Update path to llama_stack_configuration module

Using the module this way seems like a major anti-pattern that needs refactoring.

Author: samdoran

Makefile

@@ -70,7 +70,7 @@ start-llama-stack-container: build-llama-stack-image ## Start llama-stack contai
 		-v $(PWD)/$(LLAMA_STACK_CONFIG):/opt/app-root/run.yaml:z \
 		-v $(PWD)/$(CONFIG):/opt/app-root/lightspeed-stack.yaml:ro,z \
 		-v $(PWD)/scripts/llama-stack-entrypoint.sh:/opt/app-root/enrich-entrypoint.sh:ro,z \
-		-v $(PWD)/src/llama_stack_configuration.py:/opt/app-root/llama_stack_configuration.py:ro,z \
+		-v $(PWD)/src/lightspeed_stack/llama_stack_configuration.py:/opt/app-root/llama_stack_configuration.py:ro,z \
 		-e OPENAI_API_KEY \
 		-e BRAVE_SEARCH_API_KEY \
 		-e TAVILY_SEARCH_API_KEY \
@@ -129,7 +129,7 @@ clean-llama-stack: remove-llama-stack-container ## Remove container and image
 	fi
 
 run-llama-stack: ## Start Llama Stack with enriched config (for local service mode)
-	uv run src/llama_stack_configuration.py -c $(CONFIG) -i $(LLAMA_STACK_CONFIG) -o $(LLAMA_STACK_CONFIG) && \
+	uv run src/lightspeed_stack/llama_stack_configuration.py -c $(CONFIG) -i $(LLAMA_STACK_CONFIG) -o $(LLAMA_STACK_CONFIG) && \
 	uv run llama stack run $(LLAMA_STACK_CONFIG)
 
 test-unit: ## Run the unit tests

deploy/llama-stack/test.containerfile

@@ -40,7 +40,7 @@ RUN mkdir -p /opt/app-root/src/.llama/storage \
     chmod -R 775 /opt/app-root
 
 # Copy enrichment scripts for runtime config enrichment
-COPY src/llama_stack_configuration.py /opt/app-root/llama_stack_configuration.py
+COPY src/lightspeed_stack/llama_stack_configuration.py /opt/app-root/llama_stack_configuration.py
 COPY scripts/llama-stack-entrypoint.sh /opt/app-root/enrich-entrypoint.sh
 RUN chmod +x /opt/app-root/enrich-entrypoint.sh && \
     chown 1001:0 /opt/app-root/enrich-entrypoint.sh /opt/app-root/llama_stack_configuration.py

docker-compose.yaml

@@ -15,7 +15,7 @@ services:
       - ./run.yaml:/opt/app-root/run.yaml:z
       # Host copies so `docker compose up` picks up script changes without rebuilding llama-stack
       - ./scripts/llama-stack-entrypoint.sh:/opt/app-root/enrich-entrypoint.sh:ro,z
-      - ./src/llama_stack_configuration.py:/opt/app-root/llama_stack_configuration.py:ro,z
+      - ./src/lightspeed_stack/llama_stack_configuration.py:/opt/app-root/llama_stack_configuration.py:ro,z
       - ${GCP_KEYS_PATH:-./tmp/.gcp-keys-dummy}:/opt/app-root/.gcp-keys:ro
       - ./lightspeed-stack.yaml:/opt/app-root/lightspeed-stack.yaml:ro,z
       - llama-storage:/opt/app-root/src/.llama/storage

docs/design/llama-stack-config-merge/llama-stack-config-merge-spike.md

@@ -442,7 +442,7 @@ configuration model. (Full design: the spec doc.)
   - Add the unified-vs-legacy `@model_validator` to the **root**
     `Configuration` model (it spans top-level `inference.providers` and
     `llama_stack.*`).
-- New functions in `src/llama_stack_configuration.py`:
+- New functions in `src/lightspeed_stack/llama_stack_configuration.py`:
   `synthesize_configuration`, `deep_merge_list_replace`,
   `apply_high_level_inference`, `load_default_baseline`, `synthesize_to_file`.
 - A shipped default baseline at `src/data/default_run.yaml`.
@@ -468,7 +468,7 @@ Read the "Architecture" and "Implementation Suggestions" sections of
 docs/design/llama-stack-config-merge/llama-stack-config-merge.md.
 Key files to create or modify:
   src/models/config.py  (new classes; modify LlamaStackConfiguration)
-  src/llama_stack_configuration.py  (synthesize_configuration + helpers)
+  src/lightspeed_stack/llama_stack_configuration.py  (synthesize_configuration + helpers)
   src/data/default_run.yaml  (new)
   src/client.py  (library-mode wiring)
 To verify: run a unified-mode config end-to-end via `uv run lightspeed-stack -c <config>` and confirm /v1/query succeeds.
@@ -486,7 +486,7 @@ that produces a unified single-file config from an existing
 
 **Scope**:
 
-- `migrate_config_dumb()` function in `src/llama_stack_configuration.py`.
+- `migrate_config_dumb()` function in `src/lightspeed_stack/llama_stack_configuration.py`.
 - `--migrate-config`, `--run-yaml`, `--migrate-output` flags in
   `src/lightspeed_stack.py`.
 - Round-trip test: migrate → synthesize → byte-identical to original
@@ -504,7 +504,7 @@ that produces a unified single-file config from an existing
 
 ```text
 Read "Migration / backwards compatibility" and "Appendix A — Worked example: legacy → unified migration" in docs/design/llama-stack-config-merge/llama-stack-config-merge.md.
-Key files: src/lightspeed_stack.py, src/llama_stack_configuration.py,
+Key files: src/lightspeed_stack.py, src/lightspeed_stack/llama_stack_configuration.py,
 tests/unit/test_llama_stack_synthesize.py.
 To verify: migrate the repo's root run.yaml + lightspeed-stack.yaml, then
 start LCORE with the output; confirm /v1/query works.
@@ -946,7 +946,7 @@ Two files:
   (inference, safety, tool_runtime, vector_io, agents, ...), `storage`,
   `registered_resources`, `vector_stores`, `safety`.
 
-**Existing enrichment** (`src/llama_stack_configuration.py`):
+**Existing enrichment** (`src/lightspeed_stack/llama_stack_configuration.py`):
 
 - LCORE already enriches an input `run.yaml` with dynamic values from
   `lightspeed-stack.yaml`: Azure Entra ID tokens (side-effect to `.env`),
@@ -1136,7 +1136,7 @@ Relative to `upstream/main`:
 | File | Purpose |
 |---|---|
 | `src/models/config.py` | New classes: `UnifiedInferenceProvider`, `UnifiedInferenceSection`, `UnifiedLlamaStackConfig`; modified `LlamaStackConfiguration` (adds `config` field + mutual-exclusion validator). _PoC layout; the implementation follows Decision S5 — `inference.providers` on the top-level `InferenceConfiguration`, validator on the root `Configuration` model, no `UnifiedInferenceSection` (see the schema JIRA)._ |
-| `src/llama_stack_configuration.py` | New: `synthesize_configuration`, `deep_merge_list_replace`, `apply_high_level_inference`, `load_default_baseline`, `synthesize_to_file`, `migrate_config_dumb`. CLI `main()` auto-detects unified vs legacy. |
+| `src/lightspeed_stack/llama_stack_configuration.py` | New: `synthesize_configuration`, `deep_merge_list_replace`, `apply_high_level_inference`, `load_default_baseline`, `synthesize_to_file`, `migrate_config_dumb`. CLI `main()` auto-detects unified vs legacy. |
 | `src/data/default_run.yaml` | Built-in default baseline (copied from repo root `run.yaml` for the PoC — implementation JIRA should slim it down; see PoC surprise about `EXTERNAL_PROVIDERS_DIR`) |
 | `src/client.py` | Library-mode path picks synthesis for unified configs, enrichment for legacy |
 | `src/lightspeed_stack.py` | `--migrate-config`, `--run-yaml`, `--migrate-output` flags |

docs/design/llama-stack-config-merge/llama-stack-config-merge.md

@@ -3,7 +3,7 @@
 |                    |                                                                                  |
 |--------------------|----------------------------------------------------------------------------------|
 | **Date**           | 2026-04-23                                                                       |
-| **Component**      | Lightspeed Core Stack (src/models/config.py, src/llama_stack_configuration.py, src/client.py, src/lightspeed_stack.py, scripts/llama-stack-entrypoint.sh) |
+| **Component**      | Lightspeed Core Stack (src/models/config.py, src/lightspeed_stack/llama_stack_configuration.py, src/client.py, src/lightspeed_stack.py, scripts/llama-stack-entrypoint.sh) |
 | **Authors**        | Maxim Svistunov                                                                   |
 | **Feature**        | [LCORE-836](https://redhat.atlassian.net/browse/LCORE-836)                       |
 | **Spike**          | [llama-stack-config-merge-spike.md](llama-stack-config-merge-spike.md)           |
@@ -328,7 +328,7 @@ class Configuration(ConfigurationBase):
 ### API changes
 
 None at the REST API surface. Internal API additions in
-`src/llama_stack_configuration.py`:
+`src/lightspeed_stack/llama_stack_configuration.py`:
 
 - `synthesize_configuration(lcs_config, config_file_dir, default_baseline)
   -> dict` — the synthesis pipeline.
@@ -430,7 +430,7 @@ September 2026.
 | File | What to do |
 |---|---|
 | `src/models/config.py` | Add `UnifiedInferenceProvider`. Extend the existing `InferenceConfiguration` with `providers: list[UnifiedInferenceProvider]`. Add `UnifiedLlamaStackConfig` (`baseline`/`profile`/`native_override`) and a `config` field on `LlamaStackConfiguration`. Put the unified-vs-legacy `model_validator` on the **root** `Configuration` model (spans `inference.providers` + `llama_stack.*`). |
-| `src/llama_stack_configuration.py` | Add `synthesize_configuration`, `deep_merge_list_replace`, `apply_high_level_inference`, `load_default_baseline`, `synthesize_to_file`, `migrate_config_dumb`, `PROVIDER_TYPE_MAP`, `DEFAULT_BASELINE_RESOURCE`. Update `main()` to auto-detect unified vs legacy. |
+| `src/lightspeed_stack/llama_stack_configuration.py` | Add `synthesize_configuration`, `deep_merge_list_replace`, `apply_high_level_inference`, `load_default_baseline`, `synthesize_to_file`, `migrate_config_dumb`, `PROVIDER_TYPE_MAP`, `DEFAULT_BASELINE_RESOURCE`. Update `main()` to auto-detect unified vs legacy. |
 | `src/data/default_run.yaml` | New file — a thinner baseline than today's repo-root `run.yaml`. Notably do **not** reference `${env.EXTERNAL_PROVIDERS_DIR}` without a default (see "Findings discovered during PoC" in the spike doc). |
 | `src/client.py` | In `_load_library_client`: branch on `config.config` presence. Add `_synthesize_library_config()` that calls the synthesizer and writes to the deterministic path (R10). Keep `_enrich_library_config` for legacy. |
 | `src/lightspeed_stack.py` | Add `--migrate-config`, `--run-yaml`, `--migrate-output`, `--synthesized-config-output` flags. Add an early-exit branch in `main()` that dispatches to `migrate_config_dumb` when `--migrate-config` is set. Clean up stale docstring. |

docs/devel_doc/container_orchestration.md

@@ -459,7 +459,7 @@ Container logs:
 3. **Test config enrichment:**
    ```bash
    # Run enrichment script manually to check for errors
-   uv run src/llama_stack_configuration.py \
+   uv run src/lightspeed_stack/llama_stack_configuration.py \
      -c lightspeed-stack.yaml \
      -i run.yaml \
      -o /tmp/enriched-run.yaml
@@ -685,7 +685,7 @@ When the llama-stack container starts, it automatically enriches the `run.yaml`
 
 1. **Entrypoint script** (`scripts/llama-stack-entrypoint.sh`) is mounted at `/opt/app-root/enrich-entrypoint.sh`
 2. **Script runs** `/opt/app-root/.venv/bin/python3 /opt/app-root/llama_stack_configuration.py`
-3. **Enrichment logic** (`src/llama_stack_configuration.py`) reads both configs and merges them
+3. **Enrichment logic** (`src/lightspeed_stack/llama_stack_configuration.py`) reads both configs and merges them
 4. **Output** is written to `/tmp/enriched-run.yaml` inside the container
 5. **Llama Stack starts** with the enriched config
 
@@ -699,7 +699,7 @@ When the llama-stack container starts, it automatically enriches the `run.yaml`
 
 ```bash
 # Run enrichment locally to see output
-uv run src/llama_stack_configuration.py \
+uv run src/lightspeed_stack/llama_stack_configuration.py \
   -c lightspeed-stack.yaml \
   -i run.yaml \
   -o enriched-run.yaml
@@ -717,7 +717,7 @@ The container uses these volume mounts:
 | `$(PWD)/run.yaml` | `/opt/app-root/run.yaml` | rw | Llama Stack config (enriched version written here) |
 | `$(PWD)/lightspeed-stack.yaml` | `/opt/app-root/lightspeed-stack.yaml` | ro | LCORE config (read for enrichment) |
 | `$(PWD)/scripts/llama-stack-entrypoint.sh` | `/opt/app-root/enrich-entrypoint.sh` | ro | Entrypoint script with enrichment logic |
-| `$(PWD)/src/llama_stack_configuration.py` | `/opt/app-root/llama_stack_configuration.py` | ro | Python enrichment script |
+| `$(PWD)/src/lightspeed_stack/llama_stack_configuration.py` | `/opt/app-root/llama_stack_configuration.py` | ro | Python enrichment script |
 
 **SELinux labels:**
 - `:z`: Relabels for sharing between host and container (read-write)

src/lightspeed_stack/data/default_run.yaml

@@ -2,7 +2,7 @@
 #
 # This file is the starting point when a unified `lightspeed-stack.yaml`
 # selects `llama_stack.config.baseline: default` (the default) and does not
-# point at a `profile:`. The synthesizer (src/llama_stack_configuration.py)
+# point at a `profile:`. The synthesizer (src/lightspeed_stack/llama_stack_configuration.py)
 # layers enrichment, high-level `inference.providers`, and `native_override`
 # on top of this baseline to produce the final run.yaml handed to Llama Stack.
 #

tests/e2e-prow/rhoai/manifests/lightspeed/llama-stack-openai.yaml

@@ -87,7 +87,7 @@ spec:
             exit 1
           fi
           cp -f /opt/app-root/.e2e-rag-seed/kv_store.db /opt/app-root/src/.llama/storage/rag/kv_store.db
-          cp /opt/app-root/src/llama_stack_configuration.py /opt/app-root/llama_stack_configuration.py
+          cp /opt/app-root/src/lightspeed_stack/llama_stack_configuration.py /opt/app-root/llama_stack_configuration.py
           chmod -R 775 /opt/app-root && chown -R 1001:0 /opt/app-root
       volumeMounts:
         - name: app-root

tests/e2e-prow/rhoai/manifests/lightspeed/llama-stack-prow.yaml

@@ -150,7 +150,7 @@ spec:
           if [[ -f "$LIGHTSPEED_CONFIG" ]]; then
             echo "Enriching llama-stack config..."
             ENRICHMENT_FAILED=0
-            /opt/app-root/.venv/bin/python3 /opt/app-root/src/llama_stack_configuration.py \
+            /opt/app-root/.venv/bin/python3 /opt/app-root/src/lightspeed_stack/llama_stack_configuration.py \
               -c "$LIGHTSPEED_CONFIG" \
               -i "$INPUT_CONFIG" \
               -o "$ENRICHED_CONFIG" 2>&1 || ENRICHMENT_FAILED=1

tests/unit/README.md

@@ -22,7 +22,7 @@ Unit tests for the degraded mode tracker.
 Unit tests for functions defined in src/lightspeed_stack.py.
 
 ## [test_llama_stack_configuration.py](test_llama_stack_configuration.py)
-Unit tests for src/llama_stack_configuration.py.
+Unit tests for src/lightspeed_stack/llama_stack_configuration.py.
 
 ## [test_llama_stack_synthesize.py](test_llama_stack_synthesize.py)
 Unit tests for unified-mode Llama Stack configuration synthesis (LCORE-2336).