Skip to content

About

Synapse增长负责人

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

690 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

SynapseNetwork logo

Synapse-Network-Growing

Synapse-Network-Growing is the Company Ops control plane for the Synapse system. Its purpose is to turn goals, signals, incidents, and operator intent into observable agent-first workflows that can plan, execute, verify, request approval, and deliver safely.

The current operating model is:

Operating Manifest
-> Planner Sweep
-> RequirementCandidate
-> Requirement
-> Declarative Workflow Run
-> State Machine Runner
-> Atom Invocations + Blackboard + Evidence
-> Human Gate / Release / Done

The key boundary is simple: Agent is the engine, declarative state machine is the rail, human operator is the high-risk gate.

Current Architecture

The repository is no longer centered on legacy TaskBoard / CrewAI / fixed execution steps. New business flow must use:

  1. Operating Manifest: the single active strategy snapshot and budget/goal control surface.
  2. RequirementCandidate: the buffer between autonomous planning and the formal requirement pool.
  3. Requirement: the approved or materialized work item tied to a project, manifest, and goal lineage.
  4. Declarative Workflow Run: the source of truth for execution, validation, retry, evidence, and delivery.
  5. Blackboard + Artifacts: shared workflow context and immutable evidence.
  6. Human Gate: mandatory approval for production, funds, settlement, auth, external spend, and self-modifying deployment.
  7. Recurring Jobs + Watchers: observable background systems for bug sweep, notification dispatch, recurring workflow registry, and planning sweeps.

Legacy /api/tasks and /api/approvals public routes have been retired. Any remaining old task/execution internals are deletion candidates, not compatibility surfaces for new work.

Read First

Coding agents and humans should start here:

  1. ARCHITECTURE.md - short architecture constitution for coding agents.
  2. AGENTS.md - repo agent operating protocol and capability profile rules.
  3. System Design Principles - canonical engineering constraints.
  4. Declarative Agent Workflow Factory - state machine, blackboard, atoms, gates.
  5. Planning Lifecycle Operating Manifest - manifest, planner sweep, candidates, drop goal.
  6. Recurring Workflow Control Plane - scheduled jobs and dispatcher observability.
  7. Workflow Factory Frontend Control Plane - operator UI for workflow observability.
  8. Figma Driven Human-Agent Control Plane Frontend - Figma/Stitch-driven cockpit UI direction and implementation contract.
  9. Current Feature Inventory - implemented capability baseline.
  10. Ops Console Usage - local UI/API usage notes.
  11. Ops Console Page Map and E2E Validation - page-by-page function map, tests, and GoalB dogfood validation.

Historical evidence, old plans, and legacy docs are intentionally moved under docs/archive/. They are audit evidence, not current architecture sources.

Main Surfaces

  1. /command-center: Human-Agent control plane overview, desired state, blockers, active runs, and background health.
  2. /planning: active Operating Manifest, planner candidates, goal rollups, drop-goal safe halt, manifest history.
  3. /intake: requirement discovery entry point for errors, watcher events, forum feedback, and planner signals.
  4. /gates: Human Oracle queue for pending gates, failed runs, and high-risk decisions.
  5. /requirements: requirement pool and workflow readiness.
  6. /workflows: declarative workflow run operations center.
  7. /workflows/:id: explainable workflow workbench with steps, evidence, gates, delivery, and debug views.
  8. /factory/workflows: read-only workflow definition registry.
  9. /factory/atoms: read-only atom registry.
  10. /knowledge: artifacts and SOP Ledger entry point.
  11. /schedules: recurring workflow registry, run history, scheduler/dispatcher health.
  12. /system/notifications: notification queue, dispatcher health, suppression, and delivery observability.
  13. /errors: error fingerprints and bug materialization state.
  14. /projects: project registry and delivery policy configuration.
  15. /releases: PR, delivery, deploy, and rollback governance.

The current product-level validation target is GoalB: the system must show that an Operating Manifest goal can become a RequirementCandidate, then a formal Requirement, then a completed declarative WorkflowRun with evidence. See Ops Console Page Map and E2E Validation.

Required Runtime

The local backend expects Python 3.14+ through the shared workspace virtualenv:

/opt/homebrew/bin/python3.14 -m venv /Users/cliff/workspace/agent/.venv
/Users/cliff/workspace/agent/.venv/bin/python -m pip install -U pip setuptools wheel
/Users/cliff/workspace/agent/.venv/bin/pip install -r requirements.txt

Common local commands:

sh scripts/local/restart.sh
/Users/cliff/workspace/agent/.venv/bin/python -m pytest -q
cd dashboard && npm test
cd dashboard && npm run build

Planner And Runtime Config

Recommended planner adapter:

PLANNER_BACKEND=codex_sdk
PLANNER_MODEL=gpt-5.4
PLANNER_TIMEOUT=300

Supported planner adapters are:

openai | claude | copilot | codex_cli | codex_sdk

Runtime execution can still be configured independently. For local Codex CLI execution:

ORCHESTRATION_BACKEND=codex_cli
LLM_PROVIDER=codex
LLM_MODEL=gpt-5-codex
CODEX_CLI_MODEL=gpt-5-codex
CODEX_CLI_FULL_AUTO=true

For OpenAI API usage:

LLM_PROVIDER=openai
LLM_MODEL=gpt-5.4
ORCHESTRATION_BACKEND=openai_responses
OPENAI_API_KEY=...

Notification Config

Lark delivery is queued, deduplicated, and rate-limited before sending. Configure separate webhooks for alert, approval, workflow notification, and release channels:

OPS_LARK_BOT_WEBHOOK_URL=...
OPS_LARK_BOT_KEYWORD=告警
OPS_LARK_REQUIREMENT_WEBHOOK_URL=...
OPS_LARK_REQUIREMENT_KEYWORD=需求
OPS_LARK_ALERT_WEBHOOK_URL=...
OPS_LARK_ALERT_KEYWORD=告警
OPS_LARK_APPROVAL_WEBHOOK_URL=...
OPS_LARK_APPROVAL_KEYWORD=审批
OPS_LARK_RELEASE_WEBHOOK_URL=...
OPS_LARK_RELEASE_KEYWORD=发布
OPS_LARK_DELIVERY_DRY_RUN=false
OPS_NOTIFICATION_DISPATCHER_ENABLED=true
OPS_NOTIFICATION_ALERT_BURST_PER_MINUTE=5
OPS_NOTIFICATION_DEFAULT_COOLDOWN_SECONDS=900

Set OPS_LARK_DELIVERY_DRY_RUN=true when running smoke tests against configured webhooks. Dry-run mode still persists notification deliveries and renders Lark cards, but it never calls the Lark webhook.

Routing rules:

  1. P0/P1 interruption -> alert.
  2. Human gate -> approval.
  3. PR / release / deploy -> release.
  4. Workflow lifecycle summary -> workflow notification.
  5. Ordinary state transitions, atom success, artifacts, and blackboard snapshots stay in Ops Console.

Docs Layout

  1. docs/design-docs/: current architecture and formal design docs.
  2. docs/ops/: operational governance and deployment runbooks.
  3. docs/plans/: temporary staging only for new plan bundles; implementation truth remains in ARCHITECTURE.md and docs/design-docs/.
  4. docs/archive/: historical evidence, old plans, old design drafts, and retired docs.
  5. docs/assets/: architecture diagrams used by current docs.

When adding or deleting formal capabilities, update Current Feature Inventory with the same change.

About

Synapse增长负责人

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages