@mono-agent/agent-app 0.8.0 → 0.9.0

package/schema/mono-agent.config.schema.json

@@ -402,13 +402,14 @@
           "additionalProperties": false,
           "properties": {
             "provider": {
-              "description": "Configures embeddings.provider for the memory section.",
+              "description": "Embedding service used by Journal/BuJo memory: ollama, lmstudio, or openai.",
               "examples": [
                 "ollama"
               ],
               "type": "string",
               "enum": [
                 "ollama",
+                "lmstudio",
                 "openai"
               ]
             },
@@ -420,7 +421,7 @@
               "type": "string"
             },
             "endpoint": {
-              "description": "Configures embeddings.endpoint for the memory section.",
+              "description": "Provider service root. LM Studio uses <root>/v1/embeddings and defaults to http://localhost:1234.",
               "examples": [
                 "example"
               ],
@@ -434,7 +435,7 @@
               "type": "string"
             },
             "apiKeyEnv": {
-              "description": "Secret value for memory.embeddings.apiKeyEnv; prefer the env override.",
+              "description": "Environment-variable name containing an optional provider bearer token; an explicitly declared name must resolve before memory starts.",
               "examples": [
                 "example"
               ],
@@ -798,6 +799,18 @@
           "default": [],
           "uniqueItems": true
         },
+        "continuationServers": {
+          "description": "Configures continuationServers for the tools section.",
+          "examples": [
+            [
+              "example"
+            ]
+          ],
+          "type": "array",
+          "items": {
+            "type": "string"
+          }
+        },
         "mcpCallTimeoutMs": {
           "description": "Configures mcpCallTimeoutMs for the tools section.",
           "examples": [
@@ -1172,6 +1185,196 @@
         }
       }
     },
+    "continuations": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "enabled": {
+          "type": "boolean",
+          "default": true,
+          "description": "Enable the durable continuation service when continuation functionality is configured."
+        },
+        "host": {
+          "type": "string",
+          "enum": [
+            "127.0.0.1",
+            "::1",
+            "localhost"
+          ],
+          "default": "127.0.0.1",
+          "description": "Loopback-only continuation service host."
+        },
+        "port": {
+          "type": "integer",
+          "minimum": 1,
+          "maximum": 65535,
+          "default": 4319,
+          "description": "Fixed continuation service port; 0 is intentionally invalid."
+        },
+        "stateDir": {
+          "type": "string",
+          "minLength": 1,
+          "default": ".mono-agent/continuations",
+          "description": "Owner-only durable continuation state directory."
+        },
+        "namedRoutes": {
+          "type": "object",
+          "default": {},
+          "propertyNames": {
+            "minLength": 1,
+            "maxLength": 128
+          },
+          "additionalProperties": {
+            "oneOf": [
+              {
+                "type": "object",
+                "additionalProperties": false,
+                "required": [
+                  "mode",
+                  "conversationId"
+                ],
+                "properties": {
+                  "mode": {
+                    "const": "notify_if_actionable"
+                  },
+                  "conversationId": {
+                    "type": "string",
+                    "minLength": 1
+                  }
+                }
+              },
+              {
+                "type": "object",
+                "additionalProperties": false,
+                "required": [
+                  "mode",
+                  "conversationId"
+                ],
+                "properties": {
+                  "mode": {
+                    "const": "capture"
+                  },
+                  "conversationId": {
+                    "type": "string",
+                    "minLength": 1
+                  }
+                }
+              },
+              {
+                "type": "object",
+                "additionalProperties": false,
+                "required": [
+                  "mode"
+                ],
+                "properties": {
+                  "mode": {
+                    "const": "silent"
+                  }
+                }
+              }
+            ]
+          }
+        },
+        "detachedServices": {
+          "type": "array",
+          "default": [],
+          "uniqueItems": true,
+          "items": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": [
+              "name",
+              "tokenEnv"
+            ],
+            "properties": {
+              "name": {
+                "type": "string",
+                "minLength": 1,
+                "maxLength": 128
+              },
+              "tokenEnv": {
+                "type": "string",
+                "pattern": "^[A-Z_][A-Z0-9_]*$"
+              }
+            }
+          }
+        },
+        "limits": {
+          "type": "object",
+          "additionalProperties": false,
+          "default": {},
+          "properties": {
+            "maxActiveRecords": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 1000000,
+              "default": 10000
+            },
+            "maxActivePerOrigin": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 1000000,
+              "default": 500
+            },
+            "maxConcurrent": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 256,
+              "default": 16
+            },
+            "synthesisTimeoutMs": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 86400000,
+              "default": 600000
+            },
+            "deliveryTimeoutMs": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 86400000,
+              "default": 120000
+            },
+            "operatorPageSize": {
+              "type": "integer",
+              "minimum": 1,
+              "maximum": 500,
+              "default": 100
+            }
+          }
+        },
+        "retention": {
+          "type": "object",
+          "additionalProperties": false,
+          "default": {},
+          "properties": {
+            "terminalMaxRecords": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 9007199254740991,
+              "default": 50000
+            },
+            "terminalMaxAgeMs": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 9007199254740991,
+              "default": 31536000000
+            },
+            "capturedTextMaxRecords": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 9007199254740991,
+              "default": 1000
+            },
+            "capturedTextMaxAgeMs": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 9007199254740991,
+              "default": 2592000000
+            }
+          }
+        }
+      }
+    },
     "channels": {
       "type": "object",
       "additionalProperties": false,

package/skills/mono-agent-composer/SKILL.md

@@ -33,7 +33,7 @@ Do **not** read or grep the `@mono-agent` TypeScript/package source — `package
 - The deliverable is a folder that works: `mono-agent.config.json` + `IDENTITY.md` (+ optional `skills/`, `mcp.json`), validated and started — not a tutorial.
 - Start by discovering the intended agent product, not by naming packages.
 - Ask one question at a time; skip anything the user already answered.
-- Respect existing knowledge: if the folder has `AGENTS.md`, `CLAUDE.md`, `README.md`, or an existing `IDENTITY.md`, reference it from the identity instead of replacing it. Never overwrite existing files.
+- Respect existing knowledge: if the folder has `AGENTS.md`, `CLAUDE.md`, `README.md`, or `SOUL.md`, reference it from the identity instead of copying it. `IDENTITY.md` → `## Role` is the single canonical guided-init Role location. Never overwrite an existing identity; say explicitly that a newly entered Role was not written and tell the user to add or edit that heading manually.
 - Fail closed: no allowed tools, no memory writes, loopback-only network until the user opts in.
 - Do not fake runtime success, silently broaden tool access, or hide provider/MCP failures. Backup models are configured failover (`runtime.fallbackModels`), never silent substitution.
 - Secrets stay in env vars or the untracked config file; never commit tokens or `.env*` files.
@@ -67,8 +67,8 @@ Everything below runs in the user's agent folder, not the workspace.
    mono-agent init --model <ref> [--fallback-models <csv>] [--effort <level>] [--auth] [--memory lite|journal|bujo]   # bare scaffold
    ```
 
-   Either writes a `mono-agent.config.json` (with `tools.allowedTools` pre-filled from the selected capabilities' recommended tools), an `IDENTITY.md` that references any knowledge files already present, the managed project-local `mono-agent-configure` and `mono-agent-memory` skills, and `.mono-agent/` working directories (presets also emit a `.env.example` and any extra files). `--effort` writes `runtime.effort` on supporting providers (do not use it with direct `opencode:*` SDK 1.x); `--auth` opts in to provider setup before writing files; `--dry-run` previews without writing or launching auth/preflight commands. Existing scaffold/config files are never overwritten; reviewed secret setup is the deliberate exception that can transactionally replace `.env` and update `.gitignore`.
-3. **Configure.** Edit `mono-agent.config.json` to match the discovery answers. Preserve the generated `mono-agent-configure` and `mono-agent-memory` selections when appending other skills, and do not auto-select this full authoring-oriented composer inside the generated agent. Read `references/config-blueprint.md` for the full annotated config shape: every channel section, skills, MCP, memory, sandbox, and fallback models. Run `mono-agent config` to see the resolved configuration field-by-field with each value tagged `env` / `json` / `default` — the fastest way to confirm a value came from where you intended.
+   Either writes a `mono-agent.config.json` (with `tools.allowedTools` pre-filled from the selected capabilities' recommended tools), an `IDENTITY.md` whose `## Role` body is the one Role destination and which references any knowledge files already present, the managed project-local `mono-agent-configure` and `mono-agent-memory` skills, and `.mono-agent/` working directories (presets also emit a `.env.example` and any extra files). `--effort` writes `runtime.effort` on supporting providers (do not use it with direct `opencode:*` SDK 1.x); `--auth` opts in to provider setup before writing files; `--dry-run` previews without writing or launching auth/preflight commands. Existing scaffold/config files are never overwritten; reviewed secret setup is the deliberate exception that can transactionally replace `.env` and update `.gitignore`.
+3. **Configure.** Edit `mono-agent.config.json` to match the discovery answers. For a newly created identity, put the agreed text under `IDENTITY.md` → `## Role`; if it existed before init, preserve it and report that the new answer was not stored. Preserve the generated `mono-agent-configure` and `mono-agent-memory` selections when appending other skills, and do not auto-select this full authoring-oriented composer inside the generated agent. Read `references/config-blueprint.md` for the full annotated config shape: every channel section, skills, MCP, memory, sandbox, and fallback models. Run `mono-agent config` to see the resolved configuration field-by-field with each value tagged `env` / `json` / `default` — the fastest way to confirm a value came from where you intended.
 4. **Validate.**
 
    ```bash
@@ -82,7 +82,7 @@ Everything below runs in the user's agent folder, not the workspace.
    mono-agent start
    ```
 
-   Then run the acceptance smoke test matching the chosen channel (see `references/validation.md`). To change anything, edit `mono-agent.config.json` directly and run `mono-agent restart`; there is no live browser re-apply.
+   Then run the acceptance smoke test matching the chosen channel (see `references/validation.md`). To change anything, edit `mono-agent.config.json` or `IDENTITY.md` directly and run `mono-agent restart`; there is no live browser re-apply. On macOS, `mono-agent tui --configure` can open a temporary proposal-only configuration conversation against the already-running background agent. It is separate from ordinary chat, never accepts secrets, requires an out-of-band approval, and restarts or rolls back through the managed lifecycle. Off macOS, use manual edits plus `validate`, foreground `start`, and ordinary `tui`; conversational configuration is unavailable.
 
 ## When Config Is Not Enough
 

package/skills/mono-agent-composer/references/config-blueprint.md

@@ -12,7 +12,7 @@ One `mono-agent.config.json` declares the whole agent. Paths are relative to the
 ```text
 my-agent/
   mono-agent.config.json   # the single declaration below
-  IDENTITY.md              # role, boundaries, references to existing knowledge
+  IDENTITY.md              # canonical ## Role body, boundaries, references to existing knowledge
   skills/                  # optional: <skill-name>/SKILL.md per selected skill
   cron/                    # optional: <job-id>.md scheduled prompts
   mcp.json                 # optional: MCP server definitions
@@ -85,10 +85,10 @@ my-agent/
     "writeMode": "capture",                // disabled | append-host-summary | capture (bujo only)
     "maxBytes": 64000,
     "embeddings": {                        // required for journal and bujo
-      "provider": "ollama",                // ollama | openai
+      "provider": "ollama",                // ollama | lmstudio | openai; exclusive, no fallback
       "model": "nomic-embed-text:v1.5",   // use exact :v1.5 tag (pull first with ollama pull)
-      "endpoint": "http://localhost:11434",
-      "apiKeyEnv": "OPENAI_API_KEY",       // or inline "apiKey"; required for openai
+      "endpoint": "http://localhost:11434", // service root; LM Studio default http://localhost:1234
+      // "apiKeyEnv": "LM_STUDIO_API_KEY", // optional authenticated LM Studio; required for openai
       "dim": 768                           // nomic-embed-text:v1.5 output dimension
     },
     "llm": {                               // enables bujo capture and the effective bujo tier; omit for lite/journal
@@ -292,9 +292,9 @@ mono-agent restart --force  # restart AND purge persisted pi sessions (fresh sta
 
 A `.env` file in the folder is loaded automatically (exported shell variables win); use `--env-file <path>` for an alternate file. `validate --consumer <path>` loads the consumer folder's `.env` by default and resolves relative `--config` / `--env-file` paths there. `start` prints the traceability source (Phoenix when an `observability.exporters` Phoenix entry is configured, otherwise the local JSONL artifacts) and one status line per channel: `running` with its endpoint facts, `waiting_for_config` with the exact missing setting, `disabled`, or `failed` with the reason. Config is JSON-first: edit `mono-agent.config.json` directly (agents can edit it) and run `mono-agent restart` to apply — there is no live browser re-apply.
 
-For BuJo capture and the effective `bujo` tier that runs scheduled consolidation, configure `memory.llm`. Use `provider: "ollama"` with a local Ollama chat model string and optional `endpoint`, or `provider: "agent-host"` with `model` as a normal SDK runtime model reference such as `pi:openai-codex:gpt-5.5` and `executionMode: "sdk"`. `endpoint` is Ollama-only, and CLI-backed refs such as `codex:gpt-5.5` are rejected for memory LLMs until runtimes can enforce no external actions. The same values can be supplied via `MONO_AGENT_MEMORY_LLM_PROVIDER`, `MONO_AGENT_MEMORY_LLM_MODEL`, `MONO_AGENT_MEMORY_LLM_EXECUTION_MODE`, and `MONO_AGENT_MEMORY_LLM_ENDPOINT`. The standalone `memory-bujo` maintenance CLI remains Ollama-only; `agent-host` LLM capture is an in-app composition path that injects the `LlmComplete` implementation into the BuJo store.
+For BuJo capture and the effective `bujo` tier that runs scheduled consolidation, configure `memory.llm`. Use `provider: "ollama"` with a local Ollama chat model string and optional `endpoint`, or `provider: "agent-host"` with `model` as a normal SDK runtime model reference such as `pi:openai-codex:gpt-5.5` and `executionMode: "sdk"`. `endpoint` is Ollama-only, and CLI-backed refs such as `codex:gpt-5.5` are rejected for memory LLMs until runtimes can enforce no external actions. The same values can be supplied via `MONO_AGENT_MEMORY_LLM_PROVIDER`, `MONO_AGENT_MEMORY_LLM_MODEL`, `MONO_AGENT_MEMORY_LLM_EXECUTION_MODE`, and `MONO_AGENT_MEMORY_LLM_ENDPOINT`. The standalone `memory-bujo migrate` command remains Ollama-only; other maintenance commands use the configured embeddings provider. `agent-host` LLM capture is an in-app composition path that injects the `LlmComplete` implementation into the BuJo store.
 
-For operator views, run `mono-agent tui` or `mono-agent web` from any directory once the agent is started. Both discover running agents via the trace-source registry. The TUI chats over the default-on `tui` stream endpoint (`"tui": {"enabled": false}` opts out); the web PWA reads artifacts and live updates from the default-on `live` relay (`"live": {"enabled": false}` opts out). Web history/live views show agent runs by default; add `mono-agent web --include-memory` to inspect memory-maintenance runs. Both bind loopback by default. The low-level `mono-agent-tui` bin also supports `--responder <file>` (embedded, an ESM module default-exporting an `AgentResponderLike` or exporting `createResponder(env, cwd, configJson)`) and `--url <baseUrl>` (direct connect).
+For operator views, run `mono-agent tui` or `mono-agent web` from any directory once the agent is started. Both discover running agents via the trace-source registry. The TUI chats over the default-on `tui` stream endpoint (`"tui": {"enabled": false}` opts out); on macOS, `mono-agent tui --configure` opens a separate temporary proposal-only conversation against the managed background agent and must not be combined with `--local`. The web PWA reads artifacts and live updates from the default-on `live` relay (`"live": {"enabled": false}` opts out). Web history/live views show agent runs by default; add `mono-agent web --include-memory` to inspect memory-maintenance runs. Both bind loopback by default. The low-level `mono-agent-tui` bin also supports `--responder <file>` (embedded, an ESM module default-exporting an `AgentResponderLike` or exporting `createResponder(env, cwd, configJson)`) and `--url <baseUrl>` (direct connect).
 
 ## Programmatic Escape Hatch
 

package/skills/mono-agent-composer/references/discovery-questions.md

@@ -43,10 +43,10 @@ Fills one config section per choice: built-in channels use `webhook`, `openaiApi
 Question:
 
 ```text
-What is this agent's role, and does this folder already contain knowledge it must respect?
+What exact text belongs in IDENTITY.md → ## Role, and does this folder already contain knowledge it must respect?
 ```
 
-Fills: `context.identityPath` (default `./IDENTITY.md`), optional `context.soulPath`, `runtime.workspace`. `mono-agent init` detects `AGENTS.md`, `CLAUDE.md`, `README.md`, and `SOUL.md` and references them from the generated identity — keep those references rather than copying content.
+Fills: the `## Role` body in the one canonical identity file, `context.identityPath` (default `./IDENTITY.md`), optional `context.soulPath`, and `runtime.workspace`. `mono-agent init` detects `AGENTS.md`, `CLAUDE.md`, `README.md`, and `SOUL.md` and references them from a generated identity — keep those references rather than copying content. If `IDENTITY.md` already exists, preserve it unchanged, say the newly entered Role was not written, and tell the user to add or edit its `## Role` heading manually. Do not assume the heading already exists or store the unused answer elsewhere.
 
 ## 4. Skills
 
@@ -113,11 +113,17 @@ No prerequisites. No Ollama. SQLite is bundled.
 
 **Tier 3 — journal (embeddings required):**
 
-- Ask: which embeddings provider/model?
-  - Ollama default: `provider: "ollama"`, model `nomic-embed-text:v1.5`, dim `768`
-    (use the exact `:v1.5` tag; pull first with `ollama pull nomic-embed-text:v1.5`).
-  - OpenAI option: `provider: "openai"`, model `text-embedding-3-small`, API key via
-    `apiKeyEnv`, dim matching the model.
+- Guided init asks for Ollama or LM Studio, service root, exact model, actual dimension,
+  and optional auth-env name. Treat this as separate from runtime chat-model discovery.
+  - Ollama default root `http://localhost:11434`: enumerate `/api/tags`, retain only
+    `/api/show` capabilities containing `embedding`, then prove `/api/embed`.
+  - LM Studio default root `http://localhost:1234`: retain exact `type: "embedding"`
+    entries from `/api/v1/models`, use their `key`, then prove `/v1/embeddings`.
+  - Hand-authored OpenAI remains supported but is not a guided local-memory choice.
+- If typed discovery is inconclusive, ask for exact model + positive dimension, while
+  explaining that real readiness still must pass. Never substitute another provider.
+- LM Studio is keyless when `apiKeyEnv` is omitted. If named, the variable must already
+  contain the token in the owner-only agent environment; missing declared auth is `waiting`.
 
 Write:
 
@@ -129,13 +135,16 @@ Write:
   "embeddings": {
     "provider": "ollama",
     "model": "nomic-embed-text:v1.5",
+    "endpoint": "http://localhost:11434",
     "dim": 768
   }
 }
 ```
 
-After writing, remind the user to run `mono-agent validate` (checks root writability and
-provider-specific liveness; Ollama model pulls are checked only when using Ollama).
+After writing, remind the user to run `mono-agent validate` (checks root writability,
+managed provider/model/dimension identity, provider-native model typing, real finite-vector
+response, and dimension). Changing any semantic identity field on an existing root requires
+stopping the agent and running config-aware `mono-agent memory rebuild --json`.
 
 **Tier 4 — bujo (embeddings + chat model + consolidation):**
 
@@ -144,7 +153,8 @@ hybrid BM25+vector recall, entity graph, scheduled consolidation (decay + duplic
 superseding), living `index.md`, and an empty retired `future-log.md` stub. Consolidation
 is **auto-scheduled in-app** — no external cron or launchd setup needed.
 
-- Ask: which embeddings provider/model? Use the same choices as journal.
+- Ask: which embeddings provider/service-root/model/dimension/auth-env? Use the same
+  exclusive choices and real-probe contract as journal.
 - Ask: which chat LLM provider/model for LLM pipelines?
   - Ollama: local model string such as `qwen3.6:latest`; pull it first with
     `ollama pull qwen3.6:latest`.
@@ -156,6 +166,11 @@ is **auto-scheduled in-app** — no external cron or launchd setup needed.
 - Ask: should we keep the default consolidation schedule (`0 */2 * * *`), customise the
   cron expression, or disable scheduled consolidation?
 
+The embeddings service and capture LLM are independent. Choosing LM Studio embeddings does
+not move capture there; guided config keeps an explicit `agent-host` LLM, while an authored
+Ollama `memory.llm` remains valid. Standalone advanced `memory-bujo migrate` is still
+Ollama-only and outside guided init.
+
 Write (embeddings + chat model):
 
 ```jsonc

package/skills/mono-agent-composer/references/feature-coverage.md

@@ -23,18 +23,18 @@ Every framework capability and how a composed agent reaches it. This table is th
 
 | Capability | Coverage | Where |
 | --- | --- | --- |
-| Identity + optional soul documents | config | `context.identityPath`, `context.soulPath` |
+| Identity + optional soul documents; wizard Role has one explicit destination and created/preserved outcome | config + cli | `context.identityPath`, `context.soulPath`; guided Role is `IDENTITY.md` → `## Role`, and an existing identity is never overwritten |
 | Selected skills from a skills root | config | `context.skillsRoot`, `context.selectedSkills` |
 | Generated project configuration skills with progressive disclosure | config + cli | init selects `mono-agent-configure` + `mono-agent-memory` under `./skills` with `context.skillDisclosure: "index"`; drift: `mono-agent install-skill --project --check\|--update` |
 | Per-skill byte cap | config | `context.skillMaxBytes` |
 | Conversation history (bounded in-memory) | auto | 12 messages by default; twice a positive `runtime.maxTurns`; custom store via code |
 | Lite memory (FTS keyword recall + rapid-log capture; no external deps) | config | `memory.mode: "lite"`, `path`, `maxBytes`, `writeMode` |
-| Journal memory (hybrid recall BM25+vector + salience decay; needs configured embeddings) | config | `memory.mode: "journal"`, `path`, `memory.embeddings.{provider,model,dim}` (`provider: "ollama" | "openai"`) |
-| BuJo memory (journal + LLM capture/reconcile ADD/UPDATE/SUPERSEDE/NOOP + entity graph + auto-scheduled consolidation; needs embeddings + an app-level `memory.llm`) | config | `memory.mode: "bujo"`, `path`, `memory.embeddings.{provider,model,dim}`, `memory.llm` with `provider: "ollama"` (`model`, optional `endpoint`) or `provider: "agent-host"` (`model` is an SDK runtime model ref, e.g. `pi:openai-codex:gpt-5.5`, optional `executionMode: "sdk"`) — see `docs/memory/index.md` |
+| Journal memory (hybrid recall BM25+vector + salience decay; needs configured embeddings) | config | `memory.mode: "journal"`, `path`, `memory.embeddings.{provider,endpoint,model,dim,apiKeyEnv}` (`provider: "ollama" | "lmstudio" | "openai"`; exclusive, no cross-provider fallback) |
+| BuJo memory (journal + LLM capture/reconcile ADD/UPDATE/SUPERSEDE/NOOP + entity graph + auto-scheduled consolidation; needs embeddings + an app-level `memory.llm`) | config | `memory.mode: "bujo"`, `path`; selected Ollama/LM Studio/OpenAI embeddings are independent from explicit `memory.llm` with `provider: "ollama"` (`model`, optional `endpoint`) or `provider: "agent-host"` (`model` is an SDK runtime model ref, optional `executionMode: "sdk"`) — see `docs/memory/index.md` |
 | BuJo consolidation auto-scheduler (lightweight decay + duplicate superseding; in-app, no external cron needed) | config | `memory.consolidation.{enabled,cron}` (default `0 */2 * * *`); env `MONO_AGENT_MEMORY_CONSOLIDATION_CRON`, `MONO_AGENT_MEMORY_CONSOLIDATION_ENABLED` |
-| Memory out-of-band maintenance CLI (rebuild/recall/index/legacy reflect/migrate) | cli | `memory-bujo <subcommand> <root>`; opt-in `MONO_AGENT_MEMORY_EMBEDDINGS_PROVIDER`/`_MODEL`/`_DIM` for semantic recall; legacy reflect/migrate are Ollama-only and require `MONO_AGENT_MEMORY_LLM_MODEL` (optional `MONO_AGENT_MEMORY_LLM_ENDPOINT`) |
+| Memory out-of-band maintenance CLI (rebuild/recall/index/legacy reflect/migrate) | cli | `memory-bujo <subcommand> <root>`; opt-in `MONO_AGENT_MEMORY_EMBEDDINGS_PROVIDER` (`ollama`/`lmstudio`/`openai`), `_MODEL`, and `_DIM` for semantic recall; advanced `migrate` remains Ollama-only, outside guided init, and requires `MONO_AGENT_MEMORY_LLM_MODEL` (optional `_ENDPOINT`) |
 | Config-aware memory preview CLI (stats/today/show/search/top plus metadata-only audit; local search warns and falls back to FTS-only when embeddings are down) | cli | `mono-agent memory stats\|today\|show <date>\|search <query>\|top\|audit [--limit <n>] [--json]` |
-| Memory liveness check (root writable; provider-specific Ollama checks only when embeddings/chat use Ollama; BuJo LLM config + consolidation cadence — loud warn, no silent fallback) | cli | `mono-agent validate` |
+| Memory liveness check (managed tier/provider/model/dimension identity; provider-native typed discovery plus real finite-vector/dimension probe for Ollama or LM Studio; declared auth env; BuJo LLM config + consolidation cadence; no cross-provider fallback) | cli | `mono-agent validate` |
 | Host summaries appended after runs | config | `memory.writeMode: "append-host-summary"` |
 | Auto-provisioned read-only `MemoryRecall` tool exposed for every configured memory tier; no chat LLM | config | `config.memory.recallTool.enabled` (`MONO_AGENT_MEMORY_RECALL_TOOL_ENABLED`, default on; explicit false opts out) |
 
@@ -78,10 +78,10 @@ Every framework capability and how a composed agent reaches it. This table is th
 | Trace-source registry (heartbeat manifests `mono-agent status` reads) | config | `traceability.{registryDir,sourceId,sourceLabel,heartbeatMs,staleAfterMs,globalDiscovery}` |
 | Phoenix trace viewer (OTLP exporter; local JSONL artifacts are the fallback) | config | `observability.exporters` (phoenix entry) |
 | Operator console (live chat with thinking/tool/telemetry insight, run replay, config view) | cli | `mono-agent tui [--agent <label>]`; agents serve the `tui` stream endpoint by default (`tui.enabled`, loopback) |
-| Current-folder local conversation and proposal-only configuration | cli + tool | `mono-agent tui --local [--configure]`; `/configure`; host-gated `ProposeAgentConfiguration` exists only for one marked local configuration turn |
+| Managed proposal-only configuration conversation | cli + tool | macOS `mono-agent tui --configure` attaches to the authoritative background agent; `/configure`; separate configuration/ordinary conversation ids; host-gated `ProposeAgentConfiguration`; approval restarts and waits for readiness, failed start rolls files/agent back. `--local` is ordinary chat only; off macOS configuration is manual |
 | Session Recorder web PWA (read-only run browser) | cli | `mono-agent web [--host] [--port] [--no-open] [--allow-non-loopback] [--include-memory]`; consumes the default-on `live` relay and local artifacts; memory runs are opt-in |
 | Setup presets (saved answer-sets: generate config + `.env.example` + checklist) | cli | `mono-agent presets list\|show <id>`, `mono-agent init --preset <id> --yes` (`recipes`/`--recipe` deprecated aliases) |
-| Interactive setup wizard (preset/custom; walks model→channels→memory→tools→sandbox→observability) | cli | `mono-agent init` (no flags, on a TTY; `setup` alias) |
+| Interactive setup wizard (preset/custom; exact `IDENTITY.md` → `## Role` prompt/outcome; walks model→channels→memory→tools→sandbox→observability; Journal/BuJo explicitly choose Ollama or LM Studio service root/model/dimension/optional auth env using typed discovery and a real probe; macOS starts the background agent before temporary configuration) | cli | `mono-agent init` (no flags, on a TTY; `setup` alias); manual embedding entry still requires readiness probe; flags/non-TTY stay scaffold-only; unsupported platforms use manual configuration/foreground start/ordinary TUI |
 | Tools reporting + no-tools guardrail (allow-all → `All tools allowed`; explicit empty `allowedTools: []` → `waiting`; unknown-tool "did you mean"; send-tool/channel cross-checks) | cli | part of `mono-agent validate`/`doctor`; the wizard's tools step |
 | Resolved config view (every field tagged env/json/default) | cli | `mono-agent config` |
 | Scaffold / validate / start / install-skill | cli | `mono-agent init [--model <ref>] [--fallback-models <csv>] [--effort <level>] [--auth]\|validate [--consumer <path>]\|config\|presets\|start\|install-skill` |

package/skills/mono-agent-composer/references/package-map.md

@@ -50,7 +50,7 @@ Use this path when the agent needs identity, selected skills, history, and optio
 | Selected skill bodies | `@mono-agent/agent-harness` | Load only configured skills from `<skillsRoot>/<name>/SKILL.md` |
 | Memory substrate (schema, migrations, FTS+vector db, RRF) | `@mono-agent/memory/store` | SQLite storage, BM25 FTS, optional vector index, hybrid recall; re-exports `MemoryStore`/`MemoryBlock`/`MemoryWriteResult` from `@mono-agent/agent-contracts` |
 | Memory engine (all tiers: lite/journal/bujo) | `@mono-agent/memory/bujo` | `BujoMemoryStore` — tier-aware: FTS recall (lite), hybrid recall + decay (journal), LLM capture/reconcile + entity graph + scheduled consolidation (bujo) |
-| Embedding providers | `@mono-agent/memory/search` | Ollama/OpenAI embedding providers used by the store subpath for vector recall |
+| Embedding providers | `@mono-agent/memory/search` | Exclusive Ollama/LM Studio/OpenAI embedding providers used by the store subpath for vector recall; `agent-app` owns guided typed discovery and the real readiness probe |
 | Recall tool surface | `@mono-agent/agent-app` (bundled) | Auto-provisions read-only `MemoryRecall` for every configured tier and direct configured responder; automatic/tool recall share the same store and per-turn query cache |
 
 Mono-agent selected skills are not auto-selected by description. The host chooses `context.selectedSkills`, and the harness loads those exact bodies.

package/skills/mono-agent-composer/references/validation.md

@@ -80,7 +80,7 @@ pnpm run test:demo
 
 | Surface | Smoke |
 | --- | --- |
-| TUI | Start the host and complete one local prompt. |
+| TUI | Start the host, connect with ordinary `mono-agent tui`, and complete one real prompt against the running responder. |
 | Telegram | Send one allowed chat message and verify the reply. |
 | Slack | Send one allowed DM or channel message and verify formatting. |
 | Adapter send tools | When `SlackSendMessage` / `TelegramSendMessage` are available (allow-all, or an explicit `tools.allowedTools` entry) with the channel enabled, call them from a non-Slack/Telegram surface such as TUI, cron, or OpenAI API to an allowed destination and verify delivery. |
@@ -91,7 +91,7 @@ pnpm run test:demo
 | Cron | Run a one-off scheduled invocation or wait for one tick. |
 | Observability | Confirm a run writes a redacted JSONL artifact; if an `observability.exporters` Phoenix entry is set, confirm the trace appears in Phoenix. |
 | Memory recall tool | With any memory tier configured (`memory.recallTool.enabled` defaults on), ask the agent to recall an old note and confirm `MemoryRecall` appears separately from action-tool allowlists and returns it. |
-| Semantic memory search | With `memory.embeddings` set (Ollama: `ollama pull nomic-embed-text:v1.5` first), ask a paraphrased question about an old note and confirm `MemoryRecall` (hybrid keyword + semantic) returns it. |
+| Semantic memory search | With `memory.embeddings` set, first prove the configured provider only: Ollama model advertises `embedding` through `/api/show` and answers `/api/embed`, or LM Studio model has exact `type: "embedding"` in `/api/v1/models` and answers `/v1/embeddings`. Verify the finite vector dimension matches config, then ask a paraphrased question about an old note and confirm `MemoryRecall` returns it. Never accept a cross-provider fallback as proof. |
 
 ## Failure Handling