@mono-agent/agent-app 0.6.2 → 0.8.0

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

@@ -12,6 +12,22 @@
     "$schema": {
       "type": "string"
     },
+    "agent": {
+      "type": "object",
+      "additionalProperties": false,
+      "properties": {
+        "name": {
+          "description": "Public display identity used for trace labels and default A2A metadata; never used in paths or service ids.",
+          "examples": [
+            "Research Partner"
+          ],
+          "type": "string",
+          "minLength": 1,
+          "maxLength": 80,
+          "pattern": "^[^\\u0000-\\u001f\\u007f]+$"
+        }
+      }
+    },
     "runtime": {
       "type": "object",
       "additionalProperties": false,
@@ -19,12 +35,12 @@
         "model": {
           "description": "Configures model for the runtime section.",
           "examples": [
-            "pi:openai-codex:gpt-5.5"
+            "codex:gpt-5.6-terra"
           ],
           "type": "string"
         },
         "fallbackModels": {
-          "description": "Configures fallbackModels for the runtime section.",
+          "description": "Legacy fallback list whose routes inherit runtime.effort. Prefer runtime.fallbacks for new configs.",
           "examples": [
             [
               "pi:ollama:gemma4:31b"
@@ -33,7 +49,62 @@
           "type": "array",
           "items": {
             "type": "string"
-          }
+          },
+          "default": []
+        },
+        "fallbacks": {
+          "description": "Canonical ordered fallback routes. Omitted per-route effort means that provider's default.",
+          "examples": [
+            [
+              {
+                "model": "codex:gpt-5.6-sol"
+              },
+              {
+                "model": "pi:openai-codex:gpt-5.6-terra",
+                "effort": "high"
+              }
+            ]
+          ],
+          "type": "array",
+          "items": {
+            "type": "object",
+            "additionalProperties": false,
+            "required": [
+              "model"
+            ],
+            "properties": {
+              "model": {
+                "type": "string",
+                "minLength": 1
+              },
+              "effort": {
+                "type": "string",
+                "enum": [
+                  "none",
+                  "minimal",
+                  "low",
+                  "medium",
+                  "high",
+                  "xhigh",
+                  "max",
+                  "ultra"
+                ]
+              }
+            }
+          },
+          "default": []
+        },
+        "routeSafety": {
+          "description": "Uniform preserves one shared safety contract; per-route-native uses and reports each provider's explicit contract.",
+          "examples": [
+            "per-route-native"
+          ],
+          "type": "string",
+          "default": "uniform",
+          "enum": [
+            "uniform",
+            "per-route-native"
+          ]
         },
         "executionMode": {
           "description": "Configures executionMode for the runtime section.",
@@ -48,7 +119,17 @@
           "examples": [
             "medium"
           ],
-          "type": "string"
+          "type": "string",
+          "enum": [
+            "none",
+            "minimal",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max",
+            "ultra"
+          ]
         },
         "permissionMode": {
           "description": "Configures permissionMode for the runtime section.",
@@ -219,14 +300,24 @@
             "bujo"
           ],
           "type": "string",
-          "default": "bujo"
+          "default": "bujo",
+          "enum": [
+            "bujo",
+            "supermemory"
+          ]
         },
         "mode": {
           "description": "Configures mode for the memory section.",
           "examples": [
             "journal"
           ],
-          "type": "string"
+          "type": "string",
+          "default": "lite",
+          "enum": [
+            "lite",
+            "journal",
+            "bujo"
+          ]
         },
         "path": {
           "description": "Configures path for the memory section.",
@@ -246,10 +337,15 @@
         "writeMode": {
           "description": "Configures writeMode for the memory section.",
           "examples": [
-            "append-host-summary"
+            "disabled"
           ],
           "type": "string",
-          "default": "append-host-summary"
+          "default": "disabled",
+          "enum": [
+            "disabled",
+            "append-host-summary",
+            "capture"
+          ]
         },
         "supermemory": {
           "type": "object",
@@ -310,12 +406,16 @@
               "examples": [
                 "ollama"
               ],
-              "type": "string"
+              "type": "string",
+              "enum": [
+                "ollama",
+                "openai"
+              ]
             },
             "model": {
               "description": "Configures embeddings.model for the memory section.",
               "examples": [
-                "nomic-embed-text"
+                "nomic-embed-text:v1.5"
               ],
               "type": "string"
             },
@@ -388,12 +488,16 @@
               "examples": [
                 "agent-host"
               ],
-              "type": "string"
+              "type": "string",
+              "enum": [
+                "ollama",
+                "agent-host"
+              ]
             },
             "model": {
               "description": "Configures llm.model for the memory section.",
               "examples": [
-                "pi:openai-codex:gpt-5.5"
+                "pi:openai-codex:gpt-5.6-terra"
               ],
               "type": "string"
             },
@@ -438,7 +542,8 @@
               "examples": [
                 true
               ],
-              "type": "boolean"
+              "type": "boolean",
+              "default": true
             }
           }
         },
@@ -464,7 +569,178 @@
             }
           }
         }
-      }
+      },
+      "allOf": [
+        {
+          "if": {
+            "properties": {
+              "backend": {
+                "const": "bujo"
+              },
+              "mode": {
+                "const": "lite"
+              }
+            }
+          },
+          "then": {
+            "not": {
+              "anyOf": [
+                {
+                  "properties": {
+                    "embeddings": {}
+                  },
+                  "required": [
+                    "embeddings"
+                  ]
+                },
+                {
+                  "properties": {
+                    "llm": {}
+                  },
+                  "required": [
+                    "llm"
+                  ]
+                },
+                {
+                  "properties": {
+                    "consolidation": {}
+                  },
+                  "required": [
+                    "consolidation"
+                  ]
+                },
+                {
+                  "properties": {
+                    "writeMode": {
+                      "const": "capture"
+                    }
+                  },
+                  "required": [
+                    "writeMode"
+                  ]
+                }
+              ]
+            }
+          }
+        },
+        {
+          "if": {
+            "properties": {
+              "backend": {
+                "const": "bujo"
+              },
+              "mode": {
+                "const": "journal"
+              }
+            },
+            "required": [
+              "mode"
+            ]
+          },
+          "then": {
+            "required": [
+              "embeddings"
+            ],
+            "properties": {
+              "embeddings": {
+                "type": "object",
+                "minProperties": 1
+              }
+            },
+            "not": {
+              "anyOf": [
+                {
+                  "properties": {
+                    "llm": {}
+                  },
+                  "required": [
+                    "llm"
+                  ]
+                },
+                {
+                  "properties": {
+                    "consolidation": {}
+                  },
+                  "required": [
+                    "consolidation"
+                  ]
+                },
+                {
+                  "properties": {
+                    "writeMode": {
+                      "const": "capture"
+                    }
+                  },
+                  "required": [
+                    "writeMode"
+                  ]
+                }
+              ]
+            }
+          }
+        },
+        {
+          "if": {
+            "properties": {
+              "backend": {
+                "const": "bujo"
+              },
+              "mode": {
+                "const": "bujo"
+              }
+            },
+            "required": [
+              "mode"
+            ]
+          },
+          "then": {
+            "required": [
+              "embeddings",
+              "llm"
+            ],
+            "properties": {
+              "embeddings": {
+                "type": "object",
+                "minProperties": 1
+              },
+              "llm": {
+                "type": "object",
+                "properties": {
+                  "model": {}
+                },
+                "required": [
+                  "model"
+                ]
+              }
+            }
+          }
+        },
+        {
+          "if": {
+            "properties": {
+              "backend": {
+                "const": "bujo"
+              },
+              "writeMode": {
+                "const": "capture"
+              }
+            },
+            "required": [
+              "writeMode"
+            ]
+          },
+          "then": {
+            "properties": {
+              "mode": {
+                "const": "bujo"
+              }
+            },
+            "required": [
+              "mode"
+            ]
+          }
+        }
+      ]
     },
     "tools": {
       "type": "object",
@@ -507,6 +783,21 @@
           ],
           "type": "string"
         },
+        "mcpRequestContextServers": {
+          "description": "Configured stdio MCP server names that receive trusted per-request conversation, run, output-directory, and scoped progress context.",
+          "examples": [
+            [
+              "transcribe"
+            ]
+          ],
+          "type": "array",
+          "items": {
+            "type": "string",
+            "minLength": 1
+          },
+          "default": [],
+          "uniqueItems": true
+        },
         "mcpCallTimeoutMs": {
           "description": "Configures mcpCallTimeoutMs for the tools section.",
           "examples": [
@@ -534,7 +825,11 @@
           "examples": [
             "native"
           ],
-          "type": "string"
+          "type": "string",
+          "enum": [
+            "native",
+            "off"
+          ]
         },
         "network": {
           "type": "object",
@@ -546,7 +841,12 @@
                 "none"
               ],
               "type": "string",
-              "default": "none"
+              "default": "none",
+              "enum": [
+                "none",
+                "localhost",
+                "allowlist"
+              ]
             },
             "allowlist": {
               "description": "Configures network.allowlist for the sandbox section.",
@@ -604,7 +904,11 @@
             "fail-closed"
           ],
           "type": "string",
-          "default": "fail-closed"
+          "default": "fail-closed",
+          "enum": [
+            "fail-closed",
+            "unsafe-host-process"
+          ]
         },
         "unsafeAllowHostProcess": {
           "description": "Configures unsafeAllowHostProcess for the sandbox section.",
@@ -1426,6 +1730,32 @@
           "type": "object",
           "additionalProperties": true
         },
+        "sendTools": {
+          "type": "object",
+          "additionalProperties": false,
+          "properties": {
+            "scope": {
+              "description": "Bind Telegram send tools to the chat that produced the current run.",
+              "examples": [
+                "producing-conversation"
+              ],
+              "type": "string",
+              "enum": [
+                "producing-conversation"
+              ]
+            },
+            "pathScope": {
+              "description": "Confine Telegram path uploads to the current run output directory.",
+              "examples": [
+                "run-output"
+              ],
+              "type": "string",
+              "enum": [
+                "run-output"
+              ]
+            }
+          }
+        },
         "enabled": {
           "description": "Enables the telegram capability.",
           "examples": [
@@ -1514,6 +1844,40 @@
               "type": "integer"
             }
           }
+        },
+        "transcription": {
+          "type": "object",
+          "additionalProperties": false,
+          "properties": {
+            "endpoint": {
+              "description": "Configures transcription.endpoint for the telegram section.",
+              "examples": [
+                "example"
+              ],
+              "type": "string"
+            },
+            "model": {
+              "description": "Configures transcription.model for the telegram section.",
+              "examples": [
+                "example"
+              ],
+              "type": "string"
+            },
+            "language": {
+              "description": "Configures transcription.language for the telegram section.",
+              "examples": [
+                "example"
+              ],
+              "type": "string"
+            },
+            "timeoutMs": {
+              "description": "Configures transcription.timeoutMs for the telegram section.",
+              "examples": [
+                1
+              ],
+              "type": "integer"
+            }
+          }
         }
       }
     },

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

@@ -46,7 +46,7 @@ The `mono-agent` CLI ships with `@mono-agent/agent-app` on npm:
 npm install -g @mono-agent/agent-app   # or: npx @mono-agent/agent-app …
 ```
 
-To run an unreleased build instead, use a clone of the mono-agent workspace with Node 20+ and pnpm 10 or newer already installed:
+To run an unreleased build instead, use a clone of the mono-agent workspace with Node 22.19.0+ and pnpm 10 or newer already installed:
 
 ```bash
 git clone <mono-agent-repo> ~/mono-agent && cd ~/mono-agent
@@ -59,7 +59,7 @@ Everything below runs in the user's agent folder, not the workspace.
 
 ## Composition Flow
 
-1. **Discover.** Read `references/discovery-questions.md` and resolve: runtime model + backup models, channels, identity/knowledge, skills, tools/MCP, memory strategy, sandbox, observability, and the acceptance smoke test. Then run `mono-agent presets list` (and `mono-agent presets show <id>`) for a saved answer-set matching the user's intent; `references/playbooks.md` is the prose companion. If a preset fits, use it as the starting shape. The six presets are `starter`, `telegram-assistant`, `telegram-supermemory`, `slack-bot`, `local-private`, and `code-sandbox`; shapes with no preset (an OpenAI-API gateway, cron digest, A2A provider, Phoenix-observed, or a full multi-channel build) are hand-assembled from the capability modules and playbooks.
+1. **Discover.** Read `references/discovery-questions.md` and resolve: runtime model + backup models, channels, identity/knowledge, skills, tools/MCP, memory strategy, sandbox, observability, and the acceptance smoke test. Then run `mono-agent presets list` (and `mono-agent presets show <id>`) for a saved answer-set matching the user's intent; `references/playbooks.md` is the prose companion. If a preset fits, use it as the starting shape. The five core presets are `starter`, `telegram-assistant`, `slack-bot`, `local-private`, and `code-sandbox`; optional plugins such as Supermemory ship their own setup skill. Shapes with no core preset (an OpenAI-API gateway, cron digest, A2A provider, Phoenix-observed, Supermemory, or a full multi-channel build) are hand-assembled from the capability modules and playbooks.
 2. **Scaffold.** In the user's folder, prefer the preset path when one fits — scaffold non-interactively with `--yes` (the composer is not the interactive `init` wizard):
 
    ```bash
@@ -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, and `.mono-agent/` working directories (presets also emit a `.env.example` and any extra files). `--effort` writes `runtime.effort`; `--auth` opts in to provider setup before writing files; `--dry-run` previews without writing or launching auth/preflight commands. It never overwrites existing files.
-3. **Configure.** Edit `mono-agent.config.json` to match the discovery answers. 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` 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.
 4. **Validate.**
 
    ```bash

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

@@ -35,7 +35,7 @@ my-agent/
     "model": "claude:claude-sonnet-4-6",   // claude:* | codex:* | pi:<provider>:<model>
     "fallbackModels": ["pi:ollama:gemma4:31b"],
     "executionMode": "sdk",                // sdk | cli (default inferred from model)
-    "effort": "medium",                    // none|low|medium|high|xhigh|max
+    "effort": "medium",                    // none|low|medium|high|xhigh|max; omit for direct opencode:*
     "permissionMode": "default",           // default|plan|acceptEdits|bypassPermissions (CLI backends)
     "maxTurns": 0,                         // 0 or omitted means unlimited; 1-100 caps turns
     "workspace": ".",
@@ -110,7 +110,9 @@ my-agent/
     "mcpConfigPath": "./mcp.json"          // stdio/sse/http servers; inlined for SDK runtimes
   },
 
-  // Sandbox for runtime commands. Omit for no sandboxing.
+  // Sandbox for Pi-owned runtime commands. Direct Codex uses its own sandbox;
+  // Claude/direct OpenCode cannot enforce these exact srt scopes. All reject
+  // this block (pi:opencode-go:* remains a Pi route).
   "sandbox": {
     "mode": "native",                      // native (srt-wrapped) | off
     "network": { "mode": "none", "allowlist": [] }, // none|localhost|allowlist|all; *.suffix wildcards
@@ -187,8 +189,7 @@ my-agent/
     "port": 4040,
     "basePath": "/v1",                     // serves /v1/models + /v1/chat/completions (SSE)
     "allowNonLoopback": false,
-    "modelId": "my-agent",                 // model id advertised to API clients
-    "apiKey": "..."                        // optional bearer required from clients
+    "modelId": "my-agent"                  // model id advertised to API clients
   },
 
   // Telegram & Slack deliver only the FINAL answer by default (no streamed

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

@@ -10,15 +10,15 @@ Question:
 Which model should drive the agent, and should any backups take over when the provider fails?
 
 1. `claude:<model>` through SDK or CLI mode
-2. `pi:openai-codex:<model>` through SDK mode (preferred over direct Codex when Pi auth is configured)
-3. `codex:<model>` through CLI mode (direct Codex fallback path)
+2. `codex:<model>` through CLI mode (the default direct Codex path)
+3. `pi:openai-codex:<model>` through SDK mode (a selectable Pi alternative when Pi auth is configured)
 4. `pi:<provider>:<model>` through SDK mode (OpenAI, Copilot, OpenRouter, OpenCode-through-Pi, local Ollama, LM Studio, ...)
 5. A custom MonoRuntimeLike supplied programmatically (escape hatch)
 ```
 
-Fills: `runtime.model`, `runtime.fallbackModels` (ordered backup references tried on retryable provider failures), `runtime.executionMode` (usually inferred), `runtime.effort`, `runtime.maxTurns`.
+Fills: `runtime.model`, `runtime.fallbackModels` (ordered backup references tried on retryable provider failures), `runtime.executionMode` (usually inferred), `runtime.effort`, `runtime.maxTurns`. Keep a direct `codex:*` chain all-direct. Pi, Claude, and direct OpenCode may mix only with `sandbox` omitted/off; if native mono-agent sandboxing is selected, every primary/fallback/trigger model must stay on Pi (`pi:opencode-go:*` is Pi). Direct `opencode:*` is advanced scaffold/config-only, requires exact allow-all plus an explicit native `permissionMode`, and must omit `runtime.effort` under SDK 1.x.
 
-The interactive `mono-agent init` wizard discovers Pi OpenAI-Codex auth, OpenCode models, Ollama models, and LM Studio's local server best-effort. It ranks discovered `pi:openai-codex:gpt-5.5` above direct `codex:gpt-5.5`, maps discovered OpenCode options to `pi:opencode-go:<model>` for setup/preflight, and auto-adds local provider modules when a primary or fallback model uses `pi:ollama:*` or `pi:lmstudio:*`. Direct `opencode:<provider>:<model>` refs are supported only as hand-authored runtime backend config; do not present them as a first-class composer or init wizard selection. For local models also fill `providers.local` (e.g. an Ollama or LM Studio base URL plus model capabilities). Follow-up only if needed: continuous provider session per conversation (`runtime.session.mode: "continuous"`, default) versus stateless per-message.
+The interactive `mono-agent init` wizard discovers Pi OpenAI-Codex auth, OpenCode models, Ollama models, and LM Studio's local server best-effort. It defaults to direct `codex:gpt-5.6-terra` and presents both `pi:openai-codex:gpt-5.6-terra` and `pi:openai-codex:gpt-5.6-sol` as concrete selectable candidates. Direct `codex:gpt-5.6-sol` is also selectable; direct GPT-5.6 routes require Codex CLI 0.144.0 or newer. The wizard maps discovered OpenCode options to `pi:opencode-go:<model>` for setup/preflight, and auto-adds local provider modules when a primary or fallback model uses `pi:ollama:*` or `pi:lmstudio:*`. Recover missing Pi OAuth with `mono-agent auth login <provider>` (and `--pi-auth-path` when required). Direct `opencode:<provider>:<model>` refs are supported only as hand-authored runtime backend config; do not present them as a first-class composer or init wizard selection. For local models also fill `providers.local` (e.g. an Ollama or LM Studio base URL plus model capabilities). Follow-up only if needed: continuous provider session per conversation (`runtime.session.mode: "continuous"`, default) versus stateless per-message.
 
 ## 2. Channels Of Communication
 
@@ -148,8 +148,8 @@ is **auto-scheduled in-app** — no external cron or launchd setup needed.
 - 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`.
-  - agent-host: SDK runtime model reference such as `pi:openai-codex:gpt-5.5` with
-    `executionMode: "sdk"`. Do not use CLI-backed refs such as `codex:gpt-5.5`; they are
+  - agent-host: SDK runtime model reference such as `pi:openai-codex:gpt-5.6-terra` with
+    `executionMode: "sdk"`. Do not use CLI-backed refs such as `codex:gpt-5.6-terra`; they are
     rejected for memory LLMs until runtimes can enforce no external actions.
 - Ask: should per-turn intelligent capture be enabled (`writeMode: "capture"`), or only
   deterministic rapid-log summaries (`append-host-summary`) plus scheduled consolidation?
@@ -180,7 +180,7 @@ For an agent-host memory LLM, write the `llm` block as:
 ```jsonc
 "llm": {
   "provider": "agent-host",
-  "model": "pi:openai-codex:gpt-5.5",
+  "model": "pi:openai-codex:gpt-5.6-terra",
   "executionMode": "sdk"
 }
 ```
@@ -209,7 +209,7 @@ See `docs/memory/index.md` for the full tier table, config shapes, and CLI subco
 Question:
 
 ```text
-Should runtime commands run inside a sandbox?
+Should Pi-owned runtime commands run inside the native mono-agent sandbox? Direct Codex uses its own native sandbox and rejects this block; Claude and direct OpenCode reject it because their provider-owned tools cannot enforce the exact `srt` scopes.
 
 1. No sandbox for the first pass
 2. Native sandbox, no network (fail closed)