Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews.
Go to file
Harshit Singh Bhandari 33a1ee6df9
feat(tracker): ApplyTrackerFacts reducer + shared observer skeleton (#112) (#116)
* refactor(observe): extract shared observer skeleton

Move the observer-pattern-general pieces of the SCM observer into a new
backend/internal/observe package so the tracker observer (issue #35) can
build on the same primitives:

- StartPollLoop: goroutine supervisor with immediate-first-poll + ticker
  + ctx-done exit. SCM Observer.Start now delegates to it.
- CheckCredentialsOnce: lazy first-poll credential gate driven by a
  CredentialProbe closure. SCM observer keeps credentialsChecked/disabled
  as Observer fields; the shared helper mutates them via pointer so
  state ownership stays single-source.
- CacheSet[V any] / CacheDelete[V any]: one generic bounded-FIFO helper
  replaces the three near-identical cacheSet{String,Time,Bool} bodies
  and the standalone evictStrings. The SCM-side methods are now
  one-line wrappers that thread o.Cache.max into the shared helper, so
  existing call sites and tests are untouched.

SCM behavior is unchanged. The full 21-test SCM suite (including the
end-to-end test added in PR #115) plus 577 backend tests stay green
under `go test -race`.

Part of #112.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* feat(tracker): ports.TrackerObservation DTO + ApplyTrackerFacts reducer

Land the contract that the future Tracker observer (issue #35) and its
provider adapters must satisfy. No observer is wired in this PR — the
DTO + reducer are the deliverable, and locking the shape now lets the
observer + adapter work happen in small follow-up PRs.

DTO (backend/internal/ports/tracker_observations.go):
- TrackerObservation mirrors ports.SCMObservation: Fetched bool,
  ObservedAt time.Time, Provider/Host/Repo, normalized Issue facts,
  Comments, and a Changed{State, Assignee, Comments} discriminator.
- TrackerIssueObservation carries the minimal facts lifecycle needs
  today (state, assignee, title, body, timestamps); richer
  per-provider metadata stays inside each adapter.
- TrackerCommentObservation carries the comment fields needed for the
  bot-mention nudge (Author, Body, IsBot, ID for dedup).

Reducer (backend/internal/lifecycle/reactions.go):
- ApplyTrackerFacts(ctx, sessionID, ports.TrackerObservation) error,
  mirroring ApplySCMObservation's "Fetched gate → terminal-state →
  per-bucket reactions" shape.
- Three initial reactions:
    * Issue state == done | cancelled → MarkTerminated (idempotent).
    * Changed.Assignee → log only via slog.Default(). The "assignee
      changed away from AO" policy is reserved for #40.
    * Changed.Comments with bot comments → one-time nudge with
      strings.Join'd bot bodies, deduped by comment IDs.
- The nudge path reuses sendOnce with an empty prURL so the in-memory
  dedup applies but the PR-row persistence path is skipped. Tracker
  signature persistence will land with #35 alongside issue-row storage.

Tests in backend/internal/lifecycle/manager_test.go cover each branch:
terminate (done + cancelled), log-only assignee, nudge fires on new
bot comment, nudge suppressed on repeat, new bot comment id refires,
not-fetched is no-op, terminated session ignores observations.

Part of #112.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix(observe): rename CacheSet param to avoid shadowing built-in max

golangci-lint revive flagged the CacheSet generic helper's max
parameter as shadowing the built-in max() function. Rename to
maxEntries; signature change is internal to the observe package and
the SCM observer's one-line wrappers pass the value positionally, so
no call sites need updating.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* fix: honour disabled state in CheckCredentialsOnce + tighten bot-comment filter

Two P1 review findings on #116:

1. observe.CheckCredentialsOnce was returning (true, nil) on every
   call after the gate ran, even when the probe had marked the
   observer disabled, because the *checked short-circuit ignored
   *disabled. The SCM observer didn't surface this in practice — its
   Poll method has an independent `if o.disabled { return nil }`
   guard that runs first — but a future Tracker observer that relies
   on the helper's documented contract ("Observer stays disabled")
   would silently flip back to "credentials available" after the
   first poll. Change the short-circuit to `return !*disabled, nil`
   and lock the behavior with a regression test that issues repeat
   calls after the probe reported unavailable.

2. lifecycle.newBotCommentContent's "skip uninteresting comments"
   filter used && where it needed ||. A bot comment with an empty ID
   but a non-empty body slipped through and appended "" to the ids
   slice. If every bot comment in the observation had an empty ID,
   strings.Join produced "" — which matches the zero value of the
   in-memory dedup map, so sendOnce treated the nudge as
   already-sent and silently suppressed it forever. Switch to || so
   any comment missing either an ID or a body is dropped, and add a
   regression test that an empty-ID bot comment never nudges (and
   does not pollute the dedup state for a follow-up comment that has
   a real ID).

586 tests pass with -race.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

* test(observe): capture deadline once in poll-error spin-wait

The `TestStartPollLoop_LogsPollErrorWithoutPanic` spin-wait was
computing the loop bound as `time.Now().Before(time.Now().Add(200ms))`
on every iteration, which is permanently true — the loop could only
exit via the `break`. Under a scheduler delay (heavy CI load or
`GOMAXPROCS=1`) where two polls never land in time, the test would
hang until the wall-clock kill rather than failing fast.

Capture the deadline once before the loop, and tighten the assertion
to actually require two polls + done-channel closure within a bounded
window, matching `TestStartPollLoop_FirstPollImmediateThenTicks`.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-07 21:29:00 +05:30
.github/workflows ci(frontend): add react-doctor check for landing site (#151) 2026-06-07 07:11:35 +05:30
backend feat(tracker): ApplyTrackerFacts reducer + shared observer skeleton (#112) (#116) 2026-06-07 21:29:00 +05:30
docs docs: document backend code structure (#41) 2026-06-04 02:32:18 +05:30
frontend fix: 7 bugs from discussion #149 smoke walk (envelope, spawn, CDC, observer) (#153) 2026-06-07 07:35:46 +05:30
test/cli refactor: simplify session lifecycle and zellij runtime (#62) 2026-06-01 08:42:49 +05:30
.envrc Add agent adapters and wire per-session agents into the session manager (#65) 2026-06-02 16:51:32 +05:30
.gitignore Add agent adapters and wire per-session agents into the session manager (#65) 2026-06-02 16:51:32 +05:30
AGENTS.md feat: automate OpenAPI spec + frontend TS type generation (issue #102) (#103) 2026-06-05 14:45:10 +05:30
CLAUDE.md docs: add AGENTS.md (#93) 2026-06-03 04:24:04 +05:30
README.md docs: refresh README to reflect current main (#147) 2026-06-07 01:42:58 +05:30
flake.lock Add agent adapters and wire per-session agents into the session manager (#65) 2026-06-02 16:51:32 +05:30
flake.nix Add agent adapters and wire per-session agents into the session manager (#65) 2026-06-02 16:51:32 +05:30
package-lock.json feat: ao session claim-pr + spawn --claim-pr wiring (#101) 2026-06-06 00:01:03 +05:30
package.json feat: automate OpenAPI spec + frontend TS type generation (issue #102) (#103) 2026-06-05 14:45:10 +05:30

README.md

ReverbCode

A Go-backed agent orchestration daemon for supervising parallel coding-agent
sessions, with an ao CLI today and an Electron supervisor planned. The Go
module and packages remain agent-orchestrator; "ReverbCode" is the public name.

See docs/architecture.md for the backend mental model
and AGENTS.md for the contributor / worker contract.

What's shipped today

  • Loopback-only HTTP daemon (backend/internal/httpd) controlling projects,
    sessions, orchestrators, and hook callbacks over 127.0.0.1.
  • ao Cobra CLI (backend/cmd/ao) — a thin client over the daemon for daemon
    control, project/session/orchestrator management, and worker spawning.
  • Worker/orchestrator spawn into isolated git worktree workspaces, launched
    inside a zellij runtime adapter.
  • Live per-PR observation via the provider-neutral SCM observer
    (backend/internal/observe/scm/): polling loop, ETag guards, semantic
    diffing, CI/check/review-thread tracking, and lifecycle nudges for CI
    failures, review feedback, and merge conflicts.
  • Agent adapters under backend/internal/adapters/agent/: claude-code,
    codex, opencode, grok, cursor, qwen, copilot, kimi, plus
    shared activity-dispatch / hook utilities.
  • SQLite store (backend/internal/storage/sqlite/) with sqlc-generated
    queries, DB-triggered change-data-capture into change_log, and a CDC
    poller/broadcaster (backend/internal/cdc/) feeding in-process subscribers
    and an SSE replay endpoint.
  • Session lifecycle manager + reaper (backend/internal/lifecycle/,
    backend/internal/observe/reaper/): runtime/activity/PR facts reduced into
    the small durable session state, display status derived at read time.

Quick start

Requirements: Go 1.25+, zellij on PATH for the
runtime adapter, and gh (or GITHUB_TOKEN) if you want the SCM observer to
authenticate against GitHub. The SQLite driver is the pure-Go
modernc.org/sqlite — no system SQLite library is required.

cd backend
go build -o /tmp/ao ./cmd/ao

# Start the daemon and wait for /readyz.
/tmp/ao start

# Register a local git repo as a project. The id defaults to the lowercased
# base of --path; pass --id explicitly when the directory name doesn't match.
/tmp/ao project add --path /path/to/your/repo --id your-repo --name your-repo

# Spawn a worker session running the default agent.
/tmp/ao spawn --project your-repo --prompt "Refactor the auth module"

# Inspect what's running.
/tmp/ao status
/tmp/ao session ls

CLI surface

The CLI is intentionally thin: every product command resolves to a daemon HTTP
route. Run ao <command> --help for the authoritative flag shape; the table
below groups what's on main today.

Lane Command Purpose
Daemon ao start Start the daemon in the background and wait for /readyz.
Daemon ao stop Graceful shutdown via loopback POST /shutdown.
Daemon ao status Report PID/port/health/readiness from running.json.
Daemon ao daemon Hidden internal entrypoint used by ao start.
Project ao project add Register a local git repo as a project.
Project ao project ls List registered projects.
Project ao project get <id> Fetch one project.
Project ao project rm <id> Remove a project.
Session ao spawn Spawn a worker session in a registered project.
Session ao session ls List sessions (filter by project, include terminated).
Session ao session get <id> Fetch one session.
Session ao session kill <id> Terminate a session.
Session ao session rename <id> <name> Rename a session.
Session ao session restore <id> Relaunch a terminated session.
Session ao session cleanup Reclaim eligible workspaces for terminated sessions.
Session ao session claim-pr <session> <pr> Attach an existing PR to a session.
Orchestrator ao orchestrator ls List orchestrator sessions.
Messaging ao send Send a message to a running agent session.
Utility ao doctor Local health checks (config, data dir, DB, git, zellij).
Utility ao completion <shell> Generate bash/zsh/fish/powershell completions.
Utility ao version Print build metadata.
Internal ao hooks <agent> <event> Hidden adapter hook callback.

See docs/cli/ for the daemon-control intent and command shape.

Configuration

All configuration is env-driven; the daemon takes no config file. The bind
host is hard-coded to 127.0.0.1 — the daemon has no auth, CORS, or TLS, and
exposing it beyond loopback would be a security regression.

Var Default Purpose
AO_PORT 3001 Bind port; daemon fails fast if taken.
AO_REQUEST_TIMEOUT 60s Per-request timeout (Go duration).
AO_SHUTDOWN_TIMEOUT 10s Graceful-shutdown hard cap.
AO_RUN_FILE <UserConfigDir>/agent-orchestrator/running.json PID + port handshake path.
AO_DATA_DIR <UserConfigDir>/agent-orchestrator/data SQLite DB, WAL files, managed state.
AO_AGENT claude-code Default agent adapter id used by ao spawn.
AO_SESSION_ID (unset) Set inside spawned sessions; read by ao send and ao hooks.
GITHUB_TOKEN (unset) Used by the GitHub SCM and tracker adapters. Falls back to gh auth token.

Health check:

curl localhost:3001/healthz
curl localhost:3001/readyz

Architecture

The daemon is a long-running supervisor. Adapters observe external facts (PR
state, agent activity, runtime liveness); the lifecycle manager reduces those
into a small set of durable session facts (activity_state, is_terminated,
PR rows). Display status is derived from those facts at read time — it is
never stored. SQLite triggers append every user-visible change to change_log,
and the CDC poller broadcasts those events to in-process subscribers and an
SSE stream.

Full mental model and load-bearing rules: docs/architecture.md.
Package-by-package ownership: docs/backend-code-structure.md.

Testing

The local gate is the backend Go build and race-enabled test suite:

cd backend && go build ./... && go test -race ./...

GitHub Actions is the authoritative pre-merge gate; mirror its commands here
when in doubt. See AGENTS.md for the regen workflow when
touching the daemon API surface (npm run sqlc, npm run api).

Status and roadmap

Current main ships the CLI surface above, the SCM observer end-to-end
(issues #75,
#108,
#109), the agent
adapter platform, and the CDC pipeline with SSE replay. The Tracker observer
(#112) and live
pr_* event consumers (#110)
are in flight. The Electron supervisor under frontend/ is still a placeholder
shell — daemon logic stays in the Go backend.

Tracking milestone:
rewrite on GitHub.

Contributing

Repo layout and the worker contract live in AGENTS.md. Keep
changes surgical, follow the package boundaries documented in
docs/backend-code-structure.md, and prefer
adding daemon HTTP routes over leaking storage / runtime into the CLI.