Clarify operating model and project corpus state

docs/next-steps.md

@@ -9,38 +9,67 @@ AtoCore now has:
 - initial self-knowledge ingested into the live instance
 - trusted project-state entries for AtoCore itself
 - a first read-only OpenClaw integration path on the T420
+- a first real active-project corpus batch for:
+  - `p04-gigabit`
+  - `p05-interferometer`
+  - `p06-polisher`
 
 ## Immediate Next Steps
 
 1. Use the T420 `atocore-context` skill in real OpenClaw workflows
    - confirm the ergonomics are good
    - confirm the fail-open behavior remains acceptable in practice
-2. Ingest selected active projects only
-   - start with the current active project set
-   - prefer trusted operational/project sources first
-   - ingest broader PKM sources only after the trusted layer is loaded
-3. Review retrieval quality after the first real project ingestion batch
+2. Review retrieval quality after the first real project ingestion batch
    - check whether the top hits are useful
    - check whether trusted project state remains dominant
-4. Define backup and export procedures for Dalidou
+   - reduce cross-project competition and prompt ambiguity where needed
+3. Promote a small number of stable active-project facts into trusted project
+   state
+   - active architecture
+   - current selected path
+   - key constraints
+   - current next step
+4. Continue controlled project ingestion only where the current corpus is still
+   thin
+   - a few additional anchor docs per active project
+5. Define backup and export procedures for Dalidou
    - SQLite snapshot/backup strategy
    - Chroma backup or rebuild policy
-5. Keep deeper automatic runtime integration deferred until the read-only model
+6. Keep deeper automatic runtime integration deferred until the read-only model
    has proven value
 
-## Recommended Active Project Ingestion Order
+## Recommended Near-Term Project Work
+
+The first curated batch is already in.
+
+The near-term work is now:
+
+1. strengthen retrieval quality
+2. promote the most stable facts into trusted project state
+3. only then add a few more anchor docs where still needed
+
+## Recommended Additional Anchor Docs
 
 1. `p04-gigabit`
 2. `p05-interferometer`
 3. `p06-polisher`
 
-For each project:
+P04:
 
-1. identify the matching AtoDrive/project-operational sources
-2. identify the matching PKM project folder(s)
-3. ingest the trusted/operational material first
-4. ingest broader notes second
-5. review retrieval quality before moving on
+- 1 to 2 more strong study summaries
+- 1 to 2 more meeting notes with actual decisions
+
+P05:
+
+- a couple more architecture docs
+- selected vendor-response notes
+- possibly one or two NX/WAVE consumer docs
+
+P06:
+
+- more explicit interface/schema docs if needed
+- selected operations or UI docs
+- a distilled non-empty operational context doc to replace an empty `_context.md`
 
 ## Deferred On Purpose
 
@@ -56,5 +85,18 @@ The next batch is successful if:
 
 - OpenClaw can use AtoCore naturally when context is needed
 - AtoCore answers correctly for the active project set
+- retrieval surfaces the seeded project docs instead of mostly AtoCore meta-docs
 - project ingestion remains controlled rather than noisy
 - the canonical Dalidou instance stays stable
+
+## Long-Run Goal
+
+The long-run target is:
+
+- continue working normally inside PKM project stacks and Gitea repos
+- let OpenClaw keep its own memory and runtime behavior
+- let AtoCore supplement LLM work with stronger trusted context, retrieval, and
+  context assembly
+
+That means AtoCore should behave like a durable external context engine and
+machine-memory layer, not a replacement for normal repo work or OpenClaw memory.