Document organic OpenClaw routing layer

docs/current-state.md

@@ -145,6 +145,11 @@ It is important to read this staged area correctly:
   - register-project
   - update-project
   - refresh-project
+- the helper now also supports the first organic routing layer:
+  - `detect-project "<prompt>"`
+  - `auto-context "<prompt>" [budget] [project]`
+- OpenClaw can now default to AtoCore for project-knowledge questions without
+  requiring explicit helper commands from the human every time
 
 ## What Exists In Memory vs Corpus
 
@@ -217,12 +222,15 @@ This separation is healthy:
 
 ## Immediate Next Focus
 
-1. Use the new T420-side AtoCore skill and registration flow in real OpenClaw workflows
+1. Use the new T420-side organic routing layer in real OpenClaw workflows
-2. Keep the new engineering-knowledge architecture docs as implementation guidance while avoiding premature schema work
+2. Keep tightening retrieval quality for the newly seeded active projects
-3. Tighten retrieval quality for the newly seeded active projects
+3. Define the first broader AtoVault/AtoDrive ingestion batches
-4. Define the first broader AtoVault/AtoDrive ingestion batches
+4. Keep the new engineering-knowledge architecture docs as implementation guidance while avoiding premature schema work
-5. Add backup/export strategy for Dalidou machine state
+5. Expand the boring operations baseline:
-6. Only later consider deeper automatic OpenClaw integration or write-back
+   - restore validation
+   - Chroma rebuild / backup policy
+   - retention
+6. Only later consider write-back, reflection, or deeper autonomous behaviors
 
 See also:
 

docs/master-plan-status.md

@@ -63,6 +63,7 @@ These are the current practical priorities.
 
 1. Finish practical OpenClaw integration
    - make the helper lifecycle feel natural in daily use
+   - use the new organic routing layer for project-knowledge questions
    - confirm fail-open behavior remains acceptable
    - keep AtoCore clearly additive
 2. Tighten retrieval quality

docs/next-steps.md

@@ -20,8 +20,10 @@ This working list should be read alongside:
 
 ## Immediate Next Steps
 
-1. Use the T420 `atocore-context` skill in real OpenClaw workflows
+1. Use the T420 `atocore-context` skill and the new organic routing layer in
-   - confirm the ergonomics are good
+   real OpenClaw workflows
+   - confirm `auto-context` feels natural
+   - confirm project inference is good enough in practice
    - confirm the fail-open behavior remains acceptable in practice
 2. Review retrieval quality after the first real project ingestion batch
    - check whether the top hits are useful
@@ -45,8 +47,8 @@ This working list should be read alongside:
    - exercise the new SQLite + registry snapshot path on Dalidou
    - Chroma backup or rebuild policy
    - retention and restore validation
-7. Keep deeper automatic runtime integration deferred until the read-only model
+7. Keep deeper automatic runtime integration modest until the organic read-only
-   has proven value
+   model has proven value
 
 ## Trusted State Status
 
@@ -111,6 +113,8 @@ P06:
 The next batch is successful if:
 
 - OpenClaw can use AtoCore naturally when context is needed
+- OpenClaw can infer registered projects and call AtoCore organically for
+  project-knowledge questions
 - OpenClaw can also register a new project cleanly before refreshing it
 - existing project registrations can be refined safely before refresh when the
   staged source set evolves

docs/openclaw-integration-contract.md

@@ -20,10 +20,13 @@ The first safe integration foundation now exists on the T420 workspace:
   - `health`
   - `project-state`
   - `query`
+  - `detect-project`
+  - `auto-context`
   - fail-open fallback when AtoCore is unavailable
 
-This means the network and workflow foundation is working, even though deeper
+This means the network and workflow foundation is working, and the first
-automatic integration into OpenClaw runtime behavior is still deferred.
+organic routing layer now exists, even though deeper autonomous integration
+into OpenClaw runtime behavior is still deferred.
 
 ## Integration Principles
 
@@ -43,6 +46,7 @@ OpenClaw may use AtoCore for:
 - context building for contextual prompts
 - retrieval/query support
 - project-state lookup when a project is detected
+- automatic project-context augmentation for project-knowledge questions
 
 OpenClaw should not yet use AtoCore for:
 
@@ -76,6 +80,8 @@ The current helper script exposes:
 - `stats`
 - `projects`
 - `project-template`
+- `detect-project <prompt>`
+- `auto-context <prompt> [budget] [project]`
 - `propose-project ...`
 - `register-project ...`
 - `update-project ...`
@@ -117,10 +123,17 @@ Recommended first behavior:
 ## Suggested Usage Pattern
 
 1. OpenClaw receives a user request
-2. OpenClaw decides whether the request is contextual enough to query AtoCore
+2. If the prompt looks like project knowledge, OpenClaw should try:
-3. If yes, OpenClaw calls AtoCore
+   - `auto-context "<prompt>" 3000`
-4. If AtoCore returns usable context, OpenClaw includes it
+3. If the prompt is clearly asking for trusted current truth, OpenClaw should
-5. If AtoCore fails or returns nothing useful, OpenClaw proceeds normally
+   prefer:
+   - `project-state <project>`
+4. If the user explicitly asked for source refresh or ingestion, OpenClaw
+   should use:
+   - `refresh-project <id>`
+5. If AtoCore returns usable context, OpenClaw includes it
+6. If AtoCore fails, returns `no_project_match`, or is unavailable, OpenClaw
+   proceeds normally
 
 ## Deferred Work