diff --git a/Approaches.md b/Approaches.md index 6679f8f..c87cfe3 100644 --- a/Approaches.md +++ b/Approaches.md @@ -6,29 +6,35 @@ message into an **already-running Claude Code worker** — *without* spawning a new process (cold context, no live session) for every turn, which defeats the point of a persistent worker that holds `CLAUDE.md`, hooks, skills, MCP, and conversation state. -That leaves four real transports. They differ on one decisive axis: **can the driver push -into the session while it is idle/mid-run, or only at a turn boundary?** +That leaves several real transports. They differ on one decisive axis: **can the driver +push into the session while it is idle/mid-run, or only at a turn boundary?** — and, once +that is solved, on *how reliably you know when the worker is done or blocked*. ```mermaid flowchart TD Q{"How is the message
delivered into a LIVE session?"} + Q -->|"structured socket → terminal, + status events"| HD["herdr socket
(via bridged)"] Q -->|"HTTP request → terminal emulation"| AA["AgentAPI
(coder/agentapi)"] Q -->|"streaming input generator (in-process)"| SDK["Agent SDK
streaming query()"] Q -->|"worker PULLS on idle via a hook"| BUS["Message-queue
+ Stop-hook long-poll"] Q -->|"raw keystrokes into the tmux pane"| TMUX["tmux send-keys
/ PTY paste"] - AA --> V1["✅ our leading choice"] + HD --> V0["✅ our leading choice
(status events + symmetric + multiplex)"] + AA --> V1["◐ fallback injector
(swappable behind bridged)"] SDK --> V2["✅ if driver is our own code"] BUS --> V3["⚠ async bus events only
(lands at turn boundary)"] - TMUX --> V4["⚠ fragile, but the raw primitive
AgentAPI wraps"] + TMUX --> V4["⚠ fragile — the raw primitive
herdr/AgentAPI productize"] classDef pick fill:#2f855a,stroke:#22543d,color:#ffffff; + classDef alt fill:#2b6cb0,stroke:#1a365d,color:#ffffff; classDef warn fill:#b7791f,stroke:#7b341e,color:#ffffff; - class AA,V1 pick + class HD,V0 pick + class AA,V1 alt class BUS,TMUX,V3,V4 warn ``` -*Figure: picking a delivery transport by how the message enters a running session.* +*Figure: picking a delivery transport by how the message enters a running session — and how +trustworthy the "done/blocked" signal is once it does.* ## The native gap (why workarounds exist) @@ -36,39 +42,63 @@ Claude Code has **no first-class "inject a prompt into a running session"** API. explicitly-requested, still-open feature: [#27441 — inter-agent message injection](https://github.com/anthropics/claude-code/issues/27441) and [#24947 — `claude inject`](https://github.com/anthropics/claude-code/issues/24947). -Every approach below is a way around that gap. AgentAPI wins precisely because it -productizes the sturdiest workaround (terminal emulation) behind a clean HTTP contract. +Every approach below is a way around that gap. **herdr wins because it productizes the +sturdiest workaround (terminal automation) as a structured socket API that *also* streams +agent-status events** — so `bridged` gets reliable completion/blocked signals instead of +scraping a screen. -## 1. AgentAPI — HTTP over terminal emulation *(leading)* +## 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` + +`pane.send_keys` deliver a turn into the *running* pane, and `events.subscribe` +(`pane.agent_status_changed`) reports **working / blocked / done** as real events. + +- **Injects into a live session:** yes — into *either* the worker **or** the primary pane + (typing keystrokes is subscription-safe), so both directions use one mechanism. +- **Completion signal:** structured events — not the screen-stability *guess* AgentAPI makes. + The worker can even `pane.report_agent` its own state via herdr's `SKILL.md`. +- **Multiplex + persist:** a herd of workers as addressable panes; headless server survives + detach/reattach over SSH. +- **Subscription-safe:** only the worker pane launches with `ANTHROPIC_BASE_URL`; `bridged` + is a plain daemon (no quota) that enforces the boundary in code. +- **Trade-off:** herdr's socket is **local-only** (broker spans hosts, not herdr), and it is + a young, single-dev project — so `bridged` keeps the injector **pluggable** and the + durable spine on the broker. Replies are best carried as a structured envelope, not scraped. + +## 2. AgentAPI — HTTP over terminal emulation *(fallback injector)* [`coder/agentapi`](https://github.com/coder/agentapi) wraps the Claude Code **CLI** as an -HTTP server and, under the hood, **drives the CLI's terminal** (it is essentially a -hardened, stateful `tmux send-keys` with parsing). `POST /message` delivers a turn to the -*running* session; `GET /events` (SSE) streams the reply. One session per server. +HTTP server and drives the CLI's terminal underneath (essentially a hardened, stateful +`tmux send-keys` with parsing): `POST /message`, `GET /events` (SSE), `GET /status`. It was +the original leading choice; herdr now supersedes it, but it remains a **swappable fallback +injector** behind `bridged`'s interface. -- **Injects into a live session:** yes — this is its whole job. -- **Subscription-safe:** the *primary* never sets `ANTHROPIC_BASE_URL`; only the worker's - wrapped `claude` launches with `ANTHROPIC_BASE_URL=https://ollama.ltms.dev` + bearer. -- **Why chosen:** clean request/response contract, stable session, reply parsing solved — - none of the raw-keystroke fragility of doing it ourselves. See [[Architecture]]. +- **Injects into a live session:** yes — but only the *worker* (it wraps one CLI); the + primary direction still needs a broker. +- **Completion signal:** a **screen-stability heuristic**, not structured events. +- **Cross-host:** native HTTP — its one edge over herdr, but `bridged` already provides the + HTTP layer on top of herdr, so that edge is neutralized. +- **When to reach for it:** if herdr can't run, or as the second injector implementation to + de-risk herdr's immaturity. Its `msgfmt` reply parser is worth reusing regardless. -## 2. Agent SDK — streaming input *(good if the driver is our own code)* +## 3. Agent SDK — streaming input *(good if the driver is our own code)* The Claude Agent SDK (TypeScript / Python) `query()` accepts a **streaming/async input generator**, so you can feed additional messages into a live query without respawning the -process. This is the cleanest option **when the driver is a program you control** rather -than another interactive Claude session — you get typed streaming events and permission -callbacks instead of scraping a terminal. +process. Cleanest option **when the driver is a program you control** — typed streaming +events and permission callbacks instead of scraping a terminal. - **Injects into a live session:** yes, in-process. -- **Trade-off:** the worker is an SDK-hosted loop, not a stock `claude` TUI — slightly - further from "a real Claude Code process" than AgentAPI, and the driver must be code. +- **Trade-off:** the worker is an SDK-hosted loop, not a stock `claude` TUI — further from + "a real Claude Code process" than herdr/AgentAPI, and the driver must be code. -## 3. Message-queue + Stop-hook long-poll *(the genuinely hook-based path)* +## 4. Message-queue + Stop-hook long-poll *(the async layer — complementary)* -This is the **only pure-hooks** way to pull an external message into the **same** session, -and the right fit when the trigger is an **asynchronous event bus** (NATS / Redis / -webhook) rather than a synchronous driver waiting on a reply. +The **only pure-hooks** way to pull an external message into the **same** session, and the +right fit when the trigger is an **asynchronous event bus** (NATS / Redis / webhook) rather +than a synchronous driver waiting on a reply. Used as `claude-bridge`'s **Channel 2** +alongside the herdr sync channel, not as a replacement. ```mermaid sequenceDiagram @@ -91,27 +121,24 @@ sequenceDiagram - **Mechanism:** register a `Stop` hook that **long-polls** the queue for ~30s. On a hit it returns `{"decision":"block","reason":""}` — the `reason` becomes injected - context and forces another turn. On timeout it lets the session stop. The - `stop_hook_active` flag guards against infinite loops. + context and forces another turn. On timeout it lets the session stop. `stop_hook_active` + guards against infinite loops. - **Reference implementation:** **Agent Room** (`agent-room-mcp`) — `Stop` + - `UserPromptSubmit` + `SessionStart` hooks over **Redis** "rooms" that Claude Code / - Cursor / Gemini CLI publish-subscribe to. + `UserPromptSubmit` + `SessionStart` hooks over **Redis** "rooms". ([writeup](https://dev.to/agent-room/how-a-claude-code-stop-hook-unlocks-async-multi-agent-collaboration-no-polling-required-2e0e), [DIY pattern](https://claudefa.st/blog/tools/hooks/stop-hook-task-enforcement)). -- **Decisive limitation:** **pull-on-idle only** — the message lands at a **turn boundary** - (when the worker would otherwise stop), never mid-turn. Fine for "bus event wakes an idle - worker"; wrong for "interrupt a worker that's busy." -- **Lighter cousin:** a `UserPromptSubmit` hook returning `{"additionalContext":"…"}` - (e.g. [claude-mem](https://docs.claude-mem.ai/hooks-architecture) pulling from a vector - DB) — but that fires only *when a prompt is submitted*, so it can't deliver an async push. +- **Decisive limitation:** **pull-on-idle only** — the message lands at a **turn boundary**, + never mid-turn. Fine for "bus event wakes an idle worker"; wrong for "interrupt a busy + worker." (`bridged` injecting into an idle pane has the same idle-boundary property, but + with a real status gate.) +- **Lighter cousin:** a `UserPromptSubmit` hook returning `{"additionalContext":"…"}` — + fires only *when a prompt is submitted*, so it can't deliver an async push. -## 4. tmux `send-keys` / PTY paste *(the raw primitive)* +## 5. tmux `send-keys` / PTY paste *(the raw primitive)* -Inject keystrokes straight into the pane running `claude`. It is the most direct *push* -into a live session and works today, but it is terminal automation — timing-sensitive, -needs `capture-pane` to know when the worker is ready, and has no structured reply. -Existing tools that do this (hooks only fire their *outbound* notification; injection is -PTY/tmux): +Inject keystrokes straight into the pane running `claude`. The most direct *push* into a +live session, works today, but it is terminal automation — timing-sensitive, needs +`capture-pane` to know when the worker is ready, and has no structured reply. | Tool | Inbound injection | Hooks used for | |---|---|---| @@ -119,35 +146,43 @@ PTY/tmux): | [OpenACP](https://dev.to/tigergethigher/how-to-control-claude-code-from-telegram-discord-or-slack-self-hosted-open-source-1jk8) (Slack/Discord/Telegram) | Agent Client Protocol bridge | — | | [samwize Slack monitor](https://samwize.com/2026/03/14/how-i-got-claude-code-to-monitor-slack-while-i-was-on-holiday/) | `tmux send-keys` | — | -**AgentAPI is essentially this, productized** — which is why we prefer it over hand-rolled -`send-keys`. +**herdr's `send_text`/`send_keys` is this, productized** — with a stable session, structured +status events, and multiplexing — which is why we build on herdr rather than hand-rolled +`send-keys` (and why AgentAPI, the other productized form, is only the fallback). ## Research matrix -| Approach | Transport | Inject into running session? | Async push (mid-idle)? | Subscription-safe (primary) | Reply parsing | Fragility | -|---|---|---|---|---|---|---| -| **AgentAPI** ✅ | HTTP → terminal emulation | ✅ | ✅ (`POST /message`) | ✅ (worker-only env) | ✅ SSE `/events` | Low | -| **Agent SDK streaming** | in-process generator | ✅ | ✅ | ✅ | ✅ typed events | Low (but driver = code) | -| **Queue + Stop-hook** | hook long-poll | ✅ (turn boundary) | ⚠ pull-on-idle only | ✅ | via `reason` text | Medium | -| **tmux `send-keys`** | keystrokes / PTY | ✅ | ✅ | ✅ | ❌ scrape `capture-pane` | High | -| ~~`claude -p`~~ (excluded) | new process/turn | ❌ (fresh session) | — | ✅ | ✅ | — | +| Approach | Transport | Inject into running session? | Completion signal | Symmetric (both panes)? | Cross-host | Subscription-safe | Fragility | +|---|---|---|---|---|---|---|---| +| **herdr via `bridged`** ✅ | socket → terminal + events | ✅ (idle-gated) | ✅ status events | ✅ | via broker / `bridged` HTTP | ✅ (guard in code) | Low–Med (herdr young) | +| **AgentAPI** ◐ (fallback) | HTTP → terminal emulation | ✅ (worker only) | ⚠ screen-stability | ❌ | ✅ native HTTP | ✅ (worker-only env) | Low | +| **Agent SDK streaming** | in-process generator | ✅ | ✅ typed events | n/a | ✅ | ✅ | Low (driver = code) | +| **Queue + Stop-hook** | hook long-poll | ✅ (turn boundary) | via turn end | ✅ (symmetric) | ✅ | ✅ | Medium | +| **tmux `send-keys`** | keystrokes / PTY | ✅ | ❌ scrape `capture-pane` | ✅ | ⚠ ssh | ✅ | High | +| ~~`claude -p`~~ (excluded) | new process/turn | ❌ (fresh session) | ✅ | — | ✅ | ✅ | — | ## Recommendation -- **Primary Opus → worker (the bridge's main channel):** **AgentAPI** — synchronous, - parsed replies, clean subscription boundary. Selected. See [[Architecture]] / [[Setup]]. -- **External event bus → worker (async wake-ups):** layer a **Stop-hook long-poll** onto - the worker so bus events injected as `reason` resume it on idle. Complementary to - AgentAPI, not a replacement — different trigger shape. -- **Avoid hand-rolled `tmux send-keys`** unless AgentAPI can't run; it's the same idea with - all the fragility left in. +- **Primary Opus → worker (the bridge's main channel):** **herdr via `bridged`** — + status-gated injection, structured completion/blocked events, symmetric, multiplexed, + persistent, with the subscription boundary enforced in code. Selected. See + [[Message-Server]] / [[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 + `bridged` inbox bridging) onto the worker so bus events resume it on idle. Complementary + to the sync channel, not a replacement — different trigger shape. +- **Avoid hand-rolled `tmux send-keys`** unless neither herdr nor AgentAPI can run; it's the + same idea with all the fragility left in. ## Sources +- [herdr — socket API](https://herdr.dev/docs/socket-api/) · [agent guide](https://herdr.dev/agent-guide.md) · [GitHub](https://github.com/ogulcancelik/herdr) +- [coder/agentapi](https://github.com/coder/agentapi) - [Hooks reference — Claude Code Docs](https://code.claude.com/docs/en/hooks) - [Agent Room — Stop-hook async collaboration](https://dev.to/agent-room/how-a-claude-code-stop-hook-unlocks-async-multi-agent-collaboration-no-polling-required-2e0e) - [Stop-hook task-enforcement pattern](https://claudefa.st/blog/tools/hooks/stop-hook-task-enforcement) - [claude-mem hooks architecture](https://docs.claude-mem.ai/hooks-architecture) -- [coder/agentapi](https://github.com/coder/agentapi) - [Issue #27441 — inter-agent message injection](https://github.com/anthropics/claude-code/issues/27441) · [Issue #24947 — `claude inject`](https://github.com/anthropics/claude-code/issues/24947) - [Claude-Code-Remote](https://github.com/JessyTsui/Claude-Code-Remote) · [OpenACP guide](https://dev.to/tigergethigher/how-to-control-claude-code-from-telegram-discord-or-slack-self-hosted-open-source-1jk8) + diff --git a/Architecture.md b/Architecture.md index 64b3339..c63c24c 100644 --- a/Architecture.md +++ b/Architecture.md @@ -4,14 +4,20 @@ subscription) to one or more **secondary** Claude Code **workers** running a *different* model. Two channels carry traffic between them: -1. **Synchronous** — primary delegates a task and waits for the reply → **AgentAPI** (HTTP - over terminal emulation). This is the main channel. +1. **Synchronous** — primary delegates a task and streams the reply → the **`bridged` + message server driving [herdr](https://herdr.dev)**. This is the main channel; its full + design is in **[[Message-Server]]**. 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. This is the optional - layer for detached progress reports and out-of-band questions. + idle → a **message broker** polled by a `Stop`-hook long-poll (or injected by `bridged` + into an idle pane). This is the optional layer for detached progress reports and + out-of-band questions. -A third piece, **herdr**, is *not* a transport — it is the human-facing ops/observability -layer (persistence, state sidebar, a readiness gate). +The engine of the sync channel is **herdr**, fronted by `bridged`: herdr owns the PTYs, +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 +positions swapped.) ## Components @@ -21,36 +27,37 @@ flowchart TB OPUS["Claude Code · Opus 4.8
leads, reviews, merges"] end - subgraph work["SECONDARY worker(s) — off-subscription"] - AA["agentapi server
HTTP :3284"] + subgraph work["SECONDARY worker host — off-subscription"] + BD["bridged
message server
(not a claude process)"] + HERDR["herdr server
panes · agent-status"] WCC["claude (worker)
ANTHROPIC_BASE_URL set"] HOOK["Stop-hook
long-poll client"] - AA -->|"launches / drives PTY"| WCC + BD -->|"Unix socket
send_text · events.subscribe"| HERDR + HERDR -->|"drives PTY"| WCC WCC --- HOOK end BROKER["Broker
Redis Streams / NATS JetStream
inbox-primary · inbox-worker"] MODEL["ollama.ltms.dev /v1
or GX10 vLLM
(worker model)"] - HERDR["herdr server
panes · state · socket API
(ops layer, optional)"] - OPUS -->|"POST /message (sync)"| AA - AA -.->|"SSE /events (reply)"| OPUS + OPUS -->|"POST /message (sync)"| BD + BD -.->|"SSE /events (reply)"| OPUS OPUS -.->|"write / long-poll (async)"| BROKER HOOK -.->|"long-poll / write (async)"| BROKER + BD -.->|"bridge inbox ↔ session"| BROKER WCC -->|"inference"| MODEL - HERDR -.->|"send-keys · agent wait
pane read"| WCC classDef sub fill:#2b6cb0,stroke:#1a365d,color:#ffffff; classDef pick fill:#2f855a,stroke:#22543d,color:#ffffff; classDef warn fill:#b7791f,stroke:#7b341e,color:#ffffff; class OPUS sub - class AA,WCC pick - class BROKER,HERDR warn + class BD,HERDR,WCC pick + class BROKER warn ``` -*Figure: solid arrows = synchronous AgentAPI channel; dotted = the optional async broker -and the herdr ops plane. The primary's env stays clean; only the worker sets -`ANTHROPIC_BASE_URL`.* +*Figure: solid arrows = the synchronous `bridged`/herdr channel; dotted = the optional async +broker. The primary's env stays clean; only the worker sets `ANTHROPIC_BASE_URL`, and +`bridged` — a plain daemon — enforces that boundary in code.* ## Subscription boundary (the non-negotiable) @@ -58,56 +65,75 @@ The whole design exists to keep the **primary** on Pro/Max while the **worker** cheaper/local model — without a policy-violating proxy on the primary. - The **primary** `claude` process **never** sets `ANTHROPIC_BASE_URL`. It talks to the - worker over **HTTP** (AgentAPI) or a **broker**, never by re-pointing its own endpoint. + worker over **HTTP** (`bridged`) or a **broker**, never by re-pointing its own endpoint. - Only the **worker's** `claude` process launches with `ANTHROPIC_BASE_URL=https://ollama.ltms.dev` (+ `ANTHROPIC_AUTH_TOKEN` bearer) or a GX10 vLLM URL. Because it is a *separate process*, model selection is just per-process env — which also sidesteps Claude Code's lack of per-subagent provider routing (the worker is not a subagent). +- **`bridged` is not a `claude` process** and consumes zero Anthropic quota, so it may + busy-poll the broker and hold a permanent herdr event subscription with no policy concern. + Its **subscription guard** refuses to spawn a *worker* pane without `ANTHROPIC_BASE_URL` + and refuses to ever set it on a pane tagged *primary*. +- 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. > **Rule:** anything that sets `ANTHROPIC_BASE_URL` is, by definition, the worker. If you > ever feel tempted to set it on the primary, stop — that is the subscription line. -## Channel 1 — AgentAPI (synchronous, the main path) +## Channel 1 — `bridged` over herdr (synchronous, the main path) -[`coder/agentapi`](https://github.com/coder/agentapi) wraps the worker's `claude` **CLI** -as an HTTP server (`POST /message`, `GET /messages`, `GET /events` SSE, `GET /status`), -driving the CLI's terminal underneath. One session per server. +`bridged` translates a clean north-side message API (`POST /message`, `GET /events` SSE, +`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]]**. ```mermaid sequenceDiagram participant P as "Primary (Opus)" - participant A as "agentapi server" + participant S as "bridged" + participant H as "herdr" participant W as "Worker claude (other model)" - P->>A: "POST /message (task, full context inlined)" - A->>W: "inject into running session" + P->>S: "POST /message (task, full context inlined)" + S->>S: "await pane status = idle" + S->>H: "pane.send_text + send_keys enter" + H->>W: "inject into running session" activate W - W-->>A: "streamed tokens" - A-->>P: "GET /events (SSE): assistant reply" + H-->>S: "event: agent_status_changed = working" + S-->>P: "SSE: status working" + W-->>H: "produces reply (writes envelope)" + H-->>S: "event: agent_status_changed = done" deactivate W + S-->>P: "SSE: assistant reply" Note over P: "review diff / result, merge" alt worker is blocked - W-->>A: "status = blocked (needs input)" - A-->>P: "GET /status: blocked" - P->>A: "POST /message (answer inlined)" + H-->>S: "event: agent_status_changed = blocked" + S-->>P: "SSE / GET /status: blocked" + P->>S: "POST /message (answer inlined)" end ``` -*Figure: the primary delegates and waits; replies stream back parsed over SSE. A blocked -worker surfaces on `/status`, and the primary re-sends with the answer inlined -(return-and-reinvoke) — the same pattern `crush-bridge` uses.* +*Figure: the primary delegates and streams status/reply over SSE; `bridged` injects only +when the pane is `idle`, and a blocked worker surfaces on a real herdr event (not a guess). +The primary re-sends with the answer inlined — the return-and-reinvoke pattern `crush-bridge` +uses.* -Why AgentAPI over raw `tmux send-keys`: it gives a clean request/reply contract and -**parsed** replies (SSE), instead of scraping a terminal buffer. See [[Approaches]] for the -full transport comparison. +Why herdr over the earlier `agentapi` plan: structured **agent-status events** (vs a +screen-stability heuristic), **symmetric** injection into either pane, 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. ## Channel 2 — broker + Stop-hook long-poll (async, duplex) For traffic that has **no caller waiting on a connection** — a long-running worker posting progress, an out-of-band question, another agent or a webhook injecting work — use a -broker. The mechanism is symmetric, so it carries **both** directions: each side -long-polls its **own** inbox stream and writes to the **other's**. +broker. The mechanism is symmetric, so it carries **both** directions: each side long-polls +its **own** inbox stream and writes to the **other's**. `bridged` can also bridge a broker +inbox directly onto a session (delivering into an idle pane) instead of a Stop-hook. ```mermaid sequenceDiagram @@ -131,79 +157,61 @@ sequenceDiagram B-->>P: "payload → primary resumes" ``` -*Figure: a `Stop` hook long-polls the broker and injects any message as the block -`reason`, forcing another turn; on timeout the session idles. Reversing it (worker → -primary) is the same hook on the primary's inbox.* +*Figure: a `Stop` hook long-polls the broker and injects any message as the block `reason`, +forcing another turn; on timeout the session idles. Reversing it (worker → primary) is the +same hook on the primary's inbox — or `bridged` typing into the primary's idle pane.* ### Guardrails (mandatory for the async layer) | Risk | Mitigation | |------|------------| -| **Primary quota burn** | The primary must **never** perpetual-poll. Use the `Stop`-hook variant (fires only at a natural idle boundary) or pull on-demand. Free busy-polling is for the off-subscription **worker** only. | +| **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. Cap idle cycles / tokens, then **stop and respawn fresh with state on the filesystem** (Ralph-loop). Perpetual != one infinite session. | - -## herdr — ops / observability plane (optional) - -[herdr](https://github.com/ogulcancelik/herdr) is a Rust **agent multiplexer** ("tmux for -agents"): a persistent headless server + attachable TUI, each agent in a real PTY pane, a -sidebar rolling every agent up to 🔴blocked / 🟡working / 🔵done / 🟢idle, all scriptable -over a Unix-socket JSON API. - -It is **not** the transport and has **no** Claude-specific inject API — sending input is -the generic `pane send-text` / `send-keys` / `run` PTY primitive, and its Claude state -detection is **screen-manifest scraping**, not hooks. What it adds: - -- **`herdr agent wait --status idle|blocked`** — a readiness/blocked gate. An external - driver can `wait agent-status blocked → pane run ""` instead of guessing when a - pane is ready. This is the fragility that raw `send-keys` lacks. -- **Persistent server, detach/reattach over SSH** — good for a long-lived off-subscription - worker on a remote box you occasionally eyeball. -- **Multiplexing + state sidebar** — pays off once there is a *herd* of mixed workers. - -**Positioning:** AgentAPI (or the broker) is the **machine transport**; herdr is the -**human ops layer**. You can run AgentAPI-wrapped or broker-driven workers *inside* herdr -panes and use `agent wait` as the readiness gate. Caveats: replies from herdr are scraped -buffer text (not parsed like AgentAPI's SSE), and it is a very young, single-developer -project — don't put a core transport on it. +| **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. | ## Deployment shape (target) ```mermaid flowchart LR - subgraph mac["Your machine"] + subgraph mac["Your machine (subscription)"] OPUS["Primary Opus
(Claude Code)"] end - subgraph host["Worker host (off-subscription)"] + subgraph host["Worker host (off-subscription, near model)"] direction TB - HS["herdr server (optional)"] - AA2["agentapi server"] - W2["worker claude"] - HS -.-> AA2 --> W2 + BD["bridged :8080
HTTP/SSE"] + HS["herdr server"] + W2["worker claude pane(s)"] + BD -->|"Unix socket"| HS --> W2 end BR["Broker"] ML["ollama.ltms.dev / GX10 vLLM"] - OPUS -->|"HTTP"| AA2 + OPUS -->|"HTTP + SSE (sync)"| BD OPUS -.->|"async"| BR - W2 -.-> BR + BD -.-> BR W2 --> ML classDef sub fill:#2b6cb0,stroke:#1a365d,color:#ffffff; + classDef pick fill:#2f855a,stroke:#22543d,color:#ffffff; class OPUS sub + class BD,HS pick ``` -*Figure: the worker (agentapi + optional herdr) lives on an off-subscription host near the -model; the primary reaches it over HTTP (sync) and the broker (async).* +*Figure: `bridged` + herdr + workers live on an off-subscription host near the model; the +primary reaches it over HTTP (sync) and the broker (async). herdr's socket is local to the +worker host — only the broker (or `bridged`'s HTTP) crosses the network. Bind `bridged` to +localhost + tunnel, or front it with a token; never expose the port unauthenticated.* ## Related pages -- **[[Approaches]]** — why AgentAPI, and the full transport comparison (SDK, Stop-hook, tmux) -- **[[Setup]]** — running the worker agentapi server pointed at `ollama.ltms.dev` +- **[[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 ## Sources -- [coder/agentapi](https://github.com/coder/agentapi) -- [herdr — GitHub](https://github.com/ogulcancelik/herdr) · [docs](https://herdr.dev/docs/) · [agents / state detection](https://herdr.dev/docs/agents/) · [CLI reference](https://herdr.dev/docs/cli-reference/) +- [herdr — socket API](https://herdr.dev/docs/socket-api/) · [agents / state detection](https://herdr.dev/docs/agents/) · [GitHub](https://github.com/ogulcancelik/herdr) +- [coder/agentapi](https://github.com/coder/agentapi) — fallback injector - [Agent Room — Stop-hook async collaboration](https://dev.to/agent-room/how-a-claude-code-stop-hook-unlocks-async-multi-agent-collaboration-no-polling-required-2e0e) - [Hooks reference — Claude Code Docs](https://code.claude.com/docs/en/hooks) + diff --git a/Home.md b/Home.md index af153d2..1abd84d 100644 --- a/Home.md +++ b/Home.md @@ -33,11 +33,14 @@ session talks to it over HTTP. ## Pages -- **[[Architecture]]** — process model, the AgentAPI HTTP contract, subscription boundary -- **[[Approaches]]** — AgentAPI vs Agent SDK streaming vs bus/tmux (research matrix) -- **[[Setup]]** — running the worker AgentAPI server + pointing it at `ollama.ltms.dev` +- **[[Message-Server]]** — 🟢 **`bridged`**, the herdr-centric message server (current primary approach) +- **[[Architecture]]** — process model, subscription boundary, the two-channel model it refines +- **[[Approaches]]** — herdr-centric vs AgentAPI vs Agent SDK vs bus/tmux (research matrix) +- **[[Setup]]** — running herdr + `bridged` + a worker pointed at `ollama.ltms.dev` - **[[Operations]]** — health, restart, model swaps, troubleshooting ## Status -🟡 Planning — AgentAPI selected as the primary approach (2026-07-08). +🟢 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]]**. diff --git a/Message-Server.md b/Message-Server.md new file mode 100644 index 0000000..184c0e1 --- /dev/null +++ b/Message-Server.md @@ -0,0 +1,397 @@ +# 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]]). + +`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, +on Pro/Max) and one or more **secondary worker** sessions running a different/cheaper model. +It replaces the hand-rolled terminal emulation of AgentAPI by standing on herdr's structured +socket API: herdr owns the PTYs, multiplexing, persistence, and — crucially — **agent-status +events**; `bridged` owns the *policy* (subscription boundary, session lifecycle, delivery +gating) and the *client-facing contract* (HTTP/SSE + optional broker). + +## Why herdr-centric (vs AgentAPI) + +AgentAPI re-implements, per process, an in-memory terminal emulator and a *screen-stability +heuristic* to guess when the agent is done. herdr already provides all of that as a +persistent service, and adds three things AgentAPI cannot: + +| Capability | AgentAPI | herdr (via `bridged`) | +|---|---|---| +| Inject a turn into a **worker** | ✅ terminal emulation | ✅ `pane.send_text` + `pane.send_keys` | +| Inject a turn into the **primary** | ❌ (only wraps worker) | ✅ same primitive — **symmetric 2-way** | +| "Done / blocked" signal | ⚠ screen-stability heuristic | ✅ `events.subscribe(pane.agent_status_changed)` | +| Worker self-reports state | ❌ | ✅ `pane.report_agent` (via herdr `SKILL.md`) | +| Multiplex a *herd* of workers + attach/observe | ❌ one server per session | ✅ native workspaces/tabs/panes | +| Persistence / detach-reattach over SSH | ❌ | ✅ headless server | + +The trade `bridged` accepts: **no synchronous call-and-await** — every exchange is async +*return-and-reinvoke* (the same pattern `crush-bridge` uses). For a subscription-safe bridge +that is the correct pattern anyway: a primary that blocks-and-waits either freezes the UI or +busy-polls (quota burn). See **Trade-offs** below. + +## Architecture + +`bridged` is the hub. Its **south side** speaks herdr's Unix-socket JSON-RPC; its **north +side** speaks HTTP/SSE to synchronous clients and (optionally) a broker for async duplex. +herdr, `bridged`, the worker panes, and the model endpoint are colocated on the +off-subscription **worker host**; the primary reaches in over HTTP and/or the broker. + +```mermaid +flowchart TB + subgraph clients["NORTH — clients"] + OPUS["Primary Opus
(Claude Code, env CLEAN)"] + BUS["External event bus
(webhook / NATS / Redis)"] + HUMAN["Human / CLI / chat UI"] + end + + subgraph server["bridged — message server (NOT a claude process)"] + API["API layer
REST + SSE (OpenAPI)"] + SESS["Session manager
spawn · health · recycle"] + INJ["Injector
queue + status gate"] + COLL["Reply collector
envelope | pane.read"] + GUARD["Subscription guard
enforces the boundary"] + HCL["herdr socket client
NDJSON, id-correlated + events"] + API --> SESS --> INJ --> HCL + HCL --> COLL --> API + SESS --> GUARD + HCL -->|"events.subscribe"| INJ + end + + BROKER["Broker (optional)
Redis Streams / NATS JetStream
inbox-primary · inbox-worker"] + HERDR["herdr server
workspaces · panes · agent-status"] + WCC["worker claude pane(s)
ANTHROPIC_BASE_URL set"] + MODEL["ollama.ltms.dev /v1
or GX10 vLLM"] + + OPUS -->|"POST /message · GET /events"| API + BUS -.->|"async"| BROKER + HUMAN --> API + BROKER -.-> API + HCL -->|"Unix socket"| HERDR + HERDR -->|"drives PTY"| WCC + WCC -->|"inference"| MODEL + + classDef core fill:#2f855a,stroke:#22543d,color:#ffffff; + classDef ext fill:#2b6cb0,stroke:#1a365d,color:#ffffff; + classDef warn fill:#b7791f,stroke:#7b341e,color:#ffffff; + class API,SESS,INJ,COLL,GUARD,HCL core + class OPUS ext + class BROKER,HERDR,BUS warn +``` + +*Figure: `bridged` translates a clean north-side message API into herdr socket calls, gating +every injection on live agent-status events. Only the worker panes carry +`ANTHROPIC_BASE_URL`; `bridged` itself is a plain daemon and may poll/subscribe freely +because it consumes no Anthropic quota.* + +### Components + +| Component | Responsibility | +|---|---| +| **herdr socket client** | NDJSON over `~/.config/herdr/herdr.sock`; correlates responses by `id`; maintains a long-lived `events.subscribe` stream. | +| **Session manager** | Maps a logical session → herdr `workspace/tab/pane` id. Spawns the worker `claude` (env-prefixed launch line into a fresh pane's shell), health-checks, and **recycles on context ceiling** (Ralph loop, see below). | +| **Injector** | Per-pane FIFO queue. Delivers `send_text` + `send_keys "enter"` **only when** that pane's `agent_status ∈ {idle, blocked}` — never mid-run. | +| **Reply collector** | Preferred: worker writes a **structured envelope** (broker `XADD` or an HTTP callback to `bridged`). Fallback: `pane.read {source:"recent-unwrapped"}` scrape. | +| **Subscription guard** | Refuses to spawn a *worker* pane without `ANTHROPIC_BASE_URL`; refuses to *ever* set it on a pane designated *primary*; can assert egress host via `pane.process_info`. | +| **API layer** | REST + SSE, OpenAPI schema. Route names kept AgentAPI-shaped so existing clients drop in. | +| **Broker connector** *(optional)* | Bridges `inbox-*` streams ↔ session messages for async, duplex, cross-host traffic. | + +## The herdr control contract (what `bridged` drives) + +Everything `bridged` needs is in herdr's socket API (verified against `herdr.dev/docs/socket-api`): + +```jsonc +// spawn: create a pane, then launch the worker in its shell (env stays worker-only) +{"id":"1","method":"workspace.create","params":{"cwd":"~/work","label":"worker-a"}} +{"id":"2","method":"pane.send_text","params":{"pane_id":"w1:p1", + "text":"ANTHROPIC_BASE_URL=https://ollama.ltms.dev ANTHROPIC_AUTH_TOKEN=… claude"}} +{"id":"3","method":"pane.send_keys","params":{"pane_id":"w1:p1","keys":"enter"}} + +// deliver a turn (gated on status=idle|blocked) +{"id":"4","method":"pane.send_text","params":{"pane_id":"w1:p1","text":""}} +{"id":"5","method":"pane.send_keys","params":{"pane_id":"w1:p1","keys":"enter"}} + +// readiness / completion — push, not polling +{"id":"6","method":"events.subscribe","params":{"subscriptions":[ + {"type":"pane.agent_status_changed","pane_id":"w1:p1"}]}} + +// answer a blocked worker / interrupt +{"id":"7","method":"pane.send_input","params":{"pane_id":"w1:p1","keys":"ctrl+c"}} + +// fallback content read +{"id":"8","method":"pane.read","params":{"pane_id":"w1:p1","source":"recent-unwrapped","lines":200}} +``` + +> **Implementation note (verify in the CLI reference):** herdr's socket may or may not expose +> a direct "spawn command + env" primitive. `bridged` uses the robust path — create pane → +> `send_text` the env-prefixed launch line — which guarantees `ANTHROPIC_BASE_URL` lands in +> the **worker pane's shell only**. If a native spawn call exists, prefer it and pass env +> explicitly; the guard invariant is unchanged. + +## Message flow + +### Synchronous delegation (primary → worker → primary) + +```mermaid +sequenceDiagram + participant P as "Primary (Opus)" + participant S as "bridged" + participant H as "herdr" + participant W as "Worker claude" + + P->>S: "POST /sessions/{id}/message (task, context inlined)" + S->>S: "await pane status = idle" + S->>H: "pane.send_text + send_keys enter" + H->>W: "inject turn" + activate W + H-->>S: "event: agent_status_changed = working" + S-->>P: "SSE: status working" + W-->>H: "produces reply (writes envelope)" + H-->>S: "event: agent_status_changed = done" + deactivate W + S->>S: "collect reply (envelope, or pane.read fallback)" + S-->>P: "SSE: assistant reply" + Note over P: "review diff / result, merge" +``` + +*Figure: `bridged` gates injection on `idle`, streams status transitions over SSE, and +returns the reply from a structured envelope (falling back to a `recent-unwrapped` scrape).* + +### Async duplex via broker (event bus ↔ worker, worker → primary) + +```mermaid +sequenceDiagram + participant BUS as "Event bus / webhook" + participant B as "Broker (Redis/NATS)" + participant S as "bridged" + participant H as "herdr" + participant W as "Worker claude" + + BUS->>B: "XADD inbox-worker (work item)" + S->>B: "consume inbox-worker (group + XACK)" + S->>H: "inject when pane idle" + H->>W: "new turn" + W-->>S: "reply envelope (callback / XADD inbox-primary)" + S->>B: "XADD inbox-primary (result / question)" + Note over S: "primary is woken on its own idle boundary
(Stop-hook long-poll OR bridged inject into primary pane)" +``` + +*Figure: the broker is the durable, cross-host spine; `bridged` is the local actuator that +turns queued messages into herdr injections and back. Content rides the broker as structured +envelopes — herdr scrollback is never the source of truth.* + +## Worker session lifecycle + +`bridged` treats a worker as a **recyclable** resource, not one immortal session — a +long-lived pane fills its context window. When idle-cycle or token caps trip, `bridged` +snapshots state to the filesystem, kills the pane, and respawns fresh (**Ralph loop**). + +```mermaid +stateDiagram-v2 + [*] --> Spawning + Spawning --> Ready: "claude prompt detected" + Ready --> Working: "turn injected" + Working --> Blocked: "permission / question" + Blocked --> Working: "bridged answers (send_input)" + Working --> Ready: "agent_status = done" + Ready --> Recycling: "context / idle cap hit" + Recycling --> Spawning: "state persisted to disk" + Working --> Failed: "pane.exited (crash)" + Failed --> Spawning: "auto-restart + replay unacked" + Ready --> [*]: "drain / shutdown" +``` + +*Figure: the state machine `bridged` drives per worker. `Blocked`, `done`, and `exited` are +real herdr events, not heuristics — the reason herdr-centric beats screen scraping.* + +## Subscription boundary (enforced, not just documented) + +The invariant is unchanged from [[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 + busy-poll the broker and hold a permanent herdr event subscription with no policy concern. +- The **subscription guard** blocks any spawn of a *worker* pane whose launch line lacks + `ANTHROPIC_BASE_URL`, and blocks any attempt to set it on a pane tagged *primary*. +- Injecting keystrokes into the **primary** pane is subscription-safe: it is simulated + typing, identical to the human at the keyboard — the primary still talks to + `api.anthropic.com` on Pro/Max. `bridged` never re-points the primary's endpoint. +- A startup self-check asserts the primary process env has **no** `ANTHROPIC_BASE_URL` and + logs the worker's resolved egress host. + +## API surface (north side) + +Kept intentionally AgentAPI-shaped so existing clients migrate without rewrites: + +| Method + path | Purpose | +|---|---| +| `POST /sessions` | Create a worker session `{model, base_url, cwd, label}` → returns `session_id` | +| `GET /sessions` | List sessions + live `agent_status` | +| `POST /sessions/{id}/message` | Deliver a turn `{content, type:"user"\|"raw"}` (queued, status-gated) | +| `GET /sessions/{id}/events` | **SSE**: `status`, `message`, `blocked`, `exited` | +| `GET /sessions/{id}/messages` | Conversation history | +| `GET /sessions/{id}/status` | `idle` \| `working` \| `blocked` \| `done` | +| `POST /sessions/{id}/keys` | Raw keys passthrough `{keys:"ctrl+c"}` — answer/interrupt | +| `DELETE /sessions/{id}` | Drain + recycle | +| `GET /healthz` · `GET /metrics` | Liveness + Prometheus | + +## Use cases + +1. **Subscription-safe delegation (the core case).** Primary Opus offloads bulk/routine + work — codegen, refactors, test writing, log triage — to a worker on a cheap/local model, + keeping Opus's context clean and its quota for review/merge decisions. +2. **A herd of specialized workers.** One `bridged` + herdr multiplexes several workers + (e.g. a DeepSeek coder, a fast summarizer, a long-context reader), each its own pane, + each addressable by `session_id`. Rolls up to a single status sidebar. +3. **Async event-bus automation.** A webhook/CI/NATS event drops a work item on + `inbox-worker`; `bridged` wakes an idle worker, and the result flows back to the primary + (or a Slack/Telegram bridge) on `inbox-primary` — no human in the loop. +4. **Human co-pilot from anywhere.** Because herdr persists and detaches, the same worker is + reachable from a phone/chat bridge writing to the broker while you're away, and from the + attached TUI when you're back. +5. **Long-running "perpetual" workers.** The Ralph-loop lifecycle lets a worker run for hours + across many context recycles without a human respawning it, state carried on disk. + +## Deployment model + +### Single-host (default — simplest, recommended to start) + +Primary, `bridged`, herdr, and workers all on one off-subscription box. `bridged` can inject +into **both** the primary and the worker panes (both local to one herdr), so the broker is +optional. Best for a workstation or a single dev box. + +### Split-host (primary local, workers remote near the model) + +Primary Opus runs on your Mac; `bridged` + herdr + workers run on the GPU host next to +`ollama.ltms.dev` / GX10 vLLM. herdr's socket is **local-only**, so the two hosts are joined +by the **broker** (or `bridged`'s HTTP), never by a remote herdr socket. + +```mermaid +flowchart LR + subgraph mac["Your Mac (subscription)"] + OPUS["Primary Opus
(Claude Code)"] + end + subgraph host["Worker host (off-subscription, near model)"] + direction TB + BD["bridged
:8080 HTTP/SSE"] + HS["herdr server"] + W2["worker claude pane(s)"] + BD -->|"Unix socket"| HS --> W2 + end + BR["Broker
Redis / NATS"] + ML["ollama.ltms.dev / GX10 vLLM"] + + OPUS -->|"HTTP + SSE (sync)"| BD + OPUS -.->|"async duplex"| BR + BD -.-> BR + W2 --> ML + + classDef ext fill:#2b6cb0,stroke:#1a365d,color:#ffffff; + classDef core fill:#2f855a,stroke:#22543d,color:#ffffff; + classDef warn fill:#b7791f,stroke:#7b341e,color:#ffffff; + class OPUS ext + class BD,HS core + class BR warn +``` + +*Figure: only the broker (or `bridged`'s HTTP) crosses the network; herdr stays local to the +worker host. The subscription boundary tracks the host boundary — nothing on the Mac ever +sets `ANTHROPIC_BASE_URL`.* + +**Security:** bind `bridged`'s HTTP to `localhost` and reach it over an SSH tunnel, or front +it with a bearer token + TLS. Never expose the port unauthenticated — it is an agent-control +surface. (This closes the gap left by AgentAPI's open `:3284`.) + +## Proposed tech stack + +| Layer | Choice | Why | Alternative | +|---|---|---|---| +| **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 | +| **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) | +| **Testing** | **Mock herdr socket** server + golden transcripts | Deterministic CI without a real TTY | Dockerized herdr for e2e | + +**Recommendation: Go.** It gives the smallest operational footprint on the worker host, the +cleanest concurrency story for this exact fan-in shape, and direct code reuse from +`agentapi`. Pick **TypeScript** instead only if `bridged`'s primary *driver* is an Agent-SDK +program and shared types outweigh the deploy simplicity. + +### Interface sketch (Go) + +```go +// herdr socket client — one method, id-correlated; events on a separate stream. +type Herdr interface { + Call(ctx context.Context, method string, params any) (json.RawMessage, error) + Subscribe(ctx context.Context, subs []Sub) (<-chan Event, error) +} + +// Injector: deliver ONLY when the pane is safe to type into. +func (i *Injector) Deliver(ctx context.Context, pane string, text string) error { + if st := i.status[pane]; st != Idle && st != Blocked { + i.queue[pane] = append(i.queue[pane], text) // hold until next idle event + return nil + } + if _, err := i.h.Call(ctx, "pane.send_text", P{"pane_id": pane, "text": text}); err != nil { + return err + } + _, err := i.h.Call(ctx, "pane.send_keys", P{"pane_id": pane, "keys": "enter"}) + return err +} + +// Subscription guard: the boundary, in code. +func (g *Guard) AssertWorker(launch string) error { + if !strings.Contains(launch, "ANTHROPIC_BASE_URL=") { + return fmt.Errorf("refusing to spawn worker without ANTHROPIC_BASE_URL") + } + return nil +} +func (g *Guard) AssertPrimaryClean(env []string) error { + for _, e := range env { + if strings.HasPrefix(e, "ANTHROPIC_BASE_URL=") { + return fmt.Errorf("primary env is tainted — this is the subscription line") + } + } + return nil +} +``` + +## Build plan (milestones) + +| Milestone | Deliverable | Proves | +|---|---|---| +| **M0 — Spike** | herdr client + spawn one worker pane + one `send_text`/`send_keys` round-trip | herdr socket drives a real `claude` | +| **M1 — Status gate** | `events.subscribe` → Injector delivers only on `idle`/`blocked`; SSE status out | No mid-run corruption; real completion signal | +| **M2 — Boundary + lifecycle** | Subscription guard + Ralph-loop recycle + reply envelope | Subscription-safe; survives context ceiling | +| **M3 — Broker + duplex** | Redis Streams connector; worker→primary path; split-host deploy | Async, cross-host, 2-way | +| **M4 — Harden** | Auth/TLS, metrics, mock-socket CI, systemd unit | Production shape | + +## Trade-offs & risks + +| Risk | Mitigation | +|---|---| +| **No synchronous reply** — all exchanges are return-and-reinvoke | Acceptable by design (sync waiting is quota-hostile); mirrors `crush-bridge`. SSE gives near-real-time status without blocking a turn. | +| **herdr is young / single-dev** — betting transport on it | The **durable spine is the broker** (mature); herdr carries only ephemeral delivery + status. The injector is a **pluggable interface** — fall back to `tmux send-keys` or AgentAPI without touching the bus. | +| **herdr socket is local-only** | Broker (or `bridged` HTTP) is the sole cross-host link; herdr stays per-host. | +| **Mid-run interrupt still unsolved** | Same as AgentAPI. Injection gates on status; `ctrl+c` via `pane.send_input` is the only (disruptive) interrupt. | +| **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. | + +## Related pages + +- **[[Architecture]]** — the two-channel model this refines; subscription boundary +- **[[Approaches]]** — transport comparison; AgentAPI now the *fallback injector* +- **[[Home]]** — project overview + +## Sources + +- [herdr — socket API](https://herdr.dev/docs/socket-api/) · [agent guide](https://herdr.dev/agent-guide.md) · [SKILL.md](https://raw.githubusercontent.com/ogulcancelik/herdr/master/SKILL.md) · [GitHub](https://github.com/ogulcancelik/herdr) +- [coder/agentapi](https://github.com/coder/agentapi) — fallback injector; reference for `msgfmt` reply parsing +- [Issue #27441 — inter-agent message injection](https://github.com/anthropics/claude-code/issues/27441) · [#24947 — `claude inject`](https://github.com/anthropics/claude-code/issues/24947) +- [Redis Streams consumer groups](https://redis.io/docs/latest/develop/data-types/streams/) · [NATS JetStream](https://docs.nats.io/nats-concepts/jetstream) + +