livekit-plugins-satham 0.1.1__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,24 @@
1
+ """Satham speech-to-speech (satham-1) for LiveKit Agents.
2
+
3
+ from livekit.agents import AgentSession
4
+ from livekit.plugins import satham
5
+
6
+ session = AgentSession(llm=satham.RealtimeModel(greeting="Hello!", language="en"))
7
+ await session.start(agent=Agent(instructions=role, tools=[...]), room=ctx.room)
8
+ """
9
+
10
+ from livekit.agents import Plugin
11
+
12
+ from .log import logger
13
+ from .realtime import INPUT_SAMPLE_RATE, RealtimeModel, RealtimeSession
14
+ from .version import __version__
15
+
16
+ __all__ = ["INPUT_SAMPLE_RATE", "RealtimeModel", "RealtimeSession", "__version__"]
17
+
18
+
19
+ class SathamPlugin(Plugin):
20
+ def __init__(self) -> None:
21
+ super().__init__(__name__, __version__, __package__, logger)
22
+
23
+
24
+ Plugin.register_plugin(SathamPlugin())
@@ -0,0 +1,3 @@
1
+ import logging
2
+
3
+ logger = logging.getLogger("livekit.plugins.satham")
File without changes
@@ -0,0 +1,659 @@
1
+ """Satham's speech-to-speech model as a LiveKit Agents ``RealtimeModel``.
2
+
3
+ Satham hears the caller, decides when a turn ends, replies in speech and handles barge-in on the
4
+ server, so an ``AgentSession`` given this model needs no STT, LLM, TTS or VAD of its own. One
5
+ LiveKit realtime session is one Satham call:
6
+
7
+ - the LiveKit agent's ``instructions`` are the call's role and its tools are the call's tools; the
8
+ call starts once LiveKit has handed both over, and either can change mid-call. The agent speaks
9
+ first when the model has a ``greeting``, or when LiveKit asks (``session.generate_reply()``);
10
+ - ``generate_reply()`` asks for a reply now (``response.create``), and ``session.say()`` speaks
11
+ fixed words in the call's voice (``response.say``), with no TTS;
12
+ - every other setting is a control (``satham.Controls``), with OpenAI's names where LiveKit's
13
+ OpenAI realtime plugin has them, so moving an agent from OpenAI to Satham is mostly a one-line
14
+ change; ``update_options()`` changes any of them mid-call;
15
+ - caller audio is resampled to 16 kHz mono and streamed; the agent's audio, its text and the
16
+ caller's transcripts come back as LiveKit generations and transcription events. With
17
+ ``modalities=["text"]`` the agent's words go to the session's TTS instead, as with OpenAI's
18
+ text mode;
19
+ - the caller speaking over the agent interrupts it, as with any server-side turn detection; with
20
+ ``turn_detection=None`` LiveKit's own turn detection ends each turn instead;
21
+ - ``@function_tool`` tools are sent as OpenAI-style function definitions (and again whenever
22
+ LiveKit changes them); each call the agent makes is run by LiveKit, and its result goes back to
23
+ the server, which then replies, unless the tool's result asks for no reply;
24
+ - a change of language (by the caller, the reply or the client) is emitted as ``session_updated``.
25
+ """
26
+
27
+ from __future__ import annotations
28
+
29
+ import asyncio
30
+ import contextlib
31
+ import time
32
+ import weakref
33
+ from collections.abc import AsyncIterable
34
+ from dataclasses import dataclass
35
+ from typing import Any, Literal, Unpack
36
+
37
+ from livekit import rtc
38
+ from livekit.agents import llm, utils
39
+ from livekit.agents.metrics import RealtimeModelMetrics
40
+ from livekit.agents.types import NOT_GIVEN, NotGivenOr
41
+ from livekit.agents.utils import is_given
42
+
43
+ import satham
44
+ from satham import _protocol as wire
45
+ from satham.controls import to_wire
46
+
47
+ from .log import logger
48
+
49
+ INPUT_SAMPLE_RATE = 16_000
50
+ """Caller audio goes to Satham as 16 kHz mono 16-bit PCM."""
51
+ CONFIGURE_WAIT_S = 0.5
52
+ """How long a session waits for instructions and tools before starting the call anyway."""
53
+ REPLY_TIMEOUT_S = 10.0
54
+ """How long ``generate_reply`` and ``say`` wait for the reply to start."""
55
+
56
+
57
+ def _tool_choice(choice: llm.ToolChoice | None) -> str | dict[str, Any] | None:
58
+ if choice is None or isinstance(choice, str):
59
+ return choice
60
+ return {"type": "function", "function": {"name": choice["function"]["name"]}}
61
+
62
+
63
+ def _function_schemas(tools: list[llm.Tool]) -> list[dict[str, Any]]:
64
+ """LiveKit tools as OpenAI function definitions (provider tools are skipped)."""
65
+ out: list[dict[str, Any]] = []
66
+ for tool in tools:
67
+ if isinstance(tool, llm.FunctionTool):
68
+ out.append(llm.utils.build_legacy_openai_schema(tool, internally_tagged=False))
69
+ elif isinstance(tool, llm.RawFunctionTool):
70
+ raw = dict(tool.info.raw_schema)
71
+ raw.pop("meta", None)
72
+ out.append({"type": "function", "function": raw})
73
+ else:
74
+ logger.warning("Satham takes function tools only; skipping %r", tool)
75
+ return out
76
+
77
+
78
+ def _disabled(controls: dict[str, Any], key: str) -> bool:
79
+ """Whether a control group is set to off (``None``, or ``enabled: False``)."""
80
+ if key not in controls:
81
+ return False
82
+ value = controls[key]
83
+ if value is None:
84
+ return True
85
+ if hasattr(value, "model_dump"):
86
+ value = value.model_dump(exclude_none=True)
87
+ return isinstance(value, dict) and value.get("enabled") is False
88
+
89
+
90
+ class RealtimeModel(llm.RealtimeModel):
91
+ """Satham (satham-1) for ``AgentSession(llm=...)``.
92
+
93
+ The LiveKit agent's ``instructions`` become the call's instructions, and its tools the call's
94
+ tools; nothing else is needed. ``url`` and ``api_key`` name your Satham endpoint and key (or
95
+ ``$SATHAM_URL`` and ``$SATHAM_API_KEY``); ``connect_timeout`` is in seconds.
96
+
97
+ Every other keyword is a control (``satham.Controls``), sent only when set:
98
+
99
+ - OpenAI's names: ``model`` (default ``"satham-1"``), ``voice``, ``modalities``,
100
+ ``turn_detection`` (``None`` for LiveKit's own turn detection), ``temperature``,
101
+ ``input_audio_noise_reduction``, ``input_audio_transcription``,
102
+ ``max_response_output_tokens``, ``speed``, ``tool_choice``;
103
+ - Satham's own: ``greeting``, ``language``, ``language_switch``, ``voice_on_language_switch``,
104
+ ``breaths``, ``natural_pauses``, ``continuation``, ``phrasing``, ``normalise_numbers``,
105
+ ``pronunciations``, ``top_p``, ``tone``, ``repeat_guard``, ``drift_guard``, and ``agent``
106
+ (optional: a preset agent on the server).
107
+
108
+ ``modalities``, ``turn_detection`` and ``input_audio_transcription`` also decide what the
109
+ model tells LiveKit it does, so they are fixed for a model once made.
110
+ """
111
+
112
+ def __init__(
113
+ self,
114
+ *,
115
+ url: str | None = None,
116
+ api_key: str | None = None,
117
+ connect_timeout: float = 10.0,
118
+ tool_choice: llm.ToolChoice | None = None,
119
+ **controls: Unpack[satham.Controls],
120
+ ) -> None:
121
+ self._controls: dict[str, Any] = dict(controls)
122
+ modalities = list(self._controls.get("modalities") or ["text", "audio"])
123
+ super().__init__(
124
+ capabilities=llm.RealtimeCapabilities(
125
+ message_truncation=False,
126
+ turn_detection=not _disabled(self._controls, "turn_detection"),
127
+ user_transcription=not _disabled(self._controls, "input_audio_transcription"),
128
+ auto_tool_reply_generation=True,
129
+ audio_output="audio" in modalities,
130
+ manual_function_calls=False,
131
+ mutable_chat_context=False,
132
+ mutable_instructions=True,
133
+ mutable_tools=True,
134
+ per_response_tool_choice=False,
135
+ supports_say=True,
136
+ )
137
+ )
138
+ self._tool_choice = tool_choice
139
+ # Fail now, not when the first call starts: the client checks URL, key and controls.
140
+ self._client = satham.Client(url, api_key, open_timeout=connect_timeout)
141
+ to_wire(self._controls, where="session.start", limits=self._client.limits)
142
+ self._limits_loaded = False
143
+ self._limits_lock = asyncio.Lock()
144
+ self._sessions = weakref.WeakSet[RealtimeSession]()
145
+
146
+ async def _load_limits(self) -> None:
147
+ """Take the server's control ranges (``GET /v1/info``) once; keep the built-in ones else."""
148
+ async with self._limits_lock:
149
+ if self._limits_loaded:
150
+ return
151
+ self._limits_loaded = True
152
+ try:
153
+ await self._client.load_controls()
154
+ except satham.SathamError as e:
155
+ logger.debug("no control ranges from the server (%s); using the built-in ones", e)
156
+
157
+ @property
158
+ def model(self) -> str:
159
+ return str(self._controls.get("model") or "satham-1")
160
+
161
+ @property
162
+ def provider(self) -> str:
163
+ return "satham"
164
+
165
+ def session(self, *, turn_detection_disabled: bool = False) -> RealtimeSession:
166
+ if turn_detection_disabled:
167
+ logger.warning("pass turn_detection=None to the model for manual turns")
168
+ session = RealtimeSession(self)
169
+ self._sessions.add(session)
170
+ return session
171
+
172
+ def update_options(
173
+ self,
174
+ *,
175
+ tool_choice: NotGivenOr[llm.ToolChoice | None] = NOT_GIVEN,
176
+ **changes: Unpack[satham.Controls],
177
+ ) -> None:
178
+ """Change controls for new calls and every live one (``session.update``)."""
179
+ to_wire(dict(changes), where="session.update", limits=self._client.limits)
180
+ self._controls.update(changes)
181
+ if is_given(tool_choice):
182
+ self._tool_choice = tool_choice
183
+ for session in self._sessions:
184
+ session.update_options(tool_choice=tool_choice, **changes)
185
+
186
+ async def aclose(self) -> None:
187
+ for session in list(self._sessions):
188
+ await session.aclose()
189
+
190
+
191
+ @dataclass
192
+ class _Generation:
193
+ response_id: str
194
+ message_ch: utils.aio.Chan[llm.MessageGeneration]
195
+ function_ch: utils.aio.Chan[llm.FunctionCall]
196
+ text_ch: utils.aio.Chan[str]
197
+ audio_ch: utils.aio.Chan[rtc.AudioFrame]
198
+ started_at: float
199
+ text: str = ""
200
+ first_audio_at: float | None = None
201
+
202
+ def close(self) -> None:
203
+ for ch in (self.text_ch, self.audio_ch, self.function_ch, self.message_ch):
204
+ if not ch.closed:
205
+ ch.close()
206
+
207
+
208
+ class RealtimeSession(
209
+ llm.RealtimeSession[Literal["session_updated", "satham_server_event_received"]]
210
+ ):
211
+ """One Satham call inside a LiveKit ``AgentSession``.
212
+
213
+ Besides the standard realtime events it emits ``session_updated`` (a ``satham.SessionUpdated``,
214
+ when the call's language changes) and ``satham_server_event_received`` (every server event).
215
+ """
216
+
217
+ def __init__(self, realtime_model: RealtimeModel) -> None:
218
+ super().__init__(realtime_model)
219
+ self._model = realtime_model
220
+ self._controls: dict[str, Any] = dict(realtime_model._controls)
221
+ self._tool_choice = realtime_model._tool_choice
222
+ self._text_only = not realtime_model.capabilities.audio_output
223
+ self._manual_turns = not realtime_model.capabilities.turn_detection
224
+ self._pending_reply: asyncio.Future[llm.GenerationCreatedEvent] | None = None
225
+ self._tasks: set[asyncio.Task[None]] = set()
226
+ self._instructions: str | None = None
227
+ self._tools = llm.ToolContext.empty()
228
+ self._chat_ctx = llm.ChatContext.empty()
229
+ self._call: satham.Session | None = None
230
+ self._configured = asyncio.Event()
231
+ self._closing = False
232
+ self._send_ch = utils.aio.Chan[bytes | dict[str, Any]]()
233
+ self._resampler: rtc.AudioResampler | None = None
234
+ self._bstream = utils.audio.AudioByteStream(
235
+ INPUT_SAMPLE_RATE, 1, samples_per_channel=INPUT_SAMPLE_RATE // 50
236
+ )
237
+ self._generation: _Generation | None = None
238
+ self._open_calls: set[str] = set()
239
+ self._barged_in = False
240
+ language = self._controls.get("language")
241
+ self.language: str | None = None if language in (None, "auto") else str(language)
242
+ """The call's language, following ``session.updated``."""
243
+ loop = asyncio.get_running_loop()
244
+ self._configure_timer = loop.call_later(CONFIGURE_WAIT_S, self._configured.set)
245
+ self._main_atask = asyncio.create_task(self._main(), name="satham.RealtimeSession")
246
+
247
+ # -- the call ----------------------------------------------------------------------------
248
+
249
+ @property
250
+ def call(self) -> satham.Session | None:
251
+ """The underlying ``satham.Session``, once the call has started."""
252
+ return self._call
253
+
254
+ def _start_settings(self) -> dict[str, Any]:
255
+ instructions = self._instructions or None # the LiveKit agent's; "" sends none
256
+ if instructions is None and "agent" not in self._controls:
257
+ logger.warning("the LiveKit agent has no instructions: the call starts without a role")
258
+ tools = _function_schemas(self._tools.flatten())
259
+ return {
260
+ **self._controls,
261
+ "instructions": instructions,
262
+ "tools": tools or None,
263
+ "tool_choice": _tool_choice(self._tool_choice) if tools else None,
264
+ "sample_rate": INPUT_SAMPLE_RATE,
265
+ }
266
+
267
+ async def _main(self) -> None:
268
+ try:
269
+ await self._configured.wait()
270
+ await self._model._load_limits()
271
+ if self._closing:
272
+ return
273
+ started = time.perf_counter()
274
+ self._call = await self._model._client.connect(**self._start_settings())
275
+ self._report_connection_acquired(time.perf_counter() - started)
276
+ if self._call.language:
277
+ self.language = self._call.language
278
+ sender = asyncio.create_task(self._send_loop(self._call), name="satham.send")
279
+ try:
280
+ async for event in self._call:
281
+ self._on_event(event)
282
+ finally:
283
+ await utils.aio.cancel_and_wait(sender)
284
+ if not self._closing:
285
+ reason = self._call.end_reason or f"closed ({self._call.close_code})"
286
+ self._emit_error(satham.SathamError(f"the Satham call ended: {reason}"), False)
287
+ except satham.SathamError as e:
288
+ if not self._closing:
289
+ self._emit_error(e, recoverable=False)
290
+ except Exception as e:
291
+ logger.exception("Satham session failed")
292
+ self._emit_error(e, recoverable=False)
293
+ finally:
294
+ self._close_generation()
295
+ if not self._send_ch.closed:
296
+ self._send_ch.close() # the call is over: stop queueing audio for it
297
+
298
+ async def _send_loop(self, call: satham.Session) -> None:
299
+ with contextlib.suppress(satham.SessionClosedError):
300
+ async for item in self._send_ch:
301
+ if isinstance(item, bytes):
302
+ await call.send_audio(item)
303
+ else:
304
+ await call.send(item)
305
+
306
+ def _send(self, item: bytes | dict[str, Any]) -> None:
307
+ with contextlib.suppress(utils.aio.channel.ChanClosed):
308
+ self._send_ch.send_nowait(item)
309
+
310
+ def _emit_error(self, error: Exception, recoverable: bool) -> None:
311
+ self.emit(
312
+ "error",
313
+ llm.RealtimeModelError(
314
+ timestamp=time.time(),
315
+ label=self._model.label,
316
+ error=error,
317
+ recoverable=recoverable,
318
+ ),
319
+ )
320
+
321
+ # -- server events -----------------------------------------------------------------------
322
+
323
+ def _on_event(self, event: satham.Event) -> None:
324
+ self.emit("satham_server_event_received", event)
325
+ if isinstance(event, satham.ResponseAudio):
326
+ self._on_audio(event)
327
+ elif isinstance(event, satham.ResponseTextDelta):
328
+ gen = self._generation
329
+ if gen is not None and gen.response_id == event.response_id:
330
+ gen.text += event.text
331
+ with contextlib.suppress(utils.aio.channel.ChanClosed):
332
+ gen.text_ch.send_nowait(event.text)
333
+ elif isinstance(event, satham.SpeechStarted):
334
+ if self._barged_in: # already told, when the reply was cut off
335
+ self._barged_in = False
336
+ else:
337
+ self.emit("input_speech_started", llm.InputSpeechStartedEvent())
338
+ elif isinstance(event, satham.SpeechStopped):
339
+ self.emit(
340
+ "input_speech_stopped",
341
+ llm.InputSpeechStoppedEvent(user_transcription_enabled=True),
342
+ )
343
+ elif isinstance(event, satham.TranscriptPartial | satham.TranscriptFinal):
344
+ final = isinstance(event, satham.TranscriptFinal)
345
+ if final and event.text:
346
+ self._remember(llm.ChatMessage(id=event.turn_id, role="user", content=[event.text]))
347
+ self.emit(
348
+ "input_audio_transcription_completed",
349
+ llm.InputTranscriptionCompleted(
350
+ item_id=event.turn_id, transcript=event.text, is_final=final
351
+ ),
352
+ )
353
+ elif isinstance(event, satham.ResponseStarted):
354
+ self._start_generation(event.response_id)
355
+ elif isinstance(event, satham.ResponseDone | satham.ResponseInterrupted):
356
+ if isinstance(event, satham.ResponseInterrupted) and event.reason == "barge_in":
357
+ # The server stops a reply because the caller is speaking, then says so with
358
+ # input.speech_started. Tell LiveKit first, while the reply is still open, so
359
+ # it cuts the playout instead of letting the buffered audio run on.
360
+ self._barged_in = True
361
+ self.emit("input_speech_started", llm.InputSpeechStartedEvent())
362
+ self._finish_generation(event)
363
+ elif isinstance(event, satham.ToolCall):
364
+ self._on_tool_call(event)
365
+ elif isinstance(event, satham.SessionUpdated):
366
+ if event.language:
367
+ self.language = event.language
368
+ self.emit("session_updated", event)
369
+ elif isinstance(event, satham.Error) and event.code == "response_in_progress":
370
+ pending = self._pending_reply
371
+ # With manual turns the server may already be answering the committed turn: that
372
+ # reply is the one LiveKit asked for. Otherwise nothing will start: say so.
373
+ if pending is not None and not pending.done() and not self._manual_turns:
374
+ self._pending_reply = None
375
+ pending.set_exception(llm.RealtimeError(event.message, code=event.code))
376
+ elif isinstance(event, satham.Error):
377
+ logger.warning("Satham error %s: %s", event.code, event.message)
378
+ self._emit_error(
379
+ satham.SathamError(event.message, code=event.code), recoverable=not event.fatal
380
+ )
381
+
382
+ def _remember(self, item: llm.ChatItem) -> None:
383
+ items = self._chat_ctx.items
384
+ for i, existing in enumerate(items):
385
+ if existing.id == item.id:
386
+ items[i] = item
387
+ return
388
+ items.append(item)
389
+
390
+ def _start_generation(self, response_id: str) -> None:
391
+ self._close_generation()
392
+ gen = _Generation(
393
+ response_id=response_id,
394
+ message_ch=utils.aio.Chan(),
395
+ function_ch=utils.aio.Chan(),
396
+ text_ch=utils.aio.Chan(),
397
+ audio_ch=utils.aio.Chan(),
398
+ started_at=time.time(),
399
+ )
400
+ modalities: asyncio.Future[list[Literal["text", "audio"]]] = asyncio.Future()
401
+ if self._text_only:
402
+ gen.audio_ch.close() # the words go to the session's TTS, as in OpenAI's text mode
403
+ modalities.set_result(["text"])
404
+ else:
405
+ modalities.set_result(["audio", "text"])
406
+ gen.message_ch.send_nowait(
407
+ llm.MessageGeneration(
408
+ message_id=response_id,
409
+ text_stream=gen.text_ch,
410
+ audio_stream=gen.audio_ch,
411
+ modalities=modalities,
412
+ )
413
+ )
414
+ self._generation = gen
415
+ event = llm.GenerationCreatedEvent(
416
+ message_stream=gen.message_ch,
417
+ function_stream=gen.function_ch,
418
+ user_initiated=False,
419
+ response_id=response_id,
420
+ )
421
+ pending, self._pending_reply = self._pending_reply, None
422
+ if pending is not None and not pending.done():
423
+ event.user_initiated = True # the reply LiveKit asked for after ending the turn
424
+ pending.set_result(event)
425
+ self.emit("generation_created", event)
426
+
427
+ def _on_audio(self, event: satham.ResponseAudio) -> None:
428
+ gen = self._generation
429
+ if self._text_only or gen is None or gen.response_id != event.response_id or not event.data:
430
+ return
431
+ if gen.first_audio_at is None:
432
+ gen.first_audio_at = time.time()
433
+ fmt = event.format
434
+ frame = rtc.AudioFrame(
435
+ data=event.data,
436
+ sample_rate=fmt.sample_rate,
437
+ num_channels=fmt.channels,
438
+ samples_per_channel=len(event.data) // (2 * fmt.channels),
439
+ )
440
+ with contextlib.suppress(utils.aio.channel.ChanClosed):
441
+ gen.audio_ch.send_nowait(frame)
442
+
443
+ def _finish_generation(self, event: satham.ResponseDone | satham.ResponseInterrupted) -> None:
444
+ gen = self._generation
445
+ if gen is None or gen.response_id != event.response_id:
446
+ return
447
+ interrupted = isinstance(event, satham.ResponseInterrupted)
448
+ text = gen.text if interrupted else (event.text or gen.text) # type: ignore[union-attr]
449
+ if text:
450
+ self._remember(
451
+ llm.ChatMessage(
452
+ id=gen.response_id, role="assistant", content=[text], interrupted=interrupted
453
+ )
454
+ )
455
+ now = time.time()
456
+ self.emit(
457
+ "metrics_collected",
458
+ RealtimeModelMetrics(
459
+ label=self._model.label,
460
+ request_id=gen.response_id,
461
+ timestamp=gen.started_at,
462
+ duration=now - gen.started_at,
463
+ ttft=(gen.first_audio_at - gen.started_at) if gen.first_audio_at else -1,
464
+ cancelled=interrupted,
465
+ input_token_details=RealtimeModelMetrics.InputTokenDetails(),
466
+ output_token_details=RealtimeModelMetrics.OutputTokenDetails(),
467
+ ),
468
+ )
469
+ self._close_generation()
470
+
471
+ def _close_generation(self) -> None:
472
+ if self._generation is not None:
473
+ self._generation.close()
474
+ self._generation = None
475
+
476
+ def _on_tool_call(self, event: satham.ToolCall) -> None:
477
+ call = llm.FunctionCall(
478
+ id=event.call_id, call_id=event.call_id, name=event.name, arguments=event.arguments
479
+ )
480
+ self._open_calls.add(event.call_id)
481
+ self._remember(call)
482
+ gen = self._generation
483
+ if gen is None or (event.response_id and gen.response_id != event.response_id):
484
+ logger.warning("tool call %s outside its reply; answering it as failed", event.name)
485
+ self._send(wire.tool_result(event.call_id, "error: the call came outside a reply"))
486
+ self._open_calls.discard(event.call_id)
487
+ return
488
+ with contextlib.suppress(utils.aio.channel.ChanClosed):
489
+ gen.function_ch.send_nowait(call)
490
+
491
+ # -- llm.RealtimeSession -----------------------------------------------------------------
492
+
493
+ @property
494
+ def chat_ctx(self) -> llm.ChatContext:
495
+ return self._chat_ctx.copy()
496
+
497
+ @property
498
+ def tools(self) -> llm.ToolContext:
499
+ return llm.ToolContext(self._tools.flatten())
500
+
501
+ async def update_instructions(self, instructions: str) -> None:
502
+ """The call's instructions: at the start, or mid-call (``session.update``)."""
503
+ if self._call is None:
504
+ self._instructions = instructions
505
+ return
506
+ if instructions != (self._instructions or "") and instructions:
507
+ self._instructions = instructions
508
+ self._send(
509
+ wire.session_update(to_wire({"instructions": instructions}, where="session.update"))
510
+ or {}
511
+ )
512
+
513
+ async def update_chat_ctx(self, chat_ctx: llm.ChatContext) -> None:
514
+ # Satham keeps the conversation itself; what LiveKit adds that the server needs are the
515
+ # results of the tool calls it ran.
516
+ for item in chat_ctx.items:
517
+ if item.type == "function_call_output" and item.call_id in self._open_calls:
518
+ self._open_calls.discard(item.call_id)
519
+ self._remember(item)
520
+ self._send(wire.tool_result(item.call_id, item.output, respond=item.reply_required))
521
+
522
+ async def update_tools(self, tools: list[llm.Tool]) -> None:
523
+ if self._call is None:
524
+ self._tools = llm.ToolContext(tools)
525
+ self._configure_timer.cancel()
526
+ self._configured.set() # LiveKit sets instructions, history, then tools
527
+ return
528
+ schemas = _function_schemas(tools)
529
+ if schemas != _function_schemas(self._tools.flatten()):
530
+ self._tools = llm.ToolContext(tools)
531
+ message = wire.session_update({}, tools=schemas) # the whole list, replacing the last
532
+ if message is not None:
533
+ self._send(message)
534
+
535
+ def update_options(
536
+ self,
537
+ *,
538
+ tool_choice: NotGivenOr[llm.ToolChoice | None] = NOT_GIVEN,
539
+ **changes: Unpack[satham.Controls],
540
+ ) -> None:
541
+ """Change the call's controls (``session.update``); before it starts, its start."""
542
+ if is_given(tool_choice):
543
+ self._tool_choice = tool_choice
544
+ if self._call is not None:
545
+ self._send({"type": wire.SESSION_UPDATE, "tool_choice": _tool_choice(tool_choice)})
546
+ if not changes:
547
+ return
548
+ if self._call is None:
549
+ self._controls.update(changes)
550
+ return
551
+ fields = to_wire(dict(changes), where="session.update", limits=self._model._client.limits)
552
+ message = wire.session_update(fields)
553
+ if message is not None:
554
+ self._send(message)
555
+
556
+ def push_audio(self, frame: rtc.AudioFrame) -> None:
557
+ if self._closing:
558
+ return
559
+ for resampled in self._resample(frame):
560
+ for chunk in self._bstream.write(resampled.data.tobytes()):
561
+ self._send(chunk.data.tobytes())
562
+
563
+ def _resample(self, frame: rtc.AudioFrame) -> list[rtc.AudioFrame]:
564
+ if self._resampler is not None and frame.sample_rate != self._resampler._input_rate:
565
+ self._resampler = None
566
+ if self._resampler is None and (
567
+ frame.sample_rate != INPUT_SAMPLE_RATE or frame.num_channels != 1
568
+ ):
569
+ self._resampler = rtc.AudioResampler(
570
+ input_rate=frame.sample_rate, output_rate=INPUT_SAMPLE_RATE, num_channels=1
571
+ )
572
+ return self._resampler.push(frame) if self._resampler else [frame]
573
+
574
+ def push_video(self, frame: rtc.VideoFrame) -> None:
575
+ pass # Satham is audio only
576
+
577
+ def generate_reply(
578
+ self,
579
+ *,
580
+ instructions: NotGivenOr[str] = NOT_GIVEN,
581
+ tool_choice: NotGivenOr[llm.ToolChoice] = NOT_GIVEN,
582
+ tools: NotGivenOr[list[llm.Tool]] = NOT_GIVEN,
583
+ ) -> asyncio.Future[llm.GenerationCreatedEvent]:
584
+ """A reply now (``response.create``); ``instructions`` guide this reply alone."""
585
+ return self._request(
586
+ wire.response_create(instructions if is_given(instructions) and instructions else None)
587
+ )
588
+
589
+ def say(self, text: str | AsyncIterable[str]) -> asyncio.Future[llm.GenerationCreatedEvent]:
590
+ """Speak ``text`` as it is, in the call's voice (``response.say``), with no TTS."""
591
+ if isinstance(text, str):
592
+ return self._request(wire.response_say(text))
593
+ future: asyncio.Future[llm.GenerationCreatedEvent] = asyncio.Future()
594
+
595
+ async def collect() -> None:
596
+ try:
597
+ words = "".join([part async for part in text])
598
+ result = await self._request(wire.response_say(words))
599
+ except Exception as e:
600
+ if not future.done():
601
+ future.set_exception(e)
602
+ else:
603
+ if not future.done():
604
+ future.set_result(result)
605
+
606
+ task = asyncio.create_task(collect())
607
+ self._tasks.add(task)
608
+ task.add_done_callback(self._tasks.discard)
609
+ return future
610
+
611
+ def _request(self, message: dict[str, Any]) -> asyncio.Future[llm.GenerationCreatedEvent]:
612
+ """Send a reply request; the future is the generation the server starts for it."""
613
+ future: asyncio.Future[llm.GenerationCreatedEvent] = asyncio.Future()
614
+ if self._pending_reply is not None and not self._pending_reply.done():
615
+ self._pending_reply.cancel()
616
+ self._pending_reply = future
617
+ self._send(message)
618
+
619
+ def expire() -> None:
620
+ if not future.done():
621
+ future.set_exception(llm.RealtimeError("the server started no reply in time"))
622
+
623
+ handle = asyncio.get_running_loop().call_later(REPLY_TIMEOUT_S, expire)
624
+ future.add_done_callback(lambda _: handle.cancel())
625
+ return future
626
+
627
+ def commit_audio(self) -> None:
628
+ for chunk in self._bstream.flush():
629
+ self._send(chunk.data.tobytes())
630
+ self._send({"type": wire.INPUT_COMMIT})
631
+
632
+ def clear_audio(self) -> None:
633
+ self._bstream.clear()
634
+
635
+ def interrupt(self) -> None:
636
+ if self._generation is not None:
637
+ self._send({"type": wire.RESPONSE_CANCEL})
638
+
639
+ def truncate(
640
+ self,
641
+ *,
642
+ message_id: str,
643
+ modalities: list[Literal["text", "audio"]],
644
+ audio_end_ms: int,
645
+ audio_transcript: NotGivenOr[str] = NOT_GIVEN,
646
+ ) -> None:
647
+ pass # the server marks a reply cut off by barge-in itself
648
+
649
+ async def aclose(self) -> None:
650
+ if self._closing:
651
+ return
652
+ self._closing = True
653
+ self._configure_timer.cancel()
654
+ self._configured.set()
655
+ self._close_generation()
656
+ self._send_ch.close()
657
+ if self._call is not None:
658
+ await self._call.close()
659
+ await utils.aio.cancel_and_wait(self._main_atask)
@@ -0,0 +1 @@
1
+ __version__ = "0.1.1"
@@ -0,0 +1,212 @@
1
+ Metadata-Version: 2.4
2
+ Name: livekit-plugins-satham
3
+ Version: 0.1.1
4
+ Summary: Satham realtime speech-to-speech for LiveKit Agents
5
+ Project-URL: Homepage, https://satham.ai
6
+ Author: Satham
7
+ License-Expression: Apache-2.0
8
+ License-File: LICENSE
9
+ Keywords: livekit,livekit-agents,plugin,realtime,satham,speech-to-speech,voice-agent
10
+ Classifier: Development Status :: 3 - Alpha
11
+ Classifier: Framework :: AsyncIO
12
+ Classifier: Intended Audience :: Developers
13
+ Classifier: Operating System :: OS Independent
14
+ Classifier: Programming Language :: Python :: 3
15
+ Classifier: Programming Language :: Python :: 3 :: Only
16
+ Classifier: Programming Language :: Python :: 3.11
17
+ Classifier: Programming Language :: Python :: 3.12
18
+ Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
19
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
20
+ Classifier: Topic :: Software Development :: Libraries :: Python Modules
21
+ Classifier: Typing :: Typed
22
+ Requires-Python: >=3.11
23
+ Requires-Dist: livekit-agents~=1.8.12
24
+ Requires-Dist: satham~=0.1.1
25
+ Description-Content-Type: text/markdown
26
+
27
+ # livekit-plugins-satham
28
+
29
+ Satham's realtime speech-to-speech model (satham-1) as a `RealtimeModel` for LiveKit Agents. Your
30
+ LiveKit agent keeps its own instructions and tools; Satham hears the caller, ends turns, replies in
31
+ speech and handles barge-in, so the `AgentSession` needs no STT, LLM, TTS or VAD. The parameters
32
+ follow LiveKit's OpenAI `RealtimeModel`, so moving an agent from OpenAI to Satham is mostly a one-line
33
+ change.
34
+
35
+ LiveKit Agents 1.8; Python 3.11+.
36
+
37
+ ```sh
38
+ pip install livekit-plugins-satham
39
+ ```
40
+
41
+ ## Use
42
+
43
+ You pass your Satham endpoint and API key (or set `SATHAM_URL` and `SATHAM_API_KEY`); there is no
44
+ default server.
45
+
46
+ ```python
47
+ import os
48
+
49
+ from livekit.agents import (
50
+ Agent,
51
+ AgentServer,
52
+ AgentSession,
53
+ JobContext,
54
+ RunContext,
55
+ cli,
56
+ function_tool,
57
+ llm,
58
+ )
59
+ from livekit.plugins import satham
60
+
61
+
62
+ class SiteVisit(Agent):
63
+ def __init__(self) -> None:
64
+ # The agent's role and tools are Satham's instructions and tools, as they stand.
65
+ super().__init__(instructions="You are Asha, who books site visits for Example Homes.")
66
+
67
+ @function_tool
68
+ async def end_call(self, context: RunContext, reason: str = "done") -> llm.ToolResult:
69
+ """End the call when the conversation is over. Say a short goodbye in the same turn."""
70
+ await context.wait_for_playout() # let the goodbye finish
71
+ ... # hang up, e.g. delete the room
72
+ return llm.ToolResult("ended", reply_required=False)
73
+
74
+
75
+ server = AgentServer()
76
+
77
+
78
+ @server.rtc_session()
79
+ async def entrypoint(ctx: JobContext) -> None:
80
+ await ctx.connect()
81
+ session = AgentSession(
82
+ llm=satham.RealtimeModel( # was: openai.realtime.RealtimeModel(voice=...)
83
+ url=os.environ["SATHAM_URL"],
84
+ api_key=os.environ["SATHAM_API_KEY"],
85
+ greeting="Hello, this is Asha from Example Homes. Is this a good time?",
86
+ language="en",
87
+ language_switch="auto",
88
+ )
89
+ )
90
+ await session.start(agent=SiteVisit(), room=ctx.room)
91
+
92
+
93
+ if __name__ == "__main__":
94
+ cli.run_app(server)
95
+ ```
96
+
97
+ - **Instructions and tools.** The LiveKit agent's `instructions` become the call's instructions and
98
+ its `@function_tool`s the call's tools, with nothing else to set. Both can change mid-call
99
+ (`agent.update_instructions()`, `agent.update_tools()`).
100
+ - **The opening and fixed words.** With `greeting`, the agent says it first. Otherwise
101
+ `session.generate_reply(instructions=...)` asks for a reply now (Satham's `response.create`; use it in
102
+ `on_enter` to open the call), and `session.say(text)` speaks fixed words in the call's voice
103
+ (`response.say`) with no TTS. With neither, the caller speaks first.
104
+ - **Mid-call changes.** `model.update_options(...)` changes any control on every live call;
105
+ `session.current_agent.realtime_llm_session.update_options(...)` changes one call.
106
+ - **Language changes** are emitted as `session_updated` (a `satham.SessionUpdated`: the language, and
107
+ the reason `caller`, `reply` or `client`).
108
+
109
+ ## From OpenAI RealtimeModel to Satham
110
+
111
+ <!-- openai -->
112
+ | OpenAI `RealtimeModel` | Satham `RealtimeModel` | Supported | Notes |
113
+ | --- | --- | --- | --- |
114
+ | `model` | `model` | yes | default `"satham-1"` |
115
+ | `voice` | `voice` | yes | a Satham voice name, or a cloned voice's id |
116
+ | `modalities` | `modalities` | yes | `["audio", "text"]`, `["audio"]`, or `["text"]`, which hands the words to the session's TTS as OpenAI's text mode does |
117
+ | `temperature` | `temperature` | yes | |
118
+ | `turn_detection` | `turn_detection` | yes | `server_vad` and `semantic_vad` are both Satham's endpointing; `None`/`null` leaves turns to LiveKit; Satham adds `barge_in`, `continue_within_ms`, ... |
119
+ | `input_audio_noise_reduction` | `input_audio_noise_reduction` | yes | `near_field` or `far_field`; `"none"` turns it off, and null keeps the server's default (on); Satham adds `strength_db` and `apply_to_transcription` |
120
+ | `input_audio_transcription` | `input_audio_transcription` | partly | `enabled` and `code_mixed`; Satham transcribes with its own models, so OpenAI's `model` and `prompt` are ignored |
121
+ | `max_response_output_tokens` | `max_response_output_tokens` | yes | or `"inf"` |
122
+ | `speed` | `speed` | yes | |
123
+ | `tool_choice` | `tool_choice` | yes | preview: needs a server with tool support |
124
+ | `api_key` | `api_key` | yes | your Satham key |
125
+ | `base_url` | `url` | yes | your Satham endpoint |
126
+ | Agent instructions | Agent instructions | yes | can change mid-call |
127
+ | `generate_reply()` | `generate_reply()` | yes | `response.create`; `instructions` guide that reply alone |
128
+ | `session.say()` | `session.say()` | yes | `response.say`, no TTS needed (agents-js: call it on the realtime session) |
129
+ | tracing, truncation, reasoning | - | no | not applicable |
130
+ | azure_deployment, entra_token, api_version | - | no | not applicable |
131
+ | max_session_duration, conn_options | - | no | `connect_timeout` / `connectTimeoutMs` instead |
132
+ <!-- /openai -->
133
+
134
+ ## Controls
135
+
136
+ Every keyword of `RealtimeModel(...)` and `update_options(...)` besides `url`, `api_key` and
137
+ `connect_timeout`. `modalities`, `turn_detection` and `input_audio_transcription` also decide what the
138
+ model tells LiveKit it does, so they are fixed for a model once made. Controls you leave out are not
139
+ sent; values are checked against these ranges, or the server's from `GET /v1/info`.
140
+
141
+ The controls marked "needs session controls" need a Satham server with session controls (its
142
+ `GET /v1/info` lists `controls`, as the server does since 2026-11-16); an older server refuses them
143
+ when the call starts. `greeting` and `agent` belong to the start of a call. Setting
144
+ `input_audio_noise_reduction`'s `mode` alone resets `strength_db` to that mode's preset, so send both
145
+ to keep a custom strength; `None` leaves noise reduction at the server's default (on), and `"none"`
146
+ turns it off. `agent` is an optional
147
+ preset on the server and is not needed.
148
+
149
+ <!-- controls -->
150
+ | Option | Range | Default | OpenAI equivalent | Notes |
151
+ | --- | --- | --- | --- | --- |
152
+ | `instructions` | text, up to 16000 characters | none | - | the agent's role; from the LiveKit agent or Pipecat context in the adapters |
153
+ | `greeting` | text, up to 1000 characters | none | - | said first; without one the caller speaks first |
154
+ | `tools` | up to 128 functions | none | - | preview: needs a server with tool support |
155
+ | `tool_choice` | see notes | "auto" | `tool_choice` | "auto", "none", "required" or one function |
156
+ | `agent` | text, up to 64 characters | none | - | optional: a preset agent on the server, such as a demo's |
157
+ | `model` | text, up to 64 characters | "satham-1" | `model` | "satham-1" only today; needs session controls |
158
+ | `modalities` | list | ["audio", "text"] | `modalities` | ["audio", "text"], ["audio"], or ["text"]: words only, for your own TTS; needs session controls |
159
+ | `language` | `auto`, `hi`, `ta`, `te`, `kn`, `bn`, `pa`, `en` | "auto" | - | |
160
+ | `language_switch` | `auto`, `off`, or `None` | "auto" | - | |
161
+ | `voice_on_language_switch` | `keep`, `native`, or `None` | "keep" | - | |
162
+ | `turn_detection.enabled` | `True` / `False` | true | `turn_detection=None` | false (or turn_detection=None): the client ends each turn; needs session controls |
163
+ | `turn_detection.type` | `server_vad`, `semantic_vad` | "server_vad" | `turn_detection.type` | needs session controls |
164
+ | `turn_detection.threshold` | 0.1 to 0.95 | 0.5 | `turn_detection.threshold` | the speech detector's threshold; needs session controls |
165
+ | `turn_detection.eagerness` | `auto`, `low`, `medium`, `high` | "auto" | `turn_detection.eagerness` | semantic_vad's end-of-turn wait; needs session controls |
166
+ | `turn_detection.prefix_padding_ms` | 0 to 1000 | 300 | `turn_detection.prefix_padding_ms` | needs session controls |
167
+ | `turn_detection.min_speech_ms` | 50 to 1000 | 100 | - | needs session controls |
168
+ | `turn_detection.silence_duration_ms` | 150 to 2000 | 350 | `turn_detection.silence_duration_ms` | server_vad's end-of-turn wait; needs session controls |
169
+ | `turn_detection.create_response` | `True` / `False` | true | `turn_detection.create_response` | answer each turn at once; needs session controls |
170
+ | `turn_detection.interrupt_response` | `True` / `False` | true | `turn_detection.interrupt_response` | barge-in on or off; needs session controls |
171
+ | `turn_detection.barge_in.min_speech_ms` | 0 to 2000 | 400 | - | needs session controls |
172
+ | `turn_detection.barge_in.min_probability` | 0 to 1 | 0.8 | - | needs session controls |
173
+ | `turn_detection.barge_in.min_dbfs` | -90 to 0, or `None` | -40 | - | needs session controls |
174
+ | `turn_detection.continue_within_ms` | 0 to 5000, or `None` | 2000 | - | the caller carrying on in the same turn; null: off; needs session controls |
175
+ | `turn_detection.continue_max_heard_ms` | 0 to 5000 | 1000 | - | needs session controls |
176
+ | `input_audio_noise_reduction.enabled` | `True` / `False` | true | `input_audio_noise_reduction={"type": "none"}` | false, "none" or {"type": "none"}: off; needs session controls |
177
+ | `input_audio_noise_reduction.mode` | `near_field`, `far_field` | "near_field" | `input_audio_noise_reduction.type` | resets strength_db to the mode's preset (12 or 30 dB) unless both are sent; needs session controls |
178
+ | `input_audio_noise_reduction.strength_db` | 0 to 100 | 12 | - | needs session controls |
179
+ | `input_audio_noise_reduction.apply_to_transcription` | `True` / `False` | false | - | needs session controls |
180
+ | `input_audio_transcription.enabled` | `True` / `False` | true | `input_audio_transcription=None` | transcript events to the client; needs session controls |
181
+ | `input_audio_transcription.code_mixed` | `True` / `False` | true | - | English words in Latin script, and digits; needs session controls |
182
+ | `voice` | text, up to 64 characters | the language's | `voice` | |
183
+ | `breaths` | `True` / `False`, or `None` | off | - | |
184
+ | `natural_pauses` | `True` / `False`, or `None` | off | - | |
185
+ | `continuation` | `True` / `False`, or `None` | true | - | each phrase carries on from the one before; needs session controls |
186
+ | `speed` | 1 to 1 | 1.0 | `speed` | 1.0 only today; needs session controls |
187
+ | `phrasing.first_phrase_max_chars` | 1 to 120 | 120 | - | at least min_phrase_chars; needs session controls |
188
+ | `phrasing.min_phrase_chars` | 1 to 120 | 20 | - | needs session controls |
189
+ | `normalise_numbers` | `True` / `False` | true | - | numbers and amounts said as words; needs session controls |
190
+ | `pronunciations` | word to respelling | none | - | {word: respelling}, up to 200; needs session controls |
191
+ | `temperature` | 0.6 to 1.2 | 0.7 | `temperature` | needs session controls |
192
+ | `top_p` | 0.05 to 1 | 0.8 | - | needs session controls |
193
+ | `max_response_output_tokens` | 1 to 4096 | 320 | `max_response_output_tokens` | or "inf"; never above the server's; needs session controls |
194
+ | `tone` | `auto`, `conversational`, `happy`, `sad`, `excited`, `professional` | "auto" | - | "auto": the model picks; needs session controls |
195
+ | `repeat_guard` | `True` / `False` | true | - | re-asks a reply that repeats a recent one; needs session controls |
196
+ | `drift_guard` | `True` / `False` | true | - | keeps replies in the call's language; needs session controls |
197
+ <!-- /controls -->
198
+
199
+ ## Text mode, manual turns, tools, interruptions
200
+
201
+ - **`modalities=["text"]`.** The agent's words go to the `AgentSession`'s TTS, as with OpenAI's text
202
+ mode; give the session a `tts`.
203
+ - **`turn_detection=None`.** LiveKit's own turn detection (the session's VAD and turn detector) ends
204
+ each turn: the plugin commits the caller's audio, and `generate_reply()` returns the reply.
205
+ - **Tools (preview: they need a Satham server with tool support).** Each call the agent makes runs
206
+ your tool; its result goes back to the server, which replies unless the tool returns
207
+ `llm.ToolResult(..., reply_required=False)`.
208
+ - **Interruptions.** The caller speaking over the agent interrupts it and the playout stops at once.
209
+ LiveKit mutes the caller for the first 3 s of agent speech by default (`AgentSession(
210
+ aec_warmup_duration=3.0)`, off for SIP calls); set it to `None` where echo cancellation is good.
211
+ - **Not supported:** video, and reconnection (a dropped connection ends the call with an
212
+ unrecoverable error).
@@ -0,0 +1,9 @@
1
+ livekit/plugins/satham/__init__.py,sha256=CWgijFZ4HAzfz7pVOIDhos3KVBafNF2Y20Rh1Upj5nk,727
2
+ livekit/plugins/satham/log.py,sha256=gJ9jmr7uUuoMQiPoXsF2f1F1Rh9tM5vJMa2pXCLCEm8,69
3
+ livekit/plugins/satham/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
4
+ livekit/plugins/satham/realtime.py,sha256=UDBu3sqjW3JfDMzyrdkw8TWrFhkW7su8jMwRKErnMJc,28976
5
+ livekit/plugins/satham/version.py,sha256=rnObPjuBcEStqSO0S6gsdS_ot8ITOQjVj_-P1LUUYpg,22
6
+ livekit_plugins_satham-0.1.1.dist-info/METADATA,sha256=jGvVts2Y0_Bn3h3p04T1KqhS6Eh0IpPzqRgLC1-DfHI,13251
7
+ livekit_plugins_satham-0.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
8
+ livekit_plugins_satham-0.1.1.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
9
+ livekit_plugins_satham-0.1.1.dist-info/RECORD,,
@@ -0,0 +1,4 @@
1
+ Wheel-Version: 1.0
2
+ Generator: hatchling 1.27.0
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.