20 lines
1.7 KiB
Markdown
20 lines
1.7 KiB
Markdown
# Plan Map
|
|
|
|
**Workflow:** wf-decompose-c7b1125e7fe2
|
|
**Intent:** Extend the existing agent repository at https://gitea.kyndemo.live/agents/content-ingestion-agent. First, migrate the kab_ingestion package into that repository's app/ package, so the ingestion contract models and ports, the GitHub SCM connector, the SharePoint CMS connector, the ingestion orchestrator, the triggers, the governance/publication helpers and the validation helpers all live under app/ and are wired into the agent's create_agent_app entry point, its AgentCard skill list and its typed settings. Second, eliminate every placeholder file in the repository. No file may be left empty, docstring-only, comment-only, or carrying a TODO scaffold marker. Concretely: app/agent.py, app/card.py and app/config.py are currently one-line docstrings; app/__init__.py, app/nodes/__init__.py, app/states/__init__.py, app/tools/__init__.py, app/workflows/__init__.py, tests/__init__.py, requirements.txt and requirements-dev.txt are empty; tests/conftest.py is a single comment; and k8s/deployment.yaml, k8s/configmap.yaml and k8s/service.yaml each contain only the line '# TODO: generation subagent fills this in.'. Every one of these must end up with real, working, populated content appropriate to this agent - actual route wiring, an actual agent card, actual typed settings, actual pinned dependencies, actual Kubernetes manifests and actual test fixtures - rather than boilerplate.
|
|
**This repo covers:** step 0, step 1, step 2, step 3
|
|
|
|
## Dependency graph
|
|
|
|
- Step 0: no dependencies
|
|
- Step 1: depends on step 0
|
|
- Step 2: depends on step 0, step 1
|
|
- Step 3: depends on step 0, step 1, step 2
|
|
|
|
## Phase table
|
|
|
|
Phase 1: step 0
|
|
Phase 2: step 1
|
|
Phase 3: step 2
|
|
Phase 4: step 3
|