feat(runner): unify plugin execution across agents and event processors

skills/skills/.env

@@ -37,10 +37,10 @@ LANGBOT_NO_PROXY=localhost,127.0.0.1,::1
 # LANGBOT_PIPELINE_NAME=Generic QA Pipeline
 # LANGBOT_LOCAL_AGENT_PIPELINE_URL=http://127.0.0.1:3000/home/pipelines?id=<local-agent-pipeline-uuid>
 # LANGBOT_LOCAL_AGENT_PIPELINE_NAME=Local Agent QA Pipeline
-# LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL=http://127.0.0.1:3000/home/pipelines?id=<acp-agent-runner-pipeline-uuid>
-# LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME=ACP AgentRunner QA Pipeline
-# LANGBOT_ACP_AGENT_RUNNER_SSH_TARGET=yhh@101.34.71.12
-# LANGBOT_ACP_AGENT_RUNNER_SSH_PORT=22
-# LANGBOT_ACP_AGENT_RUNNER_SSH_IDENTITY_FILE=
-# LANGBOT_ACP_AGENT_RUNNER_SSH_EXTRA_OPTIONS=
-# LANGBOT_ACP_AGENT_RUNNER_REMOTE_WORKSPACE=/home/yhh/langbot-e2e/acp-workspace
+# LANGBOT_ACP_RUNNER_PIPELINE_URL=http://127.0.0.1:3000/home/pipelines?id=<acp-agent-runner-pipeline-uuid>
+# LANGBOT_ACP_RUNNER_PIPELINE_NAME=ACP Runner QA Pipeline
+# LANGBOT_ACP_RUNNER_SSH_TARGET=yhh@101.34.71.12
+# LANGBOT_ACP_RUNNER_SSH_PORT=22
+# LANGBOT_ACP_RUNNER_SSH_IDENTITY_FILE=
+# LANGBOT_ACP_RUNNER_SSH_EXTRA_OPTIONS=
+# LANGBOT_ACP_RUNNER_REMOTE_WORKSPACE=/home/yhh/langbot-e2e/acp-workspace

skills/skills/langbot-mcp-ops/SKILL.md

@@ -66,7 +66,7 @@ The tools wrap the LangBot service layer. Current tools (v1):
 | `list_bots` / `get_bot` / `create_bot` / `update_bot` / `delete_bot` | Manage messaging-platform bots (secrets redacted on read) |
 | `list_bot_event_route_statuses` | Inspect bot event-route runtime status |
 | `list_processors` / `get_processor` / `create_processor` / `update_processor` / `delete_processor` | Manage the peer Agent, Pipeline and Event processor types |
-| `get_processor_metadata` | Discover installed EventProcessor components, schemas and supported event patterns. |
+| `get_processor_metadata` | Discover installed event-capable Runner components, schemas and supported event patterns. |
 | `list_processor_runs` / `get_processor_run_events` | Read one Event processor instance run history and logs; paginate with `before_id` / `after_sequence`. |
 | `debug_agent` | Execute a synthetic Agent event (`processor_uuid`, `payload`); requires `runtime.operate`. Returns final text and up to 1000 execution events (thinking, text, tool arguments/results). Platform tools use Mock; other configured tools execute normally. Optional `payload.mock`: `errors`/`results` keyed by platform tool name, `unsupported_apis` lists unavailable platform APIs. |
 | `list_pipelines` / `get_pipeline` / `create_pipeline` / `update_pipeline` / `delete_pipeline` | Manage pipelines |

skills/skills/langbot-testing/SKILL.md

@@ -11,13 +11,13 @@ Use this skill when an agent needs to verify LangBot behavior through the WebUI
 
 - **General WebUI testing**: read `references/web-ui-testing.md`.
 - **Pipeline Debug Chat**: read `references/pipeline-debug-chat.md`.
-- **Dify AgentRunner**: read `references/dify-agent-runner.md`.
+- **Dify Runner**: read `references/dify-agent-runner.md`.
 - **Model provider setup or test button**: read `references/model-provider-testing.md`.
 - **Plugin install/runtime/tool/page smoke**: read `references/plugin-e2e-smoke.md`.
-- **Local Agent Runner**: read `references/local-agent-runner.md`.
-- **Local Agent Runner path coverage**: read `references/local-agent-runner-coverage.md`.
-- **Diff-aware AgentRunner QA after code changes**: read `references/agent-runner-qa-workflow.md`.
-- **Agent Runner release gate**: read `references/agent-runner-release-gate.md`.
+- **Local Runner**: read `references/local-agent-runner.md`.
+- **Local Runner path coverage**: read `references/local-agent-runner-coverage.md`.
+- **Diff-aware Runner QA after code changes**: read `references/agent-runner-qa-workflow.md`.
+- **Runner release gate**: read `references/agent-runner-release-gate.md`.
 - **Sandbox-backed skill authoring**: read `references/sandbox-skill-authoring.md`.
 - **LangRAG knowledge bases**: read `references/langrag-knowledge-base.md`.
 - **MCP stdio tool testing**: read `references/mcp-stdio-testing.md`.

skills/skills/langbot-testing/cases/acp-agent-runner-debug-chat.yaml

@@ -1,5 +1,5 @@
 id: acp-agent-runner-debug-chat
-title: "ACP AgentRunner can answer through Debug Chat using real remote Claude"
+title: "ACP Runner can answer through Debug Chat using real remote Claude"
 mode: agent-browser
 area: pipeline
 type: regression
@@ -19,42 +19,42 @@ env:
   - LANGBOT_FRONTEND_URL
   - LANGBOT_BACKEND_URL
 env_any:
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL|LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL|LANGBOT_ACP_RUNNER_PIPELINE_NAME
 automation: scripts/e2e/pipeline-debug-chat.mjs
 automation_env:
   - LANGBOT_FRONTEND_URL
   - LANGBOT_BACKEND_URL
   - LANGBOT_BROWSER_PROFILE
   - LANGBOT_CHROMIUM_EXECUTABLE
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL
+  - LANGBOT_ACP_RUNNER_PIPELINE_NAME
   - LANGBOT_E2E_PROMPT
   - LANGBOT_E2E_EXPECTED_TEXT
   - LANGBOT_E2E_EXPECTED_RUNNER_ID
   - LANGBOT_E2E_RESPONSE_TIMEOUT_MS
-automation_pipeline_url_env: LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
-automation_pipeline_name_env: LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
-automation_expected_runner_id: "plugin:langbot-team/ACPAgentRunner/default"
-automation_prompt: "Do not launch any background agent, subagent, task, or worker. In this current ACP session, directly call the MCP tool named langbot_get_current_event exactly once and wait for its result. After it returns, reply exactly ACP_AGENT_RUNNER_E2E_OK with no other text."
-automation_expected_text: "ACP_AGENT_RUNNER_E2E_OK"
+automation_pipeline_url_env: LANGBOT_ACP_RUNNER_PIPELINE_URL
+automation_pipeline_name_env: LANGBOT_ACP_RUNNER_PIPELINE_NAME
+automation_expected_runner_id: "plugin:langbot-team/ACPRunner/default"
+automation_prompt: "Do not launch any background agent, subagent, task, or worker. In this current ACP session, directly call the MCP tool named langbot_get_current_event exactly once and wait for its result. After it returns, reply exactly ACP_RUNNER_E2E_OK with no other text."
+automation_expected_text: "ACP_RUNNER_E2E_OK"
 automation_response_timeout_ms: "300000"
 setup_automation:
   - "node:scripts/e2e/ensure-acp-agent-runner-pipeline.mjs --write-env"
 setup_provides_env:
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL
+  - LANGBOT_ACP_RUNNER_PIPELINE_NAME
 preconditions:
   - "The remote machine has a working Claude Code login and can run npx -y @agentclientprotocol/claude-agent-acp."
   - "LangBot can non-interactively SSH to the remote machine; the runner opens the MCP reverse tunnel automatically."
 steps:
   - "Open LANGBOT_FRONTEND_URL."
-  - "Open the ACP AgentRunner QA pipeline."
-  - "Confirm the pipeline AI runner is plugin:langbot-team/ACPAgentRunner/default."
+  - "Open the ACP Runner QA pipeline."
+  - "Confirm the pipeline AI runner is plugin:langbot-team/ACPRunner/default."
   - "Open Debug Chat."
-  - "Ask the real remote Claude ACP agent to call langbot_get_current_event and return ACP_AGENT_RUNNER_E2E_OK exactly."
+  - "Ask the real remote Claude ACP agent to call langbot_get_current_event and return ACP_RUNNER_E2E_OK exactly."
 checks:
   - "UI: Debug Chat shows the user prompt."
-  - "UI: Debug Chat shows a Bot response containing ACP_AGENT_RUNNER_E2E_OK."
+  - "UI: Debug Chat shows a Bot response containing ACP_RUNNER_E2E_OK."
   - "Logs: Backend logs include Processing request from person_websocket and Streaming completed for this run."
   - "Logs: No acp runner request error appears for this run."
   - "Console: No unexpected frontend errors appear during Debug Chat."
@@ -66,13 +66,13 @@ diagnostics:
   - "Use scripts/e2e/ensure-acp-agent-runner-pipeline.mjs --write-env to create/update the pipeline."
   - "For remote Claude on 101, verify ssh yhh@101.34.71.12 can run without password prompts; no separate ssh -R process is required."
 success_patterns:
-  - "ACP_AGENT_RUNNER_E2E_OK"
+  - "ACP_RUNNER_E2E_OK"
   - "Processing request from person_websocket"
   - "Streaming completed"
 failure_patterns:
   - "acp.command_not_found"
   - "acp.process_exited"
-  - "Agent runner plugin:langbot-team/ACPAgentRunner/default execution failed"
+  - "Agent runner plugin:langbot-team/ACPRunner/default execution failed"
 troubleshooting:
   - backend-not-listening
   - plugin-runtime-timeout

skills/skills/langbot-testing/cases/agent-run-ledger-audit.yaml

@@ -1,5 +1,5 @@
 id: agent-run-ledger-audit
-title: "Persisted AgentRunner run ledger passes end-to-end invariants"
+title: "Persisted Runner run ledger passes end-to-end invariants"
 mode: probe
 area: agent
 type: regression
@@ -15,7 +15,7 @@ skills:
   - langbot-testing
 automation: scripts/e2e/agent-run-ledger-audit.mjs
 steps:
-  - "Set LANGBOT_AGENT_RUN_ID to audit a specific run, or leave it unset to audit the latest persisted AgentRunner run."
+  - "Set LANGBOT_AGENT_RUN_ID to audit a specific run, or leave it unset to audit the latest persisted Runner run."
   - "For an external runner's own CLI tools, set LANGBOT_AGENT_TOOL_AUTHORIZATION_MODE=runner-native; keep the default strict mode for Host tool calls."
   - "Read the active LangBot database configuration and inspect the selected run and its ordered events."
   - "Verify completed terminal state, run.completed, paired tool.call.started/completed events, stable tool names, and monotonic ordering."

skills/skills/langbot-testing/cases/agent-runner-async-db-readiness.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-async-db-readiness
-title: "AgentRunner async DB readiness probe"
+title: "Runner async DB readiness probe"
 mode: probe
 area: release
 type: smoke

skills/skills/langbot-testing/cases/agent-runner-behavior-matrix.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-behavior-matrix
-title: "AgentRunner deterministic behavior matrix probe"
+title: "Runner deterministic behavior matrix probe"
 mode: probe
 area: release
 type: regression

skills/skills/langbot-testing/cases/agent-runner-fixture-contract.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-fixture-contract
-title: "QA AgentRunner fixture contract probe"
+title: "QA Runner fixture contract probe"
 mode: probe
 area: release
 type: regression
@@ -17,19 +17,19 @@ env:
 automation: skills/langbot-testing/probes/agent-runner-fixture-contract.mjs
 steps:
   - "Run `rtk bin/lbs test run agent-runner-fixture-contract --dry-run` first; remove `--dry-run` after checking the planned evidence directory."
-  - "Automation imports the QA AgentRunner fixture source and executes normal, streaming, and controlled-failure paths with SDK entities."
+  - "Automation imports the QA Runner fixture source and executes normal, streaming, and controlled-failure paths with SDK entities."
 checks:
   - "automation-result.json status is pass."
-  - "probe-stdout.log contains QA_AGENT_RUNNER_FIXTURE_CONTRACT_OK."
-  - "Normal input returns QA_AGENT_RUNNER_OK:<input>."
+  - "probe-stdout.log contains QA_RUNNER_FIXTURE_CONTRACT_OK."
+  - "Normal input returns QA_RUNNER_OK:<input>."
   - "Streaming input emits message.delta chunks and completes."
-  - "Failure input returns QA_AGENT_RUNNER_CONTROLLED_FAILURE."
+  - "Failure input returns QA_RUNNER_CONTROLLED_FAILURE."
 evidence_required:
   - filesystem
 diagnostics:
   - "This validates the deterministic fixture source contract. It does not prove the plugin package is installed in a live LangBot instance."
 success_patterns:
-  - "QA_AGENT_RUNNER_FIXTURE_CONTRACT_OK"
+  - "QA_RUNNER_FIXTURE_CONTRACT_OK"
 failure_patterns:
   - "AssertionError"
   - "fixture contract exited"

skills/skills/langbot-testing/cases/agent-runner-health-visibility.yaml

@@ -25,7 +25,7 @@ automation_env:
   - LANGBOT_BROWSER_PROFILE
   - LANGBOT_CHROMIUM_EXECUTABLE
 preconditions:
-  - "The plugin runtime is enabled and connected, with at least one AgentRunner registered."
+  - "The plugin runtime is enabled and connected, with at least one Runner registered."
   - "The target is a local test instance where a temporary Agent may be created and deleted."
 steps:
   - "Read the live plugin runtime status and select a registered runner from Agent metadata."

skills/skills/langbot-testing/cases/agent-runner-ledger-concurrency.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-ledger-concurrency
-title: "AgentRunner run ledger concurrency and auth pytest probe"
+title: "Runner run ledger concurrency and auth pytest probe"
 mode: probe
 area: release
 type: regression

skills/skills/langbot-testing/cases/agent-runner-ledger-contention.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-ledger-contention
-title: "AgentRunner ledger SQLite contention probe"
+title: "Runner ledger SQLite contention probe"
 mode: probe
 area: release
 type: regression

skills/skills/langbot-testing/cases/agent-runner-ledger-invariants.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-ledger-invariants
-title: "AgentRunner ledger schema and status invariants probe"
+title: "Runner ledger schema and status invariants probe"
 mode: probe
 area: release
 type: regression

skills/skills/langbot-testing/cases/agent-runner-ledger-stress.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-ledger-stress
-title: "AgentRunner ledger lightweight stress probe"
+title: "Runner ledger lightweight stress probe"
 mode: probe
 area: release
 type: regression

skills/skills/langbot-testing/cases/agent-runner-live-install.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-live-install
-title: "QA AgentRunner package installs and registers in LangBot"
+title: "QA Runner package installs and registers in LangBot"
 mode: probe
 area: release
 type: regression
@@ -25,7 +25,7 @@ automation_expected_tool: ""
 automation_expected_runner_id: "plugin:qa/agent-runner/default"
 steps:
   - "Run `rtk bin/lbs test run agent-runner-live-install --dry-run` first; remove `--dry-run` only after readiness points at a local test LangBot instance."
-  - "Automation authenticates the local test user, uploads the QA AgentRunner .lbpkg package, waits for the install task, and reads pipeline metadata."
+  - "Automation authenticates the local test user, uploads the QA Runner .lbpkg package, waits for the install task, and reads pipeline metadata."
 checks:
   - "automation-result.json status is pass."
   - "/api/v1/plugins lists qa/agent-runner after install."

skills/skills/langbot-testing/cases/agent-runner-qa-debug-chat.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-qa-debug-chat
-title: "QA AgentRunner returns deterministic output through Debug Chat"
+title: "QA Runner returns deterministic output through Debug Chat"
 mode: agent-browser
 area: pipeline
 type: regression
@@ -17,21 +17,21 @@ skills:
 env:
   - LANGBOT_FRONTEND_URL
   - LANGBOT_BACKEND_URL
-  - LANGBOT_QA_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_QA_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_QA_RUNNER_PIPELINE_URL
+  - LANGBOT_QA_RUNNER_PIPELINE_NAME
 automation: scripts/e2e/pipeline-debug-chat.mjs
 automation_env:
   - LANGBOT_FRONTEND_URL
   - LANGBOT_BACKEND_URL
   - LANGBOT_BROWSER_PROFILE
   - LANGBOT_CHROMIUM_EXECUTABLE
-  - LANGBOT_QA_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_QA_AGENT_RUNNER_PIPELINE_NAME
-automation_pipeline_url_env: LANGBOT_QA_AGENT_RUNNER_PIPELINE_URL
-automation_pipeline_name_env: LANGBOT_QA_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_QA_RUNNER_PIPELINE_URL
+  - LANGBOT_QA_RUNNER_PIPELINE_NAME
+automation_pipeline_url_env: LANGBOT_QA_RUNNER_PIPELINE_URL
+automation_pipeline_name_env: LANGBOT_QA_RUNNER_PIPELINE_NAME
 automation_expected_runner_id: "plugin:qa/agent-runner/default"
 automation_prompt: "hello-live"
-automation_expected_text: "QA_AGENT_RUNNER_OK:hello-live"
+automation_expected_text: "QA_RUNNER_OK:hello-live"
 automation_response_timeout_ms: "120000"
 automation_debug_chat_response_p95_ms: "120000"
 automation_reset_debug_chat: "1"
@@ -39,17 +39,17 @@ setup_automation:
   - "case:agent-runner-live-install"
   - "node:scripts/e2e/ensure-qa-agent-runner-pipeline.mjs --write-env"
 setup_provides_env:
-  - LANGBOT_QA_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_QA_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_QA_RUNNER_PIPELINE_URL
+  - LANGBOT_QA_RUNNER_PIPELINE_NAME
 steps:
   - "Open LANGBOT_FRONTEND_URL."
-  - "Open the pipeline from LANGBOT_QA_AGENT_RUNNER_PIPELINE_URL or LANGBOT_QA_AGENT_RUNNER_PIPELINE_NAME."
+  - "Open the pipeline from LANGBOT_QA_RUNNER_PIPELINE_URL or LANGBOT_QA_RUNNER_PIPELINE_NAME."
   - "Confirm the pipeline AI runner is plugin:qa/agent-runner/default."
   - "Open Debug Chat."
   - "Send: hello-live."
 checks:
   - "UI: The user message appears in Debug Chat."
-  - "UI: A Bot message appears and contains QA_AGENT_RUNNER_OK:hello-live."
+  - "UI: A Bot message appears and contains QA_RUNNER_OK:hello-live."
   - "API diagnostic: pipeline config uses plugin:qa/agent-runner/default."
   - "Console: No unexpected frontend runtime errors appear during the send/receive path."
 evidence_required:
@@ -62,7 +62,7 @@ diagnostics:
   - "This is the deterministic live execution proof that sits after fixture contract and live install."
   - "If the runner id mismatch is reported, rerun ensure-qa-agent-runner-pipeline.mjs --write-env."
 success_patterns:
-  - "QA_AGENT_RUNNER_OK:hello-live"
+  - "QA_RUNNER_OK:hello-live"
 failure_patterns:
   - "plugin:qa/agent-runner/default execution failed"
   - "Action invoke_llm_stream call timed out"

skills/skills/langbot-testing/cases/agent-runner-release-preflight.yaml

@@ -19,7 +19,7 @@ env:
   - LANGBOT_BACKEND_URL
 env_any:
   - LANGBOT_LOCAL_AGENT_PIPELINE_URL|LANGBOT_LOCAL_AGENT_PIPELINE_NAME
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL|LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL|LANGBOT_ACP_RUNNER_PIPELINE_NAME
 automation: scripts/e2e/agent-runner-release-preflight.mjs
 automation_env:
   - LANGBOT_FRONTEND_URL
@@ -28,24 +28,24 @@ automation_env:
   - LANGBOT_CHROMIUM_EXECUTABLE
 automation_env_any:
   - LANGBOT_LOCAL_AGENT_PIPELINE_URL|LANGBOT_LOCAL_AGENT_PIPELINE_NAME
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL|LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL|LANGBOT_ACP_RUNNER_PIPELINE_NAME
 preconditions:
   - "LANGBOT_LOCAL_AGENT_PIPELINE_URL or LANGBOT_LOCAL_AGENT_PIPELINE_NAME points to the local-agent release pipeline."
-  - "LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL or LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME points to the ACP AgentRunner release pipeline."
+  - "LANGBOT_ACP_RUNNER_PIPELINE_URL or LANGBOT_ACP_RUNNER_PIPELINE_NAME points to the ACP Runner release pipeline."
   - "The active browser profile is authenticated for the same LangBot backend."
   - "By default the preflight performs a cheap model test for the local-agent primary model; set LANGBOT_PREFLIGHT_TEST_MODELS=0 only when deliberately classifying model credentials outside this run."
 steps:
   - "Open LANGBOT_FRONTEND_URL with the configured browser profile."
   - "Use the browser token to call LangBot backend readiness APIs without printing token values."
   - "Check plugin runtime status, Box status, required runner plugins, qa-plugin-smoke, and qa_plugin_echo."
-  - "Resolve the local-agent and ACP AgentRunner QA pipelines from their case-specific env vars."
+  - "Resolve the local-agent and ACP Runner QA pipelines from their case-specific env vars."
   - "Assert each pipeline uses the expected runner id."
   - "Assert the external runner pipeline uses the expected runner id."
   - "Assert the local-agent primary model advertises func_call and vision for the full release gate."
   - "Run the local-agent primary model test endpoint unless LANGBOT_PREFLIGHT_TEST_MODELS=0."
 checks:
   - "API diagnostic: api-diagnostic.json has no blockers and no env_issues."
-  - "API diagnostic: required pipelines resolve to plugin:langbot-team/LocalAgent/default and plugin:langbot-team/ACPAgentRunner/default."
+  - "API diagnostic: required pipelines resolve to plugin:langbot-team/LocalAgent/default and plugin:langbot-team/ACPRunner/default."
   - "API diagnostic: qa_plugin_echo is exposed by /api/v1/tools."
   - "API diagnostic: local-agent model check catches invalid credentials or missing func_call/vision before release E2E starts."
   - "Secret safety: token values, api keys, and provider secrets are not printed."

skills/skills/langbot-testing/cases/agent-runner-runtime-chaos.yaml

@@ -1,5 +1,5 @@
 id: agent-runner-runtime-chaos
-title: "AgentRunner SDK runtime chaos pytest probe"
+title: "Runner SDK runtime chaos pytest probe"
 mode: probe
 area: release
 type: regression
@@ -19,10 +19,10 @@ automation: skills/langbot-testing/probes/agent-runner-runtime-chaos.mjs
 steps:
   - "Run `rtk bin/lbs test run agent-runner-runtime-chaos --dry-run` first; remove `--dry-run` after checking the SDK repo target and evidence directory."
   - "Automation resolves LANGBOT_PLUGIN_SDK_REPO, defaulting to ../../langbot-plugin-sdk when the env var is unset."
-  - "Automation runs the existing SDK pytest files tests/runtime/plugin/test_mgr_agent_runner.py and tests/runtime/test_pull_api_handlers.py."
+  - "Automation runs the existing SDK pytest files tests/runtime/plugin/test_mgr_runner.py and tests/runtime/test_pull_api_handlers.py."
 checks:
   - "automation-result.json status is pass."
-  - "pytest exit status is 0 for the existing AgentRunner runtime and pull API handler tests."
+  - "pytest exit status is 0 for the existing Runner runtime and pull API handler tests."
   - "pytest-stdout.log and pytest-stderr.log are written under LBS_EVIDENCE_DIR."
 evidence_required:
   - filesystem

skills/skills/langbot-testing/cases/box-mcp-heartbeat-recovery.yaml

@@ -45,7 +45,7 @@ steps:
   - "Select exactly one Box child whose parent is main.py running from LANGBOT_REPO; abort on zero or multiple matches."
   - "Send SIGTERM to that Box child and poll process, Box status, MCP runtime info, and global tools for up to 30 seconds."
   - "Without running MCP setup or registration, reset Debug Chat and call qa_mcp_echo with a unique per-run value through the browser."
-  - "Audit the matching AgentRunner ledger run and require the exact qa_mcp_echo arguments plus the complete tool result text."
+  - "Audit the matching Runner ledger run and require the exact qa_mcp_echo arguments plus the complete tool result text."
 checks:
   - "The old Box PID exits and a new Box PID appears under the same LangBot parent."
   - "Box returns available=true with at least one active session and managed process."

skills/skills/langbot-testing/cases/dify-agent-debug-chat.yaml

@@ -1,5 +1,5 @@
 id: dify-agent-debug-chat
-title: "Dify AgentRunner returns a response through Pipeline Debug Chat"
+title: "Dify Runner returns a response through Pipeline Debug Chat"
 mode: agent-browser
 area: pipeline
 type: provider

skills/skills/langbot-testing/cases/skill-discovery-via-mcp-gateway.yaml

@@ -18,8 +18,8 @@ skills:
 env:
   - LANGBOT_FRONTEND_URL
   - LANGBOT_BACKEND_URL
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL
+  - LANGBOT_ACP_RUNNER_PIPELINE_NAME
 preconditions:
   - "An external-harness runner pipeline (e.g. ACP remote claude-code) is configured with langbot-assets-enabled=true so the LangBot MCP gateway is exposed to the harness."
   - "The remote harness (claude-code) is reachable and responsive (claude -p returns within the runner timeout)."
@@ -29,10 +29,10 @@ automation_env:
   - LANGBOT_FRONTEND_URL
   - LANGBOT_BROWSER_PROFILE
   - LANGBOT_CHROMIUM_EXECUTABLE
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
-  - LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
-automation_pipeline_url_env: LANGBOT_ACP_AGENT_RUNNER_PIPELINE_URL
-automation_pipeline_name_env: LANGBOT_ACP_AGENT_RUNNER_PIPELINE_NAME
+  - LANGBOT_ACP_RUNNER_PIPELINE_URL
+  - LANGBOT_ACP_RUNNER_PIPELINE_NAME
+automation_pipeline_url_env: LANGBOT_ACP_RUNNER_PIPELINE_URL
+automation_pipeline_name_env: LANGBOT_ACP_RUNNER_PIPELINE_NAME
 automation_prompt: "You have LangBot tools available via an MCP server (tools prefixed langbot_). Call langbot_list_assets with asset_types = [\"skills\",\"tools\"]. Then reply with one single line: the literal token PROBEDONE, a space, the number of skills you found, a space, and the number of tools you found."
 automation_expected_text: "PROBEDONE"
 automation_response_timeout_ms: "540000"

skills/skills/langbot-testing/cases/wizard-runner-marketplace-catalog.yaml

@@ -1,5 +1,5 @@
 id: wizard-runner-marketplace-catalog
-title: "Quick Start installs a published AgentRunner on a clean instance"
+title: "Quick Start installs a published Runner on a clean instance"
 mode: agent-browser
 area: wizard
 type: feature
@@ -27,19 +27,19 @@ preconditions:
 steps:
   - "Start an isolated first-run instance and confirm zero installed plugins and zero registered runners."
   - "Resume Quick Start at the AI Engine step with a temporary disabled Bot."
-  - "Confirm the browser requests Marketplace plugins with component_filter=AgentRunner."
+  - "Confirm the browser requests Marketplace plugins with component_filter=Runner."
   - "Confirm langbot-team/LocalAgent is published with an installable version and the Runner Extensions link is correct."
-  - "Install LocalAgent and wait for plugin initialization and AgentRunner registration."
+  - "Install LocalAgent and wait for plugin initialization and Runner registration."
   - "Confirm Create & Deploy is disabled before installation and enabled after LocalAgent is selected."
   - "Verify the layout at desktop and mobile widths."
 checks:
   - "API: The instance has zero installed plugins and zero registered runners."
   - "API: The instance wizard status is none."
-  - "Network: Marketplace search uses component_filter=AgentRunner and type_filter=plugin."
+  - "Network: Marketplace search uses component_filter=Runner and type_filter=plugin."
   - "UI: The AI Engine step displays the published langbot-team/LocalAgent card."
   - "Marketplace: LocalAgent includes latest_version so installation can proceed."
   - "Runtime: LocalAgent installs and registers plugin:langbot-team/LocalAgent/default."
-  - "UI: Browse Runner Extensions links to the AgentRunner-filtered market."
+  - "UI: Browse Runner Extensions links to the Runner-filtered market."
   - "UI: Create & Deploy transitions from disabled to enabled only after Runner selection."
   - "Console: No unexpected frontend errors appear during the flow."
   - "Cleanup: Wizard progress and the temporary Bot are removed."

skills/skills/langbot-testing/cases/workspace-compatibility-preflight.yaml

@@ -18,7 +18,7 @@ steps:
   - "Discover the active LangBot checkout and sibling workspace repositories, with LANGBOT_WORKSPACE_ROOT and repository-specific env overrides available for non-default layouts."
   - "Verify every checkout is on main or dev/4.11.x and record dirty worktrees as warnings only."
   - "Validate plugin manifest identities for LocalAgent, Control Plane, LongTermMemory, GeneralParsers, LangRAG, and Skill Authoring."
-  - "Use the LangBot virtualenv to import langbot_plugin and AgentRunner Protocol entities from the workspace SDK source tree."
+  - "Use the LangBot virtualenv to import langbot_plugin and Runner Protocol entities from the workspace SDK source tree."
 checks:
   - "workspace-preflight.json contains no failed checks."
   - "The langbot_plugin import path is inside the discovered langbot-plugin-sdk/src directory."

skills/skills/langbot-testing/cases/workspace-repository-contracts.yaml

@@ -16,7 +16,7 @@ skills:
 automation: scripts/e2e/workspace-repository-contracts.mjs
 steps:
   - "Resolve the active LangBot virtualenv and workspace SDK source path."
-  - "Run tests independently for AgentRunner, Control Plane, LongTermMemory, Parser, RAG, Skill Authoring, LocalAgent, LangBot Agent/Provider, the skills CLI, and SDK runtime contracts."
+  - "Run tests independently for Runner, Control Plane, LongTermMemory, Parser, RAG, Skill Authoring, LocalAgent, LangBot Agent/Provider, the skills CLI, and SDK runtime contracts."
   - "Run SDK packaging blackbox separately so an isolated build dependency network failure is classified as env_issue without masking product test failures."
   - "Write per-repository stdout, stderr, status, and duration under repository-contracts/."
 checks:

skills/skills/langbot-testing/fixtures/fixtures.json

@@ -1,7 +1,7 @@
 [
   {
     "id": "qa-agent-runner-behaviors",
-    "title": "Deterministic AgentRunner behavior matrix",
+    "title": "Deterministic Runner behavior matrix",
     "kind": "json",
     "path": "fixtures/agent-runner/qa-runner-behaviors.json",
     "related_cases": [
@@ -13,7 +13,7 @@
   },
   {
     "id": "qa-agent-runner-source",
-    "title": "QA deterministic AgentRunner fixture source",
+    "title": "QA deterministic Runner fixture source",
     "kind": "plugin_source",
     "path": "fixtures/plugins/qa-agent-runner/manifest.yaml",
     "related_cases": [
@@ -22,11 +22,11 @@
       "agent-runner-live-install",
       "agent-runner-qa-debug-chat"
     ],
-    "checks": ["exists", "qa_agent_runner_source"]
+    "checks": ["exists", "qa_runner_source"]
   },
   {
     "id": "qa-agent-runner-package",
-    "title": "QA deterministic AgentRunner prebuilt package",
+    "title": "QA deterministic Runner prebuilt package",
     "kind": "plugin_package",
     "path": "fixtures/plugins/qa-agent-runner/dist/qa-agent-runner-0.1.0.lbpkg",
     "related_cases": [

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/README.md

@@ -1,6 +1,6 @@
-# QA AgentRunner Fixture
+# QA Runner Fixture
 
-Deterministic AgentRunner plugin source used by `langbot-skills` probes and future browser release-gate cases.
+Deterministic Runner plugin source used by `langbot-skills` probes and future browser release-gate cases.
 
 Runner id after installation should be:
 
@@ -10,6 +10,6 @@ plugin:qa/agent-runner/default
 
 Expected behavior:
 
-- normal input returns `QA_AGENT_RUNNER_OK:<input>`
+- normal input returns `QA_RUNNER_OK:<input>`
 - input containing `stream` emits streaming chunks then completes
-- input containing `fail` returns `QA_AGENT_RUNNER_CONTROLLED_FAILURE`
+- input containing `fail` returns `QA_RUNNER_CONTROLLED_FAILURE`

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/assets/icon.svg

@@ -1,4 +1,4 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" role="img" aria-label="QA AgentRunner icon">
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" role="img" aria-label="QA Runner icon">
   <rect width="64" height="64" rx="12" fill="#111827"/>
   <path d="M16 20h32v22H35l-7 8v-8H16z" fill="#22c55e"/>
   <path d="M24 30h16" stroke="#111827" stroke-width="4" stroke-linecap="round"/>

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/components/agent_runner/default.py

@@ -1,39 +0,0 @@
-from __future__ import annotations
-
-import typing
-
-from langbot_plugin.api.definition.components.agent_runner.runner import AgentRunner
-from langbot_plugin.api.entities.builtin.agent_runner import AgentRunContext, AgentRunResult
-from langbot_plugin.api.entities.builtin.provider.message import Message, MessageChunk
-
-
-class DefaultAgentRunner(AgentRunner):
-    async def run(
-        self,
-        ctx: AgentRunContext,
-    ) -> typing.AsyncGenerator[AgentRunResult, None]:
-        text = (ctx.input.to_text() or "").strip()
-        if "fail" in text.lower():
-            yield AgentRunResult.run_failed(
-                ctx.run_id,
-                error="QA_AGENT_RUNNER_CONTROLLED_FAILURE",
-                code="qa.controlled_failure",
-                retryable=False,
-            )
-            return
-
-        content = f"QA_AGENT_RUNNER_OK:{text or 'empty'}"
-        if "stream" in text.lower():
-            for chunk in ("QA_", "AGENT_", f"RUNNER_OK:{text}"):
-                yield AgentRunResult.message_delta(
-                    ctx.run_id,
-                    MessageChunk(role="assistant", content=chunk),
-                )
-            yield AgentRunResult.run_completed(ctx.run_id, finish_reason="stop")
-            return
-
-        yield AgentRunResult.run_completed(
-            ctx.run_id,
-            Message(role="assistant", content=content),
-            finish_reason="stop",
-        )

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/components/runner/default.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+
+import typing
+
+from langbot_plugin.api.definition.components.runner.runner import Runner
+from langbot_plugin.api.entities.builtin.runner import RunnerContext, RunnerResult
+from langbot_plugin.api.entities.builtin.provider.message import Message, MessageChunk
+
+
+class DefaultRunner(Runner):
+    async def run(
+        self,
+        ctx: RunnerContext,
+    ) -> typing.AsyncGenerator[RunnerResult, None]:
+        text = (ctx.input.to_text() or '').strip()
+        if 'fail' in text.lower():
+            yield RunnerResult.run_failed(
+                ctx.run_id,
+                error='QA_RUNNER_CONTROLLED_FAILURE',
+                code='qa.controlled_failure',
+                retryable=False,
+            )
+            return
+
+        content = f'QA_RUNNER_OK:{text or "empty"}'
+        if 'stream' in text.lower():
+            for chunk in ('QA_', 'AGENT_', f'RUNNER_OK:{text}'):
+                yield RunnerResult.message_delta(
+                    ctx.run_id,
+                    MessageChunk(role='assistant', content=chunk),
+                )
+            yield RunnerResult.run_completed(ctx.run_id, finish_reason='stop')
+            return
+
+        yield RunnerResult.run_completed(
+            ctx.run_id,
+            Message(role='assistant', content=content),
+            finish_reason='stop',
+        )

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/components/runner/default.yaml

@@ -1,5 +1,5 @@
 apiVersion: langbot/v1
-kind: AgentRunner
+kind: Runner
 metadata:
   name: default
   label:
@@ -27,4 +27,4 @@ spec:
 execution:
   python:
     path: default.py
-    attr: DefaultAgentRunner
+    attr: DefaultRunner

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/main.py

@@ -3,6 +3,6 @@ from __future__ import annotations
 from langbot_plugin.api.definition.plugin import BasePlugin
 
 
-class QAAgentRunnerPlugin(BasePlugin):
+class QARunnerPlugin(BasePlugin):
     async def initialize(self) -> None:
-        self.ready_marker = "qa-agent-runner-ready"
+        self.ready_marker = 'qa-agent-runner-ready'

skills/skills/langbot-testing/fixtures/plugins/qa-agent-runner/manifest.yaml

@@ -6,20 +6,20 @@ metadata:
   repository: https://example.invalid/langbot/qa-agent-runner
   version: 0.1.0
   description:
-    en_US: Deterministic AgentRunner fixture for LangBot QA.
-    zh_Hans: LangBot QA 使用的确定性 AgentRunner 夹具。
+    en_US: Deterministic Runner fixture for LangBot QA.
+    zh_Hans: LangBot QA 使用的确定性 Runner 夹具。
   label:
-    en_US: QA AgentRunner
-    zh_Hans: QA AgentRunner
+    en_US: QA Runner
+    zh_Hans: QA Runner
   icon: assets/icon.svg
 spec:
   config: []
   components:
-    AgentRunner:
+    Runner:
       fromDirs:
-        - path: components/agent_runner/
+        - path: components/runner/
           maxDepth: 1
 execution:
   python:
     path: main.py
-    attr: QAAgentRunnerPlugin
+    attr: QARunnerPlugin

skills/skills/langbot-testing/probes/agent-runner-behavior-matrix.mjs

@@ -7,7 +7,11 @@ import { delimiter, join, resolve } from "node:path";
 import { env } from "node:process";
 
 function timestampSlug(date = new Date()) {
-  return date.toISOString().replace(/\.\d{3}Z$/, "Z").replace(/[^0-9A-Za-z]+/g, "-").replace(/^-|-$/g, "");
+  return date
+    .toISOString()
+    .replace(/\.\d{3}Z$/, "Z")
+    .replace(/[^0-9A-Za-z]+/g, "-")
+    .replace(/^-|-$/g, "");
 }
 
 function localIsoWithOffset(date = new Date()) {
@@ -51,7 +55,14 @@ function run(command, timeoutMs, childEnv) {
     });
     child.on("error", (error) => {
       clearTimeout(timeout);
-      resolveDone({ stdout, stderr, error, timedOut, status: null, signal: null });
+      resolveDone({
+        stdout,
+        stderr,
+        error,
+        timedOut,
+        status: null,
+        signal: null,
+      });
     });
     child.on("close", (status, signal) => {
       clearTimeout(timeout);
@@ -66,7 +77,7 @@ import json
 import sys
 from pathlib import Path
 
-from langbot.pkg.agent.runner.descriptor import AgentRunnerDescriptor
+from langbot.pkg.agent.runner.descriptor import RunnerDescriptor
 from langbot.pkg.agent.runner.errors import RunnerExecutionError, RunnerProtocolError
 from langbot.pkg.agent.runner.result_normalizer import AgentResultNormalizer
 
@@ -80,10 +91,10 @@ class App:
     logger = Logger()
 
 def descriptor():
-    return AgentRunnerDescriptor(
+    return RunnerDescriptor(
         id='plugin:qa/agent-runner/default',
         source='plugin',
-        label={'en_US': 'QA AgentRunner'},
+        label={'en_US': 'QA Runner'},
         plugin_author='qa',
         plugin_name='agent-runner',
         runner_name='default',
@@ -139,18 +150,26 @@ async function main() {
   const root = resolve(env.LBS_ROOT || process.cwd());
   const caseId = "agent-runner-behavior-matrix";
   const runId = env.LBS_RUN_ID || `${timestampSlug()}-${caseId}`;
-  const evidenceDir = resolve(env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId));
+  const evidenceDir = resolve(
+    env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId),
+  );
   await mkdir(evidenceDir, { recursive: true });
   const startedAt = new Date();
   const langbotRepo = resolve(root, env.LANGBOT_REPO || "..");
-  const sdkRepo = resolve(root, env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk");
+  const sdkRepo = resolve(
+    root,
+    env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk",
+  );
   const sdkSrc = resolve(sdkRepo, "src");
-  const fixturePath = resolve(root, "skills/langbot-testing/fixtures/agent-runner/qa-runner-behaviors.json");
+  const fixturePath = resolve(
+    root,
+    "skills/langbot-testing/fixtures/agent-runner/qa-runner-behaviors.json",
+  );
   const stdoutLog = join(evidenceDir, "probe-stdout.log");
   const stderrLog = join(evidenceDir, "probe-stderr.log");
   const automationResultJson = join(evidenceDir, "automation-result.json");
   const resultJson = join(evidenceDir, "result.json");
-  const timeoutMs = Number(env.LANGBOT_AGENT_RUNNER_PROBE_TIMEOUT_MS || "30000");
+  const timeoutMs = Number(env.LANGBOT_RUNNER_PROBE_TIMEOUT_MS || "30000");
   const command = {
     executable: "rtk",
     args: [resolve(langbotRepo, ".venv/bin/python"), "-c", script, fixturePath],
@@ -175,7 +194,12 @@ async function main() {
     timeout_ms: timeoutMs,
     exit_status: null,
     signal: null,
-    evidence: { stdout_log: stdoutLog, stderr_log: stderrLog, automation_result_json: automationResultJson, result_json: resultJson },
+    evidence: {
+      stdout_log: stdoutLog,
+      stderr_log: stderrLog,
+      automation_result_json: automationResultJson,
+      result_json: resultJson,
+    },
     evidence_collected: ["filesystem"],
   };
   try {
@@ -185,7 +209,9 @@ async function main() {
     } else {
       const proc = await run(command, timeoutMs, {
         ...process.env,
-        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH].filter(Boolean).join(delimiter),
+        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH]
+          .filter(Boolean)
+          .join(delimiter),
         UV_CACHE_DIR: env.UV_CACHE_DIR || join(evidenceDir, ".uv-cache"),
       });
       await writeFile(stdoutLog, proc.stdout, "utf8");
@@ -198,7 +224,10 @@ async function main() {
       } else if (proc.timedOut) {
         result.status = "fail";
         result.reason = `behavior matrix timed out after ${timeoutMs}ms`;
-      } else if (proc.status === 0 && proc.stdout.includes("QA_RUNNER_BEHAVIOR_MATRIX_OK")) {
+      } else if (
+        proc.status === 0 &&
+        proc.stdout.includes("QA_RUNNER_BEHAVIOR_MATRIX_OK")
+      ) {
         result.status = "pass";
         result.reason = "behavior matrix passed";
       } else {
@@ -219,7 +248,9 @@ async function main() {
     await writeFile(resultJson, resultText, "utf8");
     console.log(JSON.stringify(result, null, 2));
   }
-  process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1);
+  process.exit(
+    result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1,
+  );
 }
 
 await main();

skills/skills/langbot-testing/probes/agent-runner-fixture-contract.mjs

@@ -7,7 +7,11 @@ import { delimiter, join, resolve } from "node:path";
 import { env } from "node:process";
 
 function timestampSlug(date = new Date()) {
-  return date.toISOString().replace(/\.\d{3}Z$/, "Z").replace(/[^0-9A-Za-z]+/g, "-").replace(/^-|-$/g, "");
+  return date
+    .toISOString()
+    .replace(/\.\d{3}Z$/, "Z")
+    .replace(/[^0-9A-Za-z]+/g, "-")
+    .replace(/^-|-$/g, "");
 }
 
 function localIsoWithOffset(date = new Date()) {
@@ -51,7 +55,14 @@ function run(command, timeoutMs, childEnv) {
     });
     child.on("error", (error) => {
       clearTimeout(timeout);
-      resolveDone({ stdout, stderr, error, timedOut, status: null, signal: null });
+      resolveDone({
+        stdout,
+        stderr,
+        error,
+        timedOut,
+        status: null,
+        signal: null,
+      });
     });
     child.on("close", (status, signal) => {
       clearTimeout(timeout);
@@ -66,27 +77,27 @@ import importlib.util
 import sys
 from pathlib import Path
 
-from langbot_plugin.api.entities.builtin.agent_runner.context import AgentRunContext
-from langbot_plugin.api.entities.builtin.agent_runner.delivery import DeliveryContext
-from langbot_plugin.api.entities.builtin.agent_runner.event import AgentEventContext
-from langbot_plugin.api.entities.builtin.agent_runner.input import AgentInput
-from langbot_plugin.api.entities.builtin.agent_runner.resources import AgentResources
-from langbot_plugin.api.entities.builtin.agent_runner.runtime import AgentRuntimeContext
-from langbot_plugin.api.entities.builtin.agent_runner.trigger import AgentTrigger
+from langbot_plugin.api.entities.builtin.runner.context import RunnerContext
+from langbot_plugin.api.entities.builtin.runner.delivery import DeliveryContext
+from langbot_plugin.api.entities.builtin.runner.event import AgentEventContext
+from langbot_plugin.api.entities.builtin.runner.input import AgentInput
+from langbot_plugin.api.entities.builtin.runner.resources import AgentResources
+from langbot_plugin.api.entities.builtin.runner.runtime import AgentRuntimeContext
+from langbot_plugin.api.entities.builtin.runner.trigger import AgentTrigger
 
 fixture = Path(sys.argv[1])
-runner_py = fixture / "components" / "agent_runner" / "default.py"
+runner_py = fixture / "components" / "runner" / "default.py"
 manifest = fixture / "manifest.yaml"
-runner_yaml = fixture / "components" / "agent_runner" / "default.yaml"
+runner_yaml = fixture / "components" / "runner" / "default.yaml"
 assert manifest.exists(), manifest
 assert runner_yaml.exists(), runner_yaml
-spec = importlib.util.spec_from_file_location("qa_agent_runner_fixture", runner_py)
+spec = importlib.util.spec_from_file_location("qa_runner_fixture", runner_py)
 module = importlib.util.module_from_spec(spec)
 assert spec and spec.loader
 spec.loader.exec_module(module)
 
 def context(run_id, text):
-    return AgentRunContext(
+    return RunnerContext(
         run_id=run_id,
         trigger=AgentTrigger(type="message.received", source="webui"),
         event=AgentEventContext(event_id=f"evt-{run_id}", event_type="message.received", source="webui"),
@@ -97,7 +108,7 @@ def context(run_id, text):
     )
 
 async def collect(text):
-    runner = module.DefaultAgentRunner()
+    runner = module.DefaultRunner()
     results = []
     async for result in runner.run(context(f"run-{len(text)}", text)):
         results.append(result)
@@ -107,17 +118,17 @@ async def main():
     normal = await collect("hello")
     assert len(normal) == 1, normal
     assert normal[0].type.value == "run.completed"
-    assert normal[0].data["message"]["content"] == "QA_AGENT_RUNNER_OK:hello"
+    assert normal[0].data["message"]["content"] == "QA_RUNNER_OK:hello"
 
     stream = await collect("stream hello")
     assert [item.type.value for item in stream] == ["message.delta", "message.delta", "message.delta", "run.completed"]
-    assert "".join(item.data["chunk"]["content"] for item in stream[:3]) == "QA_AGENT_RUNNER_OK:stream hello"
+    assert "".join(item.data["chunk"]["content"] for item in stream[:3]) == "QA_RUNNER_OK:stream hello"
 
     failed = await collect("please fail")
     assert len(failed) == 1
     assert failed[0].type.value == "run.failed"
-    assert failed[0].data["error"] == "QA_AGENT_RUNNER_CONTROLLED_FAILURE"
-    print("QA_AGENT_RUNNER_FIXTURE_CONTRACT_OK")
+    assert failed[0].data["error"] == "QA_RUNNER_CONTROLLED_FAILURE"
+    print("QA_RUNNER_FIXTURE_CONTRACT_OK")
 
 asyncio.run(main())
 `;
@@ -126,18 +137,30 @@ async function main() {
   const root = resolve(env.LBS_ROOT || process.cwd());
   const caseId = "agent-runner-fixture-contract";
   const runId = env.LBS_RUN_ID || `${timestampSlug()}-${caseId}`;
-  const evidenceDir = resolve(env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId));
+  const evidenceDir = resolve(
+    env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId),
+  );
   await mkdir(evidenceDir, { recursive: true });
   const startedAt = new Date();
-  const sdkRepo = resolve(root, env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk");
+  const sdkRepo = resolve(
+    root,
+    env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk",
+  );
   const sdkSrc = resolve(sdkRepo, "src");
-  const fixturePath = resolve(root, "skills/langbot-testing/fixtures/plugins/qa-agent-runner");
+  const fixturePath = resolve(
+    root,
+    "skills/langbot-testing/fixtures/plugins/qa-agent-runner",
+  );
   const stdoutLog = join(evidenceDir, "probe-stdout.log");
   const stderrLog = join(evidenceDir, "probe-stderr.log");
   const automationResultJson = join(evidenceDir, "automation-result.json");
   const resultJson = join(evidenceDir, "result.json");
-  const timeoutMs = Number(env.LANGBOT_AGENT_RUNNER_PROBE_TIMEOUT_MS || "30000");
-  const command = { executable: "rtk", args: ["uv", "run", "--no-sync", "python", "-c", script, fixturePath], cwd: sdkRepo };
+  const timeoutMs = Number(env.LANGBOT_RUNNER_PROBE_TIMEOUT_MS || "30000");
+  const command = {
+    executable: "rtk",
+    args: ["uv", "run", "--no-sync", "python", "-c", script, fixturePath],
+    cwd: sdkRepo,
+  };
   const result = {
     source: "automation",
     probe: "agent-runner-fixture-contract",
@@ -156,7 +179,12 @@ async function main() {
     timeout_ms: timeoutMs,
     exit_status: null,
     signal: null,
-    evidence: { stdout_log: stdoutLog, stderr_log: stderrLog, automation_result_json: automationResultJson, result_json: resultJson },
+    evidence: {
+      stdout_log: stdoutLog,
+      stderr_log: stderrLog,
+      automation_result_json: automationResultJson,
+      result_json: resultJson,
+    },
     evidence_collected: ["filesystem"],
   };
   try {
@@ -166,7 +194,9 @@ async function main() {
     } else {
       const proc = await run(command, timeoutMs, {
         ...process.env,
-        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH].filter(Boolean).join(delimiter),
+        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH]
+          .filter(Boolean)
+          .join(delimiter),
         UV_CACHE_DIR: env.UV_CACHE_DIR || join(evidenceDir, ".uv-cache"),
       });
       await writeFile(stdoutLog, proc.stdout, "utf8");
@@ -179,9 +209,12 @@ async function main() {
       } else if (proc.timedOut) {
         result.status = "fail";
         result.reason = `fixture contract probe timed out after ${timeoutMs}ms`;
-      } else if (proc.status === 0 && proc.stdout.includes("QA_AGENT_RUNNER_FIXTURE_CONTRACT_OK")) {
+      } else if (
+        proc.status === 0 &&
+        proc.stdout.includes("QA_RUNNER_FIXTURE_CONTRACT_OK")
+      ) {
         result.status = "pass";
-        result.reason = "QA AgentRunner fixture contract passed";
+        result.reason = "QA Runner fixture contract passed";
       } else {
         result.status = "fail";
         result.reason = `fixture contract exited with status ${proc.status}`;
@@ -200,7 +233,9 @@ async function main() {
     await writeFile(resultJson, resultText, "utf8");
     console.log(JSON.stringify(result, null, 2));
   }
-  process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1);
+  process.exit(
+    result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1,
+  );
 }
 
 await main();

skills/skills/langbot-testing/probes/agent-runner-ledger-concurrency.mjs

@@ -8,7 +8,8 @@ await runPytestProbe({
   defaultRepo: "..",
   pythonPathEnvKeys: ["LANGBOT_PLUGIN_SDK_REPO"],
   defaultPythonPaths: ["../../langbot-plugin-sdk/src"],
-  description: "LangBot AgentRunner run ledger claim, lease, authorization, and runtime-admin pytest probe.",
+  description:
+    "LangBot Runner run ledger claim, lease, authorization, and runtime-admin pytest probe.",
   testTargets: [
     "tests/unit_tests/agent/test_run_ledger_store.py::test_create_queued_run_claim_renew_release",
     "tests/unit_tests/agent/test_run_ledger_store.py::test_expired_claim_can_be_reclaimed",

skills/skills/langbot-testing/probes/agent-runner-ledger-contention.mjs

@@ -7,7 +7,11 @@ import { delimiter, join, resolve } from "node:path";
 import { env } from "node:process";
 
 function timestampSlug(date = new Date()) {
-  return date.toISOString().replace(/\.\d{3}Z$/, "Z").replace(/[^0-9A-Za-z]+/g, "-").replace(/^-|-$/g, "");
+  return date
+    .toISOString()
+    .replace(/\.\d{3}Z$/, "Z")
+    .replace(/[^0-9A-Za-z]+/g, "-")
+    .replace(/^-|-$/g, "");
 }
 
 function localIsoWithOffset(date = new Date()) {
@@ -51,7 +55,14 @@ function run(command, timeoutMs, childEnv) {
     });
     child.on("error", (error) => {
       clearTimeout(timeout);
-      resolveDone({ stdout, stderr, error, timedOut, status: null, signal: null });
+      resolveDone({
+        stdout,
+        stderr,
+        error,
+        timedOut,
+        status: null,
+        signal: null,
+      });
     });
     child.on("close", (status, signal) => {
       clearTimeout(timeout);
@@ -149,18 +160,23 @@ async function main() {
   const root = resolve(env.LBS_ROOT || process.cwd());
   const caseId = "agent-runner-ledger-contention";
   const runId = env.LBS_RUN_ID || `${timestampSlug()}-${caseId}`;
-  const evidenceDir = resolve(env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId));
+  const evidenceDir = resolve(
+    env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId),
+  );
   await mkdir(evidenceDir, { recursive: true });
   const startedAt = new Date();
   const langbotRepo = resolve(root, env.LANGBOT_REPO || "..");
-  const sdkRepo = resolve(root, env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk");
+  const sdkRepo = resolve(
+    root,
+    env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk",
+  );
   const sdkSrc = resolve(sdkRepo, "src");
   const dbPath = join(evidenceDir, "ledger-contention.sqlite3");
   const stdoutLog = join(evidenceDir, "probe-stdout.log");
   const stderrLog = join(evidenceDir, "probe-stderr.log");
   const automationResultJson = join(evidenceDir, "automation-result.json");
   const resultJson = join(evidenceDir, "result.json");
-  const timeoutMs = Number(env.LANGBOT_AGENT_RUNNER_PROBE_TIMEOUT_MS || "30000");
+  const timeoutMs = Number(env.LANGBOT_RUNNER_PROBE_TIMEOUT_MS || "30000");
   const command = {
     executable: "rtk",
     args: [resolve(langbotRepo, ".venv/bin/python"), "-c", script, dbPath],
@@ -185,7 +201,13 @@ async function main() {
     timeout_ms: timeoutMs,
     exit_status: null,
     signal: null,
-    evidence: { stdout_log: stdoutLog, stderr_log: stderrLog, database: dbPath, automation_result_json: automationResultJson, result_json: resultJson },
+    evidence: {
+      stdout_log: stdoutLog,
+      stderr_log: stderrLog,
+      database: dbPath,
+      automation_result_json: automationResultJson,
+      result_json: resultJson,
+    },
     evidence_collected: ["filesystem"],
   };
   try {
@@ -195,7 +217,9 @@ async function main() {
     } else {
       const proc = await run(command, timeoutMs, {
         ...process.env,
-        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH].filter(Boolean).join(delimiter),
+        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH]
+          .filter(Boolean)
+          .join(delimiter),
         UV_CACHE_DIR: env.UV_CACHE_DIR || join(evidenceDir, ".uv-cache"),
       });
       await writeFile(stdoutLog, proc.stdout, "utf8");
@@ -208,7 +232,10 @@ async function main() {
       } else if (proc.timedOut) {
         result.status = "fail";
         result.reason = `ledger contention timed out after ${timeoutMs}ms`;
-      } else if (proc.status === 0 && proc.stdout.includes("LEDGER_CONTENTION_OK")) {
+      } else if (
+        proc.status === 0 &&
+        proc.stdout.includes("LEDGER_CONTENTION_OK")
+      ) {
         result.status = "pass";
         result.reason = "ledger contention probe passed";
       } else {
@@ -229,7 +256,9 @@ async function main() {
     await writeFile(resultJson, resultText, "utf8");
     console.log(JSON.stringify(result, null, 2));
   }
-  process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1);
+  process.exit(
+    result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1,
+  );
 }
 
 await main();

skills/skills/langbot-testing/probes/agent-runner-ledger-invariants.mjs

@@ -7,7 +7,11 @@ import { delimiter, join, resolve } from "node:path";
 import { env } from "node:process";
 
 function timestampSlug(date = new Date()) {
-  return date.toISOString().replace(/\.\d{3}Z$/, "Z").replace(/[^0-9A-Za-z]+/g, "-").replace(/^-|-$/g, "");
+  return date
+    .toISOString()
+    .replace(/\.\d{3}Z$/, "Z")
+    .replace(/[^0-9A-Za-z]+/g, "-")
+    .replace(/^-|-$/g, "");
 }
 
 function localIsoWithOffset(date = new Date()) {
@@ -55,7 +59,14 @@ function runProcess(command, timeoutMs, childEnv) {
     });
     child.on("error", (error) => {
       clearTimeout(timeout);
-      resolveDone({ stdout, stderr, error, timedOut, status: null, signal: null });
+      resolveDone({
+        stdout,
+        stderr,
+        error,
+        timedOut,
+        status: null,
+        signal: null,
+      });
     });
     child.on("close", (status, signal) => {
       clearTimeout(timeout);
@@ -124,11 +135,16 @@ async function main() {
   const root = resolve(env.LBS_ROOT || process.cwd());
   const caseId = "agent-runner-ledger-invariants";
   const runId = env.LBS_RUN_ID || `${timestampSlug()}-${caseId}`;
-  const evidenceDir = resolve(env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId));
+  const evidenceDir = resolve(
+    env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId),
+  );
   await mkdir(evidenceDir, { recursive: true });
   const startedAt = new Date();
   const langbotRepo = resolveFromRoot(root, env.LANGBOT_REPO || "..");
-  const sdkRepo = resolveFromRoot(root, env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk");
+  const sdkRepo = resolveFromRoot(
+    root,
+    env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk",
+  );
   const sdkSrc = resolve(sdkRepo, "src");
   const stdoutLog = join(evidenceDir, "probe-stdout.log");
   const stderrLog = join(evidenceDir, "probe-stderr.log");
@@ -139,7 +155,7 @@ async function main() {
     args: [resolve(langbotRepo, ".venv/bin/python"), "-c", probeScript],
     cwd: langbotRepo,
   };
-  const timeoutMs = Number(env.LANGBOT_AGENT_RUNNER_PROBE_TIMEOUT_MS || "30000");
+  const timeoutMs = Number(env.LANGBOT_RUNNER_PROBE_TIMEOUT_MS || "30000");
   const result = {
     source: "automation",
     probe: "python-sync",
@@ -174,7 +190,9 @@ async function main() {
     } else {
       const childEnv = {
         ...process.env,
-        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH].filter(Boolean).join(delimiter),
+        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH]
+          .filter(Boolean)
+          .join(delimiter),
         UV_CACHE_DIR: env.UV_CACHE_DIR || join(evidenceDir, ".uv-cache"),
       };
       await mkdir(childEnv.UV_CACHE_DIR, { recursive: true });
@@ -210,7 +228,9 @@ async function main() {
     await writeFile(resultJson, resultText, "utf8");
     console.log(JSON.stringify(result, null, 2));
   }
-  process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1);
+  process.exit(
+    result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1,
+  );
 }
 
 await main();

skills/skills/langbot-testing/probes/agent-runner-ledger-stress.mjs

@@ -7,7 +7,11 @@ import { delimiter, join, resolve } from "node:path";
 import { env } from "node:process";
 
 function timestampSlug(date = new Date()) {
-  return date.toISOString().replace(/\.\d{3}Z$/, "Z").replace(/[^0-9A-Za-z]+/g, "-").replace(/^-|-$/g, "");
+  return date
+    .toISOString()
+    .replace(/\.\d{3}Z$/, "Z")
+    .replace(/[^0-9A-Za-z]+/g, "-")
+    .replace(/^-|-$/g, "");
 }
 
 function localIsoWithOffset(date = new Date()) {
@@ -51,7 +55,14 @@ function run(command, timeoutMs, childEnv) {
     });
     child.on("error", (error) => {
       clearTimeout(timeout);
-      resolveDone({ stdout, stderr, error, timedOut, status: null, signal: null });
+      resolveDone({
+        stdout,
+        stderr,
+        error,
+        timedOut,
+        status: null,
+        signal: null,
+      });
     });
     child.on("close", (status, signal) => {
       clearTimeout(timeout);
@@ -116,17 +127,22 @@ async function main() {
   const root = resolve(env.LBS_ROOT || process.cwd());
   const caseId = "agent-runner-ledger-stress";
   const runId = env.LBS_RUN_ID || `${timestampSlug()}-${caseId}`;
-  const evidenceDir = resolve(env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId));
+  const evidenceDir = resolve(
+    env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId),
+  );
   await mkdir(evidenceDir, { recursive: true });
   const startedAt = new Date();
   const langbotRepo = resolve(root, env.LANGBOT_REPO || "..");
-  const sdkRepo = resolve(root, env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk");
+  const sdkRepo = resolve(
+    root,
+    env.LANGBOT_PLUGIN_SDK_REPO || "../../langbot-plugin-sdk",
+  );
   const sdkSrc = resolve(sdkRepo, "src");
   const stdoutLog = join(evidenceDir, "probe-stdout.log");
   const stderrLog = join(evidenceDir, "probe-stderr.log");
   const automationResultJson = join(evidenceDir, "automation-result.json");
   const resultJson = join(evidenceDir, "result.json");
-  const timeoutMs = Number(env.LANGBOT_AGENT_RUNNER_PROBE_TIMEOUT_MS || "30000");
+  const timeoutMs = Number(env.LANGBOT_RUNNER_PROBE_TIMEOUT_MS || "30000");
   const command = {
     executable: "rtk",
     args: [resolve(langbotRepo, ".venv/bin/python"), "-c", script],
@@ -150,7 +166,12 @@ async function main() {
     timeout_ms: timeoutMs,
     exit_status: null,
     signal: null,
-    evidence: { stdout_log: stdoutLog, stderr_log: stderrLog, automation_result_json: automationResultJson, result_json: resultJson },
+    evidence: {
+      stdout_log: stdoutLog,
+      stderr_log: stderrLog,
+      automation_result_json: automationResultJson,
+      result_json: resultJson,
+    },
     evidence_collected: ["filesystem"],
   };
   try {
@@ -160,7 +181,9 @@ async function main() {
     } else {
       const proc = await run(command, timeoutMs, {
         ...process.env,
-        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH].filter(Boolean).join(delimiter),
+        PYTHONPATH: [sdkSrc, process.env.PYTHONPATH]
+          .filter(Boolean)
+          .join(delimiter),
         UV_CACHE_DIR: env.UV_CACHE_DIR || join(evidenceDir, ".uv-cache"),
       });
       await writeFile(stdoutLog, proc.stdout, "utf8");
@@ -173,7 +196,10 @@ async function main() {
       } else if (proc.timedOut) {
         result.status = "fail";
         result.reason = `ledger stress timed out after ${timeoutMs}ms`;
-      } else if (proc.status === 0 && proc.stdout.includes("LEDGER_STRESS_OK")) {
+      } else if (
+        proc.status === 0 &&
+        proc.stdout.includes("LEDGER_STRESS_OK")
+      ) {
         result.status = "pass";
         result.reason = "ledger stress probe passed";
       } else {
@@ -194,7 +220,9 @@ async function main() {
     await writeFile(resultJson, resultText, "utf8");
     console.log(JSON.stringify(result, null, 2));
   }
-  process.exit(result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1);
+  process.exit(
+    result.status === "pass" ? 0 : result.status === "env_issue" ? 2 : 1,
+  );
 }
 
 await main();

skills/skills/langbot-testing/probes/agent-runner-runtime-chaos.mjs

@@ -6,9 +6,10 @@ await runPytestProbe({
   caseId: "agent-runner-runtime-chaos",
   repoEnvKey: "LANGBOT_PLUGIN_SDK_REPO",
   defaultRepo: "../../langbot-plugin-sdk",
-  description: "LangBot plugin SDK AgentRunner runtime failure, timeout, forwarding, and pull API pytest probe.",
+  description:
+    "LangBot plugin SDK Runner runtime failure, timeout, forwarding, and pull API pytest probe.",
   testTargets: [
-    "tests/runtime/plugin/test_mgr_agent_runner.py",
+    "tests/runtime/plugin/test_mgr_runner.py",
     "tests/runtime/test_pull_api_handlers.py",
   ],
 });

skills/skills/langbot-testing/probes/pytest-probe.mjs

@@ -5,7 +5,10 @@ import { basename, delimiter, join, resolve } from "node:path";
 import { env } from "node:process";
 
 function loadEnvDefaults(root) {
-  for (const path of [join(root, "skills/.env"), join(root, "skills/.env.local")]) {
+  for (const path of [
+    join(root, "skills/.env"),
+    join(root, "skills/.env.local"),
+  ]) {
     if (!existsSync(path)) continue;
     for (const rawLine of readFileSync(path, "utf8").split(/\r?\n/)) {
       const line = rawLine.trim();
@@ -14,13 +17,20 @@ function loadEnvDefaults(root) {
       if (sep === -1) continue;
       const key = line.slice(0, sep).trim();
       if (env[key]) continue;
-      env[key] = line.slice(sep + 1).trim().replace(/^["']|["']$/g, "");
+      env[key] = line
+        .slice(sep + 1)
+        .trim()
+        .replace(/^["']|["']$/g, "");
     }
   }
 }
 
 function timestampSlug(date = new Date()) {
-  return date.toISOString().replace(/\.\d{3}Z$/, "Z").replace(/[^0-9A-Za-z]+/g, "-").replace(/^-|-$/g, "");
+  return date
+    .toISOString()
+    .replace(/\.\d{3}Z$/, "Z")
+    .replace(/[^0-9A-Za-z]+/g, "-")
+    .replace(/^-|-$/g, "");
 }
 
 function localIsoWithOffset(date = new Date()) {
@@ -88,7 +98,14 @@ async function runProcess(command, timeoutMs, childEnv) {
     });
     child.on("error", (error) => {
       clearTimeout(timeout);
-      resolveDone({ stdout, stderr, error, timedOut, status: null, signal: null });
+      resolveDone({
+        stdout,
+        stderr,
+        error,
+        timedOut,
+        status: null,
+        signal: null,
+      });
     });
     child.on("close", (status, signal) => {
       clearTimeout(timeout);
@@ -109,10 +126,14 @@ export async function runPytestProbe({
 }) {
   const root = resolve(env.LBS_ROOT || process.cwd());
   loadEnvDefaults(root);
-  const resolvedTimeoutMs = Number(timeoutMs || env.LANGBOT_AGENT_RUNNER_PROBE_TIMEOUT_MS || "180000");
+  const resolvedTimeoutMs = Number(
+    timeoutMs || env.LANGBOT_RUNNER_PROBE_TIMEOUT_MS || "180000",
+  );
 
   const runId = env.LBS_RUN_ID || `${timestampSlug()}-${caseId}`;
-  const evidenceDir = resolve(env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId));
+  const evidenceDir = resolve(
+    env.LBS_EVIDENCE_DIR || join(root, "reports", "evidence", runId),
+  );
   await mkdir(evidenceDir, { recursive: true });
   const uvCacheDir = env.UV_CACHE_DIR || join(evidenceDir, ".uv-cache");
   await mkdir(uvCacheDir, { recursive: true });
@@ -171,14 +192,21 @@ export async function runPytestProbe({
       result.status = "env_issue";
       result.reason = `${repoEnvKey || "repo"} did not resolve to an existing directory: ${repoPath}`;
     } else {
-      const missingTargets = testTargets.filter((target) => !existsSync(join(repoPath, target.split("::")[0])));
+      const missingTargets = testTargets.filter(
+        (target) => !existsSync(join(repoPath, target.split("::")[0])),
+      );
       if (missingTargets.length > 0) {
         result.status = "env_issue";
         result.reason = `pytest target file(s) not found in ${basename(repoPath)}: ${missingTargets.join(", ")}`;
       } else {
         const childEnv = { ...process.env, UV_CACHE_DIR: uvCacheDir };
         if (pythonPaths.length > 0) {
-          childEnv.PYTHONPATH = [pythonPaths.join(delimiter), childEnv.PYTHONPATH].filter(Boolean).join(delimiter);
+          childEnv.PYTHONPATH = [
+            pythonPaths.join(delimiter),
+            childEnv.PYTHONPATH,
+          ]
+            .filter(Boolean)
+            .join(delimiter);
         }
         const proc = await runProcess(command, resolvedTimeoutMs, childEnv);
         result.exit_status = proc.status;
@@ -195,7 +223,11 @@ export async function runPytestProbe({
         } else if (proc.status === 0) {
           result.status = "pass";
           result.reason = `pytest passed for ${testTargets.join(", ")}.`;
-        } else if (/command not found|no such file or directory|executable file not found/i.test(`${proc.stdout}\n${proc.stderr}`)) {
+        } else if (
+          /command not found|no such file or directory|executable file not found/i.test(
+            `${proc.stdout}\n${proc.stderr}`,
+          )
+        ) {
           result.status = "env_issue";
           result.reason = `pytest command could not run in ${repoPath}. See ${stdoutLog} and ${stderrLog}.`;
         } else {

skills/skills/langbot-testing/references/agent-runner-qa-workflow.md

@@ -1,6 +1,6 @@
-# AgentRunner QA Workflow
+# Runner QA Workflow
 
-Use this workflow when an agent finishes AgentRunner-related code and enters a
+Use this workflow when an agent finishes Runner-related code and enters a
 test phase.
 
 ## Order
@@ -25,7 +25,7 @@ test phase.
      backend is available and installing the QA fixture is acceptable.
    - `rtk bin/lbs test run agent-runner-qa-debug-chat --dry-run` when WebUI live
      execution needs deterministic coverage without a model provider. This
-     case runs its setup automation first: install the QA AgentRunner fixture,
+     case runs its setup automation first: install the QA Runner fixture,
      create/update the QA pipeline, write the case-specific pipeline env, then
      execute Debug Chat.
    - `rtk bin/lbs test run agent-runner-ledger-invariants --dry-run`
@@ -51,8 +51,8 @@ only to review or adjust the generated list.
 | --- | --- | --- |
 | `LangBot/src/langbot/pkg/agent/runner/*`, `tests/unit_tests/agent/test_result_normalizer.py`, protocol/result/context/resource builders | `rtk bin/lbs test run agent-runner-fixture-contract --dry-run`; `rtk bin/lbs test run agent-runner-behavior-matrix --dry-run`; targeted LangBot unit tests for touched files | Result shape, user-visible runner output, or Debug Chat delivery changed: add `pipeline-debug-chat` or `local-agent-basic-debug-chat`. |
 | `LangBot/src/langbot/pkg/entity/persistence/agent_run.py`, `run_journal.py`, run ledger store/API/auth tests, claim/lease/status code | `rtk bin/lbs test run agent-runner-ledger-invariants --dry-run`; `rtk bin/lbs test run agent-runner-ledger-stress --dry-run`; `rtk bin/lbs test run agent-runner-ledger-contention --dry-run`; `rtk bin/lbs test run agent-runner-async-db-readiness --dry-run` before `rtk bin/lbs test run agent-runner-ledger-concurrency --dry-run` | Debug Chat run lifecycle, resume, or visible completion changed: add `local-agent-basic-debug-chat`. |
-| `langbot-plugin-sdk/src/langbot_plugin/api/entities/builtin/agent_runner/*`, `api/proxies/agent_run_api.py`, runtime pull handlers, plugin manager/runtime IO | `rtk bin/lbs test run agent-runner-runtime-chaos --dry-run`; `rtk bin/lbs test run agent-runner-behavior-matrix --dry-run`; targeted SDK pytest | Runtime delivery or tool-call surface changed: add `agent-runner-release-preflight`, then `local-agent-basic-debug-chat`. |
-| `langbot-agent-runner/*/components/agent_runner/*`, external runner daemon/client code, ACP/Codex/Claude runner command wrappers | Repo-local targeted tests; `rtk bin/lbs test run agent-runner-runtime-chaos --dry-run`; `rtk bin/lbs test run agent-runner-release-preflight --dry-run` | ACP or external coding runner behavior changed: add `acp-agent-runner-debug-chat`. |
+| `langbot-plugin-sdk/src/langbot_plugin/api/entities/builtin/runner/*`, `api/proxies/agent_run_api.py`, runtime pull handlers, plugin manager/runtime IO | `rtk bin/lbs test run agent-runner-runtime-chaos --dry-run`; `rtk bin/lbs test run agent-runner-behavior-matrix --dry-run`; targeted SDK pytest | Runtime delivery or tool-call surface changed: add `agent-runner-release-preflight`, then `local-agent-basic-debug-chat`. |
+| `langbot-agent-runner/*/components/runner/*`, external runner daemon/client code, ACP/Codex/Claude runner command wrappers | Repo-local targeted tests; `rtk bin/lbs test run agent-runner-runtime-chaos --dry-run`; `rtk bin/lbs test run agent-runner-release-preflight --dry-run` | ACP or external coding runner behavior changed: add `acp-agent-runner-debug-chat`. |
 | Prompt preprocessing, effective prompt, pipeline AI config, runner binding/default runner migration | `rtk bin/lbs test run agent-runner-behavior-matrix --dry-run`; targeted LangBot pipeline/agent tests | The runner reads host-provided prompt or saved runner config: add `local-agent-effective-prompt-debug-chat`. |
 | Context window, transcript, history/event state, compaction, checkpoint/steering | `rtk bin/lbs test run agent-runner-behavior-matrix --dry-run`; targeted LangBot agent state/context tests | Multi-turn memory, compaction, or steering behavior changed: add `local-agent-context-compaction-debug-chat` and, for steering-specific changes, `local-agent-steering-debug-chat`. |
 | Plugin tool authorization, host tool listing, MCP tool bridge, function-call conversion | `rtk bin/lbs test run agent-runner-behavior-matrix --dry-run`; targeted plugin/MCP/tool tests | Tool execution is user-visible: add `local-agent-plugin-tool-call-debug-chat`; for MCP-specific changes add `mcp-stdio-register` then `mcp-stdio-tool-call`. |

skills/skills/langbot-testing/references/agent-runner-release-gate.md

@@ -1,4 +1,4 @@
-# Agent Runner Release Gate
+# Runner Release Gate
 
 Use this reference when judging whether runner externalization is release-ready. The goal is not to enumerate every possible prompt. The gate covers product abilities and trust boundaries with deterministic normal-path cases, then leaves rare negative branches to unit and contract tests.
 
@@ -35,7 +35,7 @@ For a quick early blocker check, run:
 rtk bin/lbs test run agent-runner-release-preflight --dry-run
 ```
 
-For the code-level AgentRunner probes, run:
+For the code-level Runner probes, run:
 
 ```bash
 rtk bin/lbs test run agent-runner-behavior-matrix --dry-run
@@ -70,7 +70,7 @@ API integration gate, not a Debug Chat execution proof.
 
 `agent-runner-qa-debug-chat` is the deterministic live execution proof. It uses
 a pipeline created by `scripts/e2e/ensure-qa-agent-runner-pipeline.mjs` and
-expects Debug Chat to return `QA_AGENT_RUNNER_OK:<input>` through
+expects Debug Chat to return `QA_RUNNER_OK:<input>` through
 `plugin:qa/agent-runner/default`.
 
 `agent-runner-ledger-invariants` is the fast Host ledger probe. It uses
@@ -97,7 +97,7 @@ If it times out before any test result and a direct `aiosqlite.connect()` script
 also hangs, classify the run with troubleshooting id
 `aiosqlite-connect-hangs` instead of treating it as a browser E2E failure.
 
-`agent-runner-runtime-chaos` runs SDK AgentRunner runtime and pull API handler
+`agent-runner-runtime-chaos` runs SDK Runner runtime and pull API handler
 tests from `LANGBOT_PLUGIN_SDK_REPO` or `../langbot-plugin-sdk`.
 Each probe writes `automation-result.json` and probe logs under
 `LBS_EVIDENCE_DIR`.
@@ -108,9 +108,9 @@ Each probe writes `automation-result.json` and probe logs under
 | --- | --- | --- |
 | Authenticated WebUI session | `webui-login-state`, `agent-runner-release-preflight` | The browser profile can operate the same backend that later cases use. |
 | Generic Pipeline Debug Chat | `pipeline-debug-chat` | The WebUI Debug Chat path itself works before runner-specific failures are diagnosed. |
-| Deterministic QA runner install | `agent-runner-live-install` | A local `.lbpkg` AgentRunner package can install and register a runner. |
+| Deterministic QA runner install | `agent-runner-live-install` | A local `.lbpkg` Runner package can install and register a runner. |
 | Deterministic QA runner Debug Chat | `agent-runner-qa-debug-chat` | The installed QA runner executes through WebUI Debug Chat without a model provider. |
-| Required runner plugins | `agent-runner-release-preflight` | `langbot-team/LocalAgent` and `langbot-team/ACPAgentRunner` are visible to the host. |
+| Required runner plugins | `agent-runner-release-preflight` | `langbot-team/LocalAgent` and `langbot-team/ACPRunner` are visible to the host. |
 | Required QA plugin tools | `plugin-e2e-smoke`, `agent-runner-release-preflight`, `qa-plugin-smoke-live-install` | The deterministic `qa_plugin_echo` and `qa_plugin_fail` tools are exposed before tool-loop and tool-error cases start. |
 | Knowledge base fixture | `langrag-kb-retrieve`, `local-agent-rag-debug-chat` | LangRAG data is queryable and the runner inserts retrieved context. |
 | Effective prompt bridge | `local-agent-effective-prompt-debug-chat` | Host prompt preprocessing reaches the runner. |
@@ -149,7 +149,7 @@ rtk uv run pytest -q
 # langbot-plugin-sdk
 rtk uv run pytest -q
 
-# langbot-skills saved AgentRunner probes
+# langbot-skills saved Runner probes
 rtk bin/lbs test run agent-runner-behavior-matrix --dry-run
 rtk bin/lbs test run agent-runner-ledger-invariants --dry-run
 rtk bin/lbs test run agent-runner-ledger-stress --dry-run

skills/skills/langbot-testing/references/dify-agent-runner.md

@@ -1,4 +1,4 @@
-# Dify AgentRunner
+# Dify Runner
 
 Use this reference when validating `langbot-team/DifyAgent` through LangBot WebUI.
 

skills/skills/langbot-testing/references/local-agent-runner-coverage.md

@@ -1,4 +1,4 @@
-# Local Agent Runner Coverage
+# Local Runner Coverage
 
 Use this matrix when judging whether the external `langbot-team/LocalAgent` plugin still behaves like the old built-in local-agent runner.
 
@@ -10,7 +10,7 @@ The QA target is end-to-end behavior. UI cases prove the host, SDK, plugin runti
 - `LangBot/src/langbot/pkg/agent/runner/pipeline_adapter.py` adapts Pipeline-only fields into `ctx.adapter.extra.prompt`, `ctx.adapter.extra.params`, and optional `ctx.bootstrap.messages`.
 - `LangBot/src/langbot/pkg/agent/runner/resource_builder.py` authorizes models, fallback models, rerank models, tools, and knowledge bases for the current run.
 - `LangBot/src/langbot/pkg/plugin/handler.py` validates run-scoped model/tool/rerank access and calls the host model provider or tool manager with the current query.
-- `langbot-local-agent/components/agent_runner/default.py` selects streaming or non-streaming execution, retrieves RAG context, builds messages, invokes models with fallback, and runs tool loops.
+- `langbot-local-agent/components/runner/default.py` selects streaming or non-streaming execution, retrieves RAG context, builds messages, invokes models with fallback, and runs tool loops.
 - `langbot-local-agent/pkg/messages.py` prefers the host effective prompt from `ctx.adapter.extra.prompt`, uses `ctx.bootstrap.messages` only as a small bootstrap window, and preserves structured/multimodal input while inserting RAG context.
 
 TODO: Treat `ctx.adapter.extra.prompt` as a temporary Pipeline bridge for old

skills/skills/langbot-testing/references/local-agent-runner.md

@@ -1,10 +1,10 @@
-# Local Agent Runner
+# Local Runner
 
 Use this reference when validating the pluginized `langbot-team/LocalAgent` runner through the WebUI.
 
 The goal is behavior parity with the old built-in local-agent runner. The code does not need to be identical, but the visible behavior should match: effective prompt, current input, history, model selection and fallback, tool calling, knowledge retrieval, multimodal input, streaming and non-streaming output all have to reach the runner through the host and SDK.
 
-For path-by-path coverage, read [Local Agent Runner Coverage](local-agent-runner-coverage.md).
+For path-by-path coverage, read [Local Runner Coverage](local-agent-runner-coverage.md).
 
 ## Main Surface
 

skills/skills/langbot-testing/references/performance-reliability-testing.md

@@ -35,7 +35,7 @@ Measure user experience and internal composition separately:
 
 - WebUI load and interaction latency.
 - Debug Chat send-to-first-visible-token and send-to-completion latency.
-- Pipeline, RAG, plugin runtime, MCP, AgentRunner, and persistence segment
+- Pipeline, RAG, plugin runtime, MCP, Runner, and persistence segment
   latency.
 - Queue wait time, concurrency, throughput, timeout rate, and p95/p99 latency.
 - Startup, plugin install, knowledge-base ingestion, migration, and recovery

skills/skills/langbot-testing/references/skill-all-tool-acceptance.md

@@ -33,7 +33,7 @@ Both external runners receive the same host-generated gateway `AgentMCPServerCon
 
 This is a **runner-plugin transport detail, not a host all-tool-branch issue** — proven by **both** runners discovering skills end-to-end with the unmodified branch (see cases below).
 
-> **Correction (2026-06-22).** An earlier revision of this doc claimed acp was "blocked" on remote-ssh and *required* `langbot-assets-gateway-public-url`, based on a run that returned `PROBEDONE 0 0` / timeout. That was an **environment artifact, not an acp defect**: a duplicate backend instance (a second checkout `LangBot-master/` whose box runtime contended for the same `--ws-control-port 5410`) plus a wedged plugin runtime (host `emit_event` / `list_agent_runners` action calls timing out with `ActionCallTimeoutError`). Re-run on a clean single-instance runtime, **acp passes via the reverse tunnel with no `public-url`** (`PROBEDONE 1 17`, 8–24s).
+> **Correction (2026-06-22).** An earlier revision of this doc claimed acp was "blocked" on remote-ssh and *required* `langbot-assets-gateway-public-url`, based on a run that returned `PROBEDONE 0 0` / timeout. That was an **environment artifact, not an acp defect**: a duplicate backend instance (a second checkout `LangBot-master/` whose box runtime contended for the same `--ws-control-port 5410`) plus a wedged plugin runtime (host `emit_event` / `list_runners` action calls timing out with `ActionCallTimeoutError`). Re-run on a clean single-instance runtime, **acp passes via the reverse tunnel with no `public-url`** (`PROBEDONE 1 17`, 8–24s).
 - **Lifecycle**: discover → activate → operate (native exec under the activated mount path) → register.
 - **Backend**: docker · nsjail · e2b.
 

skills/skills/langbot-testing/references/troubleshooting.md

@@ -12,7 +12,7 @@ Date: 2026-05-16
 
 ### Symptom
 
-The WebUI can send a Debug Chat message, but the bot response is missing or says `Agent runner temporarily unavailable`. Backend logs may include `Action list_plugins call timed out`, `Action list_agent_runners call timed out`, or `Action invoke_llm_stream call timed out`.
+The WebUI can send a Debug Chat message, but the bot response is missing or says `Agent runner temporarily unavailable`. Backend logs may include `Action list_plugins call timed out`, `Action list_runners call timed out`, or `Action invoke_llm_stream call timed out`.
 
 ### Likely Cause
 
@@ -78,7 +78,7 @@ Structured entry: `../troubleshooting/marketplace-network-flaky.yaml`
 
 Marketplace icon/tag/recommendation requests can fail while plugin cards are already visible. Retry first, and use backend component endpoints only to confirm installation results.
 
-## agent-runner-actor-context-fields: AgentRunner reads old actor fields
+## agent-runner-actor-context-fields: Runner reads old actor fields
 
 Structured entry: `../troubleshooting/agent-runner-actor-context-fields.yaml`
 

skills/skills/langbot-testing/references/workspace-release-testing.md

@@ -1,6 +1,6 @@
 # Workspace Release Testing
 
-Use the workspace gates when changes span LangBot core, the plugin SDK, AgentRunner, or multiple first-party plugins.
+Use the workspace gates when changes span LangBot core, the plugin SDK, Runner, or multiple first-party plugins.
 
 ## Cost Ladder
 

skills/skills/langbot-testing/suites/langbot-workspace-release-gate.yaml

@@ -1,6 +1,6 @@
 id: langbot-workspace-release-gate
 title: "LangBot workspace top-down release gate"
-description: "Broad release gate combining deterministic repository contracts with representative browser workflows, plugin pages, RAG/parser, EBA, external AgentRunner, and one complex LocalAgent task."
+description: "Broad release gate combining deterministic repository contracts with representative browser workflows, plugin pages, RAG/parser, EBA, external Runner, and one complex LocalAgent task."
 type: release_gate
 priority: p0
 tags:

skills/skills/langbot-testing/troubleshooting/agent-runner-actor-context-fields.yaml

@@ -1,9 +1,9 @@
 id: agent-runner-actor-context-fields
-title: "AgentRunner reads old actor.type and actor.id fields"
+title: "Runner reads old actor.type and actor.id fields"
 date: 2026-05-17
 symptoms:
   - "Pipeline Debug Chat shows Agent runner execution failed."
-  - "Backend logs show an AttributeError from an AgentRunner plugin."
+  - "Backend logs show an AttributeError from an Runner plugin."
 patterns:
   - "AttributeError: 'ActorContext' object has no attribute 'type'"
   - "AttributeError: 'ActorContext' object has no attribute 'id'"
@@ -15,8 +15,8 @@ fix_steps:
   - "Update runner code to read actor.actor_type and actor.actor_id."
   - "Keep getattr fallback to type/id only if compatibility with older host data is required."
   - "Restart LangBot or the plugin runtime so the updated plugin code is loaded."
-  - "Add a regression test that builds AgentRunContext with ActorContext(actor_type=..., actor_id=...)."
-verification: "Run dify-agent-debug-chat or another AgentRunner Debug Chat and confirm the assistant/bot message contains the expected sentinel while backend logs show Streaming completed."
+  - "Add a regression test that builds RunnerContext with ActorContext(actor_type=..., actor_id=...)."
+verification: "Run dify-agent-debug-chat or another Runner Debug Chat and confirm the assistant/bot message contains the expected sentinel while backend logs show Streaming completed."
 related_cases:
   - dify-agent-debug-chat
   - pipeline-debug-chat

skills/skills/langbot-testing/troubleshooting/aiosqlite-connect-hangs.yaml

@@ -2,7 +2,7 @@ id: aiosqlite-connect-hangs
 title: "aiosqlite connect hangs before ledger pytest starts"
 category: env_issue
 symptoms:
-  - "AgentRunner ledger pytest probe times out after collecting tests but before reporting a test result."
+  - "Runner ledger pytest probe times out after collecting tests but before reporting a test result."
   - "pytest stdout stops at a line like tests/unit_tests/agent/test_run_ledger_store.py."
   - "A direct aiosqlite.connect(':memory:') script prints its first line and then hangs."
 patterns:

skills/skills/langbot-testing/troubleshooting/ambiguous-runner-default-label.yaml

@@ -1,5 +1,5 @@
 id: ambiguous-runner-default-label
-title: "AgentRunner selector shows multiple Default or 默认 options"
+title: "Runner selector shows multiple Default or 默认 options"
 date: 2026-05-17
 symptoms:
   - "The Pipeline AI runner selector shows multiple options named Default or 默认."
@@ -9,7 +9,7 @@ patterns:
   - "label.zh_Hans: 默认"
   - "label.en_US: Default"
 likely_causes:
-  - "AgentRunner component ids are commonly named default, but the user-facing metadata.label was also left generic."
+  - "Runner component ids are commonly named default, but the user-facing metadata.label was also left generic."
   - "The frontend displays metadata.label as the primary option label."
 fix_steps:
   - "Keep metadata.name as default if the plugin component id is intended to remain stable."

skills/skills/langbot-testing/troubleshooting/plugin-runtime-timeout.yaml

@@ -8,7 +8,7 @@ symptoms:
   - "Knowledge sidebar or plugin sidebar loading may hang or time out."
 patterns:
   - "Action list_plugins call timed out"
-  - "Action list_agent_runners call timed out"
+  - "Action list_runners call timed out"
   - "Action invoke_llm_stream call timed out"
   - "All models failed during streaming setup"
   - "Failed to fetch plugins for sidebar"