diff --git a/config/project-registry.json b/config/project-registry.json
index 5c385c4..9ce40da 100644
--- a/config/project-registry.json
+++ b/config/project-registry.json
@@ -15,7 +15,7 @@
     {
       "id": "p04-gigabit",
       "aliases": ["p04", "gigabit", "gigaBIT"],
-      "description": "Curated staged docs for the P04 GigaBIT mirror architecture and OTA optics project.",
+      "description": "Active P04 GigaBIT mirror project corpus from PKM plus staged operational docs.",
       "ingest_roots": [
         {
           "source": "vault",
@@ -27,7 +27,7 @@
     {
       "id": "p05-interferometer",
       "aliases": ["p05", "interferometer"],
-      "description": "Curated staged docs for the P05 interferometer architecture, vendors, and error-budget project.",
+      "description": "Active P05 interferometer corpus from PKM plus selected repo context and vendor documentation.",
       "ingest_roots": [
         {
           "source": "vault",
@@ -39,7 +39,7 @@
     {
       "id": "p06-polisher",
       "aliases": ["p06", "polisher"],
-      "description": "Curated staged docs for the P06 polisher project.",
+      "description": "Active P06 polisher corpus from PKM, software-suite notes, and selected repo context.",
       "ingest_roots": [
         {
           "source": "vault",
diff --git a/docs/current-state.md b/docs/current-state.md
index 576869c..b83b370 100644
--- a/docs/current-state.md
+++ b/docs/current-state.md
@@ -52,7 +52,7 @@ now includes a first curated ingestion batch for the active projects.
 - Dalidou Docker deployment foundation
 - initial AtoCore self-knowledge corpus ingested on Dalidou
 - T420/OpenClaw read-only AtoCore helper skill
-- first curated active-project corpus batch for:
+- full active-project markdown/text corpus wave for:
   - `p04-gigabit`
   - `p05-interferometer`
   - `p06-polisher`
@@ -87,7 +87,7 @@ The Dalidou instance already contains:
 - Master Plan V3
 - Build Spec V1
 - trusted project-state entries for `atocore`
-- curated staged project docs for:
+- full staged project markdown/text corpora for:
   - `p04-gigabit`
   - `p05-interferometer`
   - `p06-polisher`
@@ -99,12 +99,12 @@ The Dalidou instance already contains:
   - `p05-interferometer`
   - `p06-polisher`
 
-Current live stats after the latest documentation sync and active-project ingest
-passes:
+Current live stats after the full active-project wave are now far beyond the
+initial seed stage:
 
-- `source_documents`: 36
-- `source_chunks`: 568
-- `vectors`: 568
+- more than `1,100` source documents
+- more than `20,000` chunks
+- matching vector count
 
 The broader long-term corpus is still not fully populated yet. Wider project and
 vault ingestion remains a deliberate next step rather than something already
@@ -115,8 +115,8 @@ primarily visible under:
 
 - `/srv/storage/atocore/sources/vault/incoming/projects`
 
-This staged area is now useful for review because it contains the curated
-project docs that were actually ingested for the first active-project batch.
+This staged area is now useful for review because it contains the markdown/text
+project docs that were actually ingested for the full active-project wave.
 
 It is important to read this staged area correctly:
 
@@ -166,10 +166,12 @@ These are curated summaries and extracted stable project signals.
 
 In `source_documents` / retrieval corpus:
 
-- real project documents are now present for the same active project set
+- full project markdown/text corpora are now present for the active project set
 - retrieval is no longer limited to AtoCore self-knowledge only
-- the current corpus is still selective rather than exhaustive
-- that selectivity is intentional at this stage
+- the current corpus is broad enough that ranking quality matters more than
+  corpus presence alone
+- underspecified prompts can still pull in historical or archive material, so
+  project-aware routing and better ranking remain important
 
 The source refresh model now has a concrete foundation in code:
 
@@ -223,8 +225,8 @@ This separation is healthy:
 ## Immediate Next Focus
 
 1. Use the new T420-side organic routing layer in real OpenClaw workflows
-2. Keep tightening retrieval quality for the newly seeded active projects
-3. Define the first broader AtoVault/AtoDrive ingestion batches
+2. Tighten retrieval quality for the now fully ingested active project corpora
+3. Move to Wave 2 trusted-operational ingestion instead of blindly widening raw corpus further
 4. Keep the new engineering-knowledge architecture docs as implementation guidance while avoiding premature schema work
 5. Expand the boring operations baseline:
    - restore validation
@@ -234,6 +236,7 @@ This separation is healthy:
 
 See also:
 
+- [ingestion-waves.md](C:/Users/antoi/ATOCore/docs/ingestion-waves.md)
 - [master-plan-status.md](C:/Users/antoi/ATOCore/docs/master-plan-status.md)
 
 ## Guiding Constraints
diff --git a/docs/ingestion-waves.md b/docs/ingestion-waves.md
new file mode 100644
index 0000000..3f46b60
--- /dev/null
+++ b/docs/ingestion-waves.md
@@ -0,0 +1,129 @@
+# AtoCore Ingestion Waves
+
+## Purpose
+
+This document tracks how the corpus should grow without losing signal quality.
+
+The rule is:
+
+- ingest in waves
+- validate retrieval after each wave
+- only then widen the source scope
+
+## Wave 1 - Active Project Full Markdown Corpus
+
+Status: complete
+
+Projects:
+
+- `p04-gigabit`
+- `p05-interferometer`
+- `p06-polisher`
+
+What was ingested:
+
+- the full markdown/text PKM stacks for the three active projects
+- selected staged operational docs already under the Dalidou source roots
+- selected repo markdown/text context for:
+  - `Fullum-Interferometer`
+  - `polisher-sim`
+  - `Polisher-Toolhead` (when markdown exists)
+
+What was intentionally excluded:
+
+- binaries
+- images
+- PDFs
+- generated outputs unless they were plain text reports
+- dependency folders
+- hidden runtime junk
+
+Practical result:
+
+- AtoCore moved from a curated-seed corpus to a real active-project corpus
+- the live corpus now contains well over one thousand source documents and over
+  twenty thousand chunks
+- project-specific context building is materially stronger than before
+
+Main lesson from Wave 1:
+
+- full project ingestion is valuable
+- but broad historical/archive material can dilute retrieval for underspecified
+  prompts
+- context quality now depends more strongly on good project hints and better
+  ranking than on corpus size alone
+
+## Wave 2 - Trusted Operational Layer Expansion
+
+Status: next
+
+Goal:
+
+- expand `AtoDrive`-style operational truth for the active projects
+
+Candidate inputs:
+
+- current status dashboards
+- decision logs
+- milestone tracking
+- curated requirements baselines
+- explicit next-step plans
+
+Why this matters:
+
+- this raises the quality of the high-trust layer instead of only widening
+  general retrieval
+
+## Wave 3 - Broader Active Engineering References
+
+Status: planned
+
+Goal:
+
+- ingest reusable engineering references that support the active project set
+  without dumping the entire vault
+
+Candidate inputs:
+
+- interferometry reference notes directly tied to `p05`
+- polishing physics references directly tied to `p06`
+- mirror and structural reference material directly tied to `p04`
+
+Rule:
+
+- only bring in references with a clear connection to active work
+
+## Wave 4 - Wider PKM Population
+
+Status: deferred
+
+Goal:
+
+- widen beyond the active projects while preserving retrieval quality
+
+Preconditions:
+
+- stronger ranking
+- better project-aware routing
+- stable operational restore path
+- clearer promotion rules for trusted state
+
+## Validation After Each Wave
+
+After every ingestion wave, verify:
+
+- `stats`
+- project-specific `query`
+- project-specific `context-build`
+- `debug-context`
+- whether trusted project state still dominates when it should
+- whether cross-project bleed is getting worse or better
+
+## Working Rule
+
+The next wave should only happen when the current wave is:
+
+- ingested
+- inspected
+- retrieval-tested
+- operationally stable
diff --git a/docs/next-steps.md b/docs/next-steps.md
index 6707db6..f984f1a 100644
--- a/docs/next-steps.md
+++ b/docs/next-steps.md
@@ -29,9 +29,11 @@ This working list should be read alongside:
    - check whether the top hits are useful
    - check whether trusted project state remains dominant
    - reduce cross-project competition and prompt ambiguity where needed
-3. Continue controlled project ingestion only where the current corpus is still
-   thin
-   - a few additional anchor docs per active project
+   - use `debug-context` to inspect the exact last AtoCore supplement
+3. Treat the active-project full markdown/text wave as complete
+   - `p04-gigabit`
+   - `p05-interferometer`
+   - `p06-polisher`
 4. Define a cleaner source refresh model
    - make the difference between source truth, staged inputs, and machine store
      explicit
@@ -39,15 +41,20 @@ This working list should be read alongside:
    - foundation now exists via project registry + per-project refresh API
    - registration policy + template + proposal + approved registration are now
      the normal path for new projects
-5. Integrate the new engineering architecture docs into active planning, not immediate schema code
+5. Move to Wave 2 trusted-operational ingestion
+   - curated dashboards
+   - decision logs
+   - milestone/current-status views
+   - operational truth, not just raw project notes
+6. Integrate the new engineering architecture docs into active planning, not immediate schema code
    - keep `docs/architecture/engineering-knowledge-hybrid-architecture.md` as the target layer model
    - keep `docs/architecture/engineering-ontology-v1.md` as the V1 structured-domain target
    - do not start entity/relationship persistence until the ingestion, retrieval, registry, and backup baseline feels boring and stable
-6. Define backup and export procedures for Dalidou
+7. Define backup and export procedures for Dalidou
    - exercise the new SQLite + registry snapshot path on Dalidou
    - Chroma backup or rebuild policy
    - retention and restore validation
-7. Keep deeper automatic runtime integration modest until the organic read-only
+8. Keep deeper automatic runtime integration modest until the organic read-only
    model has proven value
 
 ## Trusted State Status
@@ -69,36 +76,39 @@ This materially improves `context/build` quality for project-hinted prompts.
 
 ## Recommended Near-Term Project Work
 
-The first curated batch is already in.
+The active-project full markdown/text wave is now in.
 
 The near-term work is now:
 
 1. strengthen retrieval quality
-2. add a few more anchor docs only where retrieval is still weak
+2. promote or refine trusted operational truth where the broad corpus is now too noisy
 3. keep trusted project state concise and high-confidence
+4. widen only through named ingestion waves
 
-## Recommended Additional Anchor Docs
+## Recommended Next Wave Inputs
 
-1. `p04-gigabit`
-2. `p05-interferometer`
-3. `p06-polisher`
+Wave 2 should emphasize trusted operational truth, not bulk historical notes.
 
 P04:
 
-- 1 to 2 more strong study summaries
-- 1 to 2 more meeting notes with actual decisions
+- current status dashboard
+- current selected design path
+- current frame interface truth
+- current next-step milestone view
 
 P05:
 
-- a couple more architecture docs
-- selected vendor-response notes
-- possibly one or two NX/WAVE consumer docs
+- selected vendor path
+- current error-budget baseline
+- current architecture freeze or open decisions
+- current procurement / next-action view
 
 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`
+- current system map
+- current shared contracts baseline
+- current calibration procedure truth
+- current July / proving roadmap view
 
 ## Deferred On Purpose
 
@@ -115,6 +125,8 @@ 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
+- the active-project full corpus wave can be inspected and used concretely
+  through `auto-context`, `context-build`, and `debug-context`
 - 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
diff --git a/docs/openclaw-integration-contract.md b/docs/openclaw-integration-contract.md
index e57f789..f526d23 100644
--- a/docs/openclaw-integration-contract.md
+++ b/docs/openclaw-integration-contract.md
@@ -82,6 +82,7 @@ The current helper script exposes:
 - `project-template`
 - `detect-project <prompt>`
 - `auto-context <prompt> [budget] [project]`
+- `debug-context`
 - `propose-project ...`
 - `register-project ...`
 - `update-project ...`
@@ -125,6 +126,8 @@ Recommended first behavior:
 1. OpenClaw receives a user request
 2. If the prompt looks like project knowledge, OpenClaw should try:
    - `auto-context "<prompt>" 3000`
+   - optionally `debug-context` immediately after if a human wants to inspect
+     the exact AtoCore supplement
 3. If the prompt is clearly asking for trusted current truth, OpenClaw should
    prefer:
    - `project-state <project>`
diff --git a/src/atocore/api/routes.py b/src/atocore/api/routes.py
index 6d268d1..a80b77b 100644
--- a/src/atocore/api/routes.py
+++ b/src/atocore/api/routes.py
@@ -18,6 +18,7 @@ from atocore.context.project_state import (
     set_state,
 )
 from atocore.ingestion.pipeline import (
+    exclusive_ingestion,
     get_ingestion_stats,
     get_source_status,
     ingest_configured_sources,
@@ -153,12 +154,13 @@ def api_ingest(req: IngestRequest) -> IngestResponse:
     """Ingest a markdown file or folder."""
     target = Path(req.path)
     try:
-        if target.is_file():
-            results = [ingest_file(target)]
-        elif target.is_dir():
-            results = ingest_folder(target)
-        else:
-            raise HTTPException(status_code=404, detail=f"Path not found: {req.path}")
+        with exclusive_ingestion():
+            if target.is_file():
+                results = [ingest_file(target)]
+            elif target.is_dir():
+                results = ingest_folder(target)
+            else:
+                raise HTTPException(status_code=404, detail=f"Path not found: {req.path}")
     except HTTPException:
         raise
     except Exception as e:
@@ -171,7 +173,8 @@ def api_ingest(req: IngestRequest) -> IngestResponse:
 def api_ingest_sources() -> IngestSourcesResponse:
     """Ingest enabled configured source directories."""
     try:
-        results = ingest_configured_sources()
+        with exclusive_ingestion():
+            results = ingest_configured_sources()
     except Exception as e:
         log.error("ingest_sources_failed", error=str(e))
         raise HTTPException(status_code=500, detail=f"Configured source ingestion failed: {e}")
@@ -246,7 +249,8 @@ def api_project_update(project_name: str, req: ProjectUpdateRequest) -> dict:
 def api_refresh_project(project_name: str, purge_deleted: bool = False) -> ProjectRefreshResponse:
     """Refresh one registered project from its configured ingest roots."""
     try:
-        result = refresh_registered_project(project_name, purge_deleted=purge_deleted)
+        with exclusive_ingestion():
+            result = refresh_registered_project(project_name, purge_deleted=purge_deleted)
     except ValueError as e:
         raise HTTPException(status_code=404, detail=str(e))
     except Exception as e:
diff --git a/src/atocore/ingestion/pipeline.py b/src/atocore/ingestion/pipeline.py
index ae2470b..78052ea 100644
--- a/src/atocore/ingestion/pipeline.py
+++ b/src/atocore/ingestion/pipeline.py
@@ -2,8 +2,10 @@
 
 import hashlib
 import json
+import threading
 import time
 import uuid
+from contextlib import contextmanager
 from pathlib import Path
 
 import atocore.config as _config
@@ -17,6 +19,17 @@ log = get_logger("ingestion")
 
 # Encodings to try when reading markdown files
 _ENCODINGS = ["utf-8", "utf-8-sig", "latin-1", "cp1252"]
+_INGESTION_LOCK = threading.Lock()
+
+
+@contextmanager
+def exclusive_ingestion():
+    """Serialize long-running ingestion operations across API requests."""
+    _INGESTION_LOCK.acquire()
+    try:
+        yield
+    finally:
+        _INGESTION_LOCK.release()
 
 
 def ingest_file(file_path: Path) -> dict:
diff --git a/tests/test_api_storage.py b/tests/test_api_storage.py
index 25fee45..7eefbc4 100644
--- a/tests/test_api_storage.py
+++ b/tests/test_api_storage.py
@@ -1,5 +1,7 @@
 """Tests for storage-related API readiness endpoints."""
 
+from contextlib import contextmanager
+
 from fastapi.testclient import TestClient
 
 import atocore.config as config
@@ -152,6 +154,38 @@ def test_project_refresh_endpoint_uses_registered_roots(tmp_data_dir, monkeypatc
     assert response.json()["project"] == "p05-interferometer"
 
 
+def test_project_refresh_endpoint_serializes_ingestion(tmp_data_dir, monkeypatch):
+    config.settings = config.Settings()
+    events = []
+
+    @contextmanager
+    def fake_lock():
+        events.append("enter")
+        try:
+            yield
+        finally:
+            events.append("exit")
+
+    def fake_refresh_registered_project(project_name, purge_deleted=False):
+        events.append(("refresh", project_name, purge_deleted))
+        return {
+            "project": "p05-interferometer",
+            "aliases": ["p05"],
+            "description": "P05 docs",
+            "purge_deleted": purge_deleted,
+            "roots": [],
+        }
+
+    monkeypatch.setattr("atocore.api.routes.exclusive_ingestion", fake_lock)
+    monkeypatch.setattr("atocore.api.routes.refresh_registered_project", fake_refresh_registered_project)
+
+    client = TestClient(app)
+    response = client.post("/projects/p05/refresh")
+
+    assert response.status_code == 200
+    assert events == ["enter", ("refresh", "p05", False), "exit"]
+
+
 def test_projects_template_endpoint_returns_template(tmp_data_dir, monkeypatch):
     config.settings = config.Settings()