Merge pull request #7 from reoring/chore/drop-compat-layer

chore: drop agentcore compatibility layer

Author: reoring

.gitignore

@@ -5,8 +5,8 @@ dist
 /agentcore
 /roboppi
 
-# Local AgentCore workflow state
-.agentcore-loop/
+# Local Roboppi workflow state
+.roboppi-loop/
 
 # Local scratch notes (do not commit)
 docs/wip/

AGENTS.md

@@ -1,6 +1,6 @@
 # AGENTS.md
 
-This repository ("Roboppi" / package name: `agentcore`) is a Bun + TypeScript (ESM)
+This repository ("Roboppi" / package name: `roboppi`) is a Bun + TypeScript (ESM)
 codebase that implements an execution-control runtime for agentic workers.
 
 ## Build / Lint / Test
@@ -57,11 +57,11 @@ bun test --watch test/unit                                        # watch mode
 
 ### Build
 
-Builds a native executable `./agentcore` (gitignored).
+Builds a native executable `./roboppi` (gitignored).
 
 ```bash
 make build      # or: bun run build
-make install    # /usr/local/bin/agentcore
+make install    # /usr/local/bin/roboppi
 make uninstall
 ```
 

Makefile

@@ -2,7 +2,6 @@
 .PHONY: all build test tests test-unit test-integration test-at test-branch test-all typecheck clean install uninstall dev help
 
 BIN := roboppi
-LEGACY_BIN := agentcore
 
 # Legacy build artifacts (no longer built by default)
 EXTRA_BINS := roboppi-core roboppi-workflow roboppi-daemon
@@ -20,7 +19,6 @@ all: build ## Build the binary (default)
 
 build: ## Build a single binary (roboppi)
 	$(BUN) $(BUN_FLAGS) build $(BUN_BUILD_FLAGS) --compile $(SRC) --outfile $(BIN)
-	@ln -sf $(BIN) $(LEGACY_BIN) 2>/dev/null || cp $(BIN) $(LEGACY_BIN)
 
 test: ## Run all tests
 	$(BUN) $(BUN_FLAGS) test
@@ -46,14 +44,13 @@ typecheck: ## Run TypeScript type checker
 	$(BUN) $(BUN_FLAGS) x tsc --noEmit
 
 clean: ## Remove build artifacts
-	rm -f $(BIN) $(LEGACY_BIN) $(EXTRA_BINS)
+	rm -f $(BIN) $(EXTRA_BINS)
 
 install: build ## Install binary to /usr/local/bin
 	install -m 755 $(BIN) /usr/local/bin/$(BIN)
-	@ln -sf /usr/local/bin/$(BIN) /usr/local/bin/$(LEGACY_BIN) 2>/dev/null || cp /usr/local/bin/$(BIN) /usr/local/bin/$(LEGACY_BIN)
 
 uninstall: ## Remove binary from /usr/local/bin
-	rm -f /usr/local/bin/$(BIN) /usr/local/bin/$(LEGACY_BIN) $(addprefix /usr/local/bin/,$(EXTRA_BINS))
+	rm -f /usr/local/bin/$(BIN) $(addprefix /usr/local/bin/,$(EXTRA_BINS))
 
 dev: ## Run in dev mode (no build)
 	$(BUN) $(BUN_FLAGS) run $(SRC)

README.ja.md

@@ -7,8 +7,7 @@ Roboppi（ろぼっぴ）は、エージェント（worker）の実行を安全
 Roboppi 自身が「エージェントとして仕事をする」ことは目的にしません。外部の worker CLI（OpenCode / Claude Code / Codex CLI / シェル）に重い作業（編集/コマンド/テスト）を委譲し、Roboppi は安全の不変条件（止める/制限する/観測する/隔離する）を強制します。
 
 注意: 主な CLI/バイナリ名は `roboppi` です。
-- 互換: `agentcore` はレガシー alias として残しています。
-- 環境変数/状態ディレクトリ: `ROBOPPI_` / `.roboppi-loop/` を推奨（レガシーの `AGENTCORE_` / `.agentcore-loop/` も引き続き利用可能）。
+- 環境変数/状態ディレクトリ: `ROBOPPI_` / `.roboppi-loop/` を使います。
 
 ## Roboppiでできること（Capabilities）
 
@@ -184,7 +183,7 @@ ROBOPPI_ROOT="$ROBOPPI_ROOT" bun run --cwd "$ROBOPPI_ROOT" src/workflow/run.ts \
 
 注意:
 
-- workflow は target workspace 内に `.roboppi-loop/` と `context/` を作ります（通常は gitignore 推奨。レガシーの `.agentcore-loop/` も引き続き利用可能）。
+- workflow は target workspace 内に `.roboppi-loop/` と `context/` を作ります（通常は gitignore 推奨）。
 - PR 作成は `.roboppi-loop/enable_pr` による opt-in です。
 
 ## Workflow YAML の最小例
@@ -264,9 +263,9 @@ git repo に対する workflow 実行向けに、base branch 解決 / Branch Loc
 supervised 実行では runner/daemon が Core 子プロセスを起動し、IPC 経由で step を委譲します。
 
 - 既定: 対話実行は stdio、非対話実行は socket transport が既定
-- transport 切替: `AGENTCORE_SUPERVISED_IPC_TRANSPORT=stdio|socket|tcp`
-- IPC デバッグ: `AGENTCORE_IPC_TRACE=1`
-- request timeout 調整: `AGENTCORE_IPC_REQUEST_TIMEOUT=2m`（または `AGENTCORE_IPC_REQUEST_TIMEOUT_MS=120000`）
+- transport 切替: `ROBOPPI_SUPERVISED_IPC_TRANSPORT=stdio|socket|tcp`
+- IPC デバッグ: `ROBOPPI_IPC_TRACE=1`
+- request timeout 調整: `ROBOPPI_IPC_REQUEST_TIMEOUT=2m`（または `ROBOPPI_IPC_REQUEST_TIMEOUT_MS=120000`）
 
 supervised 実行を無効化（direct 実行）:
 

README.md

@@ -11,8 +11,7 @@ Roboppi (ろぼっぴ, pronounced "roh-boh-pee") is an execution-control runtime
 It does not try to be "the agent". It enforces safety invariants around external worker CLIs (OpenCode / Claude Code / Codex CLI / plain shell), so your automation stops when it should, stays within budgets, and leaves a trail you can audit.
 
 Note: the primary CLI/binary name is `roboppi`.
-- Compatibility: `agentcore` remains as a legacy alias.
-- Env vars/state dirs: prefer `ROBOPPI_` / `.roboppi-loop/` (legacy `AGENTCORE_` / `.agentcore-loop/` are still accepted).
+- Env vars/state dirs: use `ROBOPPI_` / `.roboppi-loop/`.
 
 ## What Roboppi Can Do (Capabilities)
 
@@ -191,7 +190,7 @@ ROBOPPI_ROOT="$ROBOPPI_ROOT" bun run --cwd "$ROBOPPI_ROOT" src/workflow/run.ts \
 
 Notes:
 
-- The workflow writes state/artifacts under `.roboppi-loop/` and `context/` inside the target workspace (typically gitignored; legacy `.agentcore-loop/` is still accepted).
+- The workflow writes state/artifacts under `.roboppi-loop/` and `context/` inside the target workspace (typically gitignored).
 - PR creation is opt-in via `.roboppi-loop/enable_pr`.
 
 ## Workflow YAML At A Glance
@@ -273,9 +272,9 @@ Docs:
 Workflows/daemon run supervised by default. In supervised mode, the runner starts a Core child process and delegates steps over IPC.
 
 - Default: interactive runs typically use stdio; non-interactive runs default to a socket transport.
-- Override transport: `AGENTCORE_SUPERVISED_IPC_TRANSPORT=stdio|socket|tcp`
-- Debug IPC: `AGENTCORE_IPC_TRACE=1`
-- Tune request timeouts: `AGENTCORE_IPC_REQUEST_TIMEOUT=2m` (or `AGENTCORE_IPC_REQUEST_TIMEOUT_MS=120000`)
+- Override transport: `ROBOPPI_SUPERVISED_IPC_TRANSPORT=stdio|socket|tcp`
+- Debug IPC: `ROBOPPI_IPC_TRACE=1`
+- Tune request timeouts: `ROBOPPI_IPC_REQUEST_TIMEOUT=2m` (or `ROBOPPI_IPC_REQUEST_TIMEOUT_MS=120000`)
 
 Disable supervised mode:
 

bun.lock

@@ -820,23 +820,23 @@ Template variables available in `evaluate` / `analyze` instructions:
 
 ```bash
 # start daemon
-agentcore daemon start <daemon.yaml> [--verbose]
+roboppi daemon start <daemon.yaml> [--verbose]
 
 # check daemon status (from another terminal)
-agentcore daemon status [--state-dir <dir>]
+roboppi daemon status [--state-dir <dir>]
 
 # manual trigger (debug)
-agentcore daemon trigger <trigger_id> [--state-dir <dir>]
+roboppi daemon trigger <trigger_id> [--state-dir <dir>]
 
 # pause/resume trigger
-agentcore daemon pause <trigger_id>
-agentcore daemon resume <trigger_id>
+roboppi daemon pause <trigger_id>
+roboppi daemon resume <trigger_id>
 
 # show execution history
-agentcore daemon history [--trigger <trigger_id>] [--limit 10]
+roboppi daemon history [--trigger <trigger_id>] [--limit 10]
 
 # stop daemon
-agentcore daemon stop [--state-dir <dir>]
+roboppi daemon stop [--state-dir <dir>]
 ```
 
 ---
@@ -945,7 +945,7 @@ Log tags:
 - [ ] TriggerEngine (filter + debounce + cooldown)
 - [ ] DaemonStateStore (file-based persistence)
 - [ ] Daemon class (event loop + graceful shutdown)
-- [ ] CLI: `agentcore daemon start`
+- [ ] CLI: `roboppi daemon start`
 
 ### Phase 2: Expand event sources
 

docs/daemon-design.md

@@ -121,19 +121,19 @@ Workers provide execution environments and capabilities. AgentCore calls them th
 ```
 Scheduler (parent)
   |
-  +-- spawn(agentcore, args...)
+  +-- spawn(roboppi, args...)
   +-- JSON Lines IPC over stdin/stdout
   +-- periodic heartbeat/health monitoring
   |
-  +-> AgentCore (child)
+  +-> Roboppi Core (child)
        +-- processes externally submitted jobs
        +-- issues permits and delegates to workers
        +-- observes, limits, cuts off, escalates
 ```
 
-The Scheduler spawns AgentCore as a child process, keeps stdin/stdout open, and uses **JSON Lines** for bidirectional communication. It monitors response latency via heartbeat and checks memory/CPU thresholds periodically.
+The Scheduler spawns Roboppi Core as a child process, keeps stdin/stdout open, and uses **JSON Lines** for bidirectional communication. It monitors response latency via heartbeat and checks memory/CPU thresholds periodically.
 
-AgentCore behaves as a runtime that processes "jobs given from outside", issues Permits, and spawns/uses workers as needed.
+Roboppi Core behaves as a runtime that processes "jobs given from outside", issues Permits, and spawns/uses workers as needed.
 
 ### 3.2 Crash / hang handling (Supervisor policy)
 

docs/design.md

@@ -133,9 +133,9 @@ triggers:                           # trigger definitions (event -> workflow)
 If your workflows use `step.agent`, provide an agent catalog to the daemon:
 
 - `agents_file`: a default catalog path for the daemon (relative paths are resolved from `workspace`)
-- `AGENTCORE_AGENTS_FILE`: you can also set this via environment variables (or per-trigger via `triggers.<id>.context.env`) as a colon-separated list of YAML paths
+- `ROBOPPI_AGENTS_FILE`: you can also set this via environment variables (or per-trigger via `triggers.<id>.context.env`) as a colon-separated list of YAML paths
 
-When multiple catalogs are provided, later sources override earlier ones (so a per-trigger `context.env.AGENTCORE_AGENTS_FILE` can override the daemon-wide catalog).
+When multiple catalogs are provided, later sources override earlier ones (so a per-trigger `context.env.ROBOPPI_AGENTS_FILE` can override the daemon-wide catalog).
 
 See also: `docs/guides/agents.md`.
 
@@ -703,8 +703,8 @@ name: simple-cron
 version: "1"
 description: "A simple daemon that runs health checks every 30 seconds"
 
-workspace: "/tmp/agentcore-daemon-simple"
-state_dir: "/tmp/agentcore-daemon-simple/.daemon-state"
+workspace: "/tmp/roboppi-daemon-simple"
+state_dir: "/tmp/roboppi-daemon-simple/.daemon-state"
 
 events:
   tick:
@@ -734,8 +734,8 @@ Fires every 5 minutes via cron. An evaluate gate checks whether there are new co
 ```yaml
 name: smart-reviewer
 version: "1"
-workspace: "/tmp/agentcore-daemon-reviewer"
-state_dir: "/tmp/agentcore-daemon-reviewer/.daemon-state"
+workspace: "/tmp/roboppi-daemon-reviewer"
+state_dir: "/tmp/roboppi-daemon-reviewer/.daemon-state"
 max_concurrent_workflows: 1
 
 events:
@@ -800,8 +800,8 @@ Detect TypeScript file changes and run tests automatically.
 ```yaml
 name: file-watcher
 version: "1"
-workspace: "/tmp/agentcore-daemon-watcher"
-state_dir: "/tmp/agentcore-daemon-watcher/.daemon-state"
+workspace: "/tmp/roboppi-daemon-watcher"
+state_dir: "/tmp/roboppi-daemon-watcher/.daemon-state"
 
 events:
   src-change:
@@ -838,8 +838,8 @@ Use interval, cron, and command event sources together and start different workf
 ```yaml
 name: multi-trigger
 version: "1"
-workspace: "/tmp/agentcore-daemon-multi"
-state_dir: "/tmp/agentcore-daemon-multi/.daemon-state"
+workspace: "/tmp/roboppi-daemon-multi"
+state_dir: "/tmp/roboppi-daemon-multi/.daemon-state"
 max_concurrent_workflows: 2
 
 events:

docs/guide/daemon.md

@@ -1,6 +1,6 @@
-# AgentCore Quickstart
+# Roboppi Quickstart
 
-AgentCore is an execution-control runtime for AI agent systems. It provides safe execution control via Permits, failure cut-off via Circuit Breakers, and delegation of actual work to external Workers.
+Roboppi is an execution-control runtime for AI agent systems. It provides safe execution control via Permits, failure cut-off via Circuit Breakers, and delegation of actual work to external Workers.
 
 ## Prerequisites
 
@@ -19,22 +19,22 @@ Optional (if you plan to use them as workers):
 ## Install
 
 ```bash
-git clone <repository-url> agentcore
-cd agentcore
+git clone <repository-url> roboppi
+cd roboppi
 bun install
 ```
 
 ## Build
 
 ```bash
-make            # build a single binary -> ./roboppi (+ ./agentcore alias)
+make            # build a single binary -> ./roboppi
 ```
 
 Sanity check:
 
 ```bash
-./agentcore --version
-./agentcore --help
+./roboppi --version
+./roboppi --help
 ```
 
 Other make targets:
@@ -48,23 +48,23 @@ make install    # install to /usr/local/bin
 
 ---
 
-## Usage 1: One-shot execution with `agentcore run`
+## Usage 1: One-shot execution with `roboppi run`
 
 Use the `run` subcommand to delegate a task to a Worker using only CLI flags.
 
 ```bash
 # Generate files with OpenCode
-./agentcore run --worker opencode --workspace /tmp/demo "Create hello.ts"
+./roboppi run --worker opencode --workspace /tmp/demo "Create hello.ts"
 
 # Fix tests with Claude Code
-./agentcore run --worker claude-code --workspace ./my-project \
+./roboppi run --worker claude-code --workspace ./my-project \
   --capabilities EDIT,RUN_TESTS "Fix the failing tests"
 
 # Refactor with Codex CLI
-./agentcore run --worker codex --workspace ./src "Refactor this function"
+./roboppi run --worker codex --workspace ./src "Refactor this function"
 
 # You can also set timeouts and budgets
-./agentcore run --worker opencode --workspace /tmp/demo \
+./roboppi run --worker opencode --workspace /tmp/demo \
   --timeout 60000 --concurrency 5 "Write a README for this repo"
 ```
 
@@ -77,20 +77,20 @@ Use the `run` subcommand to delegate a task to a Worker using only CLI flags.
 | `--capabilities <csv>` | `READ,EDIT,RUN_TESTS,RUN_COMMANDS` | `EDIT` |
 | `--timeout <ms>` | task timeout | `120000` |
 
-Internally, AgentCore checks PermitGate -> CircuitBreaker -> ExecutionBudget before delegating to the worker.
+Internally, Roboppi checks PermitGate -> CircuitBreaker -> ExecutionBudget before delegating to the worker.
 
 ---
 
 ## Usage 2: IPC server mode
 
-If you run `agentcore` with no subcommand, it starts in IPC server mode. A Scheduler or custom driver can talk to it over JSON Lines.
+If you run `roboppi` with no subcommand, it starts in IPC server mode. A Scheduler or custom driver can talk to it over JSON Lines.
 
 ```bash
 # Start with defaults
-./agentcore
+./roboppi
 
 # Start with custom settings
-./agentcore --concurrency 20 --rps 100 --log-level debug
+./roboppi --concurrency 20 --rps 100 --log-level debug
 ```
 
 Shared options (also available in `run` mode):
@@ -111,7 +111,7 @@ Shared options (also available in `run` mode):
 ### Example: submit a job via JSON Lines
 
 ```bash
-echo '{"type":"submit_job","requestId":"req-1","job":{"jobId":"job-001","type":"LLM","priority":{"value":1,"class":"INTERACTIVE"},"payload":{"prompt":"hello"},"limits":{"timeoutMs":5000,"maxAttempts":3},"context":{"traceId":"t-1","correlationId":"c-1"}}}' | ./agentcore 2>/dev/null
+echo '{"type":"submit_job","requestId":"req-1","job":{"jobId":"job-001","type":"LLM","priority":{"value":1,"class":"INTERACTIVE"},"payload":{"prompt":"hello"},"limits":{"timeoutMs":5000,"maxAttempts":3},"context":{"traceId":"t-1","correlationId":"c-1"}}}' | ./roboppi 2>/dev/null
 ```
 
 Output (returned on stdout as JSON Lines):
@@ -330,7 +330,7 @@ OpenCode generates files and the result returns `SUCCEEDED`.
 
 ## Usage 5: Start with a Scheduler (full configuration)
 
-The Scheduler launches and supervises AgentCore as a child process. This includes a job queue, dedup control, retries, and a DLQ.
+The Scheduler launches and supervises Roboppi Core as a child process. This includes a job queue, dedup control, retries, and a DLQ.
 
 ```typescript
 import { Scheduler } from "./src/scheduler/index.js";
@@ -342,7 +342,7 @@ const scheduler = new Scheduler({
   retry: { baseDelayMs: 1000, maxDelayMs: 30000, maxAttempts: 3 },
 });
 
-// Start AgentCore as a child process
+// Start Roboppi Core as a child process
 await scheduler.start();
 
 // Submit a job
@@ -401,7 +401,7 @@ roboppi workflow my-workflow.yaml --verbose
 # (dev) bun run src/workflow/run.ts my-workflow.yaml --verbose
 ```
 
-For each step, AgentCore requests a Permit, delegates to the worker, and collects results. If a step fails, it aborts depending on policy.
+For each step, Roboppi Core requests a Permit, delegates to the worker, and collects results. If a step fails, it aborts depending on policy.
 
 ### Reuse worker settings with agent catalogs
 
@@ -481,7 +481,7 @@ See the [Daemon guide](./daemon.md) for details.
 | Scheduler (parent process)                    |
 | JobQueue / InFlightRegistry / RetryPolicy     |
 |  +-----------------------------------------+  |
-|  | AgentCore (child process)               |  |
+|  | Roboppi Core (child process)            |  |
 |  | PermitGate / CircuitBreaker             |  |
 |  | Watchdog / EscalationManager            |  |
 |  |  +-----------------------------------+  |  |