jambonz-python-sdk 0.2.0__tar.gz → 0.3.1__tar.gz

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/.gitignore

@@ -12,5 +12,4 @@ build/
 htmlcov/
 .coverage
 *.egg
-mcp.json
 .vscode/

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jambonz-python-sdk
-Version: 0.2.0
+Version: 0.3.1
 Summary: Python SDK for jambonz CPaaS platform
 Project-URL: Homepage, https://github.com/jambonz/jambonz-python-sdk
 Project-URL: Repository, https://github.com/jambonz/jambonz-python-sdk
@@ -106,7 +106,7 @@ async with JambonzClient(
 
 ### Spec-driven verb generation
 
-The SDK does **not** hardcode verb method signatures. Instead, verb methods (`.say()`, `.gather()`, `.dial()`, `.pipeline()`, etc.) are **auto-generated at import time** from [JSON Schema](https://github.com/jambonz/schema) files — the same schemas used by the Node.js SDK and the jambonz server.
+The SDK does **not** hardcode verb method signatures. Instead, verb methods (`.say()`, `.gather()`, `.dial()`, `.agent()`, etc.) are **auto-generated at import time** from [JSON Schema](https://github.com/jambonz/schema) files — the same schemas used by the Node.js SDK and the jambonz server.
 
 **What this means:**
 
@@ -132,7 +132,7 @@ VerbDef("new_verb", "new_verb", doc="Description.")
 
 ## Features
 
-- **All 31 jambonz verbs**: say, play, gather, dial, conference, enqueue/dequeue, hangup, pause, redirect, config, tag, dtmf, dub, message, alert, answer, leave, listen/stream, transcribe, openai_s2s, google_s2s, deepgram_s2s, elevenlabs_s2s, ultravox_s2s, s2s, llm, dialogflow, pipeline, sip_decline, sip_request, sip_refer
+- **All 31 jambonz verbs**: say, play, gather, dial, conference, enqueue/dequeue, hangup, pause, redirect, config, tag, dtmf, dub, message, alert, answer, leave, listen/stream, transcribe, openai_s2s, google_s2s, deepgram_s2s, elevenlabs_s2s, ultravox_s2s, s2s, llm, dialogflow, agent, sip_decline, sip_request, sip_refer
 - **Fluent chainable API**: `.say(...).gather(...).hangup()`
 - **Webhook transport**: `WebhookResponse` for HTTP apps (works with aiohttp, FastAPI, Flask, etc.)
 - **WebSocket transport**: `create_endpoint` with `Session`, event handling, `send()`/`reply()`
@@ -140,7 +140,7 @@ VerbDef("new_verb", "new_verb", doc="Description.")
 - **Audio streaming**: Bidirectional audio via `AudioStream`
 - **Mid-call control**: inject commands (mute, whisper, record, DTMF, tag)
 - **TTS token streaming**: `send_tts_tokens()` / `flush_tts_tokens()`
-- **Pipeline updates**: `update_pipeline()` for mid-conversation LLM changes
+- **Agent updates**: `update_agent()` for mid-conversation LLM changes
 - **Signature verification**: HMAC-SHA256 webhook signature validation
 - **Env vars**: Portal discovery via OPTIONS + runtime reading
 
@@ -153,7 +153,7 @@ See the [`examples/`](examples/) directory:
 | hello-world | [webhook](examples/hello-world/webhook_app.py) | [websocket](examples/hello-world/websocket_app.py) | Minimal greeting |
 | echo | [webhook](examples/echo/webhook_app.py) | [websocket](examples/echo/websocket_app.py) | Speech echo with gather |
 | ivr-menu | [webhook](examples/ivr-menu/webhook_app.py) | — | IVR menu with speech + DTMF |
-| voice-agent | [webhook](examples/voice-agent/webhook_app.py) | [websocket](examples/voice-agent/websocket_app.py) | LLM pipeline with tool calls |
+| voice-agent | [webhook](examples/voice-agent/webhook_app.py) | [websocket](examples/voice-agent/websocket_app.py) | LLM agent with tool calls |
 | dial | [webhook](examples/dial/webhook_app.py) | — | Outbound dial with fallback |
 | listen-record | [webhook](examples/listen-record/webhook_app.py) | [websocket](examples/listen-record/websocket_app.py) | Audio recording |
 

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/README.md

@@ -72,7 +72,7 @@ async with JambonzClient(
 
 ### Spec-driven verb generation
 
-The SDK does **not** hardcode verb method signatures. Instead, verb methods (`.say()`, `.gather()`, `.dial()`, `.pipeline()`, etc.) are **auto-generated at import time** from [JSON Schema](https://github.com/jambonz/schema) files — the same schemas used by the Node.js SDK and the jambonz server.
+The SDK does **not** hardcode verb method signatures. Instead, verb methods (`.say()`, `.gather()`, `.dial()`, `.agent()`, etc.) are **auto-generated at import time** from [JSON Schema](https://github.com/jambonz/schema) files — the same schemas used by the Node.js SDK and the jambonz server.
 
 **What this means:**
 
@@ -98,7 +98,7 @@ VerbDef("new_verb", "new_verb", doc="Description.")
 
 ## Features
 
-- **All 31 jambonz verbs**: say, play, gather, dial, conference, enqueue/dequeue, hangup, pause, redirect, config, tag, dtmf, dub, message, alert, answer, leave, listen/stream, transcribe, openai_s2s, google_s2s, deepgram_s2s, elevenlabs_s2s, ultravox_s2s, s2s, llm, dialogflow, pipeline, sip_decline, sip_request, sip_refer
+- **All 31 jambonz verbs**: say, play, gather, dial, conference, enqueue/dequeue, hangup, pause, redirect, config, tag, dtmf, dub, message, alert, answer, leave, listen/stream, transcribe, openai_s2s, google_s2s, deepgram_s2s, elevenlabs_s2s, ultravox_s2s, s2s, llm, dialogflow, agent, sip_decline, sip_request, sip_refer
 - **Fluent chainable API**: `.say(...).gather(...).hangup()`
 - **Webhook transport**: `WebhookResponse` for HTTP apps (works with aiohttp, FastAPI, Flask, etc.)
 - **WebSocket transport**: `create_endpoint` with `Session`, event handling, `send()`/`reply()`
@@ -106,7 +106,7 @@ VerbDef("new_verb", "new_verb", doc="Description.")
 - **Audio streaming**: Bidirectional audio via `AudioStream`
 - **Mid-call control**: inject commands (mute, whisper, record, DTMF, tag)
 - **TTS token streaming**: `send_tts_tokens()` / `flush_tts_tokens()`
-- **Pipeline updates**: `update_pipeline()` for mid-conversation LLM changes
+- **Agent updates**: `update_agent()` for mid-conversation LLM changes
 - **Signature verification**: HMAC-SHA256 webhook signature validation
 - **Env vars**: Portal discovery via OPTIONS + runtime reading
 
@@ -119,7 +119,7 @@ See the [`examples/`](examples/) directory:
 | hello-world | [webhook](examples/hello-world/webhook_app.py) | [websocket](examples/hello-world/websocket_app.py) | Minimal greeting |
 | echo | [webhook](examples/echo/webhook_app.py) | [websocket](examples/echo/websocket_app.py) | Speech echo with gather |
 | ivr-menu | [webhook](examples/ivr-menu/webhook_app.py) | — | IVR menu with speech + DTMF |
-| voice-agent | [webhook](examples/voice-agent/webhook_app.py) | [websocket](examples/voice-agent/websocket_app.py) | LLM pipeline with tool calls |
+| voice-agent | [webhook](examples/voice-agent/webhook_app.py) | [websocket](examples/voice-agent/websocket_app.py) | LLM agent with tool calls |
 | dial | [webhook](examples/dial/webhook_app.py) | — | Outbound dial with fallback |
 | listen-record | [webhook](examples/listen-record/webhook_app.py) | [websocket](examples/listen-record/websocket_app.py) | Audio recording |
 

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "jambonz-python-sdk"
-version = "0.2.0"
+version = "0.3.1"
 description = "Python SDK for jambonz CPaaS platform"
 readme = "README.md"
 requires-python = ">=3.10"

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/client/api.py

@@ -100,16 +100,16 @@ class CallsResource(_Resource):
         """
         return await self.update(call_sid, {"mute_status": status})
 
-    async def update_pipeline(
+    async def update_agent(
         self, call_sid: str, data: dict[str, Any]
     ) -> dict[str, Any]:
-        """Send a mid-conversation pipeline update.
+        """Send a mid-conversation agent update.
 
         Args:
             call_sid: The call to update.
-            data: Pipeline update payload.
+            data: Agent update payload.
         """
-        return await self.update(call_sid, {"pipeline_update": data})
+        return await self.update(call_sid, {"agent_update": data})
 
     async def noise_isolation(
         self, call_sid: str, status: str, opts: dict[str, Any] | None = None

jambonz_python_sdk-0.2.0/src/jambonz_sdk/schema/callbacks/pipeline-turn.schema.json → jambonz_python_sdk-0.3.1/src/jambonz_sdk/schema/callbacks/agent-turn.schema.json

@@ -1,8 +1,8 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "https://jambonz.org/schema/callbacks/pipeline-turn",
-  "title": "Pipeline EventHook Events",
-  "description": "Events sent to the pipeline verb's eventHook during a conversation. These are sent as 'pipeline:event' messages over the WebSocket connection.",
+  "$id": "https://jambonz.org/schema/callbacks/agent-turn",
+  "title": "Agent EventHook Events",
+  "description": "Events sent to the agent verb's eventHook during a conversation. These are sent as 'agent:event' messages over the WebSocket connection.",
   "type": "object",
   "oneOf": [
     {
@@ -84,7 +84,7 @@
     {
       "properties": {
         "type": {
-          "const": "agent_response",
+          "const": "llm_response",
           "description": "Sent when the LLM has finished generating its response for the current turn. Contains the complete response text."
         },
         "response": {

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/callbacks/call-status.schema.json

@@ -2,12 +2,17 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://jambonz.org/schema/callbacks/call-status",
   "title": "Call Status Webhook Payload",
-  "description": "Payload sent to the call status webhook URL whenever the call state changes (e.g. trying, in-progress, completed). The status webhook is configured at the application level in jambonz. Multiple status events are sent over the life of a call. The final event (completed or failed) includes additional fields like duration and termination cause.",
+  "description": "Payload sent to the call status webhook URL whenever the call state changes (e.g. trying, in-progress, completed). The status webhook is configured at the application level in jambonz. Multiple status events are sent over the life of a call. The final event (completed or failed) includes additional fields like duration and termination cause.\n\n**Capturing B-leg call_sid:** When using the dial verb to bridge calls, status events are sent for both legs. The A-leg (original inbound call) has `direction: 'inbound'`. The B-leg (outbound dialed call) has `direction: 'outbound'`. To capture the B-leg's call_sid for later use (e.g., injecting commands to the B-leg), listen for status events where `direction === 'outbound'` and extract the `call_sid` field.",
   "allOf": [
     { "$ref": "base" }
   ],
   "type": "object",
   "properties": {
+    "direction": {
+      "type": "string",
+      "enum": ["inbound", "outbound"],
+      "description": "Call direction. 'inbound' = A-leg (original incoming call to the application). 'outbound' = B-leg (call placed by the dial verb). Use this field to identify which leg generated the status event, especially when capturing the B-leg's call_sid for mid-call control."
+    },
     "call_termination_by": {
       "type": "string",
       "enum": ["caller", "jambonz"],

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/components/recognizer-assemblyAiOptions.schema.json

@@ -28,15 +28,15 @@
     },
     "minEndOfTurnSilenceWhenConfident": {
       "type": "number",
-      "description": "Minimum silence duration (seconds) to trigger end-of-turn when confidence is met."
+      "description": "Minimum silence duration (milliseconds) to trigger end-of-turn when confidence is met. Default: 400."
     },
     "maxTurnSilence": {
       "type": "number",
-      "description": "Maximum silence duration (seconds) before forcing end-of-turn."
+      "description": "Maximum silence duration (milliseconds) before forcing end-of-turn. Default: 1280."
     },
     "minTurnSilence": {
       "type": "number",
-      "description": "Minimum silence duration (seconds) before allowing end-of-turn."
+      "description": "Minimum silence duration (milliseconds) before allowing end-of-turn."
     },
     "keyterms": {
       "type": "array",

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/components/recognizer-deepgramOptions.schema.json

@@ -141,6 +141,11 @@
     "eagerEotThreshold": {
       "type": "number",
       "description": "Eager end-of-turn threshold for faster response."
+    },
+    "languageHints": {
+      "type": "array",
+      "items": { "type": "string" },
+      "description": "Language hints for Deepgram Flux Multilingual. BCP-47 codes (e.g. 'en', 'es', 'fr'). Biases transcription toward specified languages."
     }
   },
   "additionalProperties": false

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/components/recognizer-houndifyOptions.schema.json

@@ -47,7 +47,9 @@
       "description": "Custom vocabulary terms."
     },
     "languageModel": { "type": "string", "description": "Language model to use." },
-    "audioQueryAbsoluteTimeout": { "type": "number", "description": "Absolute timeout for audio queries." }
+    "audioQueryAbsoluteTimeout": { "type": "number", "description": "Absolute timeout for audio queries." },
+    "eoqThreshold": { "type": "number", "minimum": 0, "maximum": 1, "description": "End-of-query likelihood threshold (0.0-1.0) to trigger end of speech when segmentation is disabled. Default 0.8, set to 0 to disable." },
+    "vadStopThreshold": { "type": "number", "minimum": 0, "maximum": 1, "description": "VAD probability threshold to trigger end of speech when segmentation is disabled. When VAD drops below this value after speech is detected, streaming stops. Default 0.05, set to 0 to disable." }
   },
   "additionalProperties": false
 }

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/components/recognizer.schema.json

@@ -41,9 +41,24 @@
     },
     "hints": {
       "type": "array",
-      "items": { "type": "string" },
-      "description": "An array of words or phrases that the recognizer should favor. Use this to improve accuracy for domain-specific terminology, product names, or proper nouns.",
-      "examples": [["jambonz", "drachtio", "SIP", "WebRTC"]]
+      "items": {
+        "oneOf": [
+          { "type": "string" },
+          {
+            "type": "object",
+            "properties": {
+              "phrase": { "type": "string" },
+              "boost": { "type": "number" }
+            },
+            "required": ["phrase"]
+          }
+        ]
+      },
+      "description": "An array of words or phrases that the recognizer should favor. Each item can be a plain string or an object with 'phrase' and optional 'boost' properties.",
+      "examples": [
+        ["jambonz", "drachtio", "SIP", "WebRTC"],
+        [{"phrase": "jambonz", "boost": 20}, {"phrase": "drachtio", "boost": 10}]
+      ]
     },
     "hintsBoost": {
       "type": "number",

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/jambonz-app.schema.json

@@ -28,7 +28,7 @@
         { "$ref": "verbs/deepgram_s2s" },
         { "$ref": "verbs/ultravox_s2s" },
         { "$ref": "verbs/dialogflow" },
-        { "$ref": "verbs/pipeline" },
+        { "$ref": "verbs/agent" },
         { "$ref": "verbs/conference" },
         { "$ref": "verbs/transcribe" },
         { "$ref": "verbs/enqueue" },

jambonz_python_sdk-0.2.0/src/jambonz_sdk/schema/verbs/pipeline.schema.json → jambonz_python_sdk-0.3.1/src/jambonz_sdk/schema/verbs/agent.schema.json

@@ -1,13 +1,13 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "https://jambonz.org/schema/verbs/pipeline",
+  "$id": "https://jambonz.org/schema/verbs/agent",
   "minVersion": "10.1.0",
-  "title": "Pipeline",
-  "description": "Configures a complete STT → LLM → TTS voice AI pipeline with integrated turn detection. Provides a higher-level abstraction than manually orchestrating the individual components. Optimized for building voice AI agents with proper turn-taking behavior.",
+  "title": "Agent",
+  "description": "Configures a complete voice AI agent by wiring together STT → LLM → TTS with integrated turn detection. Provides a higher-level abstraction than manually orchestrating the individual components. Optimized for building voice AI agents with proper turn-taking behavior.",
   "type": "object",
   "properties": {
     "verb": {
-      "const": "pipeline"
+      "const": "agent"
     },
     "id": {
       "type": "string",
@@ -15,11 +15,33 @@
     },
     "stt": {
       "$ref": "../components/recognizer",
-      "description": "Speech-to-text configuration for the pipeline."
+      "description": "Speech-to-text configuration for the agent."
     },
     "tts": {
       "$ref": "../components/synthesizer",
-      "description": "Text-to-speech configuration for the pipeline."
+      "description": "Text-to-speech configuration for the agent."
+    },
+    "autoLockLanguage": {
+      "oneOf": [
+        { "type": "boolean" },
+        { "type": "string", "enum": ["always"] }
+      ],
+      "description": "When using Deepgram Flux Multilingual, automatically adjust STT language hints and switch TTS voice based on detected language. Values: false (disabled), true (lock on first utterance), 'always' (continuously adapt on every turn). Default: false.",
+      "default": false
+    },
+    "languageConfig": {
+      "type": "object",
+      "description": "Per-language overrides for TTS. Keys are BCP-47 language codes. When autoLockLanguage detects a language switch, the agent uses the corresponding config.",
+      "additionalProperties": {
+        "type": "object",
+        "properties": {
+          "tts": {
+            "$ref": "../components/synthesizer",
+            "description": "TTS config override for this language. Merged with default tts."
+          }
+        },
+        "additionalProperties": false
+      }
     },
     "turnDetection": {
       "oneOf": [
@@ -53,7 +75,7 @@
         }
       ],
       "default": "stt",
-      "description": "Turn detection strategy. Controls when the pipeline decides the user has finished speaking. STT vendors with native turn-taking (deepgramflux, assemblyai, speechmatics) always use their built-in detection regardless of this setting."
+      "description": "Turn detection strategy. Controls when the agent decides the user has finished speaking. STT vendors with native turn-taking (deepgramflux, assemblyai, speechmatics) always use their built-in detection regardless of this setting."
     },
     "bargeIn": {
       "type": "object",
@@ -86,16 +108,100 @@
     },
     "llm": {
       "type": "object",
-      "description": "LLM configuration for the pipeline. See the 'llm' verb schema for details.",
-      "additionalProperties": true
+      "description": "LLM configuration for the agent.",
+      "required": ["vendor", "model"],
+      "properties": {
+        "vendor": {
+          "type": "string",
+          "enum": [
+            "openai",
+            "anthropic",
+            "google",
+            "vertex-gemini",
+            "vertex-openai",
+            "bedrock",
+            "deepseek",
+            "azure-openai",
+            "groq",
+            "huggingface"
+          ],
+          "description": "LLM vendor id. Must match a `@jambonz/llm` registered adapter."
+        },
+        "model": {
+          "type": "string",
+          "description": "Vendor-specific model id (e.g. 'gpt-4o', 'claude-sonnet-4-5-20250929')."
+        },
+        "label": {
+          "type": "string",
+          "description": "Optional label to disambiguate when the account has multiple credentials for the same vendor."
+        },
+        "auth": {
+          "type": "object",
+          "description": "Optional inline credentials. When omitted, feature-server looks up credentials by (vendor, label) from the database.",
+          "properties": {
+            "apiKey": { "type": "string" }
+          },
+          "additionalProperties": true
+        },
+        "connectOptions": {
+          "type": "object",
+          "description": "SDK-level client options.",
+          "properties": {
+            "timeout": { "type": "number", "minimum": 0 },
+            "maxRetries": { "type": "integer", "minimum": 0 },
+            "endpoint": { "type": "string" },
+            "baseURL": { "type": "string" }
+          },
+          "additionalProperties": false
+        },
+        "llmOptions": {
+          "type": "object",
+          "description": "Per-call LLM configuration.",
+          "properties": {
+            "systemPrompt": {
+              "type": "string",
+              "description": "System prompt for the model. Placed vendor-appropriately (top-level for Anthropic/Bedrock, config.systemInstruction for Gemini, role:'system' for OpenAI-compatibles)."
+            },
+            "messages": {
+              "type": "array",
+              "description": "Seed conversation history. A role:'system' entry is extracted into systemPrompt internally.",
+              "items": { "$ref": "#/$defs/llmMessage" }
+            },
+            "initialMessages": {
+              "type": "array",
+              "description": "Alias of 'messages' (historical).",
+              "items": { "$ref": "#/$defs/llmMessage" }
+            },
+            "maxTokens": {
+              "type": "integer",
+              "minimum": 1,
+              "description": "Maximum tokens the model may generate per turn."
+            },
+            "temperature": {
+              "type": "number",
+              "minimum": 0,
+              "description": "Sampling temperature."
+            },
+            "tools": {
+              "type": "array",
+              "description": "Tool / function definitions available to the model. The MCP-flat shape `{name, description, parameters}` is canonical; the OpenAI-wrapped form `{type:'function', function:{...}}` is also accepted.",
+              "items": {
+                "type": "object"
+              }
+            }
+          },
+          "additionalProperties": false
+        }
+      },
+      "additionalProperties": false
     },
     "actionHook": {
       "$ref": "../components/actionHook",
-      "description": "A webhook invoked when the pipeline ends."
+      "description": "A webhook invoked when the agent ends."
     },
     "eventHook": {
       "$ref": "../components/actionHook",
-      "description": "A webhook invoked for pipeline events. Receives event types: 'user_transcript' (user speech recognized), 'agent_response' (assistant reply), 'user_interruption' (barge-in detected), and 'turn_end' (end-of-turn summary with transcript, response, and latency metrics)."
+      "description": "A webhook invoked for agent events. Receives event types: 'user_transcript' (user speech recognized), 'llm_response' (assistant reply), 'user_interruption' (barge-in detected), and 'turn_end' (end-of-turn summary with transcript, response, and latency metrics)."
     },
     "toolHook": {
       "$ref": "../components/actionHook",
@@ -171,15 +277,30 @@
         },
         "required": ["url"]
       },
-      "description": "External MCP servers that provide tools to the LLM. The pipeline connects at startup via SSE, discovers available tools, and makes them callable by the LLM."
+      "description": "External MCP servers that provide tools to the LLM. The agent connects at startup via SSE, discovers available tools, and makes them callable by the LLM."
     }
   },
   "required": [
     "llm"
   ],
+  "$defs": {
+    "llmMessage": {
+      "type": "object",
+      "description": "A conversation-history message. The library normalizes content to a string; adapters may carry vendor-native shapes internally.",
+      "required": ["role", "content"],
+      "properties": {
+        "role": {
+          "type": "string",
+          "enum": ["system", "user", "assistant", "tool"]
+        },
+        "content": {}
+      },
+      "additionalProperties": true
+    }
+  },
   "examples": [
     {
-      "verb": "pipeline",
+      "verb": "agent",
       "stt": {
         "vendor": "deepgram",
         "language": "en-US"
@@ -201,10 +322,10 @@
         }
       },
       "turnDetection": "stt",
-      "actionHook": "/pipeline-complete"
+      "actionHook": "/agent-complete"
     },
     {
-      "verb": "pipeline",
+      "verb": "agent",
       "stt": {
         "vendor": "deepgram",
         "language": "en-US"
@@ -234,7 +355,7 @@
         "minSpeechDuration": 0.3,
         "sticky": false
       },
-      "actionHook": "/pipeline-complete"
+      "actionHook": "/agent-complete"
     }
   ]
 }

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/verbs/dub.schema.json

@@ -3,7 +3,7 @@
   "$id": "https://jambonz.org/schema/verbs/dub",
   "minVersion": "0.9.6",
   "title": "Dub",
-  "description": "Manages audio dubbing tracks on a call. Allows adding, removing, and controlling auxiliary audio tracks that are mixed into the call audio. Used for background music, coaching whispers, or injecting audio from external sources.",
+  "description": "Manages audio dubbing tracks on a call. Allows adding, removing, and controlling auxiliary audio tracks that are mixed into the call audio. Used for background music, coaching whispers, or injecting audio from external sources.\n\n**Track Routing:** Tracks are heard by the party on whose call leg they are created. A dub verb in the main verb stack (A-leg) creates tracks heard by the caller. A dub verb nested in the dial verb's `dub` array creates tracks heard by the callee. When using injectCommand to play/say on a track from a different call leg, pass the target call's `call_sid` as the third argument to `session.injectCommand()` to route the command to the correct leg.",
   "type": "object",
   "properties": {
     "verb": {

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/schema/verbs/transcribe.schema.json

@@ -37,7 +37,8 @@
     },
     "channel": {
       "type": "number",
-      "description": "Specific audio channel to transcribe."
+      "enum": [1, 2],
+      "description": "Specific audio channel to transcribe. Channel 1 = near-end (local party's audio, i.e. caller on A-leg or callee on B-leg). Channel 2 = far-end (remote party's audio). When transcribe is nested in the dial verb, omitting channel captures both legs mixed; specifying channel: 2 isolates the B-leg's inbound audio."
     }
   },
   "examples": [

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/types/__init__.py

@@ -34,6 +34,7 @@ from jambonz_sdk.types.session import (
     WsMessageType,
 )
 from jambonz_sdk.types.verbs import (
+    AgentVerb,
     AlertVerb,
     AnswerVerb,
     AnyVerb,
@@ -56,7 +57,6 @@ from jambonz_sdk.types.verbs import (
     MessageVerb,
     OpenaiS2sVerb,
     PauseVerb,
-    PipelineVerb,
     PlayVerb,
     RedirectVerb,
     S2sVerb,
@@ -92,6 +92,7 @@ __all__ = [
     "TurnTaking",
     "Vad",
     # Verbs
+    "AgentVerb",
     "AlertVerb",
     "AnswerVerb",
     "AnyVerb",
@@ -114,7 +115,6 @@ __all__ = [
     "MessageVerb",
     "OpenaiS2sVerb",
     "PauseVerb",
-    "PipelineVerb",
     "PlayVerb",
     "RedirectVerb",
     "S2sVerb",

{jambonz_python_sdk-0.2.0 → jambonz_python_sdk-0.3.1}/src/jambonz_sdk/types/verbs.py

@@ -514,10 +514,10 @@ class DialogflowVerb(TypedDict, total=False):
     tts: Synthesizer
 
 
-class PipelineVerb(TypedDict, total=False):
-    """Integrated STT -> LLM -> TTS voice AI pipeline."""
+class AgentVerb(TypedDict, total=False):
+    """Integrated STT -> LLM -> TTS voice AI agent."""
 
-    verb: str  # "pipeline"
+    verb: str  # "agent"
     id: str
     stt: Recognizer
     tts: Synthesizer
@@ -568,5 +568,5 @@ AnyVerb = Union[
     ElevenlabsS2sVerb,
     UltravoxS2sVerb,
     DialogflowVerb,
-    PipelineVerb,
+    AgentVerb,
 ]