@apralabs/apra-fleet 0.4.0 → 0.4.1
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/README.md +145 -7
- package/dist/agents/backlog-groomer.md +17 -1
- package/dist/agents/ci-watcher.md +13 -1
- package/dist/agents/deployer.md +15 -3
- package/dist/agents/doer.md +35 -1
- package/dist/agents/harvester.md +22 -3
- package/dist/agents/integ-test-runner.md +18 -2
- package/dist/agents/kb-reconciler.md +216 -0
- package/dist/agents/plan-reviewer.md +14 -1
- package/dist/agents/planner.md +88 -5
- package/dist/agents/regression-test-runner.md +19 -1
- package/dist/agents/reviewer.md +104 -3
- package/dist/agents/schemas/doer-output.json +63 -3
- package/dist/agents/schemas/harvester-output.json +59 -2
- package/dist/agents/schemas/integ-test-runner-output.json +2 -2
- package/dist/agents/schemas/kb-reconciler-output.json +87 -0
- package/dist/agents/schemas/planner-output.json +65 -0
- package/dist/agents/schemas/reviewer-output.json +105 -8
- package/dist/cli/install.d.ts +1 -0
- package/dist/cli/install.d.ts.map +1 -1
- package/dist/cli/install.js +136 -5
- package/dist/cli/install.js.map +1 -1
- package/dist/cli/join.js +1 -1
- package/dist/cli/join.js.map +1 -1
- package/dist/cli/kb-commit.d.ts +12 -0
- package/dist/cli/kb-commit.d.ts.map +1 -0
- package/dist/cli/kb-commit.js +53 -0
- package/dist/cli/kb-commit.js.map +1 -0
- package/dist/cli/kb-directives.d.ts +17 -0
- package/dist/cli/kb-directives.d.ts.map +1 -0
- package/dist/cli/kb-directives.js +146 -0
- package/dist/cli/kb-directives.js.map +1 -0
- package/dist/cli/kb-import.d.ts +13 -0
- package/dist/cli/kb-import.d.ts.map +1 -0
- package/dist/cli/kb-import.js +56 -0
- package/dist/cli/kb-import.js.map +1 -0
- package/dist/cli/uninstall.d.ts.map +1 -1
- package/dist/cli/uninstall.js +11 -0
- package/dist/cli/uninstall.js.map +1 -1
- package/dist/cli/watch.d.ts +53 -4
- package/dist/cli/watch.d.ts.map +1 -1
- package/dist/cli/watch.js +118 -17
- package/dist/cli/watch.js.map +1 -1
- package/dist/commands/kb-server.d.ts +8 -0
- package/dist/commands/kb-server.d.ts.map +1 -0
- package/dist/commands/kb-server.js +221 -0
- package/dist/commands/kb-server.js.map +1 -0
- package/dist/index.js +77 -2
- package/dist/index.js.map +1 -1
- package/dist/os/linux.d.ts +1 -0
- package/dist/os/linux.d.ts.map +1 -1
- package/dist/os/linux.js +18 -1
- package/dist/os/linux.js.map +1 -1
- package/dist/os/os-commands.d.ts +5 -0
- package/dist/os/os-commands.d.ts.map +1 -1
- package/dist/os/windows.d.ts +35 -0
- package/dist/os/windows.d.ts.map +1 -1
- package/dist/os/windows.js +67 -31
- package/dist/os/windows.js.map +1 -1
- package/dist/providers/agy.d.ts +12 -1
- package/dist/providers/agy.d.ts.map +1 -1
- package/dist/providers/agy.js +134 -9
- package/dist/providers/agy.js.map +1 -1
- package/dist/providers/claude.d.ts +11 -1
- package/dist/providers/claude.d.ts.map +1 -1
- package/dist/providers/claude.js +47 -19
- package/dist/providers/claude.js.map +1 -1
- package/dist/providers/codex.d.ts +11 -1
- package/dist/providers/codex.d.ts.map +1 -1
- package/dist/providers/codex.js +29 -6
- package/dist/providers/codex.js.map +1 -1
- package/dist/providers/copilot.d.ts +11 -1
- package/dist/providers/copilot.d.ts.map +1 -1
- package/dist/providers/copilot.js +26 -6
- package/dist/providers/copilot.js.map +1 -1
- package/dist/providers/email/headers.d.ts +15 -0
- package/dist/providers/email/headers.d.ts.map +1 -0
- package/dist/providers/email/headers.js +42 -0
- package/dist/providers/email/headers.js.map +1 -0
- package/dist/providers/email/index.d.ts +18 -0
- package/dist/providers/email/index.d.ts.map +1 -0
- package/dist/providers/email/index.js +60 -0
- package/dist/providers/email/index.js.map +1 -0
- package/dist/providers/email/provider.d.ts +49 -0
- package/dist/providers/email/provider.d.ts.map +1 -0
- package/dist/providers/email/provider.js +2 -0
- package/dist/providers/email/provider.js.map +1 -0
- package/dist/providers/email/sendgrid.d.ts +12 -0
- package/dist/providers/email/sendgrid.d.ts.map +1 -0
- package/dist/providers/email/sendgrid.js +67 -0
- package/dist/providers/email/sendgrid.js.map +1 -0
- package/dist/providers/email/smtp.d.ts +65 -0
- package/dist/providers/email/smtp.d.ts.map +1 -0
- package/dist/providers/email/smtp.js +373 -0
- package/dist/providers/email/smtp.js.map +1 -0
- package/dist/providers/gemini.d.ts +11 -1
- package/dist/providers/gemini.d.ts.map +1 -1
- package/dist/providers/gemini.js +38 -4
- package/dist/providers/gemini.js.map +1 -1
- package/dist/providers/none.d.ts +11 -1
- package/dist/providers/none.d.ts.map +1 -1
- package/dist/providers/none.js +21 -0
- package/dist/providers/none.js.map +1 -1
- package/dist/providers/opencode.d.ts +11 -1
- package/dist/providers/opencode.d.ts.map +1 -1
- package/dist/providers/opencode.js +55 -4
- package/dist/providers/opencode.js.map +1 -1
- package/dist/providers/provider.d.ts +77 -0
- package/dist/providers/provider.d.ts.map +1 -1
- package/dist/providers/provider.js +44 -0
- package/dist/providers/provider.js.map +1 -1
- package/dist/services/agent-provisioner.d.ts.map +1 -1
- package/dist/services/agent-provisioner.js +3 -6
- package/dist/services/agent-provisioner.js.map +1 -1
- package/dist/services/cloud/lifecycle.d.ts.map +1 -1
- package/dist/services/cloud/lifecycle.js +3 -0
- package/dist/services/cloud/lifecycle.js.map +1 -1
- package/dist/services/cloud/task-wrapper.d.ts +18 -0
- package/dist/services/cloud/task-wrapper.d.ts.map +1 -1
- package/dist/services/cloud/task-wrapper.js +157 -0
- package/dist/services/cloud/task-wrapper.js.map +1 -1
- package/dist/services/github-app.d.ts.map +1 -1
- package/dist/services/github-app.js +11 -2
- package/dist/services/github-app.js.map +1 -1
- package/dist/services/knowledge/audn.d.ts +37 -0
- package/dist/services/knowledge/audn.d.ts.map +1 -0
- package/dist/services/knowledge/audn.js +219 -0
- package/dist/services/knowledge/audn.js.map +1 -0
- package/dist/services/knowledge/file-hash.d.ts +11 -0
- package/dist/services/knowledge/file-hash.d.ts.map +1 -0
- package/dist/services/knowledge/file-hash.js +123 -0
- package/dist/services/knowledge/file-hash.js.map +1 -0
- package/dist/services/knowledge/http-provider.d.ts +46 -0
- package/dist/services/knowledge/http-provider.d.ts.map +1 -0
- package/dist/services/knowledge/http-provider.js +254 -0
- package/dist/services/knowledge/http-provider.js.map +1 -0
- package/dist/services/knowledge/kb-providers.d.ts +15 -0
- package/dist/services/knowledge/kb-providers.d.ts.map +1 -0
- package/dist/services/knowledge/kb-providers.js +92 -0
- package/dist/services/knowledge/kb-providers.js.map +1 -0
- package/dist/services/knowledge/kb-scope-input.d.ts +5 -0
- package/dist/services/knowledge/kb-scope-input.d.ts.map +1 -0
- package/dist/services/knowledge/kb-scope-input.js +11 -0
- package/dist/services/knowledge/kb-scope-input.js.map +1 -0
- package/dist/services/knowledge/kb-service.d.ts +3 -0
- package/dist/services/knowledge/kb-service.d.ts.map +1 -0
- package/dist/services/knowledge/kb-service.js +2 -0
- package/dist/services/knowledge/kb-service.js.map +1 -0
- package/dist/services/knowledge/path-validation.d.ts +2 -0
- package/dist/services/knowledge/path-validation.d.ts.map +1 -0
- package/dist/services/knowledge/path-validation.js +13 -0
- package/dist/services/knowledge/path-validation.js.map +1 -0
- package/dist/services/knowledge/pre-init.d.ts +14 -0
- package/dist/services/knowledge/pre-init.d.ts.map +1 -0
- package/dist/services/knowledge/pre-init.js +147 -0
- package/dist/services/knowledge/pre-init.js.map +1 -0
- package/dist/services/knowledge/project-slug.d.ts +2 -0
- package/dist/services/knowledge/project-slug.d.ts.map +1 -0
- package/dist/services/knowledge/project-slug.js +49 -0
- package/dist/services/knowledge/project-slug.js.map +1 -0
- package/dist/services/knowledge/sqlite-provider.d.ts +147 -0
- package/dist/services/knowledge/sqlite-provider.d.ts.map +1 -0
- package/dist/services/knowledge/sqlite-provider.js +1646 -0
- package/dist/services/knowledge/sqlite-provider.js.map +1 -0
- package/dist/services/knowledge/types.d.ts +163 -0
- package/dist/services/knowledge/types.d.ts.map +1 -0
- package/dist/services/knowledge/types.js +9 -0
- package/dist/services/knowledge/types.js.map +1 -0
- package/dist/services/member-home.d.ts +89 -0
- package/dist/services/member-home.d.ts.map +1 -0
- package/dist/services/member-home.js +256 -0
- package/dist/services/member-home.js.map +1 -0
- package/dist/services/member-remote-url.d.ts +34 -0
- package/dist/services/member-remote-url.d.ts.map +1 -0
- package/dist/services/member-remote-url.js +39 -0
- package/dist/services/member-remote-url.js.map +1 -0
- package/dist/services/orphan-recovery.d.ts +5 -2
- package/dist/services/orphan-recovery.d.ts.map +1 -1
- package/dist/services/orphan-recovery.js +19 -8
- package/dist/services/orphan-recovery.js.map +1 -1
- package/dist/services/preflight-check.d.ts +56 -0
- package/dist/services/preflight-check.d.ts.map +1 -0
- package/dist/services/preflight-check.js +277 -0
- package/dist/services/preflight-check.js.map +1 -0
- package/dist/services/stall/log-path-resolver.d.ts +11 -8
- package/dist/services/stall/log-path-resolver.d.ts.map +1 -1
- package/dist/services/stall/log-path-resolver.js +17 -40
- package/dist/services/stall/log-path-resolver.js.map +1 -1
- package/dist/services/stall/stall-detector.d.ts +32 -0
- package/dist/services/stall/stall-detector.d.ts.map +1 -1
- package/dist/services/stall/stall-detector.js +149 -6
- package/dist/services/stall/stall-detector.js.map +1 -1
- package/dist/services/stall/stall-poller.d.ts +34 -0
- package/dist/services/stall/stall-poller.d.ts.map +1 -1
- package/dist/services/stall/stall-poller.js +134 -2
- package/dist/services/stall/stall-poller.js.map +1 -1
- package/dist/services/strategy.d.ts.map +1 -1
- package/dist/services/strategy.js +2 -2
- package/dist/services/strategy.js.map +1 -1
- package/dist/services/tool-registry.d.ts.map +1 -1
- package/dist/services/tool-registry.js +87 -1
- package/dist/services/tool-registry.js.map +1 -1
- package/dist/services/vcs/github.d.ts.map +1 -1
- package/dist/services/vcs/github.js +32 -1
- package/dist/services/vcs/github.js.map +1 -1
- package/dist/services/version-check.d.ts +22 -0
- package/dist/services/version-check.d.ts.map +1 -0
- package/dist/services/version-check.js +103 -0
- package/dist/services/version-check.js.map +1 -0
- package/dist/skills/fleet-sprint-cli/SKILL.md +13 -2
- package/dist/skills/pm/beads.md +6 -0
- package/dist/skills/pm/fleet-addendum.md +6 -0
- package/dist/skills/pm/index.md +56 -0
- package/dist/skills/pm/kb-reconcile.md +132 -0
- package/dist/skills/pm/kb-review.md +109 -0
- package/dist/tools/check-status.d.ts +47 -0
- package/dist/tools/check-status.d.ts.map +1 -1
- package/dist/tools/check-status.js +242 -0
- package/dist/tools/check-status.js.map +1 -1
- package/dist/tools/child-id-allocator.d.ts +2 -2
- package/dist/tools/code-intelligence-codebase-memory.d.ts +11 -0
- package/dist/tools/code-intelligence-codebase-memory.d.ts.map +1 -0
- package/dist/tools/code-intelligence-codebase-memory.js +270 -0
- package/dist/tools/code-intelligence-codebase-memory.js.map +1 -0
- package/dist/tools/code-intelligence-freshness.d.ts +2 -0
- package/dist/tools/code-intelligence-freshness.d.ts.map +1 -0
- package/dist/tools/code-intelligence-freshness.js +26 -0
- package/dist/tools/code-intelligence-freshness.js.map +1 -0
- package/dist/tools/code-intelligence-gitnexus.d.ts +14 -0
- package/dist/tools/code-intelligence-gitnexus.d.ts.map +1 -0
- package/dist/tools/code-intelligence-gitnexus.js +475 -0
- package/dist/tools/code-intelligence-gitnexus.js.map +1 -0
- package/dist/tools/code-intelligence-kb-enrich.d.ts +2 -0
- package/dist/tools/code-intelligence-kb-enrich.d.ts.map +1 -0
- package/dist/tools/code-intelligence-kb-enrich.js +65 -0
- package/dist/tools/code-intelligence-kb-enrich.js.map +1 -0
- package/dist/tools/code-intelligence-reindex.d.ts +7 -0
- package/dist/tools/code-intelligence-reindex.d.ts.map +1 -0
- package/dist/tools/code-intelligence-reindex.js +106 -0
- package/dist/tools/code-intelligence-reindex.js.map +1 -0
- package/dist/tools/code-intelligence-telemetry.d.ts +5 -0
- package/dist/tools/code-intelligence-telemetry.d.ts.map +1 -0
- package/dist/tools/code-intelligence-telemetry.js +52 -0
- package/dist/tools/code-intelligence-telemetry.js.map +1 -0
- package/dist/tools/code-intelligence-tests.d.ts +2 -0
- package/dist/tools/code-intelligence-tests.d.ts.map +1 -0
- package/dist/tools/code-intelligence-tests.js +24 -0
- package/dist/tools/code-intelligence-tests.js.map +1 -0
- package/dist/tools/code-intelligence.d.ts +114 -0
- package/dist/tools/code-intelligence.d.ts.map +1 -0
- package/dist/tools/code-intelligence.js +124 -0
- package/dist/tools/code-intelligence.js.map +1 -0
- package/dist/tools/compose-permissions.d.ts +26 -0
- package/dist/tools/compose-permissions.d.ts.map +1 -1
- package/dist/tools/compose-permissions.js +244 -33
- package/dist/tools/compose-permissions.js.map +1 -1
- package/dist/tools/execute-command.d.ts +2 -0
- package/dist/tools/execute-command.d.ts.map +1 -1
- package/dist/tools/execute-command.js +86 -16
- package/dist/tools/execute-command.js.map +1 -1
- package/dist/tools/execute-prompt.d.ts +13 -1
- package/dist/tools/execute-prompt.d.ts.map +1 -1
- package/dist/tools/execute-prompt.js +257 -45
- package/dist/tools/execute-prompt.js.map +1 -1
- package/dist/tools/kb-capture.d.ts +53 -0
- package/dist/tools/kb-capture.d.ts.map +1 -0
- package/dist/tools/kb-capture.js +130 -0
- package/dist/tools/kb-capture.js.map +1 -0
- package/dist/tools/kb-context.d.ts +17 -0
- package/dist/tools/kb-context.d.ts.map +1 -0
- package/dist/tools/kb-context.js +29 -0
- package/dist/tools/kb-context.js.map +1 -0
- package/dist/tools/kb-export.d.ts +19 -0
- package/dist/tools/kb-export.d.ts.map +1 -0
- package/dist/tools/kb-export.js +344 -0
- package/dist/tools/kb-export.js.map +1 -0
- package/dist/tools/kb-feedback.d.ts +23 -0
- package/dist/tools/kb-feedback.d.ts.map +1 -0
- package/dist/tools/kb-feedback.js +43 -0
- package/dist/tools/kb-feedback.js.map +1 -0
- package/dist/tools/kb-freshness-sweep.d.ts +14 -0
- package/dist/tools/kb-freshness-sweep.d.ts.map +1 -0
- package/dist/tools/kb-freshness-sweep.js +29 -0
- package/dist/tools/kb-freshness-sweep.js.map +1 -0
- package/dist/tools/kb-harvest.d.ts +20 -0
- package/dist/tools/kb-harvest.d.ts.map +1 -0
- package/dist/tools/kb-harvest.js +143 -0
- package/dist/tools/kb-harvest.js.map +1 -0
- package/dist/tools/kb-import.d.ts +44 -0
- package/dist/tools/kb-import.d.ts.map +1 -0
- package/dist/tools/kb-import.js +239 -0
- package/dist/tools/kb-import.js.map +1 -0
- package/dist/tools/kb-invalidate.d.ts +19 -0
- package/dist/tools/kb-invalidate.d.ts.map +1 -0
- package/dist/tools/kb-invalidate.js +34 -0
- package/dist/tools/kb-invalidate.js.map +1 -0
- package/dist/tools/kb-list.d.ts +32 -0
- package/dist/tools/kb-list.d.ts.map +1 -0
- package/dist/tools/kb-list.js +43 -0
- package/dist/tools/kb-list.js.map +1 -0
- package/dist/tools/kb-promote.d.ts +20 -0
- package/dist/tools/kb-promote.d.ts.map +1 -0
- package/dist/tools/kb-promote.js +20 -0
- package/dist/tools/kb-promote.js.map +1 -0
- package/dist/tools/kb-query.d.ts +35 -0
- package/dist/tools/kb-query.d.ts.map +1 -0
- package/dist/tools/kb-query.js +111 -0
- package/dist/tools/kb-query.js.map +1 -0
- package/dist/tools/kb-reconcile-prefilter.d.ts +14 -0
- package/dist/tools/kb-reconcile-prefilter.d.ts.map +1 -0
- package/dist/tools/kb-reconcile-prefilter.js +26 -0
- package/dist/tools/kb-reconcile-prefilter.js.map +1 -0
- package/dist/tools/kb-resolve-contradiction.d.ts +23 -0
- package/dist/tools/kb-resolve-contradiction.d.ts.map +1 -0
- package/dist/tools/kb-resolve-contradiction.js +37 -0
- package/dist/tools/kb-resolve-contradiction.js.map +1 -0
- package/dist/tools/kb-session-prime.d.ts +26 -0
- package/dist/tools/kb-session-prime.d.ts.map +1 -0
- package/dist/tools/kb-session-prime.js +392 -0
- package/dist/tools/kb-session-prime.js.map +1 -0
- package/dist/tools/kb-setup.d.ts +20 -0
- package/dist/tools/kb-setup.d.ts.map +1 -0
- package/dist/tools/kb-setup.js +49 -0
- package/dist/tools/kb-setup.js.map +1 -0
- package/dist/tools/kb-stats.d.ts +20 -0
- package/dist/tools/kb-stats.d.ts.map +1 -0
- package/dist/tools/kb-stats.js +115 -0
- package/dist/tools/kb-stats.js.map +1 -0
- package/dist/tools/member-detail.d.ts.map +1 -1
- package/dist/tools/member-detail.js +8 -0
- package/dist/tools/member-detail.js.map +1 -1
- package/dist/tools/monitor-task.d.ts.map +1 -1
- package/dist/tools/monitor-task.js +21 -3
- package/dist/tools/monitor-task.js.map +1 -1
- package/dist/tools/provision-auth.d.ts.map +1 -1
- package/dist/tools/provision-auth.js +10 -3
- package/dist/tools/provision-auth.js.map +1 -1
- package/dist/tools/register-member.d.ts +3 -0
- package/dist/tools/register-member.d.ts.map +1 -1
- package/dist/tools/register-member.js +30 -1
- package/dist/tools/register-member.js.map +1 -1
- package/dist/tools/remove-member.d.ts.map +1 -1
- package/dist/tools/remove-member.js +17 -3
- package/dist/tools/remove-member.js.map +1 -1
- package/dist/tools/report-status.d.ts.map +1 -1
- package/dist/tools/report-status.js +2 -1
- package/dist/tools/report-status.js.map +1 -1
- package/dist/tools/send-email.d.ts +69 -0
- package/dist/tools/send-email.d.ts.map +1 -0
- package/dist/tools/send-email.js +177 -0
- package/dist/tools/send-email.js.map +1 -0
- package/dist/tools/setup-ssh-key.d.ts.map +1 -1
- package/dist/tools/setup-ssh-key.js +2 -0
- package/dist/tools/setup-ssh-key.js.map +1 -1
- package/dist/tools/update-member.d.ts +3 -0
- package/dist/tools/update-member.d.ts.map +1 -1
- package/dist/tools/update-member.js +25 -1
- package/dist/tools/update-member.js.map +1 -1
- package/dist/types.d.ts +1 -0
- package/dist/types.d.ts.map +1 -1
- package/dist/utils/prompt-errors.js +1 -1
- package/dist/utils/prompt-errors.js.map +1 -1
- package/dist/utils/session-caller.d.ts +28 -0
- package/dist/utils/session-caller.d.ts.map +1 -0
- package/dist/utils/session-caller.js +24 -0
- package/dist/utils/session-caller.js.map +1 -0
- package/dist/utils/work-folder-validation.d.ts +39 -0
- package/dist/utils/work-folder-validation.d.ts.map +1 -0
- package/dist/utils/work-folder-validation.js +60 -0
- package/dist/utils/work-folder-validation.js.map +1 -0
- package/dist/workflows/auto-sprint.js +546 -6
- package/package.json +7 -4
- package/packages/apra-fleet-client/src/client/api.mjs +118 -4
- package/packages/apra-fleet-se/apra-pm/agents/backlog-groomer.md +17 -1
- package/packages/apra-fleet-se/apra-pm/agents/ci-watcher.md +13 -1
- package/packages/apra-fleet-se/apra-pm/agents/deployer.md +15 -3
- package/packages/apra-fleet-se/apra-pm/agents/doer.md +35 -1
- package/packages/apra-fleet-se/apra-pm/agents/harvester.md +22 -3
- package/packages/apra-fleet-se/apra-pm/agents/integ-test-runner.md +18 -2
- package/packages/apra-fleet-se/apra-pm/agents/kb-reconciler.md +216 -0
- package/packages/apra-fleet-se/apra-pm/agents/plan-reviewer.md +14 -1
- package/packages/apra-fleet-se/apra-pm/agents/planner.md +88 -5
- package/packages/apra-fleet-se/apra-pm/agents/regression-test-runner.md +19 -1
- package/packages/apra-fleet-se/apra-pm/agents/reviewer.md +104 -3
- package/packages/apra-fleet-se/apra-pm/agents/schemas/doer-output.json +63 -3
- package/packages/apra-fleet-se/apra-pm/agents/schemas/harvester-output.json +59 -2
- package/packages/apra-fleet-se/apra-pm/agents/schemas/integ-test-runner-output.json +2 -2
- package/packages/apra-fleet-se/apra-pm/agents/schemas/kb-reconciler-output.json +87 -0
- package/packages/apra-fleet-se/apra-pm/agents/schemas/planner-output.json +65 -0
- package/packages/apra-fleet-se/apra-pm/agents/schemas/reviewer-output.json +105 -8
- package/packages/apra-fleet-se/apra-pm/skills/pm/beads.md +6 -0
- package/packages/apra-fleet-se/apra-pm/skills/pm/fleet-addendum.md +6 -0
- package/packages/apra-fleet-se/apra-pm/skills/pm/index.md +56 -0
- package/packages/apra-fleet-se/apra-pm/skills/pm/kb-reconcile.md +132 -0
- package/packages/apra-fleet-se/apra-pm/skills/pm/kb-review.md +109 -0
- package/packages/apra-fleet-se/bin/cli.mjs +7 -0
- package/packages/apra-fleet-se/bin/serve.mjs +14 -2
- package/packages/apra-fleet-se/fleet-sprint/contracts.mjs +31 -5
- package/packages/apra-fleet-se/fleet-sprint/docs/README.md +1 -1
- package/packages/apra-fleet-se/fleet-sprint/docs/coach-role-design.md +23 -151
- package/packages/apra-fleet-se/fleet-sprint/docs/dolt-manual-recovery-verified.md +256 -0
- package/packages/apra-fleet-se/fleet-sprint/docs/dolt-sync-redesign.md +1482 -0
- package/packages/apra-fleet-se/fleet-sprint/docs/escalate-to-llm-design.md +908 -0
- package/packages/apra-fleet-se/fleet-sprint/docs/shared-orchestrator-reservation-design.md +399 -0
- package/packages/apra-fleet-se/fleet-sprint/dolt-settle.mjs +972 -0
- package/packages/apra-fleet-se/fleet-sprint/dolt-sync.mjs +167 -101
- package/packages/apra-fleet-se/fleet-sprint/errors.mjs +50 -6
- package/packages/apra-fleet-se/fleet-sprint/runner.js +1416 -116
- package/packages/apra-fleet-se/fleet-sprint/skills/fleet-sprint-cli/SKILL.md +13 -2
- package/packages/apra-fleet-se/fleet-sprint/skills/fleet-supervisor/SKILL.md +350 -0
- package/packages/apra-fleet-se/fleet-sprint/sprint-progress.mjs +101 -0
- package/packages/apra-fleet-se/fleet-sprint/vcs-providers/github.mjs +30 -17
- package/packages/apra-fleet-se/fleet-sprint/viewer-extensions.mjs +62 -2
- package/packages/apra-fleet-se/package.json +1 -0
- package/packages/apra-fleet-workflow/src/viewer/index.mjs +127 -13
- package/packages/apra-fleet-workflow/src/viewer/run-title.mjs +60 -0
- package/packages/apra-fleet-workflow/src/workflow/index.mjs +8 -4
- package/skills/fleet/knowledge-agent.md +66 -0
- package/skills/fleet/permissions.md +28 -4
- package/skills/fleet/profiles/base-dev.json +10 -1
- package/skills/fleet/profiles/base-reviewer.json +8 -1
- package/skills/fleet/profiles/tag-kb-reconciler.json +20 -0
- package/version.json +1 -1
- package/packages/apra-fleet-se/fleet-sprint/docs/dolt-tier2-runbook.md +0 -127
- package/packages/apra-fleet-se/fleet-sprint/dolt-recovery-path-b.mjs +0 -339
- package/packages/apra-fleet-se/fleet-sprint/dolt-recovery-tier2.mjs +0 -360
- package/packages/apra-fleet-se/fleet-sprint/dolt-recovery.mjs +0 -363
package/README.md
CHANGED
|
@@ -19,7 +19,7 @@ workforce -- on any machine, anywhere, using every LLM provider at once.
|
|
|
19
19
|
[](https://modelcontextprotocol.io)
|
|
20
20
|
[](https://deepwiki.com/Apra-Labs/apra-fleet)
|
|
21
21
|
|
|
22
|
-
[Quick Start](#quick-start-5-minutes) - [Live Demo](#watch-a-fleet-work) - [How It Works](#how-it-works) - [fleet-sprint Getting Started Guide](docs/fleet-sprint-getting-started.md) - [
|
|
22
|
+
[Quick Start](#quick-start-5-minutes) - [Live Demo](#watch-a-fleet-work) - [How It Works](#how-it-works) - [fleet-sprint Getting Started Guide](docs/fleet-sprint-getting-started.md) - [Website](https://apra-labs.github.io/apra-fleet)
|
|
23
23
|
|
|
24
24
|
</div>
|
|
25
25
|
|
|
@@ -58,7 +58,7 @@ One control plane. Any device. Any model. Any workflow. Any domain.
|
|
|
58
58
|
|
|
59
59
|
| Pillar | Concretely |
|
|
60
60
|
|---|---|
|
|
61
|
-
| **Any device** | Register any Windows / macOS / Linux machine (local or over SSH) as a fleet member in one command. Cloud members auto-start on demand. |
|
|
61
|
+
| **Any device** | Register any Windows / macOS / Linux machine (local or over SSH) as a fleet member in one command. Cloud members auto-start on demand. Windows members are fully supported for dispatch, command execution, and background long-running tasks (launched detached via WMI). |
|
|
62
62
|
| **Any model** | Claude, Codex, Gemini, Copilot, Antigravity, local models (any OpenAI-compatible endpoint via OpenCode) -- mixed freely. Tier-based routing (cheap / standard / premium) keeps cost governance built in. Cross-provider review is a quality mechanism: a different model, with different blind spots, checks every change. |
|
|
63
63
|
| **Any workflow** | Workflows are durable programs, not prompt chains: multi-hour, resumable, observable, with member reservations and atomic state. Write your own; ship it to the fleet. |
|
|
64
64
|
| **Any domain** | Not just software development. The pattern fits wherever work decomposes into agent-sized pieces that need orchestration and an audit trail: nightly retail replenishment (reconcile inventory deltas, draft purchase orders for sign-off), logistics exception handling (triage a delayed shipment, re-book, notify), healthcare intake (summarize referrals, check completeness, route), back-office runs (invoice matching, compliance evidence collection). Software engineering is the vertical running today -- your domain is a workflow away. |
|
|
@@ -143,9 +143,9 @@ apra-fleet workflow fleet-sprint \
|
|
|
143
143
|
Open the dashboard, watch your fleet PLAN->BUILD->REVIEW->TEST->SHIP in a loop till closure
|
|
144
144
|
|
|
145
145
|
> **New to fleet-sprint?** Read the
|
|
146
|
-
> [fleet-sprint Getting Started Guide](
|
|
147
|
-
> ([
|
|
148
|
-
> [PDF](docs/fleet-sprint-getting-started.pdf)) -- a plain-English walkthrough
|
|
146
|
+
> [fleet-sprint Getting Started Guide](https://apra-labs.github.io/apra-fleet/fleet-sprint-getting-started.html)
|
|
147
|
+
> ([Markdown](docs/fleet-sprint-getting-started.md) if you're reading this on
|
|
148
|
+
> GitHub -- [PDF](docs/fleet-sprint-getting-started.pdf)) -- a plain-English walkthrough
|
|
149
149
|
> of what it does, what you need to prepare (beads backlog, `deploy.md`,
|
|
150
150
|
> test playbooks, member registration), how to launch and monitor a sprint,
|
|
151
151
|
> and what's automated versus what's still your call.
|
|
@@ -181,6 +181,52 @@ flowchart LR
|
|
|
181
181
|
- **Workflow engine**: runs workflow programs with phases, retries, turn budgets, resumable sessions, and per-activity persistent state.
|
|
182
182
|
- **Supervisor**: always-on layer -- launch & stop sprints over HTTP, member reservation ledger, crash watchdog, run history.
|
|
183
183
|
|
|
184
|
+
## Knowledge Layer
|
|
185
|
+
|
|
186
|
+
Every agent session starts by calling `kb_session_prime`. The KB checks which
|
|
187
|
+
files have changed since last read and returns exactly those. Unchanged files
|
|
188
|
+
are served from cached summaries -- no re-read, no wasted tokens.
|
|
189
|
+
|
|
190
|
+
```
|
|
191
|
+
Cold session: kb_session_prime returns stale_files=[a.ts, b.ts, c.ts]
|
|
192
|
+
Agent reads all three, calls kb_capture for each.
|
|
193
|
+
Warm session: kb_session_prime returns stale_files=[], session_warm=true
|
|
194
|
+
Agent works from KB summaries. Zero file reads.
|
|
195
|
+
```
|
|
196
|
+
|
|
197
|
+
MCP tools that ship with the KB:
|
|
198
|
+
|
|
199
|
+
| Tool | What it does |
|
|
200
|
+
|------|--------------|
|
|
201
|
+
| `kb_session_prime` | Prime a session: stale files, fresh summaries, GitNexus call list |
|
|
202
|
+
| `kb_capture` | Store a learning, context-cache, runbook, or knowledge entry |
|
|
203
|
+
| `kb_query` | Two-level FTS retrieval (L1: title+summary, L2: full content) |
|
|
204
|
+
| `kb_list` | Audit-list entries by confidence/type/module/symbol (read-only, no use_count bump) |
|
|
205
|
+
| `kb_context` | Batch file freshness check (single git call for N files) |
|
|
206
|
+
| `kb_invalidate` | Mark files stale immediately (also called by the git hook) |
|
|
207
|
+
| `kb_promote` | Advance confidence: UNVERIFIED -> INFERRED -> CONFIRMED |
|
|
208
|
+
| `kb_harvest` | Extract learnings from a session transcript (auto-fires after execute_prompt) |
|
|
209
|
+
| `kb_export` | Write live CONFIRMED entries to `.fleet/kb-canonical.json` -- the git-shareable team bible |
|
|
210
|
+
| `kb_setup` | Install git hook, write provider config, store remote token encrypted |
|
|
211
|
+
|
|
212
|
+
Every KB tool call is scoped to the repo it is about -- a fleet server
|
|
213
|
+
handling many members across many repos never lets one repo's learnings land
|
|
214
|
+
in another repo's KB. Scope is normally derived from the caller's repo path;
|
|
215
|
+
tools also accept an explicit `repo_remote_url` so a remote member (whose
|
|
216
|
+
work folder is a path on another host, unreachable from the fleet server's
|
|
217
|
+
filesystem) resolves to the same project KB as a local clone of that repo
|
|
218
|
+
instead of a shared fallback database. The automatic post-prompt harvest and
|
|
219
|
+
the `code_context` KB enrichment path both forward this URL too, and an
|
|
220
|
+
unreachable work-folder path is never silently swapped for the fleet
|
|
221
|
+
server's own working directory -- see
|
|
222
|
+
[Per-repo KB isolation](docs/knowledge-layer.md#per-repo-kb-isolation) for
|
|
223
|
+
the full anchor and cache-keying rules.
|
|
224
|
+
|
|
225
|
+
The backend is swappable: start with local SQLite, add a central HTTP server for
|
|
226
|
+
a team, or plug in Postgres later -- all via a one-line config change.
|
|
227
|
+
|
|
228
|
+
See [docs/knowledge-layer.md](docs/knowledge-layer.md) for the full guide.
|
|
229
|
+
|
|
184
230
|
## Explore with agents. Operate with programs.
|
|
185
231
|
|
|
186
232
|
There are two ways to orchestrate agents, and apra-fleet is built on the
|
|
@@ -251,7 +297,95 @@ Secrets are entered out-of-band into a credential store and referenced as
|
|
|
251
297
|
any LLM or log. Credentials scope to members, expire on TTL, and can carry
|
|
252
298
|
a network egress policy (allow / deny / confirm). Every member runs with
|
|
253
299
|
composed, provider-native permission files -- allow-listed tools, not
|
|
254
|
-
god-mode. VCS access is provisioned and revocable per member.
|
|
300
|
+
god-mode. VCS access is provisioned and revocable per member. Permission
|
|
301
|
+
composition verifies its own delivery: a grant is read back off the target
|
|
302
|
+
member and structurally compared against what was intended before it is
|
|
303
|
+
reported as applied, so a failed or partial write is surfaced as an
|
|
304
|
+
explicit failure rather than a false success.
|
|
305
|
+
|
|
306
|
+
## Email Configuration
|
|
307
|
+
|
|
308
|
+
The fleet `send_email` tool sends email via **SendGrid** or **SMTP**. Secrets
|
|
309
|
+
are stored in the fleet credential store. Non-secret config (provider, host,
|
|
310
|
+
port, from address) is passed by the workflow in each call.
|
|
311
|
+
|
|
312
|
+
### Storing secrets (one-time setup)
|
|
313
|
+
|
|
314
|
+
Store email secrets via the CLI:
|
|
315
|
+
|
|
316
|
+
```bash
|
|
317
|
+
# SendGrid API key
|
|
318
|
+
apra-fleet secret --set sendgrid_api_key --persist
|
|
319
|
+
|
|
320
|
+
# SMTP password
|
|
321
|
+
apra-fleet secret --set smtp_password --persist
|
|
322
|
+
```
|
|
323
|
+
|
|
324
|
+
Or via the MCP tool (the path an LLM agent uses):
|
|
325
|
+
|
|
326
|
+
```json
|
|
327
|
+
{ "name": "sendgrid_api_key", "prompt": "Enter your SendGrid API key", "persist": true }
|
|
328
|
+
```
|
|
329
|
+
|
|
330
|
+
Secrets are encrypted in the fleet credential store. They never appear in
|
|
331
|
+
workflow code, config files, or environment variables.
|
|
332
|
+
|
|
333
|
+
### Sending email from a workflow
|
|
334
|
+
|
|
335
|
+
The workflow passes non-secret config inline and calls `send_email`. Load
|
|
336
|
+
your config however you prefer (JSON file, hardcoded, etc.):
|
|
337
|
+
|
|
338
|
+
```javascript
|
|
339
|
+
import { parseToolJson } from '@apralabs/apra-fleet-client';
|
|
340
|
+
import { connectFleet } from '@apralabs/apra-fleet-client/server-resolution';
|
|
341
|
+
|
|
342
|
+
const { fleetApi } = await connectFleet({ env: process.env });
|
|
343
|
+
|
|
344
|
+
// fleetApi wrappers return the raw MCP tool result ({ content: [...] });
|
|
345
|
+
// parseToolJson extracts the JSON payload.
|
|
346
|
+
const result = parseToolJson(await fleetApi.sendEmail({
|
|
347
|
+
provider: 'smtp',
|
|
348
|
+
host: 'smtp.example.com',
|
|
349
|
+
port: 587,
|
|
350
|
+
user: 'notifications@example.com',
|
|
351
|
+
from: 'noreply@example.com',
|
|
352
|
+
to: 'team@example.com',
|
|
353
|
+
subject: 'Sprint Report',
|
|
354
|
+
body: 'All tasks completed.'
|
|
355
|
+
}));
|
|
356
|
+
console.log(`Sent: ${result.messageId}`);
|
|
357
|
+
```
|
|
358
|
+
|
|
359
|
+
The SMTP password resolves from the credential store automatically. It never
|
|
360
|
+
appears in the workflow. See `examples/workflows/email-notify/` for a
|
|
361
|
+
complete runnable example and `docs/email-workflow-guide.md` for the full
|
|
362
|
+
walkthrough.
|
|
363
|
+
|
|
364
|
+
### send_email Tool Reference
|
|
365
|
+
|
|
366
|
+
| Parameter | Type | Required | Description |
|
|
367
|
+
|---|---|---|---|
|
|
368
|
+
| `provider` | `"sendgrid"` or `"smtp"` | no (default: `"sendgrid"`) | Email provider |
|
|
369
|
+
| `from` | string | yes | Sender email address |
|
|
370
|
+
| `host` | string | SMTP only | SMTP server hostname |
|
|
371
|
+
| `port` | number | no (default: 587, or 465 when `secure` is true) | SMTP server port |
|
|
372
|
+
| `user` | string | SMTP only | SMTP username |
|
|
373
|
+
| `secure` | boolean | no (default: false) | Implicit TLS (port 465). When false, STARTTLS is required. |
|
|
374
|
+
| `to` | string or string[] | yes | Recipient email address(es) |
|
|
375
|
+
| `subject` | string | yes | Email subject line |
|
|
376
|
+
| `body` | string | yes | Plain-text email body |
|
|
377
|
+
| `html` | string | no | HTML email body |
|
|
378
|
+
| `cc` | string[] | no | CC recipient addresses |
|
|
379
|
+
| `bcc` | string[] | no | BCC recipient addresses |
|
|
380
|
+
| `attachments` | attachment[] | no | File attachments (base64-encoded) |
|
|
381
|
+
|
|
382
|
+
Each attachment: `filename` (string), `content` (string, base64), `contentType` (string, optional).
|
|
383
|
+
|
|
384
|
+
Secrets are resolved from the credential store by name:
|
|
385
|
+
- **SendGrid:** `sendgrid_api_key`
|
|
386
|
+
- **SMTP:** `smtp_password`
|
|
387
|
+
|
|
388
|
+
Returns: `{ ok: true, messageId }` on success, `{ ok: false, error }` on failure.
|
|
255
389
|
|
|
256
390
|
## The packages
|
|
257
391
|
|
|
@@ -273,7 +407,7 @@ third-party verticals.
|
|
|
273
407
|
|
|
274
408
|
| Topic | Link |
|
|
275
409
|
|-------|------|
|
|
276
|
-
| **fleet-sprint Getting Started Guide (start here, plain English)** | [
|
|
410
|
+
| **fleet-sprint Getting Started Guide (start here, plain English)** | [Website](https://apra-labs.github.io/apra-fleet/fleet-sprint-getting-started.html) - [Markdown](docs/fleet-sprint-getting-started.md) - [PDF](docs/fleet-sprint-getting-started.pdf) |
|
|
277
411
|
| Codebase wiki (architecture, internals, AI Q&A) | [DeepWiki](https://deepwiki.com/Apra-Labs/apra-fleet) |
|
|
278
412
|
| Install, uninstall, the `--llm` flag | [docs/install.md](docs/install.md) |
|
|
279
413
|
| Choosing a provider (roles, gotchas, mixing providers, OpenCode/local models) | [docs/provider-guide.md](docs/provider-guide.md) |
|
|
@@ -290,6 +424,8 @@ third-party verticals.
|
|
|
290
424
|
| Git authentication | [docs/design-git-auth.md](docs/design-git-auth.md) |
|
|
291
425
|
| Cloud compute | [docs/cloud-compute.md](docs/cloud-compute.md) |
|
|
292
426
|
| Architecture | [docs/architecture.md](docs/architecture.md) |
|
|
427
|
+
| Knowledge Layer (setup, usage, provider swap) | [docs/knowledge-layer.md](docs/knowledge-layer.md) |
|
|
428
|
+
| Code intelligence provider abstraction | [docs/code-intelligence-providers.md](docs/code-intelligence-providers.md) |
|
|
293
429
|
| Hub-spoke cloud migration plan (historical; see tier-3 ownership ADR) | [docs/hub-spoke-master-plan.md](docs/hub-spoke-master-plan.md) |
|
|
294
430
|
| Tier-3 ownership decision (fleet-dashboard vs `src/hub-service/`) | [docs/adr-tier3-ownership.md](docs/adr-tier3-ownership.md) |
|
|
295
431
|
| Shared hub/dashboard API contract package | [packages/fleet-api-contract/README.md](packages/fleet-api-contract/README.md) |
|
|
@@ -302,6 +438,8 @@ third-party verticals.
|
|
|
302
438
|
| Auto-sprint CLI reference | [packages/apra-fleet-se/docs/cli-reference.md](packages/apra-fleet-se/docs/cli-reference.md) |
|
|
303
439
|
| Auto-sprint internals (cycle loop, stall detection, budget, topology) | [packages/apra-fleet-se/docs/architecture.md](packages/apra-fleet-se/docs/architecture.md) |
|
|
304
440
|
| Auto-sprint agent role contracts | [packages/apra-fleet-se/docs/role-contracts.md](packages/apra-fleet-se/docs/role-contracts.md) |
|
|
441
|
+
| fleet-supervisor skill (start/stop/restart/auto-start-on-boot, sprint launch via HTTP API) | [packages/apra-fleet-se/fleet-sprint/skills/fleet-supervisor/SKILL.md](packages/apra-fleet-se/fleet-sprint/skills/fleet-supervisor/SKILL.md) |
|
|
442
|
+
| fleet-supervisor packaging self-containment audit | [packages/apra-fleet-se/docs/supervisor-selfcontainment-audit.md](packages/apra-fleet-se/docs/supervisor-selfcontainment-audit.md) |
|
|
305
443
|
| MCP client SDK overview (transports, `ApraFleet` API) | [packages/apra-fleet-client/docs/overview.md](packages/apra-fleet-client/docs/overview.md) |
|
|
306
444
|
| MCP client SDK API reference | [packages/apra-fleet-client/docs/api-reference.md](packages/apra-fleet-client/docs/api-reference.md) |
|
|
307
445
|
| MCP client SDK getting started | [packages/apra-fleet-client/docs/getting-started.md](packages/apra-fleet-client/docs/getting-started.md) |
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: backlog-groomer
|
|
3
3
|
description: For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always evidence-and-reasoning noted. Never changes code.
|
|
4
|
-
tools: [Read, Grep, Glob, Bash]
|
|
4
|
+
tools: [Read, Grep, Glob, Bash, ToolSearch]
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# Backlog Groomer
|
|
@@ -10,6 +10,22 @@ You groom ONE operator's slice of the open beads backlog: what to pick up next,
|
|
|
10
10
|
to sprint together, what's a duplicate, what needs fixing before it's actionable. You
|
|
11
11
|
analyze AND mutate beads directly -- but you never touch code beyond reading it.
|
|
12
12
|
|
|
13
|
+
## Step 0 -- Knowledge Bank (required -- do this BEFORE any grooming decision)
|
|
14
|
+
|
|
15
|
+
1. Run ToolSearch with query `"select:mcp__apra-fleet__kb_session_prime,mcp__apra-fleet__kb_capture"`
|
|
16
|
+
2. Call `mcp__apra-fleet__kb_session_prime` with `repo_path` set to the repo whose backlog
|
|
17
|
+
you are grooming, and `hint_modules` naming the subsystems the assigned beads touch.
|
|
18
|
+
Trust CONFIRMED entries fully. Use INFERRED entries as hints, not facts. This matters
|
|
19
|
+
most for duplicate detection and sprint-set grouping: two beads that read as unrelated
|
|
20
|
+
are often the same underlying issue, and the KB is where that has already been written
|
|
21
|
+
down.
|
|
22
|
+
3. When grooming turns up a durable backlog fact -- two ids that are genuinely the same
|
|
23
|
+
work, a dependency between beads that their text does not state, or a recurring reason
|
|
24
|
+
items land unactionable -- call `mcp__apra-fleet__kb_capture` with type "knowledge".
|
|
25
|
+
Do not capture per-sprint churn; capture what stays true.
|
|
26
|
+
|
|
27
|
+
If ToolSearch returns no KB tools (MCP server not running), skip these steps and proceed.
|
|
28
|
+
|
|
13
29
|
## Usage modes
|
|
14
30
|
|
|
15
31
|
- **"Define my sprint"** -> Responsibility 1: ready/urgent items + sprint-set groups.
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: ci-watcher
|
|
3
3
|
description: Polls CI for the sprint HEAD SHA; returns green/red/not_configured/pending.
|
|
4
|
-
tools: [Bash]
|
|
4
|
+
tools: [Bash, ToolSearch]
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# CI Status Check
|
|
@@ -22,6 +22,18 @@ Your dispatch prompt must supply ONE of the two scoping forms:
|
|
|
22
22
|
`expectedHeadSha` missing), do not guess or check an arbitrary branch. Return
|
|
23
23
|
`status: "pending"` with `notes` stating which input was missing.
|
|
24
24
|
|
|
25
|
+
## Step 0 -- Knowledge Bank (required -- do this BEFORE any other work)
|
|
26
|
+
|
|
27
|
+
1. Run ToolSearch with query `"select:mcp__apra-fleet__kb_session_prime"`
|
|
28
|
+
2. Call `mcp__apra-fleet__kb_session_prime` with `repo_path` set to the repo whose CI you
|
|
29
|
+
are checking, and `hint_modules` naming its CI workflow files. Trust CONFIRMED entries
|
|
30
|
+
fully. Use INFERRED entries as hints, not facts. Known-flaky tests and known CI failure
|
|
31
|
+
modes are the point here -- they change how you read a red run.
|
|
32
|
+
3. Do NOT capture. You poll a status API; you verify no claim about this repository, so you
|
|
33
|
+
have no basis to write one down.
|
|
34
|
+
|
|
35
|
+
If ToolSearch returns no KB tools (MCP server not running), skip these steps and proceed.
|
|
36
|
+
|
|
25
37
|
## Step 1 -- List recent CI runs
|
|
26
38
|
|
|
27
39
|
Branch-scoped:
|
package/dist/agents/deployer.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: deployer
|
|
3
3
|
description: Follows deploy.md to deploy the software onto the target environment and verify it with the smoke test.
|
|
4
|
-
tools: [Read, Bash]
|
|
4
|
+
tools: [Read, Bash, ToolSearch]
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# Deployment
|
|
@@ -28,7 +28,7 @@ playbook yourself. If `deploy.md` is entirely absent (not just missing a
|
|
|
28
28
|
section), return `deployed: false` with `notes` naming the missing file -- do
|
|
29
29
|
not improvise deploy steps that are not written down in the runbook.
|
|
30
30
|
|
|
31
|
-
## Step
|
|
31
|
+
## Step 0a -- Check permissions before running anything
|
|
32
32
|
|
|
33
33
|
Read `deploy.md`. Look for a `## Permissions` section. If found, verify each
|
|
34
34
|
listed command prefix is covered by the MERGED effective permission set --
|
|
@@ -89,7 +89,19 @@ Do NOT attempt to add the permissions yourself, by editing any file directly:
|
|
|
89
89
|
tool).
|
|
90
90
|
The correct escalation when a required permission is missing from the merged
|
|
91
91
|
effective set is: ask the orchestrator/operator to run `compose_permissions`
|
|
92
|
-
with the missing grant. Do NOT proceed past Step
|
|
92
|
+
with the missing grant. Do NOT proceed past Step 0a if any permissions are missing.
|
|
93
|
+
|
|
94
|
+
## Step 0b -- Knowledge Bank (required -- do this BEFORE any deploy.md operation)
|
|
95
|
+
|
|
96
|
+
1. Run ToolSearch with query `"select:mcp__apra-fleet__kb_session_prime,mcp__apra-fleet__kb_capture"`
|
|
97
|
+
2. Call `mcp__apra-fleet__kb_session_prime` with `repo_path` set to the repo being deployed,
|
|
98
|
+
and `hint_modules` naming the deploy targets in `deploy.md`. Trust CONFIRMED entries
|
|
99
|
+
fully. Use INFERRED entries as hints, not facts.
|
|
100
|
+
3. When a deploy step fails for a non-obvious reason, or a runbook instruction turns out to
|
|
101
|
+
be wrong or incomplete, call `mcp__apra-fleet__kb_capture` with type "runbook" or
|
|
102
|
+
"learning". A deploy gotcha you had to discover is exactly what the next deploy needs.
|
|
103
|
+
|
|
104
|
+
If ToolSearch returns no KB tools (MCP server not running), skip these steps and proceed.
|
|
93
105
|
|
|
94
106
|
## deploy.md operations
|
|
95
107
|
|
package/dist/agents/doer.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: doer
|
|
3
3
|
description: Works assigned bead ids (task-type work, impl and test-dev), commits after each, stops at VERIFY checkpoint.
|
|
4
|
-
tools: [Read, Edit, Write, Bash, Grep, Glob, Agent]
|
|
4
|
+
tools: [Read, Edit, Write, Bash, Grep, Glob, Agent, ToolSearch]
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# Task Execution
|
|
@@ -58,6 +58,40 @@ persistent state in ways that abort the whole sprint. Instead leave the bead ope
|
|
|
58
58
|
Closing such a bead is legitimate ONLY when your dispatch prompt explicitly names an
|
|
59
59
|
already-collected evidence artifact for you to verify against.
|
|
60
60
|
|
|
61
|
+
## Step 0 -- Knowledge Bank (required -- do this BEFORE any other work)
|
|
62
|
+
|
|
63
|
+
1. Run ToolSearch with query
|
|
64
|
+
`"select:mcp__apra-fleet__kb_session_prime,mcp__apra-fleet__kb_query,mcp__apra-fleet__kb_capture,mcp__apra-fleet__kb_feedback,mcp__apra-fleet__code_context,mcp__apra-fleet__code_graph,mcp__apra-fleet__code_impact,mcp__apra-fleet__code_query"`
|
|
65
|
+
2. Call `mcp__apra-fleet__kb_session_prime` with `repo_path` set to the repo you are
|
|
66
|
+
working in, and `hint_symbols`/`hint_modules` relevant to the files and symbols you are
|
|
67
|
+
about to touch. Trust CONFIRMED entries fully. Use INFERRED entries as hints, not facts.
|
|
68
|
+
3. Retrieve first, then read source: before reading an unfamiliar file or function, run
|
|
69
|
+
`mcp__apra-fleet__kb_query({ query: "<name>" })` first. If it returns a CONFIRMED or
|
|
70
|
+
INFERRED entry, work from it and skip the full source read. Trust CONFIRMED fully; treat
|
|
71
|
+
INFERRED as a strong hint but verify against source when correctness matters (it may be
|
|
72
|
+
an unvalidated in-flight capture). Only fall back to a full source read if the KB is
|
|
73
|
+
cold (no entry), stale, or says "see source for details."
|
|
74
|
+
4. When you discover something non-obvious and durable (a hidden constraint, a gotcha, an
|
|
75
|
+
invariant), decide whether it is capture-worthy: run `mcp__apra-fleet__kb_query` first to
|
|
76
|
+
check for a near-duplicate entry, and skip it if one already exists. If it is new, add it
|
|
77
|
+
to your structured output's `kb_captures` array (see `agents/schemas/doer-output.json` for
|
|
78
|
+
the exact shape -- `type`, `title`, `summary`, `content`, `source_files`, optional
|
|
79
|
+
`symbols`); the engine makes the actual `kb_capture` call and logs it with your evidence.
|
|
80
|
+
Do not call `mcp__apra-fleet__kb_capture` yourself unless your dispatch context has no
|
|
81
|
+
`kb_captures` output field to write to, in which case calling it directly is the fallback.
|
|
82
|
+
5. If a KB entry you retrieved proves wrong in practice, call `mcp__apra-fleet__kb_feedback`
|
|
83
|
+
with the entry id and what was wrong.
|
|
84
|
+
6. You do not need to call `mcp__apra-fleet__kb_harvest` yourself -- the fleet auto-dispatches
|
|
85
|
+
it as a backstop after your session ends; it is not your job to invoke it.
|
|
86
|
+
7. The `code_*` tools answer a different question from the KB: the KB tells you what was
|
|
87
|
+
learned about this code, the code index tells you what this code actually connects to.
|
|
88
|
+
Before editing a symbol, use `code_context`/`code_graph` for its callers and callees and
|
|
89
|
+
`code_impact` for the blast radius of the file you are changing -- prefer them over grep
|
|
90
|
+
for symbol lookups, call-chain tracing and impact analysis. If a call reports the repo is
|
|
91
|
+
not indexed, fall back to grep and move on; do not try to build an index yourself.
|
|
92
|
+
|
|
93
|
+
If ToolSearch returns no KB tools (MCP server not running), skip these steps and proceed.
|
|
94
|
+
|
|
61
95
|
## Step 1 -- Work only your assigned bead ids
|
|
62
96
|
|
|
63
97
|
Do NOT run bare `bd ready` to discover work -- it returns ready beads from the entire
|
package/dist/agents/harvester.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: harvester
|
|
3
3
|
description: Extracts durable sprint knowledge into docs/, updates README/CHANGELOG (including pre-computed cost analysis block), defers low-priority issues, and returns OK.
|
|
4
|
-
tools: [Read, Edit, Write, Bash, Grep, Glob]
|
|
4
|
+
tools: [Read, Edit, Write, Bash, Grep, Glob, ToolSearch]
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# Sprint Harvest
|
|
@@ -31,6 +31,22 @@ pre-computed by the orchestrator in JavaScript and must be inserted byte-for-byt
|
|
|
31
31
|
and return `status: "FAILED"` with `notes` naming exactly which input was missing. Same for
|
|
32
32
|
a missing `base-branch`/`branch`: do not guess which branch to diff.
|
|
33
33
|
|
|
34
|
+
## Step 0 -- Knowledge Bank (required -- do this BEFORE any other work)
|
|
35
|
+
|
|
36
|
+
1. Run ToolSearch with query `"select:mcp__apra-fleet__kb_session_prime,mcp__apra-fleet__kb_query,mcp__apra-fleet__kb_capture,mcp__apra-fleet__kb_feedback"`
|
|
37
|
+
2. Call `mcp__apra-fleet__kb_session_prime` with `repo_path` set to the repo being harvested,
|
|
38
|
+
and `hint_symbols`/`hint_modules` relevant to the modules touched during the sprint.
|
|
39
|
+
Trust CONFIRMED entries fully. Use INFERRED entries as hints, not facts.
|
|
40
|
+
3. When you extract durable knowledge during harvest -- anything non-obvious that future
|
|
41
|
+
sprints should know -- add it to the `kb_captures` array of your structured output (type
|
|
42
|
+
"knowledge" or "learning"; dedup against the KB with `kb_query` first). The engine makes
|
|
43
|
+
the actual `kb_capture` call from that field. Calling `mcp__apra-fleet__kb_capture`
|
|
44
|
+
directly is a fallback only, for dispatch contexts with no `kb_captures` output field.
|
|
45
|
+
4. If a retrieved KB entry proves wrong in practice, call `mcp__apra-fleet__kb_feedback`
|
|
46
|
+
with the entry id and what was wrong.
|
|
47
|
+
|
|
48
|
+
If ToolSearch returns no KB tools (MCP server not running), skip these steps and proceed.
|
|
49
|
+
|
|
34
50
|
## Step 1 -- Write sprint analysis artifact (FIRST, before anything else)
|
|
35
51
|
|
|
36
52
|
Your task context includes an `analysisArtifactFile` path and an `analysisText` block.
|
|
@@ -109,7 +125,7 @@ bd list --status=open --priority=4
|
|
|
109
125
|
**Do NOT close these.** Leave every P3/P4 issue open and untouched -- a closed issue drops
|
|
110
126
|
out of `bd list --status=open` and `bd ready`, which is exactly what would hide it from
|
|
111
127
|
next sprint's planner. Deferred work stays visible by staying open at low priority under
|
|
112
|
-
the sprint root
|
|
128
|
+
the sprint root; closing is only for issues that are actually
|
|
113
129
|
resolved, stale, or superseded, and this step never makes that call. If a P3/P4 issue
|
|
114
130
|
genuinely lacks enough detail to act on later without re-investigation, add that detail
|
|
115
131
|
with `bd note <id> "..."` -- do not close it as a substitute for noting it.
|
|
@@ -142,10 +158,13 @@ placeholder):
|
|
|
142
158
|
```json
|
|
143
159
|
{
|
|
144
160
|
"status": "OK",
|
|
145
|
-
"notes": "Wrote sprint analysis artifact, extracted durable docs, updated README/CHANGELOG, confirmed 2 P3 issues remain open as backlog, pushed branch."
|
|
161
|
+
"notes": "Wrote sprint analysis artifact, extracted durable docs, updated README/CHANGELOG, confirmed 2 P3 issues remain open as backlog, pushed branch.",
|
|
162
|
+
"kb_captures": []
|
|
146
163
|
}
|
|
147
164
|
```
|
|
148
165
|
|
|
166
|
+
`kb_captures` is optional -- omit it or send `[]` when there is nothing to capture.
|
|
167
|
+
|
|
149
168
|
**Precedence**: If your dispatch prompt includes a JSON schema instruction, that schema is
|
|
150
169
|
authoritative -- respond with exactly that JSON and nothing else. It is expected to match
|
|
151
170
|
this contract; if it differs, follow the dispatch prompt.
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: integ-test-runner
|
|
3
3
|
description: Runs integ-test-playbook.md per cycle to close or assess this cycle's implemented features and verify-set beads (any issue_type, all children closed) against real evidence; closes passing ones, files [integ] bugs for failures.
|
|
4
|
-
tools: [Read, Bash, Grep, Glob]
|
|
4
|
+
tools: [Read, Bash, Grep, Glob, ToolSearch]
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# Integration Test Execution
|
|
@@ -71,6 +71,19 @@ any more -- that is `regression-test-runner`'s job, via
|
|
|
71
71
|
`regression-test-playbook.md`, once per sprint, and its result is separate
|
|
72
72
|
from and does not gate yours.
|
|
73
73
|
|
|
74
|
+
## Step 0c -- Knowledge Bank (required -- do this BEFORE working any feature)
|
|
75
|
+
|
|
76
|
+
1. Run ToolSearch with query `"select:mcp__apra-fleet__kb_session_prime,mcp__apra-fleet__kb_capture"`
|
|
77
|
+
2. Call `mcp__apra-fleet__kb_session_prime` with `repo_path` set to the repo under test, and
|
|
78
|
+
`hint_symbols`/`hint_modules` relevant to the features you were handed. Trust CONFIRMED
|
|
79
|
+
entries fully. Use INFERRED entries as hints, not facts. An entry recording that a test
|
|
80
|
+
is environment-sensitive changes how you read a single red run.
|
|
81
|
+
3. When a test turns out to be flaky or environment-sensitive, or the sandbox needs a step
|
|
82
|
+
the playbook does not record, call `mcp__apra-fleet__kb_capture` with type "knowledge" or
|
|
83
|
+
"learning".
|
|
84
|
+
|
|
85
|
+
If ToolSearch returns no KB tools (MCP server not running), skip these steps and proceed.
|
|
86
|
+
|
|
74
87
|
## Step 1 -- Work the features you were handed
|
|
75
88
|
|
|
76
89
|
Your dispatch prompt hands you an **explicit list of feature ids** -- the open features in
|
|
@@ -94,7 +107,7 @@ a time.
|
|
|
94
107
|
### Scope discipline and turn economy (stay within budget)
|
|
95
108
|
|
|
96
109
|
Your dispatch has a bounded turn budget, and historically this phase routinely
|
|
97
|
-
exhausted it and burned 15-85 min in resume/repair
|
|
110
|
+
exhausted it and burned 15-85 min in resume/repair. The budget is
|
|
98
111
|
sized so a run that is making progress is bounded by wall-clock time, not by turn
|
|
99
112
|
count -- exhausting the turn count means the run did too much work per feature or
|
|
100
113
|
polled too fast. Keep the run within budget by holding scope tight:
|
|
@@ -225,6 +238,9 @@ Do NOT close the feature. Create a bug issue, parented under the sprint scope yo
|
|
|
225
238
|
dispatch prompt named (grouping only -- see the graph-semantics section above; do NOT
|
|
226
239
|
also `bd dep add` this bug to the feature or the scope root):
|
|
227
240
|
|
|
241
|
+
`--title` is plain text only -- letters, digits, space, and `. , : ; ! ? ( ) ' _ / [ ] -`.
|
|
242
|
+
No backticks, double quotes, `$`, or backslash; put formatted detail in `--description`.
|
|
243
|
+
|
|
228
244
|
```bash
|
|
229
245
|
bd create \
|
|
230
246
|
--title="[integ] <short description of failure>" \
|