fleet/fleetd
3
0
Fork 0
Code Issues 73 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

wiki: number page filenames (1-..5-) so Gitea Pages list sorts 

- git mv content pages to N-Name.md (history preserved); Home + _Sidebar kept
- convert [[wiki-links]] to [display](numbered-slug) markdown links so
  resolution is unambiguous and prose display stays clean
Dai Ha
2026-07-11 15:13:56 +02:00
parent 2d3fb0159f
commit 0b73facb66
7 changed files with 46 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Architecture.md → 1-Architecture.md
+11 -11
@@ -7,7 +7,7 @@ model. Two channels carry traffic between them:
1. **Request/response (blocking)** — the primary delegates a task with **one blocking
request** that `bridged` (driving [herdr](https://herdr.dev)) holds open until the
worker's turn completes, then returns the reply as the response body. This is the main
channel; its full design is in **[[Message-Server]]**. "Blocking" here means a single
channel; its full design is in **[Message Server](2-Message-Server)**. "Blocking" here means a single
tool call parked on a result — *not* a busy-poll — so it costs the primary no quota.
2. **Asynchronous / duplex** — either side drops a message for the other to pick up when
idle → a **message broker** polled by a `Stop`-hook long-poll (or injected by `bridged`
@@ -18,7 +18,7 @@ The engine of the sync channel is **herdr**, fronted by `bridged`: herdr owns th
multiplexing, persistence, and **agent-status events**; `bridged` owns policy (the
subscription boundary, session lifecycle, status-gated delivery) and the client-facing
HTTP/SSE contract. (This supersedes the earlier plan, which used `coder/agentapi` as the
sync transport and treated herdr as an optional ops layer — see [[Approaches]] for why the
sync transport and treated herdr as an optional ops layer — see [Approaches](3-Approaches) for why the
positions swapped.)
## Components
@@ -79,7 +79,7 @@ cheaper/local model — without a policy-violating proxy on the primary.
`ANTHROPIC_BASE_URL` and refuses to ever set it on a pane tagged *primary*. The guard only
constrains panes `bridged` itself spawns; it **cannot** inspect a primary it does not host
(e.g. an Opus on your Mac, split-host) — that primary's env cleanliness is the operator's
responsibility, backed by a best-effort startup self-check (see [[Message-Server]]).
responsibility, backed by a best-effort startup self-check (see [Message Server](2-Message-Server)).
- Injecting keystrokes into the **primary** pane (worker → primary replies) is
subscription-safe: it is simulated typing, identical to the human at the keyboard — the
primary still authenticates to `api.anthropic.com` on Pro/Max. **This path exists only when
@@ -97,7 +97,7 @@ cheaper/local model — without a policy-violating proxy on the primary.
`GET /status`) into herdr socket calls, and — unlike a screen-stability heuristic — gates
every injection on herdr's live `agent_status_changed` events. One session per pane; many
panes per herdr. Full contract, components, and the Go interface sketch are in
**[[Message-Server]]**.
**[Message Server](2-Message-Server)**.
The primary's `POST /message` **blocks** until `bridged` sees `agent_status = done` and
collects the reply, which it returns as the response body — the primary reads it as an
@@ -140,8 +140,8 @@ the primary as the call's result; the primary re-sends the answer with a fresh b
Why herdr over the earlier `agentapi` plan: structured **agent-status events** (vs a
screen-stability heuristic), **symmetric** injection into either pane (single-host), native
**multiplexing** of a herd of workers, and **persistence/detach**. AgentAPI is kept as a
swappable *fallback injector* behind the same interface. See [[Approaches]] for the full
transport comparison and [[Message-Server]] for the design.
swappable *fallback injector* behind the same interface. See [Approaches](3-Approaches) for the full
transport comparison and [Message Server](2-Message-Server) for the design.
## Channel 2 — broker + Stop-hook long-poll (async, duplex)
@@ -185,7 +185,7 @@ primary's idle pane.*
| **Primary quota burn** | The primary must **never** perpetual-poll. Use the `Stop`-hook variant (fires only at a natural idle boundary), have `bridged` inject on idle, or pull on-demand. Free busy-polling is for `bridged` and the off-subscription **worker** only. |
| **Cross-agent ping-pong** | A→B→A→B can loop forever. `stop_hook_active` guards single-agent re-entry but **not** cross-agent. Carry a round/turn budget or a `no-reply-needed` sentinel in the message envelope. |
| **Lost / double-processed messages** | Use a broker with **ack + visibility timeout + consumer groups** (Redis Streams `XACK`, NATS JetStream). A crash mid-turn re-delivers instead of dropping. |
| **Context growth** | A perpetual worker's context window fills up. `bridged` caps idle cycles / tokens, then **recycles the pane fresh with state on the filesystem** (Ralph loop — see [[Message-Server]]). Perpetual != one infinite session. |
| **Context growth** | A perpetual worker's context window fills up. `bridged` caps idle cycles / tokens, then **recycles the pane fresh with state on the filesystem** (Ralph loop — see [Message Server](2-Message-Server)). Perpetual != one infinite session. |
## Deployment shape (target)
@@ -236,10 +236,10 @@ outage costs you the workers, never your own session.
## Related pages
- **[[Message-Server]]** — the `bridged` design: herdr control contract, lifecycle, API, tech stack
- **[[Approaches]]** — why herdr-centric, and the full transport comparison (AgentAPI, SDK, Stop-hook, tmux)
- **[[Setup]]** — running herdr + `bridged` + a worker pointed at `ollama.ltms.dev`
- **[[Operations]]** — health, restart, model swaps, troubleshooting
- **[Message Server](2-Message-Server)** — the `bridged` design: herdr control contract, lifecycle, API, tech stack
- **[Approaches](3-Approaches)** — why herdr-centric, and the full transport comparison (AgentAPI, SDK, Stop-hook, tmux)
- **[Setup](4-Setup)** — running herdr + `bridged` + a worker pointed at `ollama.ltms.dev`
- **[Operations](5-Operations)** — health, restart, model swaps, troubleshooting
## Sources
Message-Server.md → 2-Message-Server.md
+7 -7
@@ -1,7 +1,7 @@
# 2. Herdr Message Server (`bridged`)
> **Status:** 🟢 Proposed primary approach (2026-07-11) — supersedes AgentAPI as the
> centric transport. AgentAPI is retained only as a *fallback injector* (see [[Approaches]]).
> centric transport. AgentAPI is retained only as a *fallback injector* (see [Approaches](3-Approaches)).
`bridged` is a small, always-on **message server that controls [herdr](https://herdr.dev)**
and exposes a clean 2-way messaging API between a **primary** Claude Code session (Opus 4.8,
@@ -291,7 +291,7 @@ real herdr events, not heuristics — the reason herdr-centric beats screen scra
## Subscription boundary (enforced, not just documented)
The invariant is unchanged from [[Architecture]] — **anything that sets
The invariant is unchanged from [Architecture](1-Architecture) — **anything that sets
`ANTHROPIC_BASE_URL` is, by definition, the worker** — but here it is *enforced in code*:
- `bridged` is **not** a `claude` process. It consumes zero Anthropic quota, so it may
@@ -416,7 +416,7 @@ turns. Until then, treat one `bridged` as one trust domain.
| **Server core** | **Go** | Single static binary → trivial `scp`/systemd deploy to the worker host; goroutines fit the socket + HTTP + broker + SSE fan-in; mirrors `coder/agentapi` (can reuse its `msgfmt` reply parser). | Rust (matches herdr, slower to build); **TypeScript/Node** if the driver is the Agent SDK and you want shared types; Python for a quick spike. |
| **herdr transport** | Unix domain socket, **NDJSON**, `id`-correlated request/response + a persistent events stream | Native herdr contract | — |
| **North API** | **REST + SSE**, OpenAPI-generated | Drop-in for AgentAPI-shaped clients; SSE streams status/reply cheaply | gRPC (if callers are all code); WebSocket (bidi UI) |
| **Async bus** *(optional)* | **Redis Streams** (consumer groups, `XACK`, visibility timeout) | Simplest durable duplex; satisfies the async guardrails in [[Architecture]] | NATS JetStream for multi-host scale / replay |
| **Async bus** *(optional)* | **Redis Streams** (consumer groups, `XACK`, visibility timeout) | Simplest durable duplex; satisfies the async guardrails in [Architecture](1-Architecture) | NATS JetStream for multi-host scale / replay |
| **Config** | Env + YAML (`koanf`) | 12-factor; secrets via env only | — |
| **Observability** | `slog` + Prometheus `/metrics` + `/healthz` | Ops from day one | OpenTelemetry traces |
| **Process supervision** | **systemd** unit (or Docker Compose) colocating herdr + `bridged` | Restart-on-crash; ordered start (herdr before `bridged`) | k8s (overkill for one host) |
@@ -502,14 +502,14 @@ func (g *Guard) AssertLocalPrimaryClean(env []string) error {
| **Spawn-with-env uncertainty in socket API** | Launch via `send_text` of the env-prefixed command → env is provably worker-only; verify native spawn in the CLI reference and prefer it if present. |
| **Reply-scrape fragility (fallback path)** | Prefer the structured **envelope** path; scrape `recent-unwrapped` only as a last resort. |
| **herdr socket API is unversioned + single-dev churn** | Pin the herdr version in the systemd/Compose unit; keep the socket client behind the `Herdr` interface; probe `session.snapshot` shape on startup and fail fast on an unexpected schema. Don't build against `UNCERTAIN` primitives (e.g. native spawn-with-env) until confirmed in the running CLI. |
| **SPOF per channel (bridged / herdr / broker)** | Documented in [[Architecture]] → *Failure modes*. Key property: the **primary is never downstream** of a bridge component, so a total outage costs workers only, never the subscription session. |
| **SPOF per channel (bridged / herdr / broker)** | Documented in [Architecture](1-Architecture) → *Failure modes*. Key property: the **primary is never downstream** of a bridge component, so a total outage costs workers only, never the subscription session. |
| **Injection TOCTOU / shared pane** | Single-writer injector + serialized send; worker panes are bridged-owned. Residual collision corrupts a turn (recoverable), never the subscription boundary. See *Delivery gating & races*. |
## Related pages
- **[[Architecture]]** — the two-channel model this refines; subscription boundary
- **[[Approaches]]** — transport comparison; AgentAPI now the *fallback injector*
- **[[Home]]** — project overview
- **[Architecture](1-Architecture)** — the two-channel model this refines; subscription boundary
- **[Approaches](3-Approaches)** — transport comparison; AgentAPI now the *fallback injector*
- **[Home](Home)** — project overview
## Sources
Approaches.md → 3-Approaches.md
+3 -3
@@ -50,7 +50,7 @@ scraping a screen.
## 1. herdr socket API via `bridged` — structured injection + status events *(leading)*
[herdr](https://herdr.dev) is a persistent agent multiplexer (a "tmux for agents") with a
Unix-socket JSON API. `bridged` (see [[Message-Server]]) drives it: `pane.send_text` +
Unix-socket JSON API. `bridged` (see [Message Server](2-Message-Server)) drives it: `pane.send_text` +
`pane.send_keys` deliver a turn into the *running* pane, and `events.subscribe`
(`pane.agent_status_changed`) reports **working / blocked / done** as real events.
@@ -169,14 +169,14 @@ worker→primary is **not** symmetric — it goes via the broker + the primary's
"one mechanism, both directions" story holds for a single-box setup, not the distributed one.
² **"Completion signal" for `bridged` is the timing signal; reply *content* rides a worker
`Stop`-hook envelope** (see [[Message-Server]]), not the status event itself.
`Stop`-hook envelope** (see [Message Server](2-Message-Server)), not the status event itself.
## Recommendation
- **Primary Opus → worker (the bridge's main channel):** **herdr via `bridged`** —
status-gated injection, structured completion/blocked events, symmetric (single-host), multiplexed,
persistent, with the subscription boundary enforced in code. Selected. See
[[Message-Server]] / [[Architecture]].
[Message Server](2-Message-Server) / [Architecture](1-Architecture).
- **Keep AgentAPI as a swappable fallback injector** behind `bridged`'s interface, so
herdr's immaturity is a de-riskable risk rather than a load-bearing one.
- **External event bus → worker (async wake-ups):** layer a **Stop-hook long-poll** (or
Setup.md → 4-Setup.md
+4 -4
@@ -1,7 +1,7 @@
# 4. Setup
> **Status:** 🟠 Stub — scope defined, procedure not yet written. `bridged` is at the design
> stage ([[Message-Server]]); concrete install steps land with **M0–M1** of the build plan.
> stage ([Message Server](2-Message-Server)); concrete install steps land with **M0–M1** of the build plan.
This page will cover standing up the bridge on an off-subscription worker host.
@@ -19,14 +19,14 @@ This page will cover standing up the bridge on an off-subscription worker host.
subscription guard accepts it and `pane.process_info` shows the expected egress host.
5. **Primary wiring** — point the primary Opus at `bridged` over HTTP (single blocking
request per delegation); for split-host, add the primary's `Stop`-hook against the broker.
6. **Topology choice** — single-host vs split-host (see [[Message-Server]] → *Deployment
6. **Topology choice** — single-host vs split-host (see [Message Server](2-Message-Server) → *Deployment
model*), and the broker (Redis Streams / NATS) if async/duplex is needed.
## Non-negotiable during setup
The **primary** host/process must **never** be given `ANTHROPIC_BASE_URL`. Only worker panes
carry it. See [[Architecture]] → *Subscription boundary*.
carry it. See [Architecture](1-Architecture) → *Subscription boundary*.
## Related
- [[Message-Server]] · [[Architecture]] · [[Operations]] · [[Approaches]]
- [Message Server](2-Message-Server) · [Architecture](1-Architecture) · [Operations](5-Operations) · [Approaches](3-Approaches)
Operations.md → 5-Operations.md
+6 -6
@@ -1,7 +1,7 @@
# 5. Operations
> **Status:** 🟠 Stub — scope defined, runbook not yet written. Fills in as `bridged` reaches
> **M4 — Harden** (auth/TLS, metrics, systemd) in the [[Message-Server]] build plan.
> **M4 — Harden** (auth/TLS, metrics, systemd) in the [Message Server](2-Message-Server) build plan.
Day-2 runbook for a running bridge.
@@ -11,19 +11,19 @@ Day-2 runbook for a running bridge.
`agent_status` per session via `GET /sessions`.
- **Restart & recovery** — ordered restart (herdr before `bridged`); how `bridged`
re-attaches to existing panes via `session.snapshot`; broker replay of unacked items. See
[[Architecture]] → *Failure modes & single points of failure* for what each outage costs.
[Architecture](1-Architecture) → *Failure modes & single points of failure* for what each outage costs.
- **Model swaps** — repoint a worker to a different `base_url`/model by recycling its pane
(Ralph loop); the subscription guard re-validates the new host against the allowlist.
- **Lifecycle / context ceilings** — observing recycle events; confirming workers externalize
state (git + `STATE.md`) before a recycle so continuity survives (see [[Message-Server]] →
state (git + `STATE.md`) before a recycle so continuity survives (see [Message Server](2-Message-Server) →
*Worker session lifecycle*).
- **Troubleshooting** — stuck `working` (model endpoint down), `blocked` awaiting input,
injection collisions on a hand-driven pane, envelope-vs-scrape reply mismatches.
- **Security ops** — token rotation, keeping the port off public interfaces; note that one
`bridged` is currently **one trust domain** (no per-session authz yet — [[Message-Server]]
`bridged` is currently **one trust domain** (no per-session authz yet — [Message Server](2-Message-Server)
→ *Security*).
## Guardrails to watch (from [[Architecture]])
## Guardrails to watch (from [Architecture](1-Architecture))
- The **primary must never perpetual-poll** — quota burn. Async wake-ups use the `Stop`-hook
or `bridged` inject-on-idle only.
@@ -33,4 +33,4 @@ Day-2 runbook for a running bridge.
## Related
- [[Message-Server]] · [[Architecture]] · [[Setup]] · [[Approaches]]
- [Message Server](2-Message-Server) · [Architecture](1-Architecture) · [Setup](4-Setup) · [Approaches](3-Approaches)
Home.md
+9 -9
@@ -43,25 +43,25 @@ flowchart LR
- **How the primary gets a reply:** it makes **one blocking request** (a `curl`/MCP tool
call) that `bridged` holds open until the worker's turn completes, then returns the reply
as the response body. Long/detached work instead uses the async broker path (see
[[Architecture]]) — the primary never busy-polls across turns.
[Architecture](1-Architecture)) — the primary never busy-polls across turns.
- **Different model** per worker process sidesteps Claude Code's lack of per-subagent
provider routing — the worker isn't a subagent, it's its own configured process.
- **AgentAPI** ([`coder/agentapi`](https://github.com/coder/agentapi)) is retained only as a
swappable *fallback injector* behind the same interface. See [[Approaches]] for the
comparison and [[Message-Server]] for the full design.
swappable *fallback injector* behind the same interface. See [Approaches](3-Approaches) for the
comparison and [Message Server](2-Message-Server) for the full design.
## Pages
Read in order (the sidebar mirrors this):
1. **[[Architecture]]** — process model, subscription boundary, the two-channel model
2. **[[Message-Server]]** — 🟢 **`bridged`**, the herdr-centric message server (primary approach)
3. **[[Approaches]]** — herdr-centric vs AgentAPI vs Agent SDK vs bus/tmux (research matrix)
4. **[[Setup]]** — running herdr + `bridged` + a worker pointed at `ollama.ltms.dev`
5. **[[Operations]]** — health, restart, model swaps, troubleshooting
1. **[Architecture](1-Architecture)** — process model, subscription boundary, the two-channel model
2. **[Message Server](2-Message-Server)** — 🟢 **`bridged`**, the herdr-centric message server (primary approach)
3. **[Approaches](3-Approaches)** — herdr-centric vs AgentAPI vs Agent SDK vs bus/tmux (research matrix)
4. **[Setup](4-Setup)** — running herdr + `bridged` + a worker pointed at `ollama.ltms.dev`
5. **[Operations](5-Operations)** — health, restart, model swaps, troubleshooting
## Status
🟢 Design — **herdr-centric `bridged` message server** selected as the primary approach
(2026-07-11), superseding the AgentAPI plan (2026-07-08). AgentAPI is retained as a fallback
injector. See **[[Message-Server]]**.
injector. See **[Message Server](2-Message-Server)**.
_Sidebar.md
+6 -6
@@ -1,14 +1,14 @@
### 📖 claude-bridge
[[Home]] — overview & the decision
[Home](Home) — overview & the decision
**Chapters**
1. [[Architecture]] — system · invariant · 2 channels
2. [[Message-Server]] — the `bridged` design
3. [[Approaches]] — transports compared, why herdr
4. [[Setup]] — bring-up
5. [[Operations]] — day-2 runbook
1. [Architecture](1-Architecture) — system · invariant · 2 channels
2. [Message Server](2-Message-Server) — the `bridged` design
3. [Approaches](3-Approaches) — transports compared, why herdr
4. [Setup](4-Setup) — bring-up
5. [Operations](5-Operations) — day-2 runbook
---
🟢 herdr-centric `bridged` · AgentAPI = fallback