Files
fleetd/docs/CB-402-OpenCode-Adapter.md
Dai Ha 76e4b577a0
CI / build (pull_request) Successful in 1m6s
CI / contract (pull_request) Successful in 1m6s
CB-622: rename bridge_* tool names to fleet_* in Markdown docs
Rename the eleven MCP tool names (bridge_ack/ask/list/poll/profiles/reply/
send/spawn/status/stop/whoami) to their fleet_* names across the Markdown
documentation. fleet_* is written as the normal name; one deprecation note
in README.md says bridge_* still works for one release.

docs/MCP-Contract.md is renamed only inside section 6 (lines 210-293):
sections 1-5 and 7-11 are stale pre-build design text (CB-609) and are
deliberately left with old names so dead text does not look maintained.

Also renames e2e/bridge_ask_transcript.md to e2e/fleet_ask_transcript.md
to match its content. CLAUDE.md, wiki/, plugin/skills/setup/SKILL.md and
.claude/skills/port-to-opencode/SKILL.md are owned by other units and are
untouched.
2026-08-22 21:52:24 +02:00

16 KiB

CB-402 — Second peer adapter: opencode (Stage B of the Peer Launcher SPI)

Status: ✅ complete — implemented, merged (ded226a), and live-dogfooded 2026-07-29. All five increments of §4 are done, including increment 5 (the §5 live checklist). See §8 As-built for the run. Gitea issue #7 closed. Depends on: CB-401 Stage A (PeerLauncher SPI, merged 3aa69a9) Stage: 4 (Pluggable peers) · Stage B Owner action: design-note → file issue → delegate → primary-verify (per CB-401/306/307)


1. Goal

Prove the PeerLauncher SPI actually holds for a non-Claude coding agent by shipping a second, first-class in-tree adapter: opencode (opencode 1.1.31, a provider-agnostic terminal coding agent).

The product direction is heterogeneous coding agents, Claude Code first-class — not a human/mock peer. opencode is the right proof precisely because it differs from Claude Code on every seam the SPI is meant to hide:

Seam Claude Code opencode ⇒ SPI proof
Subscription boundary ANTHROPIC_BASE_URL + SubscriptionGuard.assertWorker() before any herdr call none — provider-agnostic, off-subscription by nature the guard is Claude-private, not core
MCP mount inline --mcp-config '{…}' launch flag opencode mcp add / config file (OPENCODE_CONFIG) — no inline flag "mount the bridge MCP" is adapter-private
Instruction injection --append-system-prompt "<REPLY_CHARTER>" config instructions / AGENTS.md / --agent — no append flag the reply-charter mount is adapter-private
Model selection ANTHROPIC_MODEL env -m provider/model flag env-vs-flag is adapter-private
Name / reap scheme claude-<profile>-<nonce>-<seq> opencode-<profile>-<nonce>-<seq> each adapter reaps only its own kind

Everything else — herdr tab/pane placement, the CB-306 spawn-readiness gate, CB-301-ext worktree provisioning, CB-117 orphan reap, teardown, list(), cwd resolution — is transport machinery that is identical for both. That split is the whole design.

Out of scope (deferred to Stage C / later): dynamic external plugin loading behind a trust/capability model, capability enforcement at the verb layer (Stage A only declares caps), and a human/mock peer.


2. Current state — one launcher, two concerns mixed

ClaudeCodeLauncher (584 LOC) is the sole PeerLauncher. It interleaves two concerns:

flowchart TB
    subgraph CCL["ClaudeCodeLauncher (584 LOC) — today"]
        direction TB
        T["herdr transport (GENERIC / reusable)<br/>tab-pane placement · spawn-ready gate · worktree<br/>orphan reap · teardown · list · cwd resolution · unique naming"]
        C["Claude-specific (per-agent)<br/>ANTHROPIC_BASE_URL + SubscriptionGuard · ANTHROPIC_MODEL<br/>argv --mcp-config · --append-system-prompt REPLY_CHARTER · 'claude-' name prefix"]
    end
    classDef generic fill:#2f855a,stroke:#22543d,color:#ffffff;
    classDef specific fill:#b7791f,stroke:#7b341e,color:#ffffff;
    class T generic
    class C specific

Figure 1 — the two concerns tangled inside today's single launcher; CB-402 splits them.

There is also a Stage-A deferral to finish: Bridged.main still casts (ClaudeCodeLauncher) workers at the BridgeMcp and BridgedApp constructors. Those two callers only invoke profiles(), defaultProfile(), and list() — all already on the PeerLauncher interface. The cast survives for one reason only: PeerLauncher.list() returns List<?> (element type erased) while the callers use Agent element methods in their roster join. Finishing the migration is therefore small and contained (§4.D).


3. Target design

Template-Method base + two thin adapters + a routing composite that keeps the Stage-A seam (one PeerLauncher reference held by SessionManager / BridgeMcp / BridgedApp) intact.

flowchart TB
    IFACE["«interface»<br/>PeerLauncher"]
    COMP["CompositePeerLauncher<br/>routes by profile kind; fans out list/reap/caps"]
    BASE["«abstract»<br/>HerdrPeerLauncher<br/>transport: placement · ready-gate · reap · stop · cwd · naming"]
    CCL2["ClaudeCodeLauncher<br/>hooks: guard+ANTHROPIC_* env · --mcp-config · charter flag · prefix 'claude'"]
    OCL["OpenCodeLauncher<br/>hooks: provider env · OPENCODE_CONFIG file · AGENTS charter · prefix 'opencode'"]

    IFACE -.implemented by.-> COMP
    IFACE -.implemented by.-> BASE
    BASE --> CCL2
    BASE --> OCL
    COMP -->|"kind=claude-code"| CCL2
    COMP -->|"kind=opencode"| OCL

    classDef iface fill:#2b6cb0,stroke:#1a365d,color:#ffffff;
    classDef base fill:#2f855a,stroke:#22543d,color:#ffffff;
    classDef leaf fill:#6b46c1,stroke:#44337a,color:#ffffff;
    class IFACE,COMP iface
    class BASE base
    class CCL2,OCL leaf

Figure 2 — extracted base, two adapters, and a routing composite behind the unchanged SPI.

A. Extract HerdrPeerLauncher (abstract base)

Move all transport machinery down from ClaudeCodeLauncher. What stays generic:

  • fields agents, spaces, profiles, defaultProfile, env, nameSeq, the CB-306 gate knobs (spawnReadyTimeoutMs/spawnReadyPollMs/nowMillis/sleeper), and nameNonce;
  • profiles(), defaultProfile(), parityOverlay(), effectiveCwd(…), resolveCwd;
  • the spawn(SpawnRequest) skeleton: resolve profile → cfg → hook → placement → gate → WorkerHandle;
  • spawnInTab / spawnAsPane / tidy / startUniquelyNamed (name built from a hook prefix);
  • list(), reapOrphanWorkers() / isForeignWorker / workerNonce (pattern built from the prefix hook), stop() / usesTabPlacement / isAlreadyGone;
  • waitUntilInjectableOrThrow, the WorkerHandle record, putIfPresent, resolveEnv, sleepUninterruptibly.

Two adapter hooks (abstract):

/** Label prefix for this peer kind; drives unique naming AND the orphan-reap pattern. */
protected abstract String namePrefix();               // "claude" | "opencode"

/** Build the peer-specific launch: env map + argv. Runs any pre-spawn guard here. */
protected abstract Launch buildLaunch(BridgedConfig.Worker cfg, SpawnRequest req);
record Launch(Map<String,String> env, List<String> argv) {}

capabilities() stays abstract/per-adapter (it already is). The subscription guard is not a base field — it is a constructor dependency of ClaudeCodeLauncher alone.

Reap isolation: the reap pattern becomes Pattern.compile(namePrefix() + "-.*-([0-9a-f]{6})-\\d+"), so the opencode adapter never reaps a claude-* pane and vice-versa. The composite sums both.

B. kind: config discriminator

Add one field to BridgedConfig.Worker:

String kind          // "claude-code" (default) | "opencode"
  • Compact-ctor default: kind = blank ? "claude-code" : kind.toLowerCase().
  • argv default is currently List.of("claude"); when kind=opencode and the operator left argv unset, default it to List.of("opencode"). (Handle in normalization, keyed off kind, so the record stays declarative.)
  • Keep the existing back-compat constructors; kind is additive and optional.

bridged.example.yaml documents a two-kind workers: block.

C. OpenCodeLauncher — the adapter hooks for opencode

namePrefix() → "opencode". buildLaunch(cfg, req):

  • Env: no ANTHROPIC_BASE_URL, no SubscriptionGuard call. Pass through provider credentials the operator names (reuse the existing tokenEnv indirection; opencode reads provider keys from env / opencode auth). CB-302 git-token injection is reused unchanged (it is peer-neutral: GITEA_TOKEN/GITEA_HOST).
  • MCP mount (non-invasive): opencode has no inline --mcp-config. The adapter writes a throwaway config file and points OPENCODE_CONFIG=<tempfile> in the worker env, containing the bridge MCP server block (opencode HTTP MCP schema, type: "remote") — the opencode analog of Claude Code's inline flag. Nothing is written into the worker's real project or profile.
  • Reply-charter: carry REPLY_CHARTER as an instructions entry in that same generated config (or an AGENTS.md written into the per-worker worktree, which is already a throwaway isolated checkout under CB-301-ext). Recommend the config-file route to keep the "touch nothing the user owns" invariant.
  • argv: opencode <project-or-cwd> (interactive TUI, the mode a herdr pane drives), plus -m <provider/model> when the profile sets a model.

REPLY_CHARTER is peer-neutral text — hoist it to a shared constant (base or a small PeerCharter), consumed by each adapter through its own injection mechanism.

D. CompositePeerLauncher + finish the Stage-A migration

  • Bridged.main groups configured profiles by kind, instantiates one launcher per kind present, and wraps them in CompositePeerLauncher implements PeerLauncher.
  • Routing methods (spawn(req), effectiveCwd(req), parityOverlay(name)) dispatch by the profile's kind. Fan-out methods (list(), reapOrphanWorkers(), capabilities(), profiles(), defaultProfile()) merge across sub-launchers. stop(id) tries each (teardown only knows the pane id) — already best-effort/idempotent.
  • Migrate BridgeMcp + BridgedApp to the PeerLauncher interface, dropping both (ClaudeCodeLauncher) casts. Only friction is list()'s List<?>; resolve by giving the SPI a typed roster element (small neutral PeerAgent view exposing id()/name()/status) that the CB-304 roster join consumes — or, minimally, narrow at the callsite. Prefer the typed view.
sequenceDiagram
    autonumber
    participant P as Primary
    participant M as BridgeMcp / REST
    participant C as CompositePeerLauncher
    participant O as OpenCodeLauncher
    participant B as HerdrPeerLauncher (base)
    participant H as herdr
    P->>M: fleet_spawn(profile="oc-impl")
    M->>C: spawn(SpawnRequest)
    C->>C: kind(profile)=="opencode"
    C->>O: spawn(req)
    O->>O: buildLaunch → provider env + OPENCODE_CONFIG file + argv
    O->>B: placement + startUniquelyNamed("opencode-…")
    B->>H: agent.start(name, argv, env, tab, cwd)
    B->>H: poll status until injectable (CB-306 gate)
    B-->>O: Agent
    O-->>C: PeerHandle(paneId, terminalId)
    C-->>M: PeerHandle
    M-->>P: session id

Figure 3 — an opencode spawn: composite routes by kind, adapter builds the peer-specific launch, shared base drives herdr + the readiness gate.


4. Increment plan (delegate-then-verify friendly)

  1. Extract base, no behaviour change. Introduce HerdrPeerLauncher; make ClaudeCodeLauncher extend it with namePrefix()="claude" and buildLaunch() wrapping today's guard+env+argv logic. Green build, identical tests — pure refactor. (IDE refactor where possible; the primary re-runs the gate workers can't.)
  2. kind: discriminator. Add the field + normalization + bridged.example.yaml. Default path unchanged (kind=claude-code).
  3. OpenCodeLauncher. Implement the three hooks; unit-test buildLaunch (env has no ANTHROPIC_BASE_URL; OPENCODE_CONFIG points at a file carrying the bridge MCP block + charter; argv shape).
  4. CompositePeerLauncher + wiring + finish Stage-A migration (drop the two casts).
  5. Live dogfood (§5) + wiki as-built (primary-gated submodule commit).

Each increment is independently buildable/mergeable; the feature branch stays unmerged until it is "major" (Stage-B whole), per the CB-401 bar.


5. Risks & validation (live dogfood, not assumed)

  • opencode TUI ⇄ herdr injection. herdr drives a pane by typing into a TUI. Must confirm opencode's TUI accepts injected keystrokes/submit the way claude does, and reaches an injectable status the CB-306 gate recognizes. Validation: spawn one opencode worker, watch the readiness gate pass, fleet_send a trivial task.
  • Bridge MCP visibility in opencode. Confirm OPENCODE_CONFIG (or opencode mcp add) actually surfaces the fleet_* tools inside the opencode session, and that fleet_reply is callable — the reply-charter is worthless if the tool isn't mounted. Validation: the worker completes a task by calling fleet_reply; the reply lands via the CB-307 path.
  • opencode MCP/config schema drift. opencode is fast-moving (1.1.31 today). Pin the config schema we generate against the installed version; treat the exact keys (type: "remote" vs "http", instructions shape) as a dogfood-verified fact, not an assumption.
  • Provider credentials. opencode needs a configured provider (env key or opencode auth). The dogfood profile must name a provider the host actually has, distinct from the primary's subscription.

6. Test plan

  • Unit (hermetic): base-extraction regression (existing ClaudeCodeLauncher tests pass unchanged); OpenCodeLauncher.buildLaunch env/argv/config assertions; kind normalization in BridgedConfigTest; CompositePeerLauncher routing + fan-out (merge of profiles(), summed reapOrphanWorkers(), per-kind reap isolation) with fake sub-launchers.
  • Live (dogfood, manual): the §5 checklist on the running daemon.
  • Gate (primary): IDE diagnostics 0/0 on every changed file, mvn clean install green with the surefire summary captured (not | tail), manual diff review — the authoritative checks a worker cannot self-run.

7. Open questions for the lead

  1. ✅ Provider — resolved 2026-07-29. None was needed. opencode's own gateway serves free-tier models with zero credentials (opencode auth list → 0 credentials, yet opencode run -m opencode/north-mini-code-free answers). The dogfood profile uses opencode/north-mini-code-free. It is distinct from the primary's Anthropic subscription by construction, and needs no guard entry — opencode carries no ANTHROPIC_BASE_URL, so the SubscriptionGuard does not apply to it at all.
  2. ✅ Charter carrier — confirmed as designed: generated OPENCODE_CONFIG instructions. Verified working against the installed version.
  3. ✅ Merge cadence — resolved as it happened: Stage B landed as one unit (ded226a).

8. As-built — live dogfood (2026-07-29)

Run against bridged on 127.0.0.1:8766 at main 19cdf8d, with opencode 1.18.5 installed via Homebrew. Every §5 risk is now a verified fact rather than an assumption.

The version-drift risk was the real one, and it did not bite. This adapter was designed against opencode 1.1.31; the installed version is 1.18.5. The generated config schema still validates unchanged — mcp.<name>.type: "remote", url, enabled, and instructions: [path] are all accepted, and OPENCODE_CONFIG=… opencode mcp list reports ✓ bridge connected. Pinned here as a dogfood-verified fact for 1.18.5.

§5 risk Result
opencode TUI ⇄ herdr injection; CB-306 gate ✅ peer pane=wD:p3 reached injectable state ~0.6s after agent.start
Bridge MCP visible + fleet_reply callable ✅ MCP initialize from Implementation[name=opencode, version=1.18.5]; worker replied through the tool
Config schema drift (1.1.31 → 1.18.5) ✅ unchanged, see above
Provider credentials ✅ free tier, zero credentials

Full lifecycle exercised through the REST surface:

  1. POST /workers?profile=opencode-free → 201, routed by kind: through CompositePeerLauncher to OpenCodeLauncher (spawning opencode profile=opencode-free), pane wD:p3.
  2. Readiness: {"ready":true,"status":"idle"}, roster state ready.
  3. POST /sessions/{id}/message → {"replySource":"reply","reply":"391"} — a structured fleet_reply, not the CB-115 completion-fallback transcript scrape. The clean path.
  4. DELETE /workers/wD:p3 → 204, roster empty, tolerant teardown (tab_not_found ignored — opencode had already closed its own tab).

Unplanned cross-validation with CB-501. The audit trail recorded the worker's reply as role: WORKER, actor: worker:term_657c1dad2b9731e, action: REPLY, outcome: allowed. Connection-based identity (loopback peer PID → herdr pane) classified an opencode process as a worker with no opencode-specific handling — confirming the identity model is peer-kind-agnostic, which is exactly what CB-308 needs when it stretches the roster across hosts.

CB-502 counters for the same run: bridged_sends_total{outcome="replied"} 1, bridged_replies_total{path="rendezvous"} 1, bridged_inbox_depth{...} 0.