mail-swarms 1.3.2__tar.gz → 1.3.3__tar.gz

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/AGENTS.md

@@ -182,6 +182,7 @@ registry_file = "registries/example-no-proxy.json"
 
 [server.settings]
 task_message_limit = 15
+print_llm_streams = true
 ```
 
 Environment variables:
@@ -196,7 +197,7 @@ Environment variables:
 [
   {
     "name": "example",
-    "version": "1.3.2",
+    "version": "1.3.3",
     "entrypoint": "supervisor",
     "enable_interswarm": true,
     "enable_db_agent_histories": true,
@@ -258,6 +259,7 @@ Common `agent_params`:
 - `reasoning_effort` - "minimal", "low", "medium", "high"
 - `thinking_budget` - Token budget for extended thinking
 - `stream_tokens` - Stream output to terminal
+- `print_llm_streams` - Print streamed reasoning/response chunks when streaming; runtime-level `print_llm_streams` can override this globally
 
 Note: `tool_format` is top-level, not inside `agent_params`.
 

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/CLAUDE.md

@@ -185,6 +185,7 @@ registry_file = "registries/example-no-proxy.json"
 
 [server.settings]
 task_message_limit = 15
+print_llm_streams = true
 ```
 
 **Environment variables:**
@@ -199,7 +200,7 @@ The file contains a **JSON array** of swarm definitions. Required fields: `name`
 [
   {
     "name": "example",
-    "version": "1.3.2",
+    "version": "1.3.3",
     "entrypoint": "supervisor",
     "enable_interswarm": true,
     "enable_db_agent_histories": true,
@@ -266,6 +267,7 @@ The file contains a **JSON array** of swarm definitions. Required fields: `name`
 - `reasoning_effort` - "minimal", "low", "medium", "high"
 - `thinking_budget` - Token budget for extended thinking
 - `stream_tokens` - Stream output to terminal
+- `print_llm_streams` - Print streamed reasoning/response chunks when streaming; runtime-level `print_llm_streams` can override this globally
 
 Note: `tool_format` should be a top-level agent field. If placed in agent_params, a deprecation warning is logged.
 

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mail-swarms
-Version: 1.3.2
+Version: 1.3.3
 Summary: Multi-Agent Interface Layer reference implementation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -121,7 +121,7 @@ The runtime processes MAIL messages **asynchronously**, tracks per-task state, a
 ### Installation
 ```bash
 # Clone and enter the repository
-git clone https://github.com/charonlabs/mail --branch v1.3.1
+git clone https://github.com/charonlabs/mail --branch v1.3.3
 cd mail
 
 # Install dependencies (preferred)
@@ -150,7 +150,7 @@ export ANTHROPIC_API_KEY=sk-your-anthropic-key
 export DATABASE_URL=postgresql://...
 ```
 
-Defaults for host, port, swarm metadata, and client behaviour are loaded from [`mail.toml`](mail.toml). The `[server.settings]` table exposes `task_message_limit`, which bounds how many messages the runtime will process per task when `run_continuous` is active (default `15`). Override the file or point `MAIL_CONFIG_PATH` at an alternate TOML to adjust these values per environment. Use `mail server --swarm-name/--swarm-source/--swarm-registry` (or edit `mail.toml`) to change swarm identity; `mail server` exports `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for downstream tools but does not read them as config overrides.
+Defaults for host, port, swarm metadata, and client behaviour are loaded from [`mail.toml`](mail.toml). The `[server.settings]` table exposes `task_message_limit`, which bounds how many messages the runtime will process per task when `run_continuous` is active (default `15`), and `print_llm_streams` (default `true`), which controls whether runtime-managed agents print LLM reasoning/response stream chunks to server stdout. Set `print_llm_streams=false` (or pass `mail server --print-llm-streams false`) for quieter server logs; task/event SSE streaming is unaffected. Override the file or point `MAIL_CONFIG_PATH` at an alternate TOML to adjust these values per environment. Use CLI flags such as `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` (or edit `mail.toml`) to override these at launch; `mail server` exports `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for downstream tools but does not read them as config overrides.
 
 MAIL will create the parent directory for `SWARM_REGISTRY_FILE` on startup if it is missing, so you can rely on the default `registries/` path without committing the folder.
 

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/README.md

@@ -88,7 +88,7 @@ The runtime processes MAIL messages **asynchronously**, tracks per-task state, a
 ### Installation
 ```bash
 # Clone and enter the repository
-git clone https://github.com/charonlabs/mail --branch v1.3.1
+git clone https://github.com/charonlabs/mail --branch v1.3.3
 cd mail
 
 # Install dependencies (preferred)
@@ -117,7 +117,7 @@ export ANTHROPIC_API_KEY=sk-your-anthropic-key
 export DATABASE_URL=postgresql://...
 ```
 
-Defaults for host, port, swarm metadata, and client behaviour are loaded from [`mail.toml`](mail.toml). The `[server.settings]` table exposes `task_message_limit`, which bounds how many messages the runtime will process per task when `run_continuous` is active (default `15`). Override the file or point `MAIL_CONFIG_PATH` at an alternate TOML to adjust these values per environment. Use `mail server --swarm-name/--swarm-source/--swarm-registry` (or edit `mail.toml`) to change swarm identity; `mail server` exports `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for downstream tools but does not read them as config overrides.
+Defaults for host, port, swarm metadata, and client behaviour are loaded from [`mail.toml`](mail.toml). The `[server.settings]` table exposes `task_message_limit`, which bounds how many messages the runtime will process per task when `run_continuous` is active (default `15`), and `print_llm_streams` (default `true`), which controls whether runtime-managed agents print LLM reasoning/response stream chunks to server stdout. Set `print_llm_streams=false` (or pass `mail server --print-llm-streams false`) for quieter server logs; task/event SSE streaming is unaffected. Override the file or point `MAIL_CONFIG_PATH` at an alternate TOML to adjust these values per environment. Use CLI flags such as `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` (or edit `mail.toml`) to override these at launch; `mail server` exports `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for downstream tools but does not read them as config overrides.
 
 MAIL will create the parent directory for `SWARM_REGISTRY_FILE` on startup if it is missing, so you can rely on the default `registries/` path without committing the folder.
 

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/THIRD_PARTY_NOTICES.md

@@ -5124,14 +5124,14 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
 ```
 
-## `mail-swarms==1.3.2`
+## `mail-swarms==1.3.3`
 Multi-Agent Interface Layer reference implementation
 ### License field:
 Apache-2.0
 ### Classifiers:
 License :: OSI Approved :: Apache Software License
 
-### License Text (`mail_swarms-1.3.2.dist-info/licenses/LICENSE`)
+### License Text (`mail_swarms-1.3.3.dist-info/licenses/LICENSE`)
 
 ```text
 Apache License
@@ -5337,7 +5337,7 @@ See the License for the specific language governing permissions and
 limitations under the License.
 ```
 
-### License Text (`mail_swarms-1.3.2.dist-info/licenses/NOTICE`)
+### License Text (`mail_swarms-1.3.3.dist-info/licenses/NOTICE`)
 
 ```text
 MAIL Project

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/api.md

@@ -162,7 +162,7 @@ The Python surface is designed for embedding MAIL inside other applications, bui
 
 #### `MAILSwarm` (`mail.api`)
 - **Summary**: Runtime container that owns instantiated agents/actions and embeds a `MAILRuntime`.
-- **Constructor parameters**: `name: str`, `version: str`, `agents: list[MAILAgent]`, `actions: list[MAILAction]`, `entrypoint: str`, `user_id: str = "default"`, `user_role: Literal["admin","agent","user"] = "user"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] = []`, `exclude_tools: list[str] = []`, `task_message_limit: int | None = None`, `description: str = ""`, `keywords: list[str] = []`, `enable_db_agent_histories: bool = False`.
+- **Constructor parameters**: `name: str`, `version: str`, `agents: list[MAILAgent]`, `actions: list[MAILAction]`, `entrypoint: str`, `user_id: str = "default"`, `user_role: Literal["admin","agent","user"] = "user"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] = []`, `exclude_tools: list[str] = []`, `task_message_limit: int | None = None`, `description: str = ""`, `keywords: list[str] = []`, `enable_db_agent_histories: bool = False`, `print_llm_streams: bool = True`.
 - **Key methods**:
   - `post_message(...)`, `post_message_stream(...)`, `post_message_and_run(...)`: enqueue user requests (optionally streaming or running to completion).
   - `submit_message(...)`, `submit_message_stream(...)`: submit fully-formed `MAILMessage` envelopes.
@@ -180,7 +180,7 @@ The Python surface is designed for embedding MAIL inside other applications, bui
 - **Notes**: Inline definitions from `actions` may be combined with `action_imports` that resolve to decorated `MAILAction` objects (e.g., from `mail.stdlib`).
 - **Constructor parameters**: `name: str`, `version: str`, `agents: list[MAILAgentTemplate]`, `actions: list[MAILAction]`, `entrypoint: str`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] = []`, `exclude_tools: list[str] = []`, `task_message_limit: int | None = None`, `description: str = ""`, `keywords: list[str] = []`, `public: bool = False`, `enable_db_agent_histories: bool = False`.
 - **Key methods**:
-  - `instantiate(instance_params, user_id?, user_role?, base_url?, registry_file?) -> MAILSwarm`: produce a runtime swarm (creates `SwarmRegistry` when interswarm is enabled).
+  - `instantiate(instance_params, user_id?, user_role?, base_url?, registry_file?, print_llm_streams?) -> MAILSwarm`: produce a runtime swarm (creates `SwarmRegistry` when interswarm is enabled).
   - `get_subswarm(names, name_suffix, entrypoint?) -> MAILSwarmTemplate`: filter agents into a smaller template while preserving supervisors and entrypoints.
   - `update_from_adjacency_matrix(adj: list[list[int]]) -> None`: sync template wiring back to `comm_targets` for each agent.
   - `from_swarm_json(json_str) -> MAILSwarmTemplate` / `from_swarm_json_file(swarm_name, json_filepath?) -> MAILSwarmTemplate`: rebuild from persisted JSON.
@@ -195,8 +195,9 @@ The Python surface is designed for embedding MAIL inside other applications, bui
 
 #### `MAILRuntime` (`mail.core.runtime`)
 - **Summary**: Asynchronous runtime that owns the internal message queue, tool execution, and optional interswarm router.
-- **Constructor parameters**: `agents: dict[str, AgentCore]`, `actions: dict[str, ActionCore]`, `user_id: str`, `user_role: Literal["admin","agent","user"]`, `swarm_name: str = "example"`, `entrypoint: str = "supervisor"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] | None = None`, `exclude_tools: list[str] | None = None`, `enable_db_agent_histories: bool = False`.
+- **Constructor parameters**: `agents: dict[str, AgentCore]`, `actions: dict[str, ActionCore]`, `user_id: str`, `user_role: Literal["admin","agent","user"]`, `swarm_name: str = "example"`, `entrypoint: str = "supervisor"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] | None = None`, `exclude_tools: list[str] | None = None`, `enable_db_agent_histories: bool = False`, `print_llm_streams: bool = True`.
 - Pass the lower-level `AgentCore` / `ActionCore` objects (for example via `MAILAgent.to_core()` and `MAILAction.to_core()`) when instantiating the runtime directly.
+- `print_llm_streams` is applied recursively to known agent-function wrappers (`supervisor_fn`, `action_agent_fn`, `_mail_agent`) so a runtime can centrally suppress local LLM stream printing without changing each agent definition.
 - **Key methods**:
   - `start_interswarm()`, `stop_interswarm()`, `is_interswarm_running()`.
   - `handle_interswarm_response(response_message)` and internal `_handle_local_message(message)`.

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/cli.md

@@ -17,10 +17,11 @@ The top-level parser accepts the same flags regardless of how you invoke it, for
 
 ### `mail server`
 - Configuration defaults are read from `mail.toml` (see
-  [configuration.md](./configuration.md)). Flags such as `--host`, `--port`, `--reload`, `--swarm-name`, `--swarm-source`, and `--swarm-registry` only override the values you provide.
+  [configuration.md](./configuration.md)). Flags such as `--host`, `--port`, `--reload`, `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` only override the values you provide.
 - Use `--config /path/to/mail.toml` to point at a different   configuration file for a single run. The environment variable `MAIL_CONFIG_PATH` acts as the persistent override if you prefer exporting it once.
 - Environment variables such as `AUTH_ENDPOINT` and `TOKEN_INFO_ENDPOINT` remain required; `LITELLM_PROXY_API_BASE` is required only if your swarm uses `use_proxy=true`. The CLI does not provide defaults for these. When launched via `mail server`, defaults from `mail.toml` are exported to `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for you.
 - Pass `--debug` (or set `[server].debug = true`) when you need the debug-only surface, including the OpenAI-compatible `/responses` endpoint. Leave it off for production deployments.
+- Use `--print-llm-streams true|false` to control whether runtime-managed agents print LLM reasoning/response stream chunks to server stdout. This does not affect SSE event streaming returned by `message-stream`/`POST /message`.
 - Example:
 
   ```bash

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/configuration.md

@@ -20,6 +20,7 @@ registry = "registries/example-no-proxy.json"
 
 [server.settings]
 task_message_limit = 15
+print_llm_streams = true
 
 [client]
 timeout = 3600.0
@@ -28,10 +29,10 @@ verbose = false
 
 - The `[server]` table controls how Uvicorn listens (`port`, `host`, `reload`) and whether debug-only integrations are exposed (`debug`).
 - The `[server.swarm]` table specifies the persistent swarm template (`source`), the registry persistence file (`registry` or `registry_file`), and the runtime swarm name (`name`).
-- The `[server.settings]` table currently exposes `task_message_limit`, which caps how many MAIL messages a task will process in continuous mode before yielding control. Increase the number if your agents require longer conversations per task.
+- The `[server.settings]` table exposes `task_message_limit`, which caps how many MAIL messages a task will process in continuous mode before yielding control, and `print_llm_streams`, which controls whether runtime-managed agents print LLM reasoning/response stream output to the server console. Set `print_llm_streams = false` for quieter logs (SSE event streaming is unchanged).
 - The `[client]` table exposes `timeout` (seconds) and `verbose` (bool). They feed `ClientConfig`, which in turn sets the default timeout and whether the CLI/HTTP client emit debug logs.
 - Instantiating `ServerConfig()` or `ClientConfig()` with no arguments uses these values as defaults; if a key is missing or the file is absent, the literal defaults above are applied.
-- The CLI command `mail server` accepts `--port`, `--host`, `--reload`, `--debug`, `--swarm-name`, `--swarm-source`, and `--swarm-registry`. Provided flags override the file-driven defaults, while omitted flags continue to use `mail.toml` values.
+- The CLI command `mail server` accepts `--port`, `--host`, `--reload`, `--debug`, `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false`. Provided flags override the file-driven defaults, while omitted flags continue to use `mail.toml` values.
 - The CLI command `mail client` honors `timeout` from `[client]` and allows `--timeout` to override it per invocation.
 - Set `MAIL_CONFIG_PATH` to point at an alternate `mail.toml` (for example per environment). `mail server --config /path/to/mail.toml` temporarily overrides this variable for the lifetime of the command.
 - Toggle `[server].debug` (or pass `mail server --debug`) when you need the optional OpenAI-compatible `/responses` endpoint or other debug helpers exposed by the FastAPI app. Leave it `false` for production deployments to keep the surface minimal.
@@ -68,7 +69,7 @@ verbose = false
 [
     {
         "name": "example",
-        "version": "1.3.2",
+        "version": "1.3.3",
         "entrypoint": "supervisor",
         "enable_interswarm": true,
         "agents": [

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/docker.md

@@ -51,7 +51,7 @@ docker build -t mail-server .
 The build context must contain the repository so that the `COPY` commands pick up the source and configuration files.
 
 ## Run the container
-The server requires the same environment variables as the native quickstart (`AUTH_ENDPOINT`, `TOKEN_INFO_ENDPOINT`, and `LITELLM_PROXY_API_BASE` only if your swarm uses `use_proxy=true`). Pass them via `--env` flags or an env file. To change swarm name/source/registry, mount a custom `mail.toml` and set `MAIL_CONFIG_PATH` or pass `mail server --swarm-name/--swarm-source/--swarm-registry` in the container command.
+The server requires the same environment variables as the native quickstart (`AUTH_ENDPOINT`, `TOKEN_INFO_ENDPOINT`, and `LITELLM_PROXY_API_BASE` only if your swarm uses `use_proxy=true`). Pass them via `--env` flags or an env file. To change swarm name/source/registry or runtime LLM stream-print behavior, mount a custom `mail.toml` and set `MAIL_CONFIG_PATH` or pass `mail server` flags such as `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` in the container command.
 
 ```bash
 # Option 1: export locally then forward with --env

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/factories.md

@@ -35,6 +35,8 @@ analytics_agent = LiteLLMAgentFunction(
     max_tokens=6000,
     memory=True,
     use_proxy=True,
+    stream_tokens=True,
+    print_llm_streams=True,
 )
 ```
 
@@ -108,10 +110,12 @@ Factory call signatures follow a convention:
 
 - **Top-level parameters** (`comm_targets`, `tools`, `name`, `enable_entrypoint`, etc.) describe the agent's static wiring and are typically supplied from `swarms.json` or other configuration.
 - **Instance parameters** (`user_token`, instance-level overrides) are filled when the swarm or agent instance is created.
-- **Internal parameters (`agent_params`)** (`llm`, `system`, `reasoning_effort`, `thinking_budget`) control the LLM call and are often set by package defaults or environment configuration.
+- **Internal parameters (`agent_params`)** (`llm`, `system`, `reasoning_effort`, `thinking_budget`, `stream_tokens`, `print_llm_streams`) control the LLM call and are often set by package defaults or environment configuration.
 
 `LiteLLMAgentFunction` closes over the supplied top-level settings and uses the instance parameters provided when the swarm is instantiated (for example, a per-user `user_token`).
 
+When a `MAILRuntime` is created with `print_llm_streams=False`, it best-effort propagates that value down to these function wrappers so stream output is centrally suppressed even if individual agent params were set to `true`.
+
 ## Integrating with Swarms
 
 Agent definitions in `swarms.json` reference factories via import strings, for example:

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/quickstart.md

@@ -13,7 +13,7 @@ This guide gets you running a local MAIL swarm and interacting with it.
 ### Cloning the repo
 ```bash
 git clone https://github.com/charonlabs/mail.git \
---branch v1.3.2
+--branch v1.3.3
 ```
 
 ### Installing dependencies
@@ -26,7 +26,7 @@ pip install -e .
 ```
 
 ## Environment & Config
-- Start with `mail.toml` (checked into the repo) to control default host, port, swarm source, client timeout, and `[server.settings.task_message_limit]`. Copy it if you need environment-specific values and point `MAIL_CONFIG_PATH` (or `--config`) at the new file.
+- Start with `mail.toml` (checked into the repo) to control default host, port, swarm source, client timeout, and `[server.settings]` values (`task_message_limit`, `print_llm_streams`). Copy it if you need environment-specific values and point `MAIL_CONFIG_PATH` (or `--config`) at the new file.
 - Minimum environment variables:
   - `AUTH_ENDPOINT`, `TOKEN_INFO_ENDPOINT` for auth (see [configuration.md](/docs/configuration.md))
   - `LITELLM_PROXY_API_BASE` for LLM access only when `use_proxy=true`

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/stdlib/README.md

@@ -12,7 +12,7 @@ To use one of these actions from configuration:
 ```json
 {
   "name": "example",
-  "version": "1.3.2",
+  "version": "1.3.3",
   "entrypoint": "supervisor",
   "agents": [...],
   "actions": [],

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/docs/troubleshooting.md

@@ -31,6 +31,7 @@ This list is not exhaustive, and probably never will be. If you run into any res
 
 ## Logs
 - **Enable logging** to debug flow and events
+- If model reasoning/token stream output is too noisy in server logs, set `[server.settings].print_llm_streams = false` (or launch with `mail server --print-llm-streams false`)
 - See [src/mail/utils/logger.py](/src/mail/utils/logger.py) for initialization
 
 ## Where to ask

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/llms.txt

@@ -90,7 +90,7 @@ The runtime processes MAIL messages **asynchronously**, tracks per-task state, a
 ### Installation
 ```bash
 # Clone and enter the repository
-git clone https://github.com/charonlabs/mail --branch v1.3.1
+git clone https://github.com/charonlabs/mail --branch v1.3.3
 cd mail
 
 # Install dependencies (preferred)
@@ -119,7 +119,7 @@ export ANTHROPIC_API_KEY=sk-your-anthropic-key
 export DATABASE_URL=postgresql://...
 ```
 
-Defaults for host, port, swarm metadata, and client behaviour are loaded from [`mail.toml`](mail.toml). The `[server.settings]` table exposes `task_message_limit`, which bounds how many messages the runtime will process per task when `run_continuous` is active (default `15`). Override the file or point `MAIL_CONFIG_PATH` at an alternate TOML to adjust these values per environment. Use `mail server --swarm-name/--swarm-source/--swarm-registry` (or edit `mail.toml`) to change swarm identity; `mail server` exports `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for downstream tools but does not read them as config overrides.
+Defaults for host, port, swarm metadata, and client behaviour are loaded from [`mail.toml`](mail.toml). The `[server.settings]` table exposes `task_message_limit`, which bounds how many messages the runtime will process per task when `run_continuous` is active (default `15`), and `print_llm_streams` (default `true`), which controls whether runtime-managed agents print LLM reasoning/response stream chunks to server stdout. Set `print_llm_streams=false` (or pass `mail server --print-llm-streams false`) for quieter server logs; task/event SSE streaming is unaffected. Override the file or point `MAIL_CONFIG_PATH` at an alternate TOML to adjust these values per environment. Use CLI flags such as `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` (or edit `mail.toml`) to override these at launch; `mail server` exports `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for downstream tools but does not read them as config overrides.
 
 MAIL will create the parent directory for `SWARM_REGISTRY_FILE` on startup if it is missing, so you can rely on the default `registries/` path without committing the folder.
 
@@ -284,10 +284,11 @@ The top-level parser accepts the same flags regardless of how you invoke it, for
 
 ### `mail server`
 - Configuration defaults are read from `mail.toml` (see
-  [configuration.md](./configuration.md)). Flags such as `--host`, `--port`, `--reload`, `--swarm-name`, `--swarm-source`, and `--swarm-registry` only override the values you provide.
+  [configuration.md](./configuration.md)). Flags such as `--host`, `--port`, `--reload`, `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` only override the values you provide.
 - Use `--config /path/to/mail.toml` to point at a different   configuration file for a single run. The environment variable `MAIL_CONFIG_PATH` acts as the persistent override if you prefer exporting it once.
 - Environment variables such as `AUTH_ENDPOINT` and `TOKEN_INFO_ENDPOINT` remain required; `LITELLM_PROXY_API_BASE` is required only if your swarm uses `use_proxy=true`. The CLI does not provide defaults for these. When launched via `mail server`, defaults from `mail.toml` are exported to `SWARM_NAME`, `SWARM_SOURCE`, `SWARM_REGISTRY_FILE`, and `BASE_URL` for you.
 - Pass `--debug` (or set `[server].debug = true`) when you need the debug-only surface, including the OpenAI-compatible `/responses` endpoint. Leave it off for production deployments.
+- Use `--print-llm-streams true|false` to control whether runtime-managed agents print LLM reasoning/response stream chunks to server stdout. This does not affect SSE event streaming returned by `message-stream`/`POST /message`.
 - Example:
 
   ```bash
@@ -499,6 +500,8 @@ analytics_agent = LiteLLMAgentFunction(
     max_tokens=6000,
     memory=True,
     use_proxy=True,
+    stream_tokens=True,
+    print_llm_streams=True,
 )
 ```
 
@@ -572,10 +575,12 @@ Factory call signatures follow a convention:
 
 - **Top-level parameters** (`comm_targets`, `tools`, `name`, `enable_entrypoint`, etc.) describe the agent's static wiring and are typically supplied from `swarms.json` or other configuration.
 - **Instance parameters** (`user_token`, instance-level overrides) are filled when the swarm or agent instance is created.
-- **Internal parameters (`agent_params`)** (`llm`, `system`, `reasoning_effort`, `thinking_budget`) control the LLM call and are often set by package defaults or environment configuration.
+- **Internal parameters (`agent_params`)** (`llm`, `system`, `reasoning_effort`, `thinking_budget`, `stream_tokens`, `print_llm_streams`) control the LLM call and are often set by package defaults or environment configuration.
 
 `LiteLLMAgentFunction` closes over the supplied top-level settings and uses the instance parameters provided when the swarm is instantiated (for example, a per-user `user_token`).
 
+When a `MAILRuntime` is created with `print_llm_streams=False`, it best-effort propagates that value down to these function wrappers so stream output is centrally suppressed even if individual agent params were set to `true`.
+
 ## Integrating with Swarms
 
 Agent definitions in `swarms.json` reference factories via import strings, for example:
@@ -640,6 +645,7 @@ This list is not exhaustive, and probably never will be. If you run into any res
 
 ## Logs
 - **Enable logging** to debug flow and events
+- If model reasoning/token stream output is too noisy in server logs, set `[server.settings].print_llm_streams = false` (or launch with `mail server --print-llm-streams false`)
 - See [src/mail/utils/logger.py](/src/mail/utils/logger.py) for initialization
 
 ## Where to ask
@@ -1034,7 +1040,7 @@ This guide gets you running a local MAIL swarm and interacting with it.
 ### Cloning the repo
 ```bash
 git clone https://github.com/charonlabs/mail.git \
---branch v1.3.2
+--branch v1.3.3
 ```
 
 ### Installing dependencies
@@ -1047,7 +1053,7 @@ pip install -e .
 ```
 
 ## Environment & Config
-- Start with `mail.toml` (checked into the repo) to control default host, port, swarm source, client timeout, and `[server.settings.task_message_limit]`. Copy it if you need environment-specific values and point `MAIL_CONFIG_PATH` (or `--config`) at the new file.
+- Start with `mail.toml` (checked into the repo) to control default host, port, swarm source, client timeout, and `[server.settings]` values (`task_message_limit`, `print_llm_streams`). Copy it if you need environment-specific values and point `MAIL_CONFIG_PATH` (or `--config`) at the new file.
 - Minimum environment variables:
   - `AUTH_ENDPOINT`, `TOKEN_INFO_ENDPOINT` for auth (see [configuration.md](/docs/configuration.md))
   - `LITELLM_PROXY_API_BASE` for LLM access only when `use_proxy=true`
@@ -2518,7 +2524,7 @@ The Python surface is designed for embedding MAIL inside other applications, bui
 
 #### `MAILSwarm` (`mail.api`)
 - **Summary**: Runtime container that owns instantiated agents/actions and embeds a `MAILRuntime`.
-- **Constructor parameters**: `name: str`, `version: str`, `agents: list[MAILAgent]`, `actions: list[MAILAction]`, `entrypoint: str`, `user_id: str = "default"`, `user_role: Literal["admin","agent","user"] = "user"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] = []`, `exclude_tools: list[str] = []`, `task_message_limit: int | None = None`, `description: str = ""`, `keywords: list[str] = []`, `enable_db_agent_histories: bool = False`.
+- **Constructor parameters**: `name: str`, `version: str`, `agents: list[MAILAgent]`, `actions: list[MAILAction]`, `entrypoint: str`, `user_id: str = "default"`, `user_role: Literal["admin","agent","user"] = "user"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] = []`, `exclude_tools: list[str] = []`, `task_message_limit: int | None = None`, `description: str = ""`, `keywords: list[str] = []`, `enable_db_agent_histories: bool = False`, `print_llm_streams: bool = True`.
 - **Key methods**:
   - `post_message(...)`, `post_message_stream(...)`, `post_message_and_run(...)`: enqueue user requests (optionally streaming or running to completion).
   - `submit_message(...)`, `submit_message_stream(...)`: submit fully-formed `MAILMessage` envelopes.
@@ -2536,7 +2542,7 @@ The Python surface is designed for embedding MAIL inside other applications, bui
 - **Notes**: Inline definitions from `actions` may be combined with `action_imports` that resolve to decorated `MAILAction` objects (e.g., from `mail.stdlib`).
 - **Constructor parameters**: `name: str`, `version: str`, `agents: list[MAILAgentTemplate]`, `actions: list[MAILAction]`, `entrypoint: str`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] = []`, `exclude_tools: list[str] = []`, `task_message_limit: int | None = None`, `description: str = ""`, `keywords: list[str] = []`, `public: bool = False`, `enable_db_agent_histories: bool = False`.
 - **Key methods**:
-  - `instantiate(instance_params, user_id?, user_role?, base_url?, registry_file?) -> MAILSwarm`: produce a runtime swarm (creates `SwarmRegistry` when interswarm is enabled).
+  - `instantiate(instance_params, user_id?, user_role?, base_url?, registry_file?, print_llm_streams?) -> MAILSwarm`: produce a runtime swarm (creates `SwarmRegistry` when interswarm is enabled).
   - `get_subswarm(names, name_suffix, entrypoint?) -> MAILSwarmTemplate`: filter agents into a smaller template while preserving supervisors and entrypoints.
   - `update_from_adjacency_matrix(adj: list[list[int]]) -> None`: sync template wiring back to `comm_targets` for each agent.
   - `from_swarm_json(json_str) -> MAILSwarmTemplate` / `from_swarm_json_file(swarm_name, json_filepath?) -> MAILSwarmTemplate`: rebuild from persisted JSON.
@@ -2551,8 +2557,9 @@ The Python surface is designed for embedding MAIL inside other applications, bui
 
 #### `MAILRuntime` (`mail.core.runtime`)
 - **Summary**: Asynchronous runtime that owns the internal message queue, tool execution, and optional interswarm router.
-- **Constructor parameters**: `agents: dict[str, AgentCore]`, `actions: dict[str, ActionCore]`, `user_id: str`, `user_role: Literal["admin","agent","user"]`, `swarm_name: str = "example"`, `entrypoint: str = "supervisor"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] | None = None`, `exclude_tools: list[str] | None = None`, `enable_db_agent_histories: bool = False`.
+- **Constructor parameters**: `agents: dict[str, AgentCore]`, `actions: dict[str, ActionCore]`, `user_id: str`, `user_role: Literal["admin","agent","user"]`, `swarm_name: str = "example"`, `entrypoint: str = "supervisor"`, `swarm_registry: SwarmRegistry | None = None`, `enable_interswarm: bool = False`, `breakpoint_tools: list[str] | None = None`, `exclude_tools: list[str] | None = None`, `enable_db_agent_histories: bool = False`, `print_llm_streams: bool = True`.
 - Pass the lower-level `AgentCore` / `ActionCore` objects (for example via `MAILAgent.to_core()` and `MAILAction.to_core()`) when instantiating the runtime directly.
+- `print_llm_streams` is applied recursively to known agent-function wrappers (`supervisor_fn`, `action_agent_fn`, `_mail_agent`) so a runtime can centrally suppress local LLM stream printing without changing each agent definition.
 - **Key methods**:
   - `start_interswarm()`, `stop_interswarm()`, `is_interswarm_running()`.
   - `handle_interswarm_response(response_message)` and internal `_handle_local_message(message)`.
@@ -3419,7 +3426,7 @@ docker build -t mail-server .
 The build context must contain the repository so that the `COPY` commands pick up the source and configuration files.
 
 ## Run the container
-The server requires the same environment variables as the native quickstart (`AUTH_ENDPOINT`, `TOKEN_INFO_ENDPOINT`, and `LITELLM_PROXY_API_BASE` only if your swarm uses `use_proxy=true`). Pass them via `--env` flags or an env file. To change swarm name/source/registry, mount a custom `mail.toml` and set `MAIL_CONFIG_PATH` or pass `mail server --swarm-name/--swarm-source/--swarm-registry` in the container command.
+The server requires the same environment variables as the native quickstart (`AUTH_ENDPOINT`, `TOKEN_INFO_ENDPOINT`, and `LITELLM_PROXY_API_BASE` only if your swarm uses `use_proxy=true`). Pass them via `--env` flags or an env file. To change swarm name/source/registry or runtime LLM stream-print behavior, mount a custom `mail.toml` and set `MAIL_CONFIG_PATH` or pass `mail server` flags such as `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false` in the container command.
 
 ```bash
 # Option 1: export locally then forward with --env
@@ -4721,6 +4728,7 @@ registry = "registries/example-no-proxy.json"
 
 [server.settings]
 task_message_limit = 15
+print_llm_streams = true
 
 [client]
 timeout = 3600.0
@@ -4729,10 +4737,10 @@ verbose = false
 
 - The `[server]` table controls how Uvicorn listens (`port`, `host`, `reload`) and whether debug-only integrations are exposed (`debug`).
 - The `[server.swarm]` table specifies the persistent swarm template (`source`), the registry persistence file (`registry` or `registry_file`), and the runtime swarm name (`name`).
-- The `[server.settings]` table currently exposes `task_message_limit`, which caps how many MAIL messages a task will process in continuous mode before yielding control. Increase the number if your agents require longer conversations per task.
+- The `[server.settings]` table exposes `task_message_limit`, which caps how many MAIL messages a task will process in continuous mode before yielding control, and `print_llm_streams`, which controls whether runtime-managed agents print LLM reasoning/response stream output to the server console. Set `print_llm_streams = false` for quieter logs (SSE event streaming is unchanged).
 - The `[client]` table exposes `timeout` (seconds) and `verbose` (bool). They feed `ClientConfig`, which in turn sets the default timeout and whether the CLI/HTTP client emit debug logs.
 - Instantiating `ServerConfig()` or `ClientConfig()` with no arguments uses these values as defaults; if a key is missing or the file is absent, the literal defaults above are applied.
-- The CLI command `mail server` accepts `--port`, `--host`, `--reload`, `--debug`, `--swarm-name`, `--swarm-source`, and `--swarm-registry`. Provided flags override the file-driven defaults, while omitted flags continue to use `mail.toml` values.
+- The CLI command `mail server` accepts `--port`, `--host`, `--reload`, `--debug`, `--swarm-name`, `--swarm-source`, `--swarm-registry`, and `--print-llm-streams true|false`. Provided flags override the file-driven defaults, while omitted flags continue to use `mail.toml` values.
 - The CLI command `mail client` honors `timeout` from `[client]` and allows `--timeout` to override it per invocation.
 - Set `MAIL_CONFIG_PATH` to point at an alternate `mail.toml` (for example per environment). `mail server --config /path/to/mail.toml` temporarily overrides this variable for the lifetime of the command.
 - Toggle `[server].debug` (or pass `mail server --debug`) when you need the optional OpenAI-compatible `/responses` endpoint or other debug helpers exposed by the FastAPI app. Leave it `false` for production deployments to keep the surface minimal.
@@ -4769,7 +4777,7 @@ verbose = false
 [
     {
         "name": "example",
-        "version": "1.3.2",
+        "version": "1.3.3",
         "entrypoint": "supervisor",
         "enable_interswarm": true,
         "agents": [

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/mail.toml

@@ -11,7 +11,8 @@ registry = "registries/example-no-proxy.json"
 
 [server.settings]
 task_message_limit = 15
+print_llm_streams = true
 
 [client]
 timeout = 3600.0
-verbose = false
+verbose = false

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mail-swarms"
-version = "1.3.2"
+version = "1.3.3"
 description = "Multi-Agent Interface Layer reference implementation"
 readme = "README.md"
 requires-python = ">=3.12"

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/scripts/output/mail.toml

@@ -15,3 +15,4 @@ public = false
 
 [server.settings]
 task_message_limit = 30
+print_llm_streams = true

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/src/mail/api.py

@@ -748,6 +748,7 @@ class MAILSwarm:
         description: str = "",
         keywords: list[str] = [],
         enable_db_agent_histories: bool = False,
+        print_llm_streams: bool = True,
     ) -> None:
         self.name = name
         self.version = version
@@ -763,6 +764,7 @@ class MAILSwarm:
         self.task_message_limit = task_message_limit
         self.description = description
         self.keywords = keywords
+        self.print_llm_streams = print_llm_streams
         self.adjacency_matrix, self.agent_names = self._build_adjacency_matrix()
         self.supervisors = [agent for agent in agents if agent.can_complete_tasks]
         self._agent_cores = {agent.name: agent.to_core() for agent in agents}
@@ -778,6 +780,7 @@ class MAILSwarm:
             breakpoint_tools=breakpoint_tools,
             exclude_tools=exclude_tools,
             enable_db_agent_histories=enable_db_agent_histories,
+            print_llm_streams=print_llm_streams,
         )
         self._validate()
 
@@ -1543,6 +1546,7 @@ class MAILSwarmTemplate:
         user_role: Literal["admin", "agent", "user"] = "user",
         base_url: str = "http://localhost:8000",
         registry_file: str | None = None,
+        print_llm_streams: bool = True,
     ) -> MAILSwarm:
         """
         Instantiate a MAILSwarm from a MAILSwarmTemplate.
@@ -1638,6 +1642,7 @@ class MAILSwarmTemplate:
             description=self.description,
             keywords=self.keywords,
             enable_db_agent_histories=self.enable_db_agent_histories,
+            print_llm_streams=print_llm_streams,
         )
 
     def get_subswarm(

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/src/mail/cli.py

@@ -68,10 +68,18 @@ def _run_server_with_args(args: argparse.Namespace) -> None:
         if args.swarm_registry is not None:
             swarm_overrides["registry_file"] = args.swarm_registry
 
+        settings_overrides: dict[str, object] = {}
+        if args.print_llm_streams is not None:
+            settings_overrides["print_llm_streams"] = args.print_llm_streams
+
         if swarm_overrides:
             server_overrides["swarm"] = base_config.swarm.model_copy(
                 update=swarm_overrides
             )
+        if settings_overrides:
+            server_overrides["settings"] = base_config.settings.model_copy(
+                update=settings_overrides
+            )
 
         effective_config = (
             base_config.model_copy(update=server_overrides)
@@ -345,6 +353,12 @@ def main() -> None:
         required=False,
         help="registry file of the swarm",
     )
+    server_parser.add_argument(
+        "--print-llm-streams",
+        type=_str_to_bool,
+        required=False,
+        help="whether to print LLM reasoning/response streams to the console (true/false)",
+    )
 
     # command `client`
     client_parser = subparsers.add_parser("client", help="run the MAIL client")

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/src/mail/config/server.py

@@ -68,6 +68,7 @@ def _load_defaults_from_toml() -> tuple[dict[str, Any], dict[str, Any], dict[str
     }
     settings_defaults: dict[str, Any] = {
         "task_message_limit": 15,
+        "print_llm_streams": True,
     }
 
     if tomllib is None:
@@ -118,6 +119,9 @@ def _load_defaults_from_toml() -> tuple[dict[str, Any], dict[str, Any], dict[str
                     "task_message_limit": settings_section.get(
                         "task_message_limit", settings_defaults["task_message_limit"]
                     ),
+                    "print_llm_streams": settings_section.get(
+                        "print_llm_streams", settings_defaults["print_llm_streams"]
+                    ),
                 }
 
     logger.info(
@@ -153,6 +157,9 @@ class SettingsConfig(BaseModel):
     task_message_limit: int = Field(
         default_factory=lambda: _settings_defaults()["task_message_limit"]
     )
+    print_llm_streams: bool = Field(
+        default_factory=lambda: _settings_defaults()["print_llm_streams"]
+    )
 
 
 class ServerConfig(BaseModel):

{mail_swarms-1.3.2 → mail_swarms-1.3.3}/src/mail/core/runtime.py

@@ -94,6 +94,7 @@ class MAILRuntime:
         breakpoint_tools: list[str] | None = None,
         exclude_tools: list[str] | None = None,
         enable_db_agent_histories: bool = False,
+        print_llm_streams: bool = True,
     ):
         # Use a priority queue with a deterministic tiebreaker to avoid comparing dicts
         # Structure: (priority, seq, message)
@@ -142,6 +143,7 @@ class MAILRuntime:
         self.manual_return_events: dict[str, asyncio.Event] = defaultdict(asyncio.Event)
         self.manual_return_messages: dict[str, MAILMessage | None] = defaultdict(None)
         self.exclude_tools = list(exclude_tools or [])
+        self.print_llm_streams = print_llm_streams
         self.response_messages: dict[str, MAILMessage] = {}
         self.last_breakpoint_caller: dict[str, str] = {}
         self.last_breakpoint_tool_calls: dict[str, list[AgentToolCall]] = {}
@@ -151,6 +153,42 @@ class MAILRuntime:
         self.outstanding_requests: dict[str, dict[str, int]] = defaultdict(
             lambda: defaultdict(int)
         )
+        self._apply_llm_stream_settings()
+
+    def _apply_llm_stream_settings(self) -> None:
+        """
+        Best-effort propagation of LLM stream print settings to agent functions.
+        """
+        seen: set[int] = set()
+        for agent in self.agents.values():
+            self._set_llm_stream_setting(agent.function, seen)
+
+    def _set_llm_stream_setting(
+        self, fn: Any, seen: set[int], value: bool | None = None
+    ) -> None:
+        """
+        Recursively apply print_llm_streams to known agent function wrappers.
+        """
+        if fn is None:
+            return
+        fn_id = id(fn)
+        if fn_id in seen:
+            return
+        seen.add(fn_id)
+        stream_value = self.print_llm_streams if value is None else value
+
+        if hasattr(fn, "print_llm_streams"):
+            try:
+                setattr(fn, "print_llm_streams", stream_value)
+            except Exception:  # pragma: no cover - defensive
+                logger.debug(
+                    f"{self._log_prelude()} unable to update print_llm_streams on {fn}"
+                )
+
+        for attr in ("supervisor_fn", "action_agent_fn", "_mail_agent"):
+            inner = getattr(fn, attr, None)
+            if inner is not None:
+                self._set_llm_stream_setting(inner, seen, stream_value)
 
     def _log_prelude(self) -> str:
         """