feat(db): add project personas and skills tables

* Introduce project_personas table with foreign keys to projects and agent_personas
* Add project_skills table with foreign key to projects and agent_skills
* Include override boolean field in agent_persona_skills and project_skills
* Update schema and migration files to reflect new tables and fields
* Enhance CORS handling to reflect request origin

README.md

@@ -65,6 +65,11 @@ The AMCS directory is used to store configuration and code for the Avalon Memory
 | `add_project_guardrail` | Link a guardrail to a project; pass `project` if client is stateless |
 | `remove_project_guardrail` | Unlink a guardrail from a project; pass `project` if client is stateless |
 | `list_project_guardrails` | Guardrails for a project; pass `project` if client is stateless |
+| `bootstrap_world_model` | Validate and activate a project, then load effective skills, guardrails, personas, and bounded context |
+| `add_project_persona` | Link a persona to a project and optionally make it the default |
+| `remove_project_persona` | Unlink a persona from a project |
+| `set_default_project_persona` | Select the default persona for a project |
+| `list_project_personas` | List project personas and identify the default |
 | `get_version_info` | Build version, commit, and date |
 | `describe_tools` | List all available MCP tools with names, descriptions, categories, and model-authored usage notes; call this at the start of a session to orient yourself |
 | `annotate_tool` | Persist your own usage notes for a specific tool; notes are returned by `describe_tools` in future sessions |
@@ -216,9 +221,9 @@ Use `get_version_info` to retrieve the runtime build metadata:
 
 ## Agent Skills and Guardrails
 
-Skills and guardrails are reusable agent behaviour instructions and constraints that can be attached to projects.
+Skills and guardrails are reusable agent behaviour instructions and constraints that can be attached to projects. Projects can also expose personas and a default persona through the world model.
 
-**At the start of every project session, always call `list_project_skills` and `list_project_guardrails` first.** Use the returned skills and guardrails to guide agent behaviour for that project. Only generate or create new skills/guardrails if none are returned. If your MCP client does not preserve sessions across calls, pass `project` explicitly instead of relying on `set_active_project`.
+**At the start of every project session, read `amcs://world-model/intro` and call `bootstrap_world_model` with an explicit project.** Apply its skills, guardrails, and default persona before continuing. If your MCP client does not preserve sessions across calls, keep passing `project` explicitly.
 
 ### Skills
 
@@ -243,10 +248,12 @@ Severity levels: `low`, `medium`, `high`, `critical`.
 Link existing skills and guardrails to a project so they are automatically available when that project is active:
 
 ```json
-{ "project": "my-project", "skill_id": "<uuid>" }
-{ "project": "my-project", "guardrail_id": "<uuid>" }
+{ "project": "my-project", "skill_id": 42, "override": false }
+{ "project": "my-project", "guardrail_id": 17 }
 ```
 
+Skills are additive by default. Set `override: true` on a project-skill or persona-skill link only when that skill must replace a lower-precedence skill with the same name. World-model precedence is project, selected persona, then runtime. Guardrails are additive and later layers cannot weaken them.
+
 ## Configuration
 
 Config is YAML-driven. Copy `configs/config.example.yaml` and set:
@@ -417,7 +424,7 @@ Returns `{"file": {...}, "uri": "amcs://files/<id>"}`. Pass `thought_id`/`projec
 
 ### MCP resources
 
-Stored files are also exposed as MCP resources at `amcs://files/{id}`. MCP clients can read raw binary content directly via `resources/read` without going through `load_file`.
+Stored files are also exposed as MCP resources at `amcs://files/{id}`. MCP clients can read raw binary content directly via `resources/read` without going through `load_file`. The startup guide is available at `amcs://world-model/intro`.
 
 ### HTTP upload and download