@chankov/agent-fleet 2.1.1 → 2.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.pi/agent-fleet/scripts/lib/fleet-codex-connections.ts +1 -1
- package/.pi/agent-fleet/scripts/lib/fleet-codex-instructions.ts +3 -1
- package/.pi/agent-fleet/scripts/lib/fleet-codex-local-mcp.ts +13 -4
- package/.pi/agent-fleet/scripts/lib/fleet-codex-response-read.ts +26 -0
- package/.pi/agent-fleet/scripts/lib/fleet-codex-response-transport.ts +38 -0
- package/.pi/harnesses/agent-hub/README.md +1 -1
- package/.pi/harnesses/agent-hub/context-continuity-compat.ts +18 -3
- package/.pi/harnesses/agent-hub/package.json +1 -1
- package/.pi/harnesses/coms/package.json +1 -1
- package/.pi/harnesses/damage-control-continue/package.json +1 -1
- package/.pi/harnesses/lib/coms-core.ts +21 -7
- package/.pi/harnesses/lib/coms-response-read.ts +107 -0
- package/.pi/harnesses/lib/fleet-notification-validation.ts +4 -3
- package/.pi/harnesses/lib/fleet-transcript-store.ts +1 -1
- package/.versions/2.1.2/.pi/agent-fleet/hermes/README.md +347 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/desktop-plugins/agent-fleet-herdr/plugin.js +1291 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/desktop-plugins/agent-fleet-herdr/presentation.js +672 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/desktop-plugins/agent-fleet-monitor/plugin.js +19 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/desktop-plugins/agent-fleet-monitor/state.js +10 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/gates/gate-o-capability.md +8 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/gates/gate-o-validator-fixtures.json +1 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/activity.py +773 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/coms_registry.py +134 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/coms_send.py +350 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/herdr_source.py +193 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/manifest.json +4 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/plugin_api.py +444 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/sessions.py +205 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/tasks.py +300 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/dashboard/watch.py +819 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-herdr/plugin.yaml +8 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-monitor/dashboard/adapter.py +139 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-monitor/dashboard/manifest.json +11 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/plugins/agent-fleet-monitor/dashboard/plugin_api.py +50 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-conductor/SKILL.md +84 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-liaison/SKILL.md +84 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/SKILL.md +76 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/manifest.json +1 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog.py +249 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_actions.py +124 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_contract.py +76 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_delivery.py +10 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_engine.py +128 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_judgment.py +41 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_recovery.py +103 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_state.py +163 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/skills/hub-watchdog/scripts/watchdog_transport.py +138 -0
- package/.versions/2.1.2/.pi/agent-fleet/hermes/watchdog-tests/__init__.py +0 -0
- package/.versions/2.1.2/.pi/agent-fleet/hooks/coms-stop-hook.mjs +84 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/claude-code-preflight.ts +70 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/coms-claude-bridge.ts +440 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/coms-cli.ts +430 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/coms-hermes-bridge.ts +416 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/exec-at-target.ts +10 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/fixtures/fleet-codex-allowlist-store-child.ts +31 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/fixtures/response-fixture.ts +23 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/fleet-codex-local-mcp.mjs +26 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/fleet-codex-local-mcp.ts +59 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/fleet.ts +248 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/flow.ts +166 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/hermes-monitor-capability-runner.ts +25 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/hermes-monitor-scenario.ts +474 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/hermes-watchdog-capability-probe.ts +45 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/install-hermes-plugin.sh +180 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/claude-bridge-core.ts +208 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/codex-desktop-queue-host.ts +106 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/codex-unix-queue-rpc.ts +91 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/coms-envelope.ts +582 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fake-herdr-server.ts +88 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-allowlist-store.ts +367 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-allowlist.ts +175 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-answer-transport.ts +73 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-answers.ts +74 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-connections.ts +70 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-event-reply.ts +58 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-event-runtime.ts +116 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-instruction-store.ts +428 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-instruction-transport.ts +160 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-instructions.ts +175 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-local-mcp.ts +415 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-native-history.ts +215 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-observation-store.ts +208 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-observe-transport.ts +49 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-observe.ts +93 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-overview.ts +52 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-permission-transport.ts +23 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-permissions.ts +83 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-readonly.ts +213 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-relay-latency.ts +45 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-response-read.ts +26 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-response-transport.ts +38 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-codex-resync.ts +212 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/fleet-command.ts +268 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/flow-command.ts +107 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/flow-maintenance.ts +238 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/herdr-layout.ts +281 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-bridge-core.ts +241 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-monitor-events.ts +1 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-monitor-herdr.ts +2 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-monitor-model.ts +3 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-monitor-registry.ts +2 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-monitor-socket.ts +2 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/hermes-monitor-store.ts +2 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/monitor-env.ts +146 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/peer-launch.ts +318 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/peer-target.ts +1 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/persona-banner.ts +62 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/persona-dirs.ts +25 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/resource-closure.js +1 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/runtime-dependencies.js +124 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/session-launch.ts +56 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/spawn-stagger.ts +101 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/team-project.ts +178 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/lib/team-snapshot.ts +160 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/package-lock.json +57 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/package.json +10 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/peer-banner.ts +41 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/peer-launch.ts +289 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/pi-session.ts +9 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/team-snapshot.ts +245 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/team-up.ts +385 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/agent-phase.ts +181 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/changes.ts +61 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/debate.ts +149 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/env.ts +36 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/envelopes.ts +169 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/gates.ts +81 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/git.ts +99 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/isolated-snapshot.ts +130 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/merge.ts +95 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/model-profile.ts +22 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/model-visibility.ts +92 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/permissions.ts +137 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/personas.ts +57 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/poll.ts +86 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/project-policy.ts +37 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/quality.ts +65 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/run.ts +109 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/scout-data-boundary.ts +55 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/trace.ts +52 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/voices.ts +128 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/writer-lease-race.worker.mjs +36 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/lib/writer-lease.ts +148 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/tsconfig.json +22 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/wf-build-test.ts +61 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/wf-debate.ts +87 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/wf-document.ts +50 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/wf-poll.ts +95 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/wf-quality.ts +20 -0
- package/.versions/2.1.2/.pi/agent-fleet/scripts/workflows/wf-scout.ts +40 -0
- package/.versions/2.1.2/.pi/agents/dispatch-policy.yaml +32 -0
- package/.versions/2.1.2/.pi/agents/model-profiles.yaml +134 -0
- package/.versions/2.1.2/.pi/agents/peers.yaml +147 -0
- package/.versions/2.1.2/.pi/agents/teams.yaml +41 -0
- package/.versions/2.1.2/.pi/agents/voices.yaml +13 -0
- package/.versions/2.1.2/.pi/damage-control-rules.yaml +297 -0
- package/.versions/2.1.2/.pi/extensions/btw/README.md +120 -0
- package/.versions/2.1.2/.pi/extensions/btw/index.ts +916 -0
- package/.versions/2.1.2/.pi/extensions/btw/package.json +6 -0
- package/.versions/2.1.2/.pi/extensions/btw/state.js +179 -0
- package/.versions/2.1.2/.pi/extensions/chrome-devtools-mcp/README.md +55 -0
- package/.versions/2.1.2/.pi/extensions/chrome-devtools-mcp/index.ts +93 -0
- package/.versions/2.1.2/.pi/extensions/chrome-devtools-mcp/package.json +6 -0
- package/.versions/2.1.2/.pi/extensions/compact-and-continue/README.md +42 -0
- package/.versions/2.1.2/.pi/extensions/compact-and-continue/index.ts +136 -0
- package/.versions/2.1.2/.pi/extensions/compact-and-continue/package.json +6 -0
- package/.versions/2.1.2/.pi/extensions/mcp-bridge/README.md +46 -0
- package/.versions/2.1.2/.pi/extensions/mcp-bridge/index.ts +206 -0
- package/.versions/2.1.2/.pi/extensions/mcp-bridge/package.json +6 -0
- package/.versions/2.1.2/.pi/extensions/package-lock.json +1175 -0
- package/.versions/2.1.2/.pi/extensions/package.json +9 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/README.md +224 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/config.ts +199 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/examples/stt.json +35 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/index.ts +248 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/package.json +6 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/providers.ts +214 -0
- package/.versions/2.1.2/.pi/extensions/pi-voice-stt/recorder.ts +158 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/README.md +1584 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/acceptance.ts +204 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/access-approval.ts +266 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/action-authorization.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-contract.ts +43 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-evidence.ts +64 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-hub.ts +55 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-runtime.ts +56 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-sources-worker.mjs +4 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-sources.ts +74 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/agentic-state.ts +23 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/approval-wait.ts +1 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/artifacts.js +146 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/assertion-ledger.js +68 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/assist-profile.ts +19 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/backend-policy.js +174 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/bounded-output.ts +26 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/budget-recovery.ts +123 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/capability-confirmation.ts +47 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/capability-packs.ts +184 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agent-model-thinking.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agent-model.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agent-models-substitute.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-add.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-drop.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-history.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-kill.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-list.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-restart.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-save.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/agents-team.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/audit.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/compound.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/coms.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/config.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/context-command.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/context.ts +47 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/debate.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/dispatch-policy.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/handoff.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/hub-report.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/models.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/poll.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/recover.ts +61 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/retry.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/task-triage-recover.ts +12 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/task-triage-waive.ts +12 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/watchdog.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/work-mode.ts +29 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/commands/zoom.ts +10 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/config/agents.ts +181 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/config/model-profiles.ts +237 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/config/overrides.ts +166 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context/agent-state.ts +30 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context/assertions-artifacts.ts +221 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context/budgets.ts +152 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context/hub-state.ts +40 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-budget-snapshot.ts +105 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-compaction-monitor.ts +35 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-compaction-preflight.ts +21 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-compaction-runtime.ts +69 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-compaction.ts +34 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity-broker.ts +44 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity-child.ts +83 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity-client.ts +22 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity-compat.ts +45 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity-owners.ts +17 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity-registry.ts +8 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-continuity.ts +82 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-pressure.ts +222 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/context-window.js +108 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-approval.ts +83 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-broker.ts +125 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-contract.ts +22 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-descendant.ts +76 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-hub.ts +263 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-identity.ts +12 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-owners.ts +59 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-state.ts +43 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/damage-guard-test-tsconfig.json +19 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/debate-command.ts +176 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/delegate.ts +478 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/deterministic-fs.ts +195 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/diagnostic-probe-extension.ts +26 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/diagnostic-series-budget.ts +178 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-coms.ts +258 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-core.ts +27 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-native-complete.ts +176 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-native-prepare.ts +301 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-native-spawn.ts +262 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-native-types.ts +293 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-native.ts +236 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-observability.ts +225 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-triage-contract.ts +27 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-triage-eval.ts +77 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-triage-policy.ts +29 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-triage-runtime.ts +55 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/dispatch-triage-state.ts +33 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/docs-lane.js +123 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/drift-judge.ts +352 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/drift-runtime.ts +480 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/drift-system1-policy.ts +39 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/drift-system1.ts +469 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/drift-watchdog.js +349 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/evidence-manifest.ts +51 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/evidence-rules.js +96 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/execution-evidence.ts +96 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/execution-trace.ts +241 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/external-blocker.js +92 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/adapters.ts +88 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/broker-client.ts +62 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/broker.ts +128 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/child-extension.ts +42 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/descendant.ts +67 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/discovery-worker.mjs +15 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/discovery.ts +126 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/evaluate.ts +57 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/hub.ts +170 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/native-context.ts +8 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/native-fixture.test-support.ts +108 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/owners.ts +100 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/results.ts +55 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/runtime.ts +130 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/semantic-profiles.ts +18 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/sources.ts +69 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/file-discovery/state.ts +22 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/filesystem-tool.ts +166 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/fixtures/registration-surface.json +68 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/fixtures/t0a-synthetic/catalog.ts +189 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/footer.ts +30 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/helpers.ts +270 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/history-projection.ts +116 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/hub-state-audit.js +41 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/index.ts +2705 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/input/completions.ts +82 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/input/shortcuts.ts +23 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/lifecycle/context-pressure.ts +231 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/lifecycle/monitor-session.ts +104 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/lifecycle/session-orchestration.ts +145 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/lifecycle/turn-handlers.ts +90 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-control.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-invoke-journal.ts +131 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-invoke.ts +92 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-lifecycle.ts +13 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-publisher.ts +59 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-recovery.ts +3 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-runtime.ts +3 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/monitor-session-bridge.ts +266 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/no-progress.ts +622 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/operator-current-state.ts +53 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/operator-watchdog.ts +97 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/orchestration-activation.ts +109 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/orchestration-metrics.ts +78 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/orchestration-route.ts +68 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/package.json +7 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/peer-spawn-plan.ts +116 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/permission-channel.ts +87 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/permission-relay.ts +84 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/policy/models.ts +153 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/policy/profile-activation.ts +62 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/policy/profile-runtime.ts +120 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/policy/roster.ts +94 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/policy/work-mode.ts +142 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/poll-command.ts +176 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/presentation.ts +54 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/private-config-current-state.ts +81 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/private-config-fixtures.ts +26 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/private-config-review.ts +100 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-config.ts +22 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-evaluate.ts +138 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-external-git.ts +82 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-external.ts +142 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-feedback.ts +104 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-findings.ts +115 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-local.ts +89 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-observer.ts +106 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-rules.ts +171 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-runtime.ts +318 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-selection.ts +68 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-snapshot-worker.mjs +12 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-snapshot.ts +279 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/proactive-types.ts +70 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/process-obligations.ts +177 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/prompts/context.ts +55 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/prompts/fragments.ts +86 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/prompts/session-start.ts +90 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/prompts/system-prompt.ts +125 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/provider-semaphore.js +138 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/reconcile.ts +26 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/recover-policy.ts +44 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/recover-state.ts +104 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/recovery-contract.ts +151 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/rerun-policy.ts +40 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/research/controls.ts +74 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/research/runtime.ts +215 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/research/spawn-run.ts +221 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/research-watchdog.ts +40 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/return-contract.js +371 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/return-extract.js +77 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/review-closure.ts +43 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/review-continuity.ts +73 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/review-findings.js +96 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/review-reuse.ts +47 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/review-verdict.ts +6 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/routing-observation.ts +41 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/routing-proposal.ts +46 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/run-budget.js +342 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/run-namespace.js +93 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/runtime-receipts.ts +63 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/runtime-test-check.ts +85 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/safety-routing.ts +28 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/scope-gate.js +233 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/session-audit.ts +331 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/session-health.js +110 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/session-start.ts +42 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/spawn.ts +702 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/specialist-result-receipt.ts +13 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/specialist-result.ts +78 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/system1-activity.ts +625 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/system1-communication-store.ts +225 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/system1-report.ts +275 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/system1-runtime.ts +271 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-continuation.ts +4 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-resume-contract.ts +80 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-authorization.ts +170 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-config.ts +21 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-contract.ts +14 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-live-stage-boundary.mjs +49 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-obligations.ts +120 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-policy.ts +16 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-review-contract.mjs +43 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-reviewer-only-contract.mjs +156 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-reviewer-only-diagnostics.mjs +112 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-runtime.ts +130 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-stage-guard.ts +21 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/task-triage-state.ts +46 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/timeline.ts +72 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tool-catalog-runtime.ts +79 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tool-catalog-state.ts +123 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tool-protocol.ts +134 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/action-executors.ts +216 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/ask-system1-files.ts +15 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/ask-system1.ts +25 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/coms-tools.ts +139 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/context.ts +147 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/dispatch-agent.ts +92 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/dispatch-execution.ts +777 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/dispatch-triage.ts +16 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/execution-orchestration.ts +22 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/fleet-tools.ts +201 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/herdr-executors.ts +100 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/run-flow.ts +146 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/set-task-tier.ts +31 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/spawn-research.ts +67 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/team-adjust.ts +29 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tools/verification-contract.ts +81 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/tsconfig.json +22 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/types.ts +66 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/activity-dots.ts +25 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/context-budget.ts +89 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/detail-panel.ts +192 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/fleet-actions.ts +78 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/fleet-dashboard.ts +163 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/fleet-editor.ts +44 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/fleet-source.ts +179 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/grid.ts +159 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/history-store.ts +137 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/history.ts +234 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/pool.ts +103 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/running-strip.ts +2 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/system1-communication.ts +59 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/ui/zoom.ts +206 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/unknown-tool-counter.ts +116 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/version.ts +42 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/watchdog-evaluation.ts +110 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/work-mode-controls.ts +56 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/work-mode.ts +188 -0
- package/.versions/2.1.2/.pi/harnesses/agent-hub/write-isolation.ts +187 -0
- package/.versions/2.1.2/.pi/harnesses/ask-user-remote/README.md +59 -0
- package/.versions/2.1.2/.pi/harnesses/ask-user-remote/index.ts +571 -0
- package/.versions/2.1.2/.pi/harnesses/ask-user-remote/questions.ts +206 -0
- package/.versions/2.1.2/.pi/harnesses/ask-user-remote/race-core.js +124 -0
- package/.versions/2.1.2/.pi/harnesses/ask-user-remote/runtime-ask.ts +90 -0
- package/.versions/2.1.2/.pi/harnesses/coms/README.md +105 -0
- package/.versions/2.1.2/.pi/harnesses/coms/index.ts +308 -0
- package/.versions/2.1.2/.pi/harnesses/coms/package.json +7 -0
- package/.versions/2.1.2/.pi/harnesses/coms/version.ts +42 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/README.md +161 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/index.ts +659 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/package.json +7 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/result-screen.ts +98 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/system1-child.ts +45 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/system1-client.ts +85 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/system1-guard.ts +65 -0
- package/.versions/2.1.2/.pi/harnesses/damage-control-continue/version.ts +42 -0
- package/.versions/2.1.2/.pi/harnesses/lib/approval-wait.ts +17 -0
- package/.versions/2.1.2/.pi/harnesses/lib/bash-policy-analysis.ts +185 -0
- package/.versions/2.1.2/.pi/harnesses/lib/changed-file-diagnostics.ts +642 -0
- package/.versions/2.1.2/.pi/harnesses/lib/clarification-policy.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/lib/coms-core-io.ts +422 -0
- package/.versions/2.1.2/.pi/harnesses/lib/coms-core.ts +734 -0
- package/.versions/2.1.2/.pi/harnesses/lib/coms-instruction-receipts.ts +113 -0
- package/.versions/2.1.2/.pi/harnesses/lib/coms-observation.ts +74 -0
- package/.versions/2.1.2/.pi/harnesses/lib/coms-registry-entry.ts +99 -0
- package/.versions/2.1.2/.pi/harnesses/lib/coms-response-read.ts +107 -0
- package/.versions/2.1.2/.pi/harnesses/lib/context-budget-child-prompt.ts +214 -0
- package/.versions/2.1.2/.pi/harnesses/lib/context-budget-hub-prompt.ts +121 -0
- package/.versions/2.1.2/.pi/harnesses/lib/context-budget-view.ts +112 -0
- package/.versions/2.1.2/.pi/harnesses/lib/context-budget.ts +114 -0
- package/.versions/2.1.2/.pi/harnesses/lib/context-compaction-policy.js +35 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-action-hash.ts +28 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-auto-policy.ts +52 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-control-presentation.ts +14 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-control-shared.ts +276 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-guard-port.ts +25 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-policy.ts +35 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-result-evidence.ts +25 -0
- package/.versions/2.1.2/.pi/harnesses/lib/damage-result-view.ts +16 -0
- package/.versions/2.1.2/.pi/harnesses/lib/deterministic-handle-path.ts +25 -0
- package/.versions/2.1.2/.pi/harnesses/lib/exact-permission-port.ts +38 -0
- package/.versions/2.1.2/.pi/harnesses/lib/execution-trace.ts +45 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fixtures/context-budget-profiles.json +11 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fixtures/hub-prompt-operator.legacy.txt +73 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fixtures/hub-prompt-orchestrator.legacy.txt +73 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-codex-event-bridge.ts +82 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-config/cli-bridge.ts +111 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-config/mutations.ts +201 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-config/snapshot.ts +417 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-config/transition.ts +68 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-config/ui.ts +269 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-config/view.ts +338 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-connection-control.ts +77 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-dashboard-ops.ts +178 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-dashboard-view.ts +174 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-detail-view.ts +339 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-event-source.ts +21 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-notification-validation.ts +67 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-overlay.ts +26 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-panel.ts +34 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-question-reference.ts +42 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-read-model.ts +609 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-selection.ts +24 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-strip-controller.ts +75 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-strip-view.ts +179 -0
- package/.versions/2.1.2/.pi/harnesses/lib/fleet-transcript-store.ts +244 -0
- package/.versions/2.1.2/.pi/harnesses/lib/herdr-client.ts +472 -0
- package/.versions/2.1.2/.pi/harnesses/lib/herdr-presence.ts +399 -0
- package/.versions/2.1.2/.pi/harnesses/lib/hermes-monitor-events.ts +136 -0
- package/.versions/2.1.2/.pi/harnesses/lib/hermes-monitor-herdr.ts +28 -0
- package/.versions/2.1.2/.pi/harnesses/lib/hermes-monitor-model.ts +18 -0
- package/.versions/2.1.2/.pi/harnesses/lib/hermes-monitor-registry.ts +6 -0
- package/.versions/2.1.2/.pi/harnesses/lib/hermes-monitor-socket.ts +163 -0
- package/.versions/2.1.2/.pi/harnesses/lib/hermes-monitor-store.ts +31 -0
- package/.versions/2.1.2/.pi/harnesses/lib/identical-dialog.ts +27 -0
- package/.versions/2.1.2/.pi/harnesses/lib/installation-state.js +62 -0
- package/.versions/2.1.2/.pi/harnesses/lib/peer-target.ts +24 -0
- package/.versions/2.1.2/.pi/harnesses/lib/policy-roots.js +117 -0
- package/.versions/2.1.2/.pi/harnesses/lib/policy-roots.ts +32 -0
- package/.versions/2.1.2/.pi/harnesses/lib/process-shared.ts +9 -0
- package/.versions/2.1.2/.pi/harnesses/lib/resource-closure.js +26 -0
- package/.versions/2.1.2/.pi/harnesses/lib/safe-source-read.js +29 -0
- package/.versions/2.1.2/.pi/harnesses/lib/semantic-approval.ts +80 -0
- package/.versions/2.1.2/.pi/harnesses/lib/session-target.ts +62 -0
- package/.versions/2.1.2/.pi/harnesses/lib/spawned-peers.js +191 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-agentic.js +15 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-context-compaction.js +16 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-damage-guard.js +24 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-file-discovery.js +23 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-json.js +37 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-loader.js +53 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-proactive.js +68 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-triage.js +42 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config-v2.js +112 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/config.js +50 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/contracts.ts +154 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/demo.ts +95 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/jev.ts +503 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/payload-screen.ts +65 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/selection.js +11 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/service.ts +245 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/worktree-scopes.js +110 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/worktree-scopes.ts +13 -0
- package/.versions/2.1.2/.pi/harnesses/lib/system1/worktree-service.ts +24 -0
- package/.versions/2.1.2/.pi/harnesses/lib/target-capabilities.js +7 -0
- package/.versions/2.1.2/.pi/harnesses/lib/update-check.ts +227 -0
- package/.versions/2.1.2/.pi/harnesses/lib/workspace-context.js +115 -0
- package/.versions/2.1.2/.pi/harnesses/lib/workspace-context.ts +22 -0
- package/.versions/2.1.2/.pi/harnesses/package-lock.json +2121 -0
- package/.versions/2.1.2/.pi/harnesses/package.json +13 -0
- package/.versions/2.1.2/.pi/prompts/af-build.md +27 -0
- package/.versions/2.1.2/.pi/prompts/af-code-simplify.md +22 -0
- package/.versions/2.1.2/.pi/prompts/af-constraints.md +31 -0
- package/.versions/2.1.2/.pi/prompts/af-plan.md +17 -0
- package/.versions/2.1.2/.pi/prompts/af-review.md +16 -0
- package/.versions/2.1.2/.pi/prompts/af-set-hermes-telegram.md +15 -0
- package/.versions/2.1.2/.pi/prompts/af-set-hermes-watchdog.md +6 -0
- package/.versions/2.1.2/.pi/prompts/af-setup-rules.md +20 -0
- package/.versions/2.1.2/.pi/prompts/af-ship.md +17 -0
- package/.versions/2.1.2/.pi/prompts/af-spec.md +15 -0
- package/.versions/2.1.2/.pi/prompts/af-test.md +19 -0
- package/.versions/2.1.2/.pi/skills/bowser/SKILL.md +145 -0
- package/.versions/2.1.2/.version +1 -0
- package/.versions/2.1.2/agents/architect.md +24 -0
- package/.versions/2.1.2/agents/bowser.md +28 -0
- package/.versions/2.1.2/agents/builder.md +55 -0
- package/.versions/2.1.2/agents/code-reviewer.md +209 -0
- package/.versions/2.1.2/agents/deep-researcher.md +32 -0
- package/.versions/2.1.2/agents/documenter.md +22 -0
- package/.versions/2.1.2/agents/orchestrator.md +22 -0
- package/.versions/2.1.2/agents/plan-reviewer.md +83 -0
- package/.versions/2.1.2/agents/planner.md +107 -0
- package/.versions/2.1.2/agents/releaser.md +24 -0
- package/.versions/2.1.2/agents/researcher.md +30 -0
- package/.versions/2.1.2/agents/security-auditor.md +167 -0
- package/.versions/2.1.2/agents/test-engineer.md +153 -0
- package/.versions/2.1.2/agents/web-debugger.md +44 -0
- package/.versions/2.1.2/agents/web-performance-auditor.md +194 -0
- package/.versions/2.1.2/bin/catalog/harness-runtime-closure.json +85 -0
- package/.versions/2.1.2/docs/ARCHITECTURE.md +1195 -0
- package/.versions/2.1.2/docs/agent-fleet-setup.md +1143 -0
- package/.versions/2.1.2/docs/claude-code-coms-bridge.md +147 -0
- package/.versions/2.1.2/docs/codex-local-mcp.md +503 -0
- package/.versions/2.1.2/docs/codex-session-bridge.md +44 -0
- package/.versions/2.1.2/docs/codex-setup.md +183 -0
- package/.versions/2.1.2/docs/coms-hermes-bridge.md +188 -0
- package/.versions/2.1.2/docs/fleet-native-voice.md +145 -0
- package/.versions/2.1.2/docs/getting-started.md +126 -0
- package/.versions/2.1.2/docs/npm-install.md +535 -0
- package/.versions/2.1.2/docs/pi-extensions.md +455 -0
- package/.versions/2.1.2/docs/pi-setup.md +92 -0
- package/.versions/2.1.2/docs/skill-anatomy.md +150 -0
- package/.versions/2.1.2/install-manifest.json +3239 -0
- package/.versions/2.1.2/justfile +247 -0
- package/.versions/2.1.2/manifest-meta.json +1087 -0
- package/.versions/2.1.2/references/accessibility-checklist.md +160 -0
- package/.versions/2.1.2/references/communication-contract.md +26 -0
- package/.versions/2.1.2/references/definition-of-done.md +67 -0
- package/.versions/2.1.2/references/fleet-coordination-patterns.md +171 -0
- package/.versions/2.1.2/references/observability-checklist.md +92 -0
- package/.versions/2.1.2/references/orchestration-patterns.md +370 -0
- package/.versions/2.1.2/references/performance-checklist.md +236 -0
- package/.versions/2.1.2/references/prompting-patterns.md +380 -0
- package/.versions/2.1.2/references/security-checklist.md +245 -0
- package/.versions/2.1.2/references/testing-patterns.md +235 -0
- package/.versions/2.1.2/references/workflow-authoring.md +304 -0
- package/.versions/2.1.2/skills/_internal/grilling.md +59 -0
- package/.versions/2.1.2/skills/browser-testing-with-devtools/SKILL.md +351 -0
- package/.versions/2.1.2/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/2.1.2/skills/compound-learning/SKILL.md +137 -0
- package/.versions/2.1.2/skills/constraint-driven-development/SKILL.md +338 -0
- package/.versions/2.1.2/skills/constraint-driven-development/references/floor-guard.md +99 -0
- package/.versions/2.1.2/skills/context-engineering/SKILL.md +341 -0
- package/.versions/2.1.2/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/2.1.2/skills/designing-agents/SKILL.md +394 -0
- package/.versions/2.1.2/skills/designing-agents/pi-harness-authoring.md +222 -0
- package/.versions/2.1.2/skills/drafting-workflows/SKILL.md +143 -0
- package/.versions/2.1.2/skills/drafting-workflows/scripts/make-workflow.ts +177 -0
- package/.versions/2.1.2/skills/fleet-connect/SKILL.md +25 -0
- package/.versions/2.1.2/skills/fleet-native-voice/SKILL.md +87 -0
- package/.versions/2.1.2/skills/fleet-native-voice/agents/openai.yaml +4 -0
- package/.versions/2.1.2/skills/fleet-native-voice.zip +0 -0
- package/.versions/2.1.2/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/2.1.2/skills/git-workflow-and-versioning/SKILL.md +316 -0
- package/.versions/2.1.2/skills/idea-refine/SKILL.md +182 -0
- package/.versions/2.1.2/skills/idea-refine/examples.md +238 -0
- package/.versions/2.1.2/skills/idea-refine/frameworks.md +99 -0
- package/.versions/2.1.2/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/2.1.2/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/2.1.2/skills/incremental-implementation/SKILL.md +353 -0
- package/.versions/2.1.2/skills/incremental-implementation.zip +0 -0
- package/.versions/2.1.2/skills/interview-me/SKILL.md +226 -0
- package/.versions/2.1.2/skills/orchestration-verification/SKILL.md +182 -0
- package/.versions/2.1.2/skills/peer-coms/SKILL.md +90 -0
- package/.versions/2.1.2/skills/performance-optimization/SKILL.md +496 -0
- package/.versions/2.1.2/skills/planning-and-task-breakdown/SKILL.md +318 -0
- package/.versions/2.1.2/skills/planning-and-task-breakdown.zip +0 -0
- package/.versions/2.1.2/skills/repository-ai-setup/SKILL.md +135 -0
- package/.versions/2.1.2/skills/repository-ai-setup/references/agent-fleet-ai-state.template.json +4 -0
- package/.versions/2.1.2/skills/repository-ai-setup/references/apply-contract.md +74 -0
- package/.versions/2.1.2/skills/repository-ai-setup/references/provenance-template.md +16 -0
- package/.versions/2.1.2/skills/repository-ai-setup/references/setup-flow.md +108 -0
- package/.versions/2.1.2/skills/repository-ai-setup/references/verify-setup.md +20 -0
- package/.versions/2.1.2/skills/repository-ai-setup.zip +0 -0
- package/.versions/2.1.2/skills/security-and-hardening/SKILL.md +524 -0
- package/.versions/2.1.2/skills/spec-driven-development/SKILL.md +295 -0
- package/.versions/2.1.2/skills/spec-driven-development.zip +0 -0
- package/.versions/2.1.2/skills/using-agent-skills/SKILL.md +198 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/LICENSE +21 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/README.md +430 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/api-and-interface-design/SKILL.md +367 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/browser-testing-with-devtools/SKILL.md +317 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/ci-cd-and-automation/SKILL.md +390 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/code-review-and-quality/SKILL.md +396 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/code-simplification/SKILL.md +331 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/constraint-driven-development/SKILL.md +311 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/constraint-driven-development/references/floor-guard.md +99 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/context-engineering/SKILL.md +337 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/debugging-and-error-recovery/SKILL.md +300 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/deprecation-and-migration/SKILL.md +247 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/documentation-and-adrs/SKILL.md +288 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/doubt-driven-development/SKILL.md +243 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/frontend-ui-engineering/SKILL.md +328 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/git-workflow-and-versioning/SKILL.md +355 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/idea-refine/SKILL.md +178 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/idea-refine/examples.md +238 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/idea-refine/frameworks.md +99 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/idea-refine/refinement-criteria.md +113 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/idea-refine/scripts/idea-refine.sh +15 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/incremental-implementation/SKILL.md +249 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/interview-me/SKILL.md +225 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/observability-and-instrumentation/SKILL.md +238 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/performance-optimization/SKILL.md +496 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/planning-and-task-breakdown/SKILL.md +257 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/security-and-hardening/SKILL.md +524 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/shipping-and-launch/SKILL.md +330 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/source-driven-development/SKILL.md +216 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/spec-driven-development/SKILL.md +245 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/test-driven-development/SKILL.md +398 -0
- package/.versions/2.1.2/vendor/agent-skills-upstream/skills/using-agent-skills/SKILL.md +192 -0
- package/CHANGELOG.md +7 -0
- package/docs/ARCHITECTURE.md +8 -0
- package/docs/codex-local-mcp.md +16 -0
- package/docs/fleet-native-voice.md +8 -0
- package/docs/system1-context-continuity.md +11 -5
- package/install-manifest.json +1 -1
- package/package.json +1 -1
- package/skills/fleet-native-voice.zip +0 -0
|
@@ -0,0 +1,183 @@
|
|
|
1
|
+
# Codex MCP setup for Agent Fleet
|
|
2
|
+
|
|
3
|
+
Register the native `af-local-read` MCP server and install the `fleet-native-voice` skill at the **user level** of a local Codex host with one explicit, deterministic command:
|
|
4
|
+
|
|
5
|
+
```bash
|
|
6
|
+
agent-fleet set-codex-mcp status
|
|
7
|
+
agent-fleet set-codex-mcp install
|
|
8
|
+
```
|
|
9
|
+
|
|
10
|
+
This guide covers installation, verification, migration, and removal only. Tool usage, permissions, observations, instructions, state layout, and error codes are in the [native Codex MCP guide](codex-local-mcp.md); the conversational layer is in the [voice workflow](fleet-native-voice.md). Installing Fleet itself is covered by [Fleet setup](agent-fleet-setup.md).
|
|
11
|
+
|
|
12
|
+
## Status and decision
|
|
13
|
+
|
|
14
|
+
**Status:** implemented on 2026-11-07 as `agent-fleet set-codex-mcp`. The decisions below were taken by the maintainer on 2026-11-04 and are recorded here instead of in an ADR directory.
|
|
15
|
+
|
|
16
|
+
- **D1 — scope.** The user level is the default: the MCP entry lives in `$CODEX_HOME/config.toml` and the skill copy in `~/.agents/skills/`. This explicitly replaces the earlier guidance, which configured a project-local `.codex/config.toml` table and a project-local skill symlink or ZIP extraction. That project-local setup remains a manual alternative (below), not the recommended path.
|
|
17
|
+
- **D2 — who installs.** A separate command, invoked explicitly by the operator: `agent-fleet set-codex-mcp <status|install|update|uninstall>`. `agent-fleet setup` does not call it, installs nothing for Codex, and still writes only inside the workspace. Like `set-hermes-watchdog`, writing outside the workspace is an operator decision.
|
|
18
|
+
- **D3 — where the decision is recorded.** Here, at the top of the guide operators read.
|
|
19
|
+
- **D4 — state namespace (delegated).** A new namespace with the defaults below. An earlier smoke or manual namespace is neither migrated nor touched; see [Migrate from a project-local configuration](#migrate-from-a-project-local-configuration).
|
|
20
|
+
|
|
21
|
+
Why user level: `codex mcp add` has no scope flag and always writes `$CODEX_HOME/config.toml`; a user-level entry follows the operator into every project; and the skill is a package artifact, not a per-project file.
|
|
22
|
+
|
|
23
|
+
## Requirements
|
|
24
|
+
|
|
25
|
+
- A POSIX host (Linux or macOS) with the same OS user running Codex and the Fleet/Pi sessions. The server and the command refuse Windows.
|
|
26
|
+
- Node.js **22.18 or newer** for the launcher. `--node` defaults to the Node that runs the command. A lower or undeterminable version is refused; the package's general Node 18 engine requirement is not sufficient for this server.
|
|
27
|
+
- A stable Agent Fleet runtime: a checkout or a global install (`npm install -g @chankov/agent-fleet`). A temporary `npx` cache is refused as a launcher location, because Codex would keep a path that disappears.
|
|
28
|
+
- The Codex CLI with `codex mcp add`, `codex mcp remove`, and `codex mcp list --json` (verified with codex-cli 0.166.0). The command never edits `config.toml` itself.
|
|
29
|
+
- Running Fleet/Pi sessions are not required to install; they are required to use the tools.
|
|
30
|
+
|
|
31
|
+
## What the command does
|
|
32
|
+
|
|
33
|
+
| Action | Writes | Effect |
|
|
34
|
+
| --- | --- | --- |
|
|
35
|
+
| `status` | nothing | Reports the resolved launcher, the `af-local-read` entry state, a project shadow if any, the skill copy state, both receipts, warnings, and refusals. Exit 2 when a refusal is present. |
|
|
36
|
+
| `install`, `update` | `$CODEX_HOME/config.toml` through `codex mcp add`; `~/.agents/skills/fleet-native-voice`; receipts and backups under `$CODEX_HOME/agent-fleet/` | The same behaviour, chosen by intent: probe the launcher, back up, register, re-read, then install the skill copy. |
|
|
37
|
+
| `uninstall` | the same places | Removes only the entry and skill tree that a receipt proves this command created. Keeps every state root, journal, archive, and backup. |
|
|
38
|
+
|
|
39
|
+
Output is JSON. Exit `0` is success or no change, `1` a failure, `2` a `status` with refusals. `--dry-run` prints the planned modes, the exact `codex` arguments, and the backup paths; it neither probes nor writes. `--force` is required to replace an entry or tree that differs from what the command would write, or to remove one without a matching receipt.
|
|
40
|
+
|
|
41
|
+
An `install` or `update` runs in this order, and stops at the first failure without writing anything further:
|
|
42
|
+
|
|
43
|
+
1. `status` is evaluated. Any refusal stops the run before a probe.
|
|
44
|
+
2. The exact launcher is started once over STDIO, exchanges `initialize` (protocol `2025-06-18`) and `tools/list`, and is terminated. The server must identify itself as `af-local-read` and advertise at least one tool. No tool is called, so no policy state is created. The tool count is reported, never compared with a fixed number.
|
|
45
|
+
3. `config.toml` is copied to `$CODEX_HOME/agent-fleet/backups/config.toml-<timestamp>` with mode `0600`. `codex mcp add` rewrites the file and drops inline comments inside other tables, so this copy is the only place those comments survive.
|
|
46
|
+
4. `codex mcp add af-local-read -- <node> <runtime> --registry-root … --policy-root … --host-profile … --principal …` runs. It always writes `$CODEX_HOME/config.toml`.
|
|
47
|
+
5. `codex mcp list --json` is re-read. The entry must match the launcher exactly before the receipt is written; otherwise the run fails and names the backup.
|
|
48
|
+
6. The skill is extracted from the packaged `skills/fleet-native-voice.zip` into a private staging directory, verified against the package, and moved into place atomically. Directories end up `0700` and files `0600`.
|
|
49
|
+
|
|
50
|
+
Entry and skill states, as `status` reports them:
|
|
51
|
+
|
|
52
|
+
| State | Meaning | `install` / `update` |
|
|
53
|
+
| --- | --- | --- |
|
|
54
|
+
| `missing` | no entry, or no skill directory | add the entry / install the copy |
|
|
55
|
+
| `current` | matches the launcher or the package, and the receipt is `managed` | no change |
|
|
56
|
+
| `adoptable` (entry), or `current` with an `unmanaged` receipt (skill) | matches, but was not written by this command | only the receipt is written |
|
|
57
|
+
| `drifted` | differs from the launcher, the package, or the receipt; for the entry also `enabled = false`, an `env`, `env_vars`, `cwd`, or a non-STDIO transport | refused; `--force` backs it up and replaces it |
|
|
58
|
+
| `broken` (entry) | the recorded command or runtime path does not exist | refused; `--force` backs it up and replaces it |
|
|
59
|
+
| `symlink` (skill) | the skill path is a symlink | always refused; remove the symlink yourself |
|
|
60
|
+
|
|
61
|
+
Receipts are `managed` when they match what is installed, `unmanaged` when absent, and `drifted` when present but unreadable or mismatched. A stale receipt without an entry or tree is removed by `uninstall`.
|
|
62
|
+
|
|
63
|
+
### Defaults
|
|
64
|
+
|
|
65
|
+
| Setting | Default | Override |
|
|
66
|
+
| --- | --- | --- |
|
|
67
|
+
| Codex home | `$CODEX_HOME`, else `~/.codex` | environment only |
|
|
68
|
+
| Node | the Node running the command | `--node <path>` |
|
|
69
|
+
| Runtime | `<package>/.pi/agent-fleet/scripts/fleet-codex-local-mcp.mjs` | derived from the installed package |
|
|
70
|
+
| `--registry-root` | `$PI_COMS_DIR`, else `~/.pi/coms` | `--registry-root <dir>` |
|
|
71
|
+
| `--policy-root` | `$CODEX_HOME/agent-fleet/state/fleet-native` | `--policy-root <dir>` |
|
|
72
|
+
| `--host-profile` | `desktop` | `--host-profile <name>` |
|
|
73
|
+
| `--principal` | `local-user` | `--principal <name>` |
|
|
74
|
+
| `--legacy-state-root` | not set | `--legacy-state-root <dir>` |
|
|
75
|
+
|
|
76
|
+
The launcher flags mean what the [native guide](codex-local-mcp.md#persistent-state-and-journal-upgrades) describes: the registry root is the existing COMS root (`projects/<project>/agents/*.json`, `sockets/<sessionId>.sock`), the policy root is a dedicated private directory for native bindings, and the host profile and principal are stable labels that partition state without proving OS identity. The server creates the policy root on first enrollment and uses the sibling directories `.observations`, `.instructions`, `.reports`, and `.permissions` next to it. For the default policy root the command creates its parent `state/`; an explicit `--policy-root` must already have an existing parent.
|
|
77
|
+
|
|
78
|
+
Registry, policy, and legacy roots must be normalized absolute paths with no symlink in their existing prefix, and must not overlap each other or the derived siblings; the command applies the same check as the server before writing. Keep the profile, principal, and policy root stable: changing any of them selects a different namespace, not a migration. The optional `--legacy-state-root` is the read-only archive of the retired CLI described under [preserving existing CLI data](codex-local-mcp.md#preserve-existing-cli-data-without-replaying-it); the command validates the path and passes it through, nothing more.
|
|
79
|
+
|
|
80
|
+
`enabled_tools` is deliberately **not** set. The whole catalogue is exposed, so the tools loaded in a chat match the installed source and the entry does not go stale when a release adds a tool. The Pi-side event relay readiness check also requires the complete loaded catalogue; a filtered list makes it refuse.
|
|
81
|
+
|
|
82
|
+
## Verify
|
|
83
|
+
|
|
84
|
+
1. Run `agent-fleet set-codex-mcp status`. Expect `mcpState: "current"`, `skillState: "current"`, both receipt states `managed`, `projectShadow.shadowed: false`, and an empty `errors` list.
|
|
85
|
+
2. Reload Codex through the host's supported procedure, open a **new** chat, and call `fleet_diagnostics {}`. It reports the Node runtime, protocol, and loaded tool names without touching the registry or policy state. A host that was already running may still show an older catalogue until it is reloaded.
|
|
86
|
+
3. In the same chat call `fleet_discover` for an explicit running project. `STATE_MISSING` or `NOT_ALLOWED` is the expected answer for a conversation that has not enrolled; it is not a setup error.
|
|
87
|
+
|
|
88
|
+
Registration exposes the tools in every Codex chat of this user. It grants nothing: each chat still enrolls each target through the reviewed `fleet_binding_prepare` / `fleet_binding_commit` flow under [connect a target](codex-local-mcp.md#connect-a-target-and-manage-permissions), and answers and approvals retain their separate per-action confirmation requirements. An explicit user send to one unambiguous, already selected current session with read+send uses technical prepare/commit without a second conversational confirmation; model-initiated or substantively expanded instructions still require a fresh preview confirmation, while ambiguity or a changed session stops the send. See [send an instruction](codex-local-mcp.md#send-an-instruction). Review the host's normal project-trust and MCP approval settings; do not disable protections to make this server load.
|
|
89
|
+
|
|
90
|
+
### nvm and other version managers
|
|
91
|
+
|
|
92
|
+
When `--node` resolves under `~/.nvm/versions/`, `status` and `install` print a warning rather than refusing. The entry stores that Node binary's absolute path, so after switching or upgrading Node the recorded path can disappear or stop matching. Run `agent-fleet set-codex-mcp update` afterwards so Codex keeps a working launcher; until then `status` reports the entry as `broken` or `drifted`. `uninstall` still works in that state, because it judges the entry against its receipt, not against the current Node.
|
|
93
|
+
|
|
94
|
+
## What this command does not install
|
|
95
|
+
|
|
96
|
+
These are separate, user-owned, Pi-side opt-ins. `set-codex-mcp` neither creates, reads, nor manages them, and `uninstall` leaves them alone:
|
|
97
|
+
|
|
98
|
+
- **Event relay.** `/af-codex-events prepare|enable <private-config>`, its private JSON config, and its `.event-ingress` / `.desktop-events` journals — see [explicit production event ingress](codex-local-mcp.md#explicit-production-event-ingress-disabled-until-approved).
|
|
99
|
+
- **Damage Control auto policy.** The optional `.pi/damage-control-auto-policy.yaml` — see [machine Damage Control permissions](codex-local-mcp.md#machine-damage-control-permissions-source-checkpoint).
|
|
100
|
+
- **Desktop queue adapter.** The experimental private Unix-socket queue path — see [the opt-in Desktop queue adapter](codex-local-mcp.md#experimental-opt-in-desktop-queue-adapter).
|
|
101
|
+
|
|
102
|
+
## Manual project-level alternative
|
|
103
|
+
|
|
104
|
+
A project-local configuration is still possible and is **not** managed by the command. Codex reads a trusted project's `.codex/config.toml` when its working directory is inside that project, and an entry there with the same server name **shadows** the user-level entry for that project. `status` reports this as `projectShadow.shadowed: true` with the shadowing transport, and never edits the project file.
|
|
105
|
+
|
|
106
|
+
Merge the following table into `<project>/.codex/config.toml` without replacing unrelated configuration. Every `/absolute/path/...` value is a placeholder; TOML paths are literal and do not expand `~` or environment variables.
|
|
107
|
+
|
|
108
|
+
```toml
|
|
109
|
+
[mcp_servers.af-local-read]
|
|
110
|
+
command = "/absolute/path/to/node"
|
|
111
|
+
args = [
|
|
112
|
+
"/absolute/path/to/agent-fleet/.pi/agent-fleet/scripts/fleet-codex-local-mcp.mjs",
|
|
113
|
+
"--registry-root", "/absolute/path/to/coms",
|
|
114
|
+
"--policy-root", "/absolute/path/to/private-state/fleet-native",
|
|
115
|
+
"--host-profile", "desktop",
|
|
116
|
+
"--principal", "local-user"
|
|
117
|
+
]
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
Use the `.mjs` bootstrap for both checkout and package installs: it loads this distribution's TypeScript sources through Node's scoped loader, whereas Node's automatic TypeScript stripping refuses files beneath `node_modules`. Configure it as local STDIO, not an HTTP service; the launcher reads no roots or identity from environment variables. A manual table has no backup, no probe, no re-read, and no receipt; keep `enabled_tools` unset for the reasons above, or maintain the list yourself on every release.
|
|
121
|
+
|
|
122
|
+
For a project-local skill, Codex also scans `<project>/.agents/skills/`. From a checkout, link the source; from a package, extract the archive. Both commands refuse to touch an existing destination, including a dangling symlink:
|
|
123
|
+
|
|
124
|
+
```sh
|
|
125
|
+
mkdir -p .agents/skills
|
|
126
|
+
test ! -e .agents/skills/fleet-native-voice && test ! -L .agents/skills/fleet-native-voice && \
|
|
127
|
+
ln -s ../../skills/fleet-native-voice .agents/skills/fleet-native-voice
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
```sh
|
|
131
|
+
mkdir -p .agents/skills
|
|
132
|
+
test ! -e .agents/skills/fleet-native-voice && test ! -L .agents/skills/fleet-native-voice && \
|
|
133
|
+
unzip -n /absolute/path/to/agent-fleet/skills/fleet-native-voice.zip -d .agents/skills
|
|
134
|
+
```
|
|
135
|
+
|
|
136
|
+
Keep one copy of the skill per host where you can; a user-level copy and a project-local copy of the same skill are two things to keep in step.
|
|
137
|
+
|
|
138
|
+
## Migrate from a project-local configuration
|
|
139
|
+
|
|
140
|
+
1. Inside the project, run `agent-fleet set-codex-mcp status`. `projectShadow` shows the project table and the policy root, profile, and principal it uses.
|
|
141
|
+
2. Decide which namespace the user-level entry should select. Rights are bound to one Codex conversation (its thread UUID) and one target epoch, so a **new** chat has no rights in either namespace and nothing needs migrating for it. To keep using an existing chat's bindings, pass that chat's `--policy-root`, `--host-profile`, `--principal`, and `--legacy-state-root` explicitly to `install`. Otherwise accept the defaults; the old namespace stays on disk untouched, and deleting it later is your decision, never the command's.
|
|
142
|
+
3. Run `agent-fleet set-codex-mcp install`.
|
|
143
|
+
4. Remove the `[mcp_servers.af-local-read]` table from the project `.codex/config.toml` yourself, or the whole file when it holds nothing else. Until you do, `status` keeps reporting the shadow and Codex keeps using the project entry inside that project. Any manual `enabled_tools` list goes with it.
|
|
144
|
+
5. Remove the project-local skill symlink or directory under `<project>/.agents/skills/` so one copy remains.
|
|
145
|
+
6. Reload Codex, open a new chat, and run the [verification](#verify) steps.
|
|
146
|
+
7. If an `/af-codex-events` private config exists, it names a binding and epoch of the old namespace and chat. After enrolling in the new chat, update that config and run `/af-codex-events prepare` again; the command does not touch it.
|
|
147
|
+
|
|
148
|
+
## Remove
|
|
149
|
+
|
|
150
|
+
Removing the registration does **not** revoke persisted permissions, so remove rights first, while the tools are still available:
|
|
151
|
+
|
|
152
|
+
1. In every chat that holds rights, use the reviewed `fleet_binding_prepare` intents: `forget` removes read, send, and approve for a binding; `revoke_send` or `revoke_approve` remove one right while keeping read. Verify afterwards with `fleet_check_read` and `fleet_permissions`. Historical receipts remain readable; that is not a live grant. See [security limits and removal](codex-local-mcp.md#security-limits-and-removal).
|
|
153
|
+
2. Run `agent-fleet set-codex-mcp uninstall`. It backs up `config.toml`, runs `codex mcp remove af-local-read`, re-reads the list, deletes both receipts, and moves the skill tree to `$CODEX_HOME/agent-fleet/backups/fleet-native-voice-uninstall-<timestamp>`. An entry or tree without a matching receipt needs `--force`; a skill symlink is refused regardless.
|
|
154
|
+
3. Reload Codex through the host's supported procedure.
|
|
155
|
+
|
|
156
|
+
The result reports `bindingsRetained: true`. Policy roots and their siblings, the legacy archive, the backups, any `/af-codex-events` config and journals, and the auto policy file all stay in place. Deleting them is a separate decision; the command never does it, and it never stops Fleet peers.
|
|
157
|
+
|
|
158
|
+
## Files this command touches
|
|
159
|
+
|
|
160
|
+
| Path | Written by |
|
|
161
|
+
| --- | --- |
|
|
162
|
+
| `$CODEX_HOME/config.toml` | `codex mcp add` / `codex mcp remove` only |
|
|
163
|
+
| `$CODEX_HOME/agent-fleet/af-local-read.receipt.json`, `fleet-native-voice.receipt.json` | `install`, `update`, `uninstall` (mode `0600`) |
|
|
164
|
+
| `$CODEX_HOME/agent-fleet/backups/config.toml-<timestamp>` | every `install`, `update`, or `uninstall` that changes the entry |
|
|
165
|
+
| `$CODEX_HOME/agent-fleet/backups/fleet-native-voice-<timestamp>`, `fleet-native-voice-uninstall-<timestamp>` | a replaced or removed skill tree |
|
|
166
|
+
| `$CODEX_HOME/agent-fleet/state/` | created empty as the parent of the default policy root |
|
|
167
|
+
| `~/.agents/skills/fleet-native-voice/` | `install`, `update`, `uninstall` |
|
|
168
|
+
|
|
169
|
+
Never touched: a project `.codex/config.toml` or `.agents/skills/`, the contents of any policy root or sibling, the legacy archive, the `/af-codex-events` config, `.pi/damage-control-auto-policy.yaml`, and anything inside the workspace.
|
|
170
|
+
|
|
171
|
+
## Troubleshooting
|
|
172
|
+
|
|
173
|
+
| Symptom | What it means |
|
|
174
|
+
| --- | --- |
|
|
175
|
+
| `status` exits 2 with `errors` | A refusal: Node too old, an `npx` runtime, a relative or overlapping root, a symlinked state root, an unsafe profile or principal name, or an unsupported platform. Nothing was written; fix the listed cause. |
|
|
176
|
+
| `codex mcp list --json` returned unexpected output | The installed Codex CLI differs from the verified one; check `codex --version`. |
|
|
177
|
+
| `af-local-read probe failed … LOCAL_MCP_START_FAILED` | The runtime distribution is incomplete or the Node is too old. Nothing was written. |
|
|
178
|
+
| `codex reports no af-local-read entry after add` | Codex did not persist the entry as expected. No receipt was written; inspect `config.toml` and the named backup. |
|
|
179
|
+
| `projectShadow.shadowed: true` | A project table shadows the user entry in this project. Remove that table yourself. |
|
|
180
|
+
| entry `drifted` or `broken` after a Node change | Run `agent-fleet set-codex-mcp update`. |
|
|
181
|
+
| skill `symlink` | The command never follows or replaces it; remove the symlink yourself first. |
|
|
182
|
+
|
|
183
|
+
For tool-level error codes such as `IDENTITY_REQUIRED`, `STATE_MISSING`, or `NOT_ALLOWED`, see the [native guide's troubleshooting table](codex-local-mcp.md#troubleshooting).
|
|
@@ -0,0 +1,188 @@
|
|
|
1
|
+
# coms Hermes bridge
|
|
2
|
+
|
|
3
|
+
> The optional `hub-watchdog` is not this bridge and is not a coms conductor. It has no
|
|
4
|
+
> Herdr, shell, direct-tool, peer-delegation, service, or gateway authority. `hermes send --to`
|
|
5
|
+
> is an explicit destination mechanism, never origin-route evidence. Gate O has no checked-in
|
|
6
|
+
> live proof, so the supported watchdog posture is journal-only/dormant: no delivery,
|
|
7
|
+
> steering, cancellation, or recovery. It must not send an out-of-turn update, wake a chat, or
|
|
8
|
+
> fall back to another route. See [the watchdog runbook](hermes-watchdog-supervisor.md).
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
Protocol contract for the Hermes ⇄ pi `coms` bridge. The first implemented daemon is `.pi/agent-fleet/scripts/coms-hermes-bridge.ts`, which registers a `user-remote` peer and turns coms prompt envelopes into Hermes/Telegram questions.
|
|
12
|
+
|
|
13
|
+
## Pieces
|
|
14
|
+
|
|
15
|
+
| Piece | Role |
|
|
16
|
+
| --- | --- |
|
|
17
|
+
| `.pi/agent-fleet/scripts/coms-hermes-bridge.ts` | Daemon peer, default name `user-remote`, purpose `Remote human via Hermes/Telegram`. Accepts prompt, cancel, and ping envelopes. |
|
|
18
|
+
| `.pi/agent-fleet/scripts/lib/hermes-bridge-core.ts` | Pure contract logic: qid validation, Telegram formatting, answer-file validation, answer mapping, timeout outcome, state transitions, and log records. |
|
|
19
|
+
| `.pi/agent-fleet/scripts/lib/coms-envelope.ts` | Shared non-pi envelope wire shapes, including additive `cancel` envelopes. |
|
|
20
|
+
| `~/.pi/coms/hermes-bridge/questions/` | Private answer-file wire written by the Hermes gateway/liaison. |
|
|
21
|
+
| `~/.pi/coms/hermes-bridge/log.ndjson` | Bridge observability log. |
|
|
22
|
+
|
|
23
|
+
## user-remote topology
|
|
24
|
+
|
|
25
|
+
1. A pi peer sends a coms `prompt` envelope to `user-remote`.
|
|
26
|
+
2. The bridge derives `qid` from `prompt.msg_id`, formats the question, and runs `hermes send --to <target> <message>` (`<target>` defaults to `telegram`). For a topic, copy the target accepted by `hermes send --list telegram`; depending on the Hermes output format, its `id` may already contain the `:<thread_id>` suffix, so do not append the thread twice.
|
|
27
|
+
3. The human replies in Telegram; the Hermes gateway/liaison writes the answer file.
|
|
28
|
+
4. The bridge polls the questions directory, validates the file, maps the answer, sends a coms `response` envelope, and removes the answer file.
|
|
29
|
+
|
|
30
|
+
## Protocol contract v1
|
|
31
|
+
|
|
32
|
+
### qid and correlation
|
|
33
|
+
|
|
34
|
+
`qid` is exactly the prompt envelope's `msg_id`. It must match the 26-character Crockford ULID regex `^[0-9A-HJKMNP-TV-Z]{26}$`. The same `qid` is the only correlation key across coms, Telegram, answer files, state, and logs.
|
|
35
|
+
|
|
36
|
+
### Telegram question format
|
|
37
|
+
|
|
38
|
+
`formatTelegramQuestion` emits UTF-16 text capped at 4096 code units:
|
|
39
|
+
|
|
40
|
+
```text
|
|
41
|
+
❓ [HUB-Q:<qid>] <question>
|
|
42
|
+
|
|
43
|
+
📁 Project: <coms-project>
|
|
44
|
+
|
|
45
|
+
Context: <context, truncated if needed>
|
|
46
|
+
|
|
47
|
+
Options:
|
|
48
|
+
1. <title> — <description>
|
|
49
|
+
...
|
|
50
|
+
|
|
51
|
+
↩ Reply to this message, or type: HUB-Q:<qid>: <answer>
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
`Project:` is always present and comes from the bridge's validated `--project` scope, making simultaneous questions from different pools distinguishable. `Context:` is omitted when absent. `Options:` is omitted when no options are supplied. Context receives the remaining budget after the header, project, options, and reply instruction.
|
|
55
|
+
|
|
56
|
+
### Answer-file path, schema, and validation
|
|
57
|
+
|
|
58
|
+
The private wire path is:
|
|
59
|
+
|
|
60
|
+
```text
|
|
61
|
+
~/.pi/coms/hermes-bridge/questions/<qid>.answer.json
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
Schema:
|
|
65
|
+
|
|
66
|
+
```json
|
|
67
|
+
{
|
|
68
|
+
"qid": "<26-character Crockford ULID>",
|
|
69
|
+
"answer": "<text>",
|
|
70
|
+
"answered_by": "telegram:<user>",
|
|
71
|
+
"at": "<ISO timestamp>"
|
|
72
|
+
}
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
Validation rejects and ignores files unless all conditions hold: filename ends in `.answer.json`; filename qid is valid; filename qid is currently pending; JSON parses; object fields match the schema; `at` parses as a timestamp; and body `qid` equals the filename qid. Rejection reasons are `invalid_path`, `invalid_qid`, `foreign_qid`, `invalid_json`, `invalid_schema`, and `qid_mismatch`; the daemon logs rejected files as `answer_rejected` and removes them. Exception: an `invalid_json` file is treated as a possible partial write and left in place for a short grace window (`max(2 × poll interval, 1s)` from first sighting); it is rejected and removed only if it still fails to parse after the grace expires.
|
|
76
|
+
|
|
77
|
+
### Answer mapping
|
|
78
|
+
|
|
79
|
+
If options exist and the trimmed answer is a 1-based number for an option, the response is `{ "kind": "selection", "selections": ["<option title>"] }`. If options exist and the trimmed answer case-insensitively equals an option title, it maps to the same selection shape. All other answers map to `{ "kind": "freeform", "text": "<trimmed answer>" }`.
|
|
80
|
+
|
|
81
|
+
### Cancel semantics
|
|
82
|
+
|
|
83
|
+
`cancel` is an additive coms envelope with shape `{ "type": "cancel", "msg_id", "from", "to", "created_at", "ref_msg_id" }`; `ref_msg_id` is the target `qid`. The bridge acks well-formed cancel envelopes before handling them.
|
|
84
|
+
|
|
85
|
+
For a pending qid, cancel clears the timeout, removes the pending question, records terminal state `cancelled`, appends a `cancelled` log event, and sends a Telegram note: `✖ [HUB-Q:<qid>] The question was cancelled — it was answered from the console.` Cancel for a non-pending or invalid qid is a no-op after the envelope ack. A later answer file for a closed qid is treated as `late_answer`: logged, removed, and answered in Telegram with a polite ignored note; no response envelope is sent.
|
|
86
|
+
|
|
87
|
+
**Cancellation is local wait abandonment.** Cancelling a coms-backed run ends only this side's wait. The remote peer is not signalled and may keep working, so a `cancelled` state here is a statement about the local wait, never about the remote task. It follows that watchdog auto-recovery is forbidden for coms runs: no automatic retry, re-dispatch, retarget, or recovery invoke may follow a coms cancellation, and a cancelled coms run is never a recovery target. An explicit `hermes send --to <destination>` remains a destination-only mechanism chosen by a human; it is not evidence of an origin route and must not be used to "reply" to a cancelled run.
|
|
88
|
+
|
|
89
|
+
### Timeouts
|
|
90
|
+
|
|
91
|
+
The per-question remote timeout defaults to `PI_COMS_TIMEOUT_MS`, or `1800000` ms when unset/invalid; `--timeout <ms>` overrides it. On timeout, the bridge removes the pending question, records terminal state `timeout`, logs `timeout`, sends the Telegram note `⌛ [HUB-Q:<qid>] The question timed out after <ms>ms.`, and sends an error response envelope with error `no remote answer within <ms>ms` and `response: null`.
|
|
92
|
+
|
|
93
|
+
### States
|
|
94
|
+
|
|
95
|
+
Question states are in-memory per qid: `pending`, `delivered`, `answered`, `cancelled`, and `timeout`. Implemented transitions are: `null + question_received → pending`; `pending + delivered → delivered`; `pending + delivery_error → null`; `pending|delivered + answered → answered` (the daemon currently answers from delivered or pending if the file arrives quickly); `pending|delivered + cancelled → cancelled`; `pending|delivered + timeout → timeout`; and terminal `answered|cancelled|timeout + late_answer` remains terminal.
|
|
96
|
+
|
|
97
|
+
### ndjson logging
|
|
98
|
+
|
|
99
|
+
The bridge appends one JSON object per line to `~/.pi/coms/hermes-bridge/log.ndjson`. Core log records have shape `{ "at": "<ISO>", "qid": "<qid>", "event": "<event>", "detail"?: <value> }`. Contract events are `question_received`, `delivered`, `delivery_error`, `answered`, `cancelled`, `timeout`, and `late_answer`; the daemon also writes `answer_rejected` for invalid answer files. Ping agent cards report `queue_depth` as the current number of pending questions.
|
|
100
|
+
|
|
101
|
+
## Hermes as conductor
|
|
102
|
+
|
|
103
|
+
Hermes can also act as the conductor without this daemon: use `coms-cli list` to discover peers and `coms-cli send --await --timeout <ms>` to delegate to hub-team pi peers, then synthesize the results for the human. This conductor topology uses the existing coms CLI as the bridge; no standing Hermes peer is required.
|
|
104
|
+
|
|
105
|
+
Launch a visible conductor workspace with:
|
|
106
|
+
|
|
107
|
+
```bash
|
|
108
|
+
just fleet conductor hermes docs # live conductor + team workspace
|
|
109
|
+
just fleet conductor hermes docs --dry-run # preview; no Herdr calls
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
The live recipe reuses `.pi/agent-fleet/scripts/team-up.ts --conductor`: it creates a normal herdr workspace labeled `<worktree-tag>-conductor-<team>` (the tag is the last dot-segment of the checkout's basename, so the same team from a different worktree gets its own workspace), places a `conductor` pane running `hermes -p dev`, and tiles the chosen team beside it. Team peers keep their normal coms harness and herdr presence reporting, so they continue to show agent state in the sidebar; Hermes' own herdr-agent-state plugin is responsible for the conductor pane's state.
|
|
113
|
+
|
|
114
|
+
### Telegram bridge control command
|
|
115
|
+
|
|
116
|
+
The outbound `hermes send` path needs a configured Telegram channel but no skill. Full reply round-trip additionally needs Agent Fleet's `hub-liaison` skill in the profile that owns the running Telegram gateway. Pi uses the namespaced command:
|
|
117
|
+
|
|
118
|
+
```text
|
|
119
|
+
/af-set-hermes-telegram status --profile default
|
|
120
|
+
/af-set-hermes-telegram install --profile default
|
|
121
|
+
/af-set-hermes-telegram install --profile default --force --restart
|
|
122
|
+
/af-set-hermes-telegram on 7883056502:1735 --profile default
|
|
123
|
+
/af-set-hermes-telegram off 7883056502:1735
|
|
124
|
+
```
|
|
125
|
+
|
|
126
|
+
Claude Code exposes the unprefixed `/set-hermes-telegram`; the arguments and backend are identical. The deterministic CLI can also be called directly with `agent-fleet set-hermes-telegram ...`.
|
|
127
|
+
|
|
128
|
+
#### `status` and profile resolution
|
|
129
|
+
|
|
130
|
+
`status` is read-only. It verifies the Hermes executable/profile, compares the complete installed `hub-liaison` tree to the version packaged with Agent Fleet, asks Hermes whether the skill is enabled, checks `terminal` and `file` toolsets for the `telegram` platform, and reports gateway state. `--profile <name>` is recommended. Without it the controller selects a profile only when `hermes gateway list` reports exactly one running gateway; zero or multiple running gateways fail closed and require an explicit profile.
|
|
131
|
+
|
|
132
|
+
#### `install`
|
|
133
|
+
|
|
134
|
+
`install` writes to `<Hermes-profile-path>/skills/hub-liaison`, where the profile path comes from `hermes profile show <name>` (important because the `default` profile is normally `~/.hermes`, while named profiles normally live below `~/.hermes/profiles/`). Installation behavior is:
|
|
135
|
+
|
|
136
|
+
- missing skill: copied atomically from the packaged Agent Fleet source;
|
|
137
|
+
- byte-identical tree: no-op;
|
|
138
|
+
- differing tree: refused unless `--force` is explicit;
|
|
139
|
+
- forced replacement: the previous tree is moved first to `<profile>/backups/agent-fleet/hub-liaison-<timestamp>`;
|
|
140
|
+
- symlinks or unsupported filesystem entries in either skill tree are refused;
|
|
141
|
+
- the installed tree is fingerprinted again, then `hermes --profile <name> skills list --enabled-only` and `tools list --platform telegram` are run for verification.
|
|
142
|
+
|
|
143
|
+
The command does not silently broaden Telegram tool permissions. If `terminal` or `file` is disabled, it prints the explicit remediation:
|
|
144
|
+
|
|
145
|
+
```bash
|
|
146
|
+
hermes --profile <name> tools enable --platform telegram terminal file
|
|
147
|
+
```
|
|
148
|
+
|
|
149
|
+
If the skill itself is disabled, use `hermes --profile <name> skills config`. A running gateway is restarted only with explicit `--restart`; otherwise the command prints the required restart command. A stopped gateway is never started as a side effect. No install/status/on/off action sends a test Telegram message.
|
|
150
|
+
|
|
151
|
+
#### `on` and `off`
|
|
152
|
+
|
|
153
|
+
`on` fails before touching Herdr unless the selected gateway is running, `hub-liaison` is current and enabled, and both required Telegram toolsets are enabled. It then closes any existing pane labeled `hermes-bridge` in the current workspace, creates a new right-hand pane in that **same Herdr workspace**, labels it `hermes-bridge`, and starts the daemon with `telegram:<id>` as its exact target. The selected profile is forwarded as `--hermes-profile`, so every question, timeout, cancel, and late-answer send executes as `hermes --profile <name> send ...` rather than silently falling back to Hermes' sticky default. `off` remains available even when Hermes readiness is broken, closes the bridge pane, creates nothing, and is idempotent.
|
|
154
|
+
|
|
155
|
+
The Telegram destination must contain digits only (`<chat_id>`) or two digit groups separated by one colon (`<chat_id>:<topic_id>`). Values such as `telegram:123`, `123:`, `123:456:789`, spaces, signs, and letters are rejected. The controller infers the coms project independently from the current hub process's explicit `--project`, then `PI_COMS_PROJECT`, then `default`.
|
|
156
|
+
|
|
157
|
+
The manual equivalent is:
|
|
158
|
+
|
|
159
|
+
```bash
|
|
160
|
+
node --experimental-strip-types .pi/agent-fleet/scripts/coms-hermes-bridge.ts \
|
|
161
|
+
--project af \
|
|
162
|
+
--hermes-profile default \
|
|
163
|
+
--timeout 1800000 \
|
|
164
|
+
--to 'telegram:<chat_id>:<thread_id>'
|
|
165
|
+
just fleet team docs --project af
|
|
166
|
+
```
|
|
167
|
+
|
|
168
|
+
Repeated value flags such as two `--to` arguments are rejected at startup rather than silently selecting one destination. The `ask-user-remote` wrapper resolves the explicit Pi `--project` flag when the tool executes, so non-default hubs discover `user-remote` in their own pool.
|
|
169
|
+
|
|
170
|
+
Hard boundary: the Hermes conductor must not run `herdr` commands, drive panes, create/kill workspaces, or manage fleet lifecycle. Herdr driving stays with the human/orchestrator so the damage-control model remains intact; see `.pi/damage-control-rules.yaml` for the authoritative no-herdr boundary. Hermes may only operate inside the project coms pool through the documented coms CLI commands.
|
|
171
|
+
|
|
172
|
+
## Hermes and the experimental ChatGPT session client
|
|
173
|
+
|
|
174
|
+
Hermes/Telegram remains the **inbound** human `ask_user` route. The experimental
|
|
175
|
+
ChatGPT Fleet session client is ChatGPT-initiated and is not an inbound question
|
|
176
|
+
channel. See the [session client runbook](codex-session-bridge.md).
|
|
177
|
+
|
|
178
|
+
Both conductor contracts are advisory outside Pi damage-control: Pi wraps Pi
|
|
179
|
+
tool calls, not Hermes or Codex, and neither has an OS command allowlist.
|
|
180
|
+
Human confirmation, approvals, and sandboxing reduce risk but do not
|
|
181
|
+
technically enforce either external contract.
|
|
182
|
+
|
|
183
|
+
## Deferred
|
|
184
|
+
|
|
185
|
+
- Standing conductor peer for pi → Hermes inbound messages.
|
|
186
|
+
- Telegram-driven conductor profile.
|
|
187
|
+
- Group/multi-recipient questions and non-text answers.
|
|
188
|
+
- Kanban-driven orchestration on top of the same conductor contract.
|
|
@@ -0,0 +1,145 @@
|
|
|
1
|
+
# Native voice workflow for Agent Fleet
|
|
2
|
+
|
|
3
|
+
Use the `fleet-native-voice` skill to discuss explicitly named Fleet/Pi sessions in one Codex conversation. Codex keeps spoken replies brief while retaining complete action previews and correlation details in the written chat.
|
|
4
|
+
|
|
5
|
+
The skill is a conversational layer over the existing local `af-local-read` MCP server. It does not add a voice engine, a transport, new tools, or permissions. For installation, see the [Codex MCP setup guide](codex-setup.md); for the full tool catalogue, storage, and error codes, see the [native Codex MCP guide](codex-local-mcp.md).
|
|
6
|
+
|
|
7
|
+
## What has actually been verified
|
|
8
|
+
|
|
9
|
+
A spoken request through **Codex desktop in the same chat** reached the agent through a voice-to-agent handoff. The agent made native discovery and read-policy checks for two explicitly named targets, received fresh registry entries and expected `NOT_ALLOWED` results without new grants, and returned the results to the active voice conversation.
|
|
10
|
+
|
|
11
|
+
This establishes that bounded desktop voice-to-agent route, not every action described below as a live voice-tested capability. In particular:
|
|
12
|
+
|
|
13
|
+
- Installing a skill, using dictation, seeing a microphone button, or succeeding in text mode does not prove native voice compatibility.
|
|
14
|
+
- Successful observations, instruction delivery, and question answers through the native tools are distinct from testing those actions through voice. Do not assume voice-driven mutations have been verified.
|
|
15
|
+
- There is no mobile/remote compatibility promise, public endpoint, tunnel, background listener, or idle-chat wake in this workflow.
|
|
16
|
+
- The recorded handoff does not attest synthesized-audio delivery, human origin, or compatibility with every Codex build or voice host.
|
|
17
|
+
|
|
18
|
+
Use the availability check below in your own intended chat and host. If the native tools are missing, report the limitation rather than substituting another route.
|
|
19
|
+
|
|
20
|
+
## Install the skill and configure MCP separately
|
|
21
|
+
|
|
22
|
+
You need a compatible local Codex host, already running Fleet/Pi sessions, and the native MCP server registered. The server registration and the skill copy are installed together by one explicit command, described in the [Codex MCP setup guide](codex-setup.md):
|
|
23
|
+
|
|
24
|
+
```bash
|
|
25
|
+
agent-fleet set-codex-mcp install
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
That guide covers Node.js 22.18+, the local POSIX/socket requirements, private state locations, the verification steps, and the manual project-local alternative for the skill. The installed entrypoint is `~/.agents/skills/fleet-native-voice/SKILL.md`, with UI metadata at `agents/openai.yaml`. Check that Codex discovers `$fleet-native-voice` in the intended chat; if discovery or configuration loading needs a host lifecycle action, use the host's supported user-controlled procedure. The skill does not restart the app or activate tools automatically.
|
|
29
|
+
|
|
30
|
+
**Skill installation does not configure or start the MCP server, and neither grants access.** The `chatgpt-client` installer feature and CLI are retired; see [migration and retained data](codex-session-bridge.md). They are not a fallback for this workflow. The native voice skill is deliberately excluded from the Pi installer catalogue: a Pi persona does not have Codex-host native tools.
|
|
31
|
+
|
|
32
|
+
## Start with a no-grant availability check
|
|
33
|
+
|
|
34
|
+
Invoke `$fleet-native-voice` for native Fleet requests in text or voice. Native MCP is the current route; the retired CLI is not a fallback. If a project's old rules still require the CLI, surface that conflict and obtain an explicit routing decision rather than silently overriding the rules. Invoking the skill grants no access.
|
|
35
|
+
|
|
36
|
+
Choose actual `project/peer` names from your Fleet setup. All names in the examples below are illustrative; replace them with your intended running targets.
|
|
37
|
+
|
|
38
|
+
In the same chat, use your host's normal voice UI to say something like:
|
|
39
|
+
|
|
40
|
+
> Use the native Fleet workflow. Discover shop/orchestrator and api/orchestrator and check whether this chat has read permission. Do not grant any new rights, send instructions, or read peer transcripts.
|
|
41
|
+
|
|
42
|
+
Confirm that the actual native `fleet_discover` and `fleet_check_read` calls occurred for those targets, and inspect the returned source statuses. `STATE_MISSING` or `NOT_ALLOWED` can be expected for a new or ungranted conversation; neither is permission to enroll automatically. Discovery reads registry candidates, and the read check is registry-only, not a transcript read or receiver capability test.
|
|
43
|
+
|
|
44
|
+
A partial or stale registry result is a gap, not positive availability evidence. If the host uses a voice-to-agent handoff, distinguish that from direct voice execution when reporting the result. If tools or trusted host context are absent, stop the affected operation. Do not replace native calls with shell commands, another chat's metadata, another peer, or a remote service.
|
|
45
|
+
|
|
46
|
+
## Name connections explicitly
|
|
47
|
+
|
|
48
|
+
Use canonical `project/peer` selectors. You can supply friendly labels:
|
|
49
|
+
|
|
50
|
+
> In this chat, call shop/orchestrator frontend and api/orchestrator backend.
|
|
51
|
+
|
|
52
|
+
Codex keeps the label's canonical target, exact `sessionId`/`startedAt` epoch, known rights, and observation time. The label is a conversational convenience, not authority. The server chooses binding aliases; a friendly label does not create a custom enrollment alias.
|
|
53
|
+
|
|
54
|
+
If a mapping is missing, ambiguous, or uncertain because of speech recognition, clarify it before acting. “The other one,” the current working directory, a last-used target, or a matching question title is not enough. No mappings or permissions are restored from another chat or raw policy files.
|
|
55
|
+
|
|
56
|
+
To connect for reading, ask:
|
|
57
|
+
|
|
58
|
+
> Connect shop/orchestrator for read access only. Show me the exact preview before changing permissions.
|
|
59
|
+
|
|
60
|
+
Codex discovers the current target and prepares `enroll_read`. Review the exact target, epoch, old/proposed rights, effects, and expiry; **then** confirm before `fleet_binding_commit`. Existing current read rights do not require a new enrollment. After a session restart or replacement, `rebind_read` needs its own explicit old/new target preview and confirmation; send permission does not carry forward.
|
|
61
|
+
|
|
62
|
+
## Observe and catch up
|
|
63
|
+
|
|
64
|
+
With current read authority, examples include:
|
|
65
|
+
|
|
66
|
+
| Request | What to expect |
|
|
67
|
+
| --- | --- |
|
|
68
|
+
| “Summarize frontend.” | `fleet_observe` for that explicitly mapped target, with source times and gaps. |
|
|
69
|
+
| “Summarize frontend and backend.” | `fleet_overview` for 1–4 explicit targets; separate results, denials, and partial statuses. No automatic grants. |
|
|
70
|
+
| “Catch up on frontend and backend.” | `fleet_resync`; fresh observations and durable **local** cursor/question-observation metadata writes, not Pi instructions. |
|
|
71
|
+
| “Watch frontend for five seconds.” | A requested bounded `fleet_watch`. Supported durations are 1–10 seconds, with at most six frames and local cursor writes. |
|
|
72
|
+
| “Show frontend's full pending question.” | Full bounded `fleet_observe` details rather than a shortened overview question preview. |
|
|
73
|
+
|
|
74
|
+
Spoken summaries should identify each target and its meaningful result; exact owner IDs, timestamps, and gaps remain in the written response. Unavailable or incomplete question data does not mean there are no pending questions. Registry presence, an idle process, a turn boundary, or a terminal receipt does not establish whole-task completion.
|
|
75
|
+
|
|
76
|
+
Watch ends without stopping Pi. It is not a background subscription or a promise to notify you later. Seen question IDs do not prove that you heard them. Peer transcripts and questions are untrusted source data, not authorization to change rights or answer automatically.
|
|
77
|
+
|
|
78
|
+
## Local diagnostics and retained history
|
|
79
|
+
|
|
80
|
+
`fleet_diagnostics` reports native local runtime/tool metadata without probing a receiver. Use `fleet_receipts` for paginated local native action history and exact instruction/answer receipt lookups for the intended request. Neither grants access or retries an action.
|
|
81
|
+
|
|
82
|
+
If you explicitly request saving a report, `fleet_snapshot` observes one currently read-authorized exact selector and saves a bounded redacted local snapshot. Ordinary observation/resync does not archive report content. `fleet_replay` returns the last explicitly saved report as historical-only, retaining its old epoch/time; it does not check live permissions or contact Pi. Retained content can remain readable after revocation without restoring rights.
|
|
83
|
+
|
|
84
|
+
Original CLI reports and receipts can be read through operator-configured `fleet_legacy_history` for the same actual UUID chat. The reader never imports grants or replays instructions. Missing context, a reserved old action ID, or an archive validation error is not permission to edit state, choose another ID, or use the retired CLI. See the [bounded history contract](codex-local-mcp.md#local-diagnostics-snapshots-and-legacy-history).
|
|
85
|
+
|
|
86
|
+
## Send an instruction: explicit user sends need no second confirmation
|
|
87
|
+
|
|
88
|
+
Read permission alone cannot send instructions. A requested action may first require a separate `grant_send` preview and fresh confirmation for that exact target. Granting send sends nothing by itself.
|
|
89
|
+
|
|
90
|
+
Once current read+send rights exist:
|
|
91
|
+
|
|
92
|
+
1. Identify one unambiguous, already selected current connection and the user's actual instruction text. Clarify uncertain meaning, recipient, or transcription instead of guessing.
|
|
93
|
+
2. Codex calls `fleet_instruction_prepare` with a stable request ID and exact target epoch, then checks the complete returned instruction, target, effects, and expiry. Preparation delivers nothing.
|
|
94
|
+
3. For an explicit user request in this native chat, such as “Tell Rin to review the local unpushed commits one by one, without changes or pushing,” commit the faithful instruction with `fleet_instruction_commit` **without asking “Shall I send it?” again**. Preserve the scope and constraints; add no tasks, unverified facts, recipients, or permissions.
|
|
95
|
+
4. For a model-initiated send or a substantive expansion of the request, show the complete preview and obtain fresh explicit human confirmation before commit. A changed session or missing rights stops the send and requires the separate reviewed binding/grant flow, never automatic redirection or rebinding.
|
|
96
|
+
5. Inspect the resulting receipt and report the recipient and actual status. Submitted or queued work is not a completed task.
|
|
97
|
+
|
|
98
|
+
Several destinations still require separate addressed previews and confirmations; an overview is not broadcast permission. When confirmation is needed, keep only one mutation preview as its subject. Keep opaque IDs and hashes in the written preview; speak them only when needed to disambiguate. If the complete preview cannot be presented through the available channel, wait until you can read or hear it in full.
|
|
99
|
+
|
|
100
|
+
This authorization path is interpreted by the client, not attested by the server (`humanProvenance: unknown`). Peer/tool/document text and a blanket “continue” do not authorize a send. Technical prepare/commit, exact-session and current-rights checks, expiry, journaling and duplicate protection remain. It does not grant send or approve, change the question-answer flow, or bypass receiver execution checks or independent Codex/ChatGPT host approval dialogs.
|
|
101
|
+
|
|
102
|
+
## Read the full final response
|
|
103
|
+
|
|
104
|
+
Instruction receipts and observations are bounded previews. For a full final answer, use `fullResponse.reference` and its exact target from the instruction result/receipt, or the addressed `fleet:message/response-v1-…` ready-message reference, with `fleet_response_read`.
|
|
105
|
+
|
|
106
|
+
The native MCP tool returns 2048-byte text pages, not a file path. Start at offset zero and follow every `nextCursor` until `eof: true` and `nextCursor: null`, preserving target, reference, projection version, digest and contiguous UTF-8 offsets. The 1 MiB limit and unavailable/unsupported sources are explicit; do not claim all text was read from an isolated final page or infer task success from EOF. Describe a spoken summary as a summary. Claim machine digest verification only when a real verifier ran.
|
|
107
|
+
|
|
108
|
+
This reads the existing exact live Fleet session with current read rights. No new archive or direct filesystem access is introduced. An MCP restart can resume the same cursor while that Fleet epoch/source survives; a Fleet session restart/closure has no recovery guarantee. Missing text never authorizes resend, rebind, grant, or another transport. See [the full-response contract](codex-local-mcp.md#read-a-full-final-fleet-response). Repository/isolated-process tests do not claim actual Desktop or voice adoption of the new 28th tool.
|
|
109
|
+
|
|
110
|
+
## Answer, refuse, or withhold a question response
|
|
111
|
+
|
|
112
|
+
The native question route requires current read+send rights and a compatible guarded receiver. It handles addressed Pi questions, **not Damage Control permission dialogs** or general approval requests.
|
|
113
|
+
|
|
114
|
+
1. Obtain the full question, context, exact option titles/descriptions, and effective multiple-selection/freeform/comment flags. If several questions are pending, identify which one you are answering. Retain the exact target, question ID, and tool-call ID in the written chat.
|
|
115
|
+
2. Give your actual response. Codex preserves option titles exactly and clarifies uncertain transcription; it does not choose a default or infer an answer from a blanket “continue.”
|
|
116
|
+
3. Codex freshly checks the same pending question and calls `fleet_answer_prepare` for your exact answer or refusal.
|
|
117
|
+
4. Review the complete returned question/flags, normalized response, target, effects, and expiry. Give a **new** explicit confirmation before one `fleet_answer_commit`. The answer you gave in step 2 is not this confirmation.
|
|
118
|
+
5. Inspect the actual receipt. Accepted, late, expired, rejected, and unknown outcomes are different; no success is inferred from silence.
|
|
119
|
+
|
|
120
|
+
These requests have distinct meanings:
|
|
121
|
+
|
|
122
|
+
- **“Choose Stop.”** If `Stop` is an offered option, it is an ordinary selection, not the refusal operation.
|
|
123
|
+
- **“I refuse this question.”** An explicit addressed refusal uses `operation: refusal, response: null`. It resolves that question as declined/cancelled; it does not cancel the Pi turn.
|
|
124
|
+
- **“Do not send my answer.”** Withhold delivery; do not turn it into a refusal sent to Pi.
|
|
125
|
+
- **“Stop.”** If the intended effect is unclear, clarify rather than guessing between watch, question, permissions, or task cancellation.
|
|
126
|
+
|
|
127
|
+
If you change your response during confirmation, leave the old proposal uncommitted and prepare the new response with its own confirmation. If the question resolves or the owner changes, do not redirect the old answer elsewhere. Keep pending decisions in the written chat as well as the voice exchange.
|
|
128
|
+
|
|
129
|
+
## Handle uncertainty and finish safely
|
|
130
|
+
|
|
131
|
+
- Proposals expire after 300 seconds and are lost on server restart. A new preview needs a new confirmation; do not reuse expired consent.
|
|
132
|
+
- For an unknown instruction or answer outcome, keep the original request ID and inspect `fleet_instruction_receipt` or `fleet_answer_receipt`. Remote refresh requires current read authority. Do not resend automatically, switch IDs, guess a new target, or fall back to the CLI to force delivery.
|
|
133
|
+
- Bounded/volatile receiver evidence may be missing after a restart or capacity limit. Missing evidence is not proof of failed delivery. Already-started actions are not promised rollback.
|
|
134
|
+
- Missing/corrupt state and journal-upgrade requirements are operator conditions. Initialization or migration has a separate exact preview/confirmation workflow; migration also requires operator-confirmed writer quiescence. Connecting or invoking the skill does not authorize either.
|
|
135
|
+
|
|
136
|
+
For temporary access, request cleanup explicitly:
|
|
137
|
+
|
|
138
|
+
| Request | Effect after exact preview and fresh confirmation |
|
|
139
|
+
| --- | --- |
|
|
140
|
+
| “Revoke send access for frontend.” | `revoke_send` removes send while retaining read. A successful read afterward is expected. |
|
|
141
|
+
| “Forget this chat's frontend binding.” | `forget` removes both read and send for that binding. Verify `NOT_ALLOWED` afterward. |
|
|
142
|
+
|
|
143
|
+
Remove only the intended binding's access, not unrelated rights. Historical local receipts can remain readable after revocation; that is not a live read grant. Cleanup does not undo accepted work or stop Pi. Removing a skill or MCP registration alone does not revoke persisted permissions; see [MCP security and removal](codex-local-mcp.md#security-limits-and-removal).
|
|
144
|
+
|
|
145
|
+
End each exchange by stating what was observed or submitted, which decision remains pending, and any important gap. Spoken confirmation does not upgrade API `humanProvenance: unknown` to authenticated human origin. The same cooperative same-user policy, non-atomic observation/dispatch limits, independent Pi/Damage Control protections, and lack of exactly-once guarantees described in the MCP guide still apply.
|