl/contracts.md
View file

@ -23,7 +23,7 @@ _sheme in (De)serialize_, ne poslovne logike.
| -------------------------------------- | --------------------- | ------------------------------------------------------------------------- |
| `clawdie.interagent.run-manifest.v1` | `RunManifest` | Beleži tek gradnje/testa — vloga, agent, artefakti, povzetek. |
| `clawdie.runtime-version-inventory.v1` | `RuntimeInventory` | Posnetek izvajalnega okolja gostitelja — OS, različice paketov, npm/node. |
| `clawdie.provider-test.result.v1` | `ProviderSmokeResult` | Rezultat sonde predpomnilnika DeepSeek in obračun žetonov. |
| `clawdie.provider-test.result.v1` | `ProviderSmokeResult` | Rezultat sonde predpomnilnika DeepSeek in obračun žetonov. |
Konstante shem in strukture živijo v `crates/colibri-contracts/src/lib.rs`.

6
docs/wiki/sl/index.md
View file

@ -59,19 +59,19 @@ clippy.
| [headroom-sidecar](./headroom-sidecar.md) | Neobvezni stranski vagon za stiskanje rezultatov orodij in njegov protokol Unix vtičnice |
| [jail-confinement](./jail-confinement.md) | Trajne proti prehodnim ječam, pravilnik načina priv, ponovna uporaba omejitve zaganjalnika za strežnike MCP |
| [mother-hive](./mother-hive.md) | Arhitektura matičnega MCP — SSH s prisiljenim ukazom, enojni-dom-v-colibri, peer avtentikacija, ključ-na-semenu |
| [hive-pane](./hive-pane.md) | Steklena plošča za panj — opazovanje stroškov več vozlišč, odkrivanje A2A in operaterska nadzorna plošča |
| [hive-pane](./hive-pane.md) | Steklena plošča za panj — opazovanje stroškov več vozlišč, odkrivanje A2A in operaterska nadzorna plošča |
| [naming-decisions](./naming-decisions.md) | Imenik preimenovanj, nevtralnih glede na opremo / arhitekturnih — dostavljenih in v teku |
| [daemon-not-demon](./daemon-not-demon.md) | Zakaj rečemo daemon (duh pomočnik) in ne demon (hudič) — angleško + slovensko |
| [layered-soul](./layered-soul.md) | Kako Colibri danes uporablja repozitorij pregledanega konteksta layered-soul proti načrtovanemu |
| [task-board](./task-board.md) | Točkovanje po zmožnostih, cron razporejanje, praznjenje vnosne vrste, podlaga SQLite |
| [quality-gates](./quality-gates.md) | `ci-checks.sh` kot preverjanje pred združitvijo; zakaj je odmik prej dosegel `main` |
| [contracts](./contracts.md) | Stabilne JSON sheme (run-manifest, runtime-inventory, provider-test), zlati testi |
| [contracts](./contracts.md) | Stabilne JSON sheme (run-manifest, runtime-inventory, provider-test), zlati testi |
| [store-schema](./store-schema.md) | Usklajevalna shema SQLite in disciplina migracij |
| [external-mcp](./external-mcp.md) | Most MCP za urejevalnike + zunanji gostitelj stdio MCP; dovoljenja za branje/pisanje/zunanji-klic |
| [operator-cli](./operator-cli.md) | CLI `colibri` kot tanek tipiziran odjemalec Unix vtičnice prek API procesa v ozadju |
| [tui](./tui.md) | Odjemalec terminalske nadzorne plošče (colibri-tui) proti avtomatu stanj colibri-glasspane |
| [terminal](./terminal.md) | Odločitev o terminalski zmožnosti (Kitty, razširjeno poročanje tipk, prehod tmux, SSH terminfo) |
| [runtime-inventory](./runtime-inventory.md) | Popis izvajalnega okolja gostitelja + bralnik statusa čuvaja; aditivne, bralne integracije |
| [skills-catalog](./skills-catalog.md) | Bralni izvajalni porabnik za pregledane artefakte veščin |
| [skills-catalog](./skills-catalog.md) | Bralni izvajalni porabnik za pregledane artefakte veščin |
| [vault-provision](./vault-provision.md) | Oskrba datotek env, gnana z Vaultwarden, v ječe po zagonu agenta |
| [deployment](./deployment.md) | Nameščevalnik gostitelja (clawdie): postavitev ZFS, storitev rc.d/systemd, varnost suhega teka |

10
docs/wiki/tui.md
View file

@ -81,7 +81,7 @@ should be revisited.
| `s` | Spawn a local `colibri-test-agent` |
| `x` | Stop the selected pane |
| `Enter` | Open/close the detail pane for the selected row |
| `Tab` / `Shift+Tab` | Cycle through distinct sessions (incl. "All") |
| `Tab` / `Shift+Tab` | Cycle through distinct sessions (incl. "All") |
| `j` / `k` or `↓` / `↑` | Navigate the pane table |
| `n` / `N` | Jump to next / previous **attention** pane |
| `a` | Toggle the attention filter (only attention) |
@ -137,10 +137,10 @@ renders. This makes attention impossible to miss without consuming extra space.
### Row highlight inverts on selection
| Row state | Normal | Selected |
| --------- | --------------------------- | ----------------------------------------- |
| Attention | `bg(DarkRed)` + `fg(White)` | `bg(DarkGray)` + `fg(LightRed)` + bold |
| Normal | (plain) | `bg(DarkGray)` |
| Row state | Normal | Selected |
| --------- | --------------------------- | -------------------------------------- |
| Attention | `bg(DarkRed)` + `fg(White)` | `bg(DarkGray)` + `fg(LightRed)` + bold |
| Normal | (plain) | `bg(DarkGray)` |
Attention rows are impossible to miss; the inversion on selection confirms
which one the cursor is on without losing the attention signal.

2
scripts/check-format.sh
View file

@ -8,4 +8,4 @@ ROOT_DIR="$(CDPATH= cd -- "$(dirname -- "$0")/.." && pwd)"
cd "$ROOT_DIR"
exec npx --yes prettier@3 --check '**/*.md'
exec npx --yes prettier@3.8.4 --check '**/*.md'