"""Background reply generation. Generation used to be driven by the SSE request: the browser opening the stream was what produced the tokens, so navigating away cancelled the reply mid- sentence. Here it runs as its own task instead, and the SSE endpoint merely *follows* it. Closing the page, opening another chat, or starting a new one leaves the answer being written; coming back attaches to it and immediately receives everything produced so far. The registry is in-process, which is right for the single-worker deployment this ships with. Several workers would need the state in the database or a broker, because the request that follows a generation would not necessarily land in the process running it. """ from __future__ import annotations import asyncio import contextlib import json import logging import time import uuid from dataclasses import dataclass, field, replace from datetime import UTC, datetime, timedelta from sqlalchemy import select from lembas.db.models import KIND_AGENT, ROLE_ASSISTANT, ROLE_USER, Chat, Message, User from lembas.db.session import session_scope from lembas.services import canvas as canvas_service from lembas.services import chat as chat_service from lembas.services import compaction as compaction_service from lembas.services import interaction, settings_store, tokens, tool_labels from lembas.services import metrics as metrics_service from lembas.services import prompts as prompts_service from lembas.services import tools as tools_service from lembas.services.agent import policy as agent_policy from lembas.services.agent import session as agent_session from lembas.services.agent import tools as agent_tools from lembas.services.llm.openai_client import ( LLMError, chunk_usage, delta_reasoning, delta_text, delta_tool_calls, stream_chat, ) from lembas.services.reasoning import REASONING, ReasoningSplitter from lembas.services.tools import ToolOutcome log = logging.getLogger(__name__) # How often the partial answer is offered to followers. Markdown is re-rendered # whole each time -- a list or a code fence is only correct once its context # exists -- so this trades a little work for formatting that appears as the # model writes. 100ms is below the threshold where the eye reads it as stepping. RENDER_INTERVAL = 0.1 # Finished generations linger so a follower attaching at the last moment still # gets the final frames, then are pruned. KEEP_FINISHED = timedelta(minutes=5) # What "no ceiling" resolves to. A setting of 0 means an administrator does not # want a round limit, but a loop needs *some* stop or a model stuck calling one # cheap tool runs until the process does. This is high enough never to be # reached by anything but that. MAX_TOOL_ROUNDS = 200 # How many times in a row a reply that stopped with plan tasks outstanding may # be told to carry on. Two, so a model that genuinely has nothing left to do can # say so and be believed rather than argued with indefinitely. MAX_NUDGES = 2 # How much of the window a request may occupy before the next round is refused. # A tool round appends an assistant turn and a tool turn per call, so a reply # that keeps calling tools grows its own request until the endpoint refuses it -- # and `_maybe_compact` runs once, before the first round, so nothing was watching # it after that. The only other guard, `max_total_output_bytes`, defaults to a # megabyte, which is about 260k tokens: larger than the window of nearly every # model this talks to, so it never fired first. # # The tenth left over is room to answer in. Stopping with an explanation beats an # upstream error that says only that the request was too long. CONTEXT_HEADROOM = 0.9 @dataclass class Generation: """The live state of one reply being written.""" chat_id: str message_id: str content: list[str] = field(default_factory=list) reasoning: list[str] = field(default_factory=list) reasoning_ms: int = 0 # One entry per tool call made while producing this reply, in order. Shown # live as the model works and kept on the message afterwards. tool_events: list[dict] = field(default_factory=list) # --- What it cost -------------------------------------------------------- # Prompt and completion are summed across tool rounds: what the reply cost. # context_tokens is overwritten each round with that round's prompt plus # completion, because a three-round reply pays for its prompt three times # but only ever occupies the window once. prompt_tokens: int = 0 completion_tokens: int = 0 context_tokens: int = 0 context_limit: int = 0 # Filled from the assembled request before the first chunk, so a follower # has a percentage to show while the reply is still being written -- real # usage only arrives in a single chunk at the very end. prompt_estimate: int = 0 # Every round's estimate added up, against `prompt_estimate` being only the # latest. The two answer different questions and both are wanted: what the # reply *cost* is the sum, because a three-round reply pays for its prompt # three times; what it *occupies* is the last one. That is exactly the split # the reported figures already use between `prompt_tokens` and # `context_tokens`, so the fallback mirrors it rather than inventing a # second convention. prompt_estimate_total: int = 0 rounds: int = 0 # time.monotonic() at the start. A field rather than a local in `_run` # because `_follow` is a different function that sees only this object, and # without it there is nothing to compute a live tokens/second against. started_at: float = 0.0 elapsed_ms: int = 0 error: str = "" stopped: bool = False done: bool = False # Bumped on every change. Followers compare against it rather than being # woken individually: with a 100ms cadence a short poll is simpler than # future bookkeeping, and cannot drop a wakeup. version: int = 0 # What the reply is doing when it is not producing tokens. Shown in the # streaming bubble, because a silent multi-second pause before the first # token is what a hang looks like. status: str = "" # Number of browsers currently watching. Decides whether a finished reply # counts as unread. followers: int = 0 finished_at: datetime | None = None cancel: bool = False # Set while the reply is stopped waiting for a person -- an approval, or a # question the model asked. None at every other moment. Read by `_follow`, # which sends the card, and by `request_stop`, which resolves it: `cancel` # is otherwise only ever read between streamed chunks, and there are no # chunks while this is set. pending: interaction.Interruption | None = None # Seconds spent waiting for a person, cumulative. Taken off the wall-clock # budget so that thinking time is the model's and not the reader's. waited: float = 0.0 # How much tool output this reply has handed back, against the agent budget. # A model that fills its own context with build logs has no room left to # answer with. output_bytes: int = 0 # A plan proposed in Plan mode, or one being kept current while it is # carried out. See services/plans.py for the shape. Written onto the # message, so the Execute button sends exactly what was proposed rather than # something parsed back out of prose. plan: dict | None = None # Whether that plan came from `plan_submit`, which ends the turn, rather # than from `plan_update`, which does not. Both write `plan` so that # `_persist` stays one writer with one rule; only this decides whether the # tools are withdrawn for a final round. plan_final: bool = False # Which files this reply has put in the canvas panel. Seeded once from # `chat.canvas_json` where `_run` already has the chat loaded, then mutated # in place -- two `file_read` calls in one round that each re-read the row # would leave only the second, which is the lost update `plan` above # documents. Folded back by `_persist`, the single writer. canvas: dict = field(default_factory=dict) # The queue, seen from the reply's side. `drained` says this reply's ending # handed the next waiting prompt to a fresh one; `injected_ids` names the # prompts taken into *this* reply between two rounds of tool calls. Both are # read only by `_follow`, which turns them into bubbles on the `done` frame # -- the one frame that reaches a browser after a reply is over. drained: bool = False injected_ids: list[str] = field(default_factory=list) # How many times *in a row* this reply has ended with plan tasks still open # and been told to carry on. Reset the moment it calls a tool again, so the # count is of consecutive stops rather than of stops in total. nudges: int = 0 def touch(self) -> None: self.version += 1 @property def text(self) -> str: return "".join(self.content) @property def thinking(self) -> str: return "".join(self.reasoning) _RUNNING: dict[str, Generation] = {} _TASKS: dict[str, asyncio.Task] = {} def get(message_id: str) -> Generation | None: return _RUNNING.get(message_id) def request_stop(message_id: str) -> bool: """Ask a running generation to stop. Returns whether one was found.""" generation = _RUNNING.get(message_id) if generation is None or generation.done: return False generation.cancel = True # A paused reply produces no chunks, and the chunk loop is the only place # `cancel` is ever read -- so without this, Stop does nothing at all while # an approval card is on screen. Resolving the pause is the wakeup; `_run` # then takes its ordinary stopped path rather than needing a second branch. if generation.pending is not None: generation.pending.resolve(interaction.CANCELLED) return True def answer( chat_id: str, interaction_id: str, *, verdict: str = "", answers: dict[str, str] | None = None, ) -> bool: """Resolve whichever running reply is parked on this interruption. A linear scan of the registry: it holds one entry per reply in flight, and this runs at human speed. Scoped to the chat because the caller has already checked that this reader owns *that* chat, and an id alone would not. """ for generation in _RUNNING.values(): pending = generation.pending if generation.chat_id != chat_id or pending is None or pending.id != interaction_id: continue outcome = verdict if verdict in _VERDICTS else interaction.ANSWER return pending.resolve(outcome, answers=answers) return False def pending_items(chat_id: str, interaction_id: str) -> tuple[interaction.Item, ...]: """What the card this chat is waiting on is asking about. For the route that has to record what "always" meant. It must be read *before* the pause is resolved: `interaction.wait_for` clears `generation.pending` in its `finally`, so a moment later there is nothing left to read and "always" would silently remember nothing. Empty when there is no such pause -- already answered, timed out, or the server restarted -- which is the same answer `answer` gives, and means a stale card records nothing rather than half of something. """ for generation in _RUNNING.values(): pending = generation.pending if generation.chat_id != chat_id or pending is None or pending.id != interaction_id: continue return pending.items return () def running_for(chat_id: str) -> Generation | None: """The reply being written in this chat, if there is one. A linear scan for the reason `answer` gives above: one entry per reply in flight, consulted at human speed. `_prune` first, because a finished generation lingers `KEEP_FINISHED` so that late followers still get the final frames -- and without the sweep those five minutes would look like a chat that is permanently busy, and queue everything typed into it. """ _prune() for generation in _RUNNING.values(): if generation.chat_id == chat_id and not generation.done: return generation return None _VERDICTS = (interaction.ALLOW, interaction.ALLOW_ALWAYS, interaction.DENY) def _prune() -> None: cutoff = datetime.now(UTC) - KEEP_FINISHED now = time.monotonic() for message_id, generation in list(_RUNNING.items()): # A paused reply is deliberately not `done` -- a page reload has to be # able to reattach to it. Its timeout is what stops it lingering, and # this is the belt to that pair of braces: a deadline long past means # the timeout did not fire, and a task parked forever is worse than one # that gives up. pending = generation.pending if pending is not None and now > pending.expires_at + KEEP_FINISHED.total_seconds(): log.warning("resolving a stuck interaction on message %s", message_id) pending.resolve(interaction.EXPIRED) if generation.done and generation.finished_at and generation.finished_at < cutoff: _RUNNING.pop(message_id, None) _TASKS.pop(message_id, None) def ensure(chat_id: str, message_id: str) -> Generation: """Start generating this reply if it is not already under way. Idempotent, because more than one thing can ask for it: the route that created the message, and any page load that finds the message unfinished. `_prune` runs first, not after the lookup. Below it, a stale entry could never expire: the early return is the only path a repeated id takes, so the sweep was unreachable for exactly the message that needed it. """ _prune() existing = _RUNNING.get(message_id) if existing is not None: return existing generation = Generation(chat_id=chat_id, message_id=message_id) _RUNNING[message_id] = generation _TASKS[message_id] = asyncio.create_task(_run(generation)) return generation def restart(chat_id: str, message_id: str) -> Generation: """Produce this reply again, discarding any finished attempt at it. `ensure` is idempotent on purpose, and that is load-bearing: a page load finding an unfinished reply must attach to it rather than start a second one, and `_follow` calls it too. Regeneration is the one caller that means the opposite. It is also the one caller that reuses an existing Message row -- blanked and marked incomplete -- rather than creating a new one. The finished Generation for that id is still in the registry, because finished ones linger KEEP_FINISHED so a follower arriving at the last moment still gets the final frames. `ensure` handed that one straight back: no request was made, `_follow` replayed the previous answer, and the `done` frame re-rendered a streaming shell because the row said incomplete. That was the reconnect loop, and the Send button stuck on Stop. """ previous = _RUNNING.pop(message_id, None) task = _TASKS.pop(message_id, None) if previous is not None and not previous.done: previous.cancel = True if task is not None: task.cancel() return ensure(chat_id, message_id) async def shutdown() -> None: """Stop every running generation, keeping what each has produced.""" for task in list(_TASKS.values()): task.cancel() for task in list(_TASKS.values()): with contextlib.suppress(asyncio.CancelledError, Exception): await task async def _run(generation: Generation) -> None: """Produce one reply, then persist it. Never raises into the task. A reply is not necessarily one request. When tools are offered and the model asks to use one, the loop below runs it, appends the result to the conversation and asks again -- up to tools_service.MAX_ROUNDS times, after which the model has to answer with what it has. Text produced before a tool call is kept, so a model that narrates what it is about to look up does not lose that when the results come back. """ splitter = ReasoningSplitter() started = time.monotonic() generation.started_at = started reasoning_started: float | None = None question = "" endpoint = model_id = None needs_title = False title_prompt = "" # Bound before the try, because the finally clears the credential on it and # a chat that has been deleted returns before it would otherwise be set. tool_context = None try: # Before the request is assembled, so build_request is called once and # what goes out is the compacted conversation -- there is no second # assembly path. Here rather than in post_message because that route's # whole contract is to return immediately, and a three-second # summarisation in front of it would break exactly that. await _maybe_compact(generation) # Before the session opens, for the same reason compaction is: the # listing is an SSH round trip, and holding a database session across # one to save opening a second is the wrong trade. `build_request` # below reads whatever this left in the cache and never fetches. await _warm_project(generation) with session_scope() as db: chat = db.get(Chat, generation.chat_id) message = db.get(Message, generation.message_id) if chat is None or message is None: generation.error = "That chat no longer exists." return endpoint, model_id = chat_service.resolve_endpoint(db, chat) owner = db.get(User, chat.user_id) # Read while the session is open: everything below outlives it. # Resolved once, so that what the loop is allowed to *run* is the # same set the endpoint was *offered* -- not whatever happens to # exist by the time a call comes back. toolset = tools_service.resolve_tools(db, chat, owner) offered = toolset.schemas payload = chat_service.build_request( db, chat, upto=message, tools=offered, user=owner ) question = _question_from(payload) needs_title = not chat.title_generated # An agent chat is titled from its opening words and never costs a # model call for it. That prompt is a good title already -- somebody # starting one states an objective, not a topic -- while an ordinary # chat opens with a question, whose answer is what makes a title # worth asking for. Read here with the rest, because titling happens # after this session has closed. title_from_prompt = chat.kind == KIND_AGENT # Seeded once, here, where the chat is already loaded. Mutated from # then on; see the field's own note. generation.canvas = { "tabs": list((chat.canvas_json or {}).get("tabs") or []), "active": (chat.canvas_json or {}).get("active") or "", } # Read here, with the rest, because titling happens after this # session has closed and must not open another one. title_prompt = prompts_service.resolve(db, "task.title") tool_context = tools_service.context_for(db, owner, chat, tools=toolset) model = chat_service.model_for(db, chat) generation.context_limit = model.context_length if model is not None else 0 # Kept for `_inject`, which builds a user turn after this session # has closed. A turn taken in mid-reply has to be shaped exactly as # the same words typed a moment later would have been -- images to a # vision model, a plain string to anything else, or the endpoint # rejects the whole request. vision = chat_service.model_supports(db, chat, "vision") chat_rounds = settings_store.chat_rounds(db) nudge_enabled = bool(settings_store.agents(db).get("nudge_unfinished")) limits = tool_context.agent.limits if tool_context.agent else None # A ceiling, not a schedule -- the loop below ends the moment a round # produces no tool calls, which is the model saying it is done. Zero # means an ordinary chat has no ceiling either; `steps` is already a # runaway backstop rather than a budget, so an agent chat is bounded by # tokens and the clock instead. budget = limits.steps if limits else (chat_rounds or MAX_TOOL_ROUNDS) # Set once a budget has run out, holding the last round open with the # tools withdrawn so the reply ends in an answer rather than in silence. # See `_wrap_up`. `budget + 2` rather than `+ 1` is that extra round: # the iteration at `budget` is where the overrun is noticed, and the one # after it is where the model gets to say what it found. wrapping_up = False for round_number in range(budget + 2): generation.rounds = round_number + 1 # Recomputed every round, against once before the loop. The request # grows by an assistant turn and a tool turn per call each time, so # a single estimate taken up front described the first round and # nothing after it -- and for the endpoints that send no usage block # at all (llama.cpp, Ollama and friends) that estimate *is* the # figure everything downstream reports. A forty-round reply showed # the first round's prompt as the whole reply's. generation.prompt_estimate = tokens.estimate_request(payload) generation.prompt_estimate_total += generation.prompt_estimate # Before spending a request that cannot fit. Outside the agent # branch below on purpose: an ordinary chat with a round budget can # fill a small window too, and `context_limit` is what decides, # not what kind of chat it is. # The one budget that still stops dead rather than asking for a final # answer. Every other one can afford one more request; this one is # the finding that there is no room for a request, and a wrap-up # round would be the same overflow with an upstream error instead of # an explanation. if round_number and _too_big(generation): _gave_up(generation, "with no room left in the context window") break # Checked between rounds, never mid-stream: cutting a reply off in # the middle of a sentence to enforce a budget produces garbage, and # Stop already covers the mid-stream case. Time spent waiting for a # person is subtracted -- somebody who thinks for ten minutes about # one command should not thereby spend the whole allowance. if limits is not None and round_number and not wrapping_up: spent = (time.monotonic() - started) - generation.waited ran_out = "" if spent > limits.wall_seconds: ran_out = f"after {spent / 60:.0f} minutes" elif generation.output_bytes > limits.output_bytes: ran_out = "with too much output to read" else: written = _written(generation) if limits.completion_tokens and written > limits.completion_tokens: ran_out = f"after writing about {written:,} tokens" if ran_out: offered, payload = _wrap_up(generation, ran_out, payload) wrapping_up = True accumulator = tools_service.ToolCallAccumulator() # Text the model produced in *this* round, needed separately from # generation.content when echoing the assistant turn back. round_text: list[str] = [] async for chunk in stream_chat(endpoint, payload): counts = chunk_usage(chunk) if counts is not None: generation.prompt_tokens += counts.get("prompt_tokens", 0) generation.completion_tokens += counts.get("completion_tokens", 0) # Overwritten, not summed: this round's prompt already # contains every earlier round. generation.context_tokens = counts.get("prompt_tokens", 0) + counts.get( "completion_tokens", 0 ) generation.touch() thought = delta_reasoning(chunk) if thought: if reasoning_started is None: reasoning_started = time.monotonic() generation.reasoning.append(thought) generation.touch() if offered: fragments = delta_tool_calls(chunk) if fragments: accumulator.feed(fragments) text = delta_text(chunk) if text: for kind, piece in splitter.feed(text): if kind == REASONING: if reasoning_started is None: reasoning_started = time.monotonic() generation.reasoning.append(piece) else: if reasoning_started is not None and not generation.reasoning_ms: generation.reasoning_ms = int( (time.monotonic() - reasoning_started) * 1000 ) generation.content.append(piece) round_text.append(piece) generation.touch() if generation.cancel: generation.stopped = True break # Let followers and other tasks run between chunks. await asyncio.sleep(0) # The round is over, so anything the splitter is still holding back # against a `` tag split across chunks is not a tag. Flushed # here rather than only after the loop, because `round_text` is # echoed back as an assistant turn -- for a tool round and for a # nudge alike -- and a turn missing its last few words is a turn the # model is asked to continue from having apparently trailed off. for kind, piece in splitter.flush(): if kind == REASONING: generation.reasoning.append(piece) else: generation.content.append(piece) round_text.append(piece) calls = accumulator.calls if generation.stopped or not calls: # The model says it is done. Believe it -- unless this is an # agent chat whose plan still has work in it, in which case ask # once. `_nudge` returns the turn to send, or None. added = _nudge( generation, tool_context, enabled=nudge_enabled, stopped=generation.stopped, round_number=round_number, budget=budget, ) if added is None: break # Its own words go back with the nudge. Without the assistant # turn the model is asked to carry on from a transcript in which # it never spoke, and repeats itself. said = "".join(round_text).strip() messages = [*payload["messages"]] if said: messages.append({"role": "assistant", "content": said}) payload = {**payload, "messages": [*messages, added]} continue # Something was called, so whatever it said it had finished, it had # not. The count is of *consecutive* stops. generation.nudges = 0 if round_number >= budget: # Out of rounds with the model still asking for tools. # # The tools are withdrawn and it is asked once more, rather than # the reply simply ending here. A model that goes straight to # tool calls has written no prose at all by this point, so # breaking produced an empty bubble with an error line under it # -- somebody watching a good piece of research get to its sixth # search saw the whole thing thrown away. What it has gathered is # in the transcript either way; one more request turns it into an # answer. # # `budget`, not `MAX_ROUNDS`. The loop is sized by the budget # above and the message below has always reported it, but the # comparison was against the global 3 -- so an agent chat allowed # forty steps stopped after three and said it had taken forty. # Two numbers, one of them wrong, in code whose whole job is to # say what happened. howmany = "one round" if budget == 1 else f"{budget} rounds" offered, payload = _wrap_up( generation, f"after {howmany} of tool calls", payload, name=calls[0]["name"], ) if wrapping_up: # Already asked, and it called a tool anyway -- which it # cannot do, since none were offered. A backstop, not a path. break wrapping_up = True continue # Parsed once, here, and shared by everything below: the approval # card, `policy.decide`, and the runner. See `_arguments_for`. arguments = _arguments_for(tool_context, calls) # The mode and the chat's allow list, re-read. Both are things a # person changes *while watching this reply*, and both were # snapshotted for its whole life -- so switching to Auto went on # asking about every call, and "Always allow this" was stored and # then ignored until the next turn. Between rounds, never within # one: what this round has already queued was decided under the mode # that was in force when it was queued. _refresh_agent(tool_context) # Decided before anything runs, never during. A round's calls run # together under a semaphore, and four people-shaped pauses inside # that gather would queue behind each other invisibly -- see # services/interaction.py. decided, allowed, edited = await _authorise( generation, tool_context, calls, arguments ) if generation.stopped: break messages = [ # The **raw** arguments string, not the parsed dict: the # endpoint has to see back exactly what it sent, or an # id-matching server pairs its own call with something it does # not recognise. # # Built after `_authorise` rather than before it, because a # command corrected on the approval card is written back into # `calls` there. The other order sent the model the command it # proposed while a different one ran, and every later round # reasoned from a transcript that was quietly false. *payload["messages"], tools_service.assistant_turn(calls, "".join(round_text)), ] generation.status = _tool_status(calls) generation.touch() try: outcomes = await _run_calls( tool_context, calls, arguments, decided=decided, allowed=allowed ) finally: generation.status = "" generation.touch() for index, (call, outcome) in enumerate(zip(calls, outcomes, strict=True)): if index in edited: # A command somebody corrected on the card is theirs, not # the model's. Shown as such, for the same reason a plan # goes back quoted and attributed: text must not arrive # wearing an authorship it does not have, in either # direction. outcome.event["edited"] = True generation.tool_events.append(outcome.event) generation.output_bytes += len(outcome.content) messages.append(tools_service.tool_turn(call, outcome.content)) if opened := outcome.event.get("canvas"): # A runner cannot write the message row, so the loop carries # this exactly as it carries a merged plan. Never activated: # an agent reads forty files in a long reply, and dragging # somebody through all of them -- or away from a file they # are editing -- is what makes a panel like this unusable. canvas_service.open_tab(generation.canvas, opened, activate=False) if outcome.event.get("plan"): generation.plan = outcome.event["plan"] # Only `plan_submit` sets this. `plan_update` writes the # same key -- so `_persist` stays one writer with one # rule -- but is bookkeeping mid-work and must not end the # reply, or the turn would stop dead every time a task was # ticked off. if outcome.event.get("plan_final"): generation.plan_final = True generation.touch() # Something typed while this reply was working. Taken in here, at a # round boundary, rather than made to wait for the whole reply: an # agent that has just finished one loop and is about to start # another is exactly when "actually, do it the other way" is worth # having. # # Only while there is a round left to answer in. Injecting into the # last one would deliver the prompt into a reply that then runs out # of budget without addressing it -- and it is marked delivered, so # nothing would ever send it again. Below that line it waits for # `_drain`, which always gives it a reply of its own. if round_number + 1 < budget and ( added := _inject(generation, generation.chat_id, vision) ): messages.append(added) payload = {**payload, "messages": messages} # A plan ends the turn. One more request so the model can say what # it proposed and why -- a bubble containing only a card reads as # though it had nothing to add -- but with the tools withdrawn, so # "one more round" cannot become three rounds of it changing its # mind about a plan the reader is being asked to approve. if generation.plan_final: offered = [] payload.pop("tools", None) for kind, piece in splitter.flush(): (generation.reasoning if kind == REASONING else generation.content).append(piece) generation.touch() except LLMError as exc: generation.error = exc.message log.info("generation failed for chat %s: %s", generation.chat_id, exc.message) except asyncio.CancelledError: # Shutdown, not a reader navigating away -- that no longer reaches here. generation.stopped = True raise except Exception: # noqa: BLE001 - a task that dies silently is worse generation.error = "Something went wrong while generating this reply." log.exception("unexpected generation failure for chat %s", generation.chat_id) finally: if reasoning_started is not None and not generation.reasoning_ms: generation.reasoning_ms = int((time.monotonic() - reasoning_started) * 1000) generation.elapsed_ms = int((time.monotonic() - started) * 1000) if not generation.completion_tokens: # The endpoint reported nothing, so fall back to the estimate. Marked # as such everywhere it is shown -- four characters to a token is # wrong enough on code and CJK to be worth saying out loud. generation.completion_tokens = tokens.estimate( generation.text + generation.thinking ) # Mirroring the reported figures exactly: the prompt is summed # across rounds because it was paid for each time, while what the # reply *occupies* is the last round's prompt plus what was written. # Both used to come from one estimate taken before the first round. generation.prompt_tokens = ( generation.prompt_estimate_total or generation.prompt_estimate ) generation.context_tokens = generation.prompt_estimate + generation.completion_tokens # Naming the chat is a second, short completion, so it has to happen # here rather than in the synchronous persist step below. Best-effort: # a chat title is never worth surfacing an error for. title = "" if needs_title and question: if title_from_prompt or generation.error or endpoint is None: title = chat_service.fallback_title(question) else: with contextlib.suppress(Exception): title = await chat_service.generate_title( endpoint, model_id, question, generation.text, template=title_prompt, ) title = title or chat_service.fallback_title(question) # The decrypted SSH credential dies with the reply rather than with the # object holding it. A finished Generation lingers KEEP_FINISHED so a # follower arriving at the last moment still gets the final frames, and # a private key should not sit in memory for five minutes waiting on # that. if tool_context is not None and getattr(tool_context, "agent", None) is not None: tool_context.agent.clear() # Written *before* `done`, because `_follow` breaks out of its loop the # moment it sees that flag and immediately re-renders the bubble from # the row. The other order left a window in which the finished frame # showed the previous turn's stored values. _persist(generation, title, time.monotonic() - started) # After the row is authoritative and before `done`, for the same reason # `_persist` is: `_follow` breaks the instant it sees that flag, and the # frame it then sends is the one that has to carry the next turn's # bubbles. There is no push channel that outlives a single reply. _drain(generation) generation.done = True generation.finished_at = datetime.now(UTC) generation.touch() # How long a reply will wait for a directory listing before starting without # one. Short on purpose: the listing is a convenience and the reply is the # thing somebody is waiting for. A walk that outruns this keeps going in the # background and the next turn has it. INDEX_WAIT = 6.0 async def _warm_project(generation: Generation) -> None: """Fill this chat's project caches: the directory listing, and AGENTS.md. Never raises and never blocks for long. `harness` reads both caches synchronously while assembling the system message, so something has to fill them, and this is the one place in a reply's life that is both asynchronous and already doing network work. One function for both because it already resolves the chat, the owner and the context, and doing that twice would be two sessions for nothing. The first reply in a brand-new chat on a big tree may start before the walk finishes. That is deliberate: the fragments carrying them vanish when they are empty rather than appearing as headings with nothing under them, and by the following turn they are there. **The skip is per cache.** It used to be one early return on the listing being present, and bolting a second cache on behind that would have meant the new one was silently never warmed on any chat that had a listing -- which is to say, on every chat after the first reply. """ from lembas.services.agent import index as index_service from lembas.services.agent import instructions as instructions_service from lembas.services.agent import session as agent_session try: with session_scope() as db: values = settings_store.agents(db) chat = db.get(Chat, generation.chat_id) if chat is None or chat.kind != KIND_AGENT: return owner = db.get(User, chat.user_id) context = agent_session.resolve(db, chat, owner) profile_id = chat.ssh_profile_id or "" if context is None or not profile_id: return where = (profile_id, context.project_dir) jobs = [] if values.get("index_enabled") and index_service.cached(*where) is None: jobs.append( index_service.ensure(context.executor(), profile_id, context.project_dir) ) if values.get("instructions_enabled") and instructions_service.cached(*where) is None: jobs.append( instructions_service.ensure( context.executor(), profile_id, context.project_dir, budget=int(values.get("instructions_chars") or 0), ) ) if not jobs: return await asyncio.wait_for(asyncio.gather(*jobs), timeout=INDEX_WAIT) except TimeoutError: log.debug("index for chat %s outran its wait; carrying on", generation.chat_id) except Exception as exc: # noqa: BLE001 - a missing listing is not a failed reply log.info("could not warm the index for chat %s: %s", generation.chat_id, exc) async def _maybe_compact(generation: Generation) -> None: """Summarise the earlier turns if the window is about to be full. Never raises. A failed compaction logs and sends the uncompacted request, which either works or fails upstream with a message that says what actually happened -- refusing to answer because the summariser was unavailable would be a worse trade. The awaited call is deliberately outside any session, the same shape titling uses: read everything needed, close, ask, reopen to write. """ try: with session_scope() as db: chat = db.get(Chat, generation.chat_id) message = db.get(Message, generation.message_id) if chat is None or message is None: return pending = _pending_text(db, message) if not compaction_service.should_compact(db, chat, pending=pending): return template = prompts_service.resolve(db, "task.compact") upto = compaction_service.last_complete(db, chat) if not template.strip() or upto is None: return endpoint, model_id = chat_service.resolve_endpoint(db, chat) transcript = compaction_service.transcript(db, chat, upto=upto) previous = compaction_service.previous_summary_block(chat) upto_id = upto.id generation.status = "Summarising earlier messages…" generation.touch() summary = await chat_service.summarise_for_compaction( endpoint, model_id, transcript=transcript, previous_summary=previous, template=template, ) if not summary: return with session_scope() as db: chat = db.get(Chat, generation.chat_id) upto = db.get(Message, upto_id) if chat is None or upto is None: return compaction_service.apply(chat, summary=summary, upto=upto) db.commit() log.info("chat %s compacted automatically through %s", chat.id, upto_id) except Exception: # noqa: BLE001 - the reply matters more than the tidy-up log.exception("automatic compaction failed for chat %s", generation.chat_id) finally: generation.status = "" generation.touch() # How many of a round's tool calls may be in flight at once. A bound rather # than none: a model that asks for eight would otherwise open eight sockets and # eight database sessions at the same moment. MAX_PARALLEL_TOOLS = 4 def _gave_up(generation, why: str) -> None: """Stop, and leave something in the transcript saying why. A reply that simply stopped would look like the model losing interest. The event is the same shape the out-of-rounds branch uses, so it renders with everything else. """ generation.tool_events.append( { "name": "budget", "kind": "agent", "status": "error", "results": [], "error": f"Stopped {why}. Ask again to carry on from here.", } ) generation.touch() def _refresh_agent(context) -> None: """Pick up a mode or an allow-list change made while this reply is running. Its own short session: `ToolContext` is a session-free snapshot precisely so nothing in a tool holds a live one, and this is one primary-key lookup plus a settings read on a loop that is already doing network work per round. Silent on failure. A chat deleted mid-reply is not a reason to fail the reply, and the reply is about to end anyway. """ agent = getattr(context, "agent", None) if agent is None: return with contextlib.suppress(Exception), session_scope() as db: agent_session.refresh(db, agent) def _wrap_up(generation, why: str, payload: dict, *, name: str = "budget") -> tuple[list, dict]: """A budget has run out. Withdraw the tools and ask for an answer. Returns the empty tool list and the payload without its `tools` array, so the next request is one the model can only answer. Every budget used to end the reply where it was noticed, which is fine for a model that narrates as it works and produces nothing at all for one that goes straight to tool calls: an empty bubble with a red line under it, and a good piece of research thrown away at its sixth search. What it has gathered is already in the transcript, so one more request without tools turns it into an answer. That is the same move `plan_submit` makes -- a turn should not end mid-sentence -- and it is why the loop runs to `budget + 2`. The event still goes in the transcript. The reader has to be able to tell an answer the model chose to give from one it gave because it ran out of room, and those read identically otherwise. """ generation.tool_events.append( { "name": name, "kind": "agent", "status": "error", "results": [], "error": ( f"Stopped {why}. What follows is an answer from what had been " "gathered by then; ask again to carry on." ), } ) generation.touch() return [], {key: value for key, value in payload.items() if key != "tools"} def _nudge( generation: Generation, context, *, enabled: bool, stopped: bool, round_number: int, budget: int, ) -> dict | None: """The turn telling an agent to carry on, or None to let the reply end. A model that stops with work outstanding is the failure `core.keep_working` is worded against, and prompting is the cheaper half of the fix. This is the other half, and it only fires where there is something objective to check against: an open task on the chat's own plan. Without a plan there is nothing to be wrong about, so nothing happens -- a model that has genuinely finished must be able to say so and be believed. Every "no" is a plain None: * the setting is off, or the reply was stopped, or it errored; * this is not an agent chat, or is one in Plan mode -- `plan_submit` ends the turn deliberately and nudging past it would be arguing with the whole point of the mode; * there is no plan, or every task on it is done or dropped; * there is no round left to carry on in, or it has already been asked MAX_NUDGES times in a row. The last one is recorded rather than silent. A reply that stopped twice with work outstanding is worth being able to see afterwards. """ agent = getattr(context, "agent", None) if not enabled or stopped or generation.error or agent is None: return None if agent.mode == agent_policy.MODE_PLAN or generation.plan_final: return None plan = generation.plan if generation.plan is not None else agent.plan open_tasks = [ task for phase in (plan or {}).get("phases", []) for task in phase.get("tasks", []) if task.get("status") not in ("done", "dropped") ] if not open_tasks: return None if round_number >= budget: return None if generation.nudges >= MAX_NUDGES: generation.tool_events.append( { "name": "plan_update", "kind": "plan", "status": "error", "error": ( f"Stopped with {len(open_tasks)} task(s) still open on the " f"plan, after being asked twice to carry on." ), "results": [], } ) generation.touch() return None generation.nudges += 1 remaining = "\n".join(f"- {task['id']} {task['text']}" for task in open_tasks[:8]) # A user turn, and phrased as the reader would phrase it. Everything else # this codebase injects is quoted and attributed because it came out of a # file or a machine; this is the application speaking on the reader's behalf # about the reader's own plan, which is the one case where that is honest. return { "role": "user", "content": ( "The plan still has work in it:\n" f"{remaining}\n\n" "Carry on with the next one. If something here cannot be done, or is " "no longer worth doing, mark it dropped with plan_update and say why " "— do not leave it open and stop." ), } def _too_big(generation: Generation) -> bool: """Whether the request about to go out leaves no room to answer in. `context_limit` of 0 is *unknown*, not small -- the rule this codebase already applies to the context percentage and to automatic compaction -- so a model nobody has declared a window for is never stopped by this. That is the honest answer: the alternative is refusing to work on every model an administrator has not filled a number in for. """ if not generation.context_limit: return False return generation.prompt_estimate > generation.context_limit * CONTEXT_HEADROOM def _written(generation: Generation) -> int: """How much this reply has written so far, in tokens, reported or estimated. Both, because neither alone is enough. `completion_tokens` is only populated when the endpoint sends a usage block, and a good half of the ones this talks to -- llama.cpp, Ollama and friends -- never do; the fallback estimate is otherwise computed once, in `_run`'s `finally:`, long after the loop that needs it. A ceiling reading only the reported figure would work on OpenAI and silently do nothing everywhere else, which is the worst kind of limit: one that looks configured. Reasoning counts. It was generated and it was paid for, even though it is deliberately never replayed as context. """ return max( generation.completion_tokens, tokens.estimate(generation.text + generation.thinking), ) def _tool_status(calls: list[dict]) -> str: """What to show while tools run. A remote tool -- an HTTP endpoint, an MCP server -- can take seconds with nothing streaming, and a silent pause is exactly what a hang looks like. """ if len(calls) == 1: return f"Running {tool_labels.label_for(calls[0]['name'])}…" return f"Running {len(calls)} tools…" def _book(context) -> dict: """The tools this request may call, keyed by name. `context.tools` is authoritative *even when empty* -- a dict means somebody resolved a set. Only `None` means nobody did, which is the one case that falls back to the import-time registry. """ return context.tools if context.tools is not None else tools_service.REGISTRY def _arguments_for(context, calls: list[dict]) -> list[dict]: """Every call's arguments in this round, parsed once. Once, and shared: the card, the policy and the runner all read the same dict. Two parsers meant a model could emit malformed JSON and get an approval card with an empty command body while `run_tool`'s own fallback handed the raw string to `shell_run` and ran it. """ book = _book(context) return [ tools_service.parse_arguments(book.get(call["name"]), call["arguments"]) for call in calls ] def _describe(name: str, args: dict) -> tuple[str, str]: """What an approval card says about one call: a title, and the detail. The detail is the thing being agreed to -- the command line, the path -- and is shown verbatim and escaped. A summary that paraphrased it would be a card approving something other than what runs. Delegated to services/tool_labels.py, which the transcript and the status line read too. This used to be a hand-written if-chain and was the fourth place with its own wording for the same tool. """ return tool_labels.describe(name, args) def _approvals(context, calls: list[dict], arguments: list[dict]) -> list[interaction.Item]: """The calls in this round that a person has to allow before they run. Only in an agent chat: `context.agent` is None everywhere else, and an ordinary conversation behaves exactly as it did. Within one, *every* call goes through the table, including the built-in ones -- `notes_edit` writes, and Plan mode meaning "look but do not touch" has to mean that too. `arguments` is what `_arguments_for` parsed, positionally matched to `calls`. Deliberately not re-parsed here: the card has to describe what the runner will actually be given. """ agent = getattr(context, "agent", None) if agent is None: return [] book = _book(context) items: list[interaction.Item] = [] for index, call in enumerate(calls): tool = book.get(call["name"]) if tool is None or tool.risk == tools_service.RISK_ASK: continue # unknown names are refused by run_tool; questions are their own card args = arguments[index] command = str(args.get("command") or "") if call["name"] == "shell_run" else "" decision = agent_policy.decide( mode=agent.mode, risk=tool.risk, tool_name=call["name"], command=command, allow=agent.allow, deny=agent.deny, ) if decision.verdict == agent_policy.ALLOW: continue title, detail = _describe(call["name"], args) items.append( interaction.Item( index=index, key=f"a{index}", kind=interaction.KIND_APPROVAL, tool_name=call["name"], title=f"{title} on {agent.label}", detail=detail, reason=decision.reason, purpose=agent_tools.why_of(args), # A card showing one argument can offer to correct it. A model # proposing the right command with one flag wrong is the common # case, and Allow-or-Don't makes that a whole round trip to # explain. Anything whose detail is a summary rather than a # value cannot be put back and is not offered the box. editable=bool(tool_labels.DETAIL_KEYS.get(call["name"])), ) ) return items def _ask_items(context, calls: list[dict], arguments: list[dict]) -> list[interaction.Item]: """Which of this round's calls need a person, and what to show about each. Looked up through `context.tools`, the map of what was actually offered -- the same authority `run_tool` uses. A name that is not in it is left alone here and refused there, so an unknown tool cannot smuggle itself past by being unclassifiable. """ book = _book(context) items: list[interaction.Item] = [] for index, call in enumerate(calls): tool = book.get(call["name"]) if tool is None or tool.risk != tools_service.RISK_ASK: continue args = arguments[index] for asked in _questions_in(args): options = [str(o).strip() for o in (asked.get("options") or []) if str(o).strip()] items.append( interaction.Item( index=index, key=f"q{len(items)}", kind=interaction.KIND_QUESTION, tool_name=call["name"], title=str(asked.get("question") or "").strip() or "A question for you", options=tuple(options[: interaction.MAX_OPTIONS]), ) ) return items def _questions_in(args: dict) -> list[dict]: """The questions in one `ask_user` call, however it was spelled. The schema asks for a list of objects, and a capable model sends that. A small one sends a bare `question` string, or a list of plain strings, or one object where a list belonged -- all of which mean something obvious, so they are read rather than refused. Getting this wrong costs a whole round trip and produces a card saying "A question for you" and nothing else. """ raw = args.get("questions") if raw is None: raw = args.get("question") if raw is None: return [] if isinstance(raw, str | dict): raw = [raw] if not isinstance(raw, list): return [] out: list[dict] = [] for entry in raw[: interaction.MAX_QUESTIONS]: if isinstance(entry, str) and entry.strip(): # A bare string, possibly alongside a sibling `options` that was # meant to go with it -- which only makes sense for a lone question. out.append({"question": entry, "options": args.get("options") if len(raw) == 1 else []}) elif isinstance(entry, dict) and str(entry.get("question") or "").strip(): out.append(entry) return out async def _authorise( generation, context, calls: list[dict], arguments: list[dict] ) -> tuple[dict[int, ToolOutcome], set[int], set[int]]: """Which of this round's calls may run, and what the others answer instead. Returns outcomes keyed by the call's index, the indices a person allowed, and the indices whose command they corrected on the way. Every index the caller does not find in the first is cleared to run; every index it does find is answered without the runner being reached at all. That is what keeps `zip(calls, outcomes, strict=True)` aligned -- an endpoint matching on `tool_call_id` pairs the wrong content with the right id otherwise. Also returns the indices a person explicitly allowed, so the runners can be told. They re-check the mode as a backstop and would otherwise refuse the very thing that was just approved -- the mode says "ask", and asking is what happened. A command corrected on the card is written back into `arguments` **in place**, because that same list is what `_run_calls` hands to `run_tool` as `parsed=` and `run_tool` never re-parses. Editing the item would do nothing: `Item` is display-only and frozen. This is the one place the two meet. """ questions = _ask_items(context, calls, arguments) approvals = _approvals(context, calls, arguments) items = [*approvals, *questions] if not items: return {}, set(), set() timeout = float(context.interaction_timeout or 900) pause = interaction.build(uuid.uuid4().hex, items, timeout=timeout) generation.status = interaction.summarise(pause.items) reply = await interaction.wait_for(generation, pause, timeout=timeout) generation.status = "" if reply.ended: generation.stopped = True return {}, set(), set() decided: dict[int, ToolOutcome] = {} allowed: set[int] = set() edited: set[int] = set() # An approval that came back as a refusal answers its call without the # runner being reached; one that came back allowed is simply left out, which # is how `_run_calls` is told to go ahead. for item in approvals: if not reply.permitted: decided[item.index] = _not_allowed(item, reply) continue if _apply_edit(calls, arguments, item, reply) != item.detail: # So the transcript can say the command was changed before it ran. # Without it a reader scrolling back sees a command attributed to # the model that the model never wrote. edited.add(item.index) allowed.add(item.index) # Questions are grouped back by call, because one `ask_user` call may have # carried several and the endpoint expects exactly one tool turn per call. grouped: dict[int, list[interaction.Item]] = {} for item in questions: grouped.setdefault(item.index, []).append(item) for index, asked in grouped.items(): decided[index] = _answered(asked, reply) return decided, allowed, edited def _apply_edit( calls: list[dict], arguments: list[dict], item: interaction.Item, reply: interaction.Reply, ) -> str: """Put a corrected command back where the runner will find it. Returns what is going to run, edited or not, so the caller can record the right thing. Two writes, and both are needed: `arguments[index]` is what `run_tool` is handed as `parsed=`, and it never re-parses -- so this is the only write that reaches the runner. Editing the item would do nothing at all: `Item` is frozen and display-only. `call["arguments"]`, the raw string, is rewritten beside it, because that is what goes back to the endpoint as the assistant turn. Otherwise the model is told it ran what it proposed rather than what actually ran, and every later round reasons from a transcript that is quietly false. Nothing is re-checked against the mode or the lists. That is the same line the terminal panel and the directory browser draw, and here it is not even close: the deny list resolves to ASK rather than to a refusal -- it means "always ask about this" -- and a person who has typed the command themselves and pressed Allow is exactly the asking it was demanding. Re-asking would put the same card up again with no way past it. The instance's list still governs the *model*: a pattern remembered by "always allow" is checked by `decide`, where a deny hit wins before the allow list is even read. """ if not item.editable: return item.detail edited = reply.answer_to(item) key = tool_labels.DETAIL_KEYS.get(item.tool_name) if not edited or edited == item.detail or not key: return item.detail arguments[item.index] = {**arguments[item.index], key: edited} calls[item.index] = { **calls[item.index], "arguments": json.dumps(arguments[item.index]), } return edited def _not_allowed(item: interaction.Item, reply: interaction.Reply) -> ToolOutcome: """What the model is told when a person declined, or never answered. Told plainly, and told to stop rather than to try again: a model that reads "not allowed" as "not allowed *that way*" will spend the rest of the reply looking for a way round, which is the opposite of what the refusal meant. """ event = { "name": item.tool_name, "kind": "agent", "label": item.title, "query": item.detail, "results": [], } if reply.outcome == interaction.EXPIRED: return ToolOutcome( "Nobody answered, so this was not run. Stop and say what you were " "about to do and why.", {**event, "status": "error", "error": "Not answered."}, ) return ToolOutcome( "They declined this. Do not try it another way — say what you were " "going to do and ask what they would prefer.", {**event, "status": "error", "error": "Declined."}, ) def _answered(items: list[interaction.Item], reply: interaction.Reply) -> ToolOutcome: """What one `ask_user` call gets back, however many questions it put.""" event = { "name": items[0].tool_name, "kind": "ask", "label": "Asked you", "query": "; ".join(item.title for item in items), "results": [], } if reply.outcome == interaction.EXPIRED: return ToolOutcome( "They did not answer. Carry on as best you can without it, or say " "what you still need.", {**event, "status": "error", "error": "No answer.", "text": ""}, ) answered = [(item, reply.answer_to(item)) for item in items] given = [(item, text) for item, text in answered if text] if not given: return ToolOutcome( "They closed the question without answering.", {**event, "status": "error", "error": "No answer.", "text": ""}, ) # Each answer is quoted next to the question it belongs to. With four # questions on one card, a bare list of answers would leave the model # matching them up by position and sometimes getting it wrong. lines = [f"{item.title}\n → {text}" for item, text in given] skipped = [item for item, text in answered if not text] if skipped: lines.append( "They left unanswered: " + "; ".join(item.title for item in skipped) ) body = "\n\n".join(lines) return ToolOutcome(f"They answered:\n\n{body}", {**event, "status": "ok", "text": body}) async def _run_calls( context, calls: list[dict], arguments: list[dict], *, decided: dict[int, ToolOutcome] | None = None, allowed: set[int] | None = None, ) -> list: """Run one round's calls together, results in call order. Sequential was right when every tool was a local database read. A remote one is latency-bound, and three two-second calls in a row are six seconds of a reply looking hung -- while the model has already been told it may ask for several at once. The results are indexed rather than appended as they finish, because each tool turn has to line up with the assistant turn's `tool_calls`: an endpoint matching on `tool_call_id` would otherwise pair the right id with the wrong content the moment two calls came back out of order. Safe to run together because `run_tool` never raises, so no failure cancels its siblings, and each runner opens its own `session_scope()` against a database in WAL mode with a busy timeout. """ limit = asyncio.Semaphore(MAX_PARALLEL_TOOLS) async def one(index: int, call: dict): # Already answered by a person, or refused before it got here. It still # occupies its index, because the tool turns have to line up. if decided and index in decided: return decided[index] # A per-call copy for anything a person allowed, so the runner's own # check does not undo their decision. A copy rather than a flag on the # shared context, because a round runs its calls together and only some # of them were approved. ctx = context if allowed and index in allowed and getattr(context, "agent", None) is not None: ctx = replace(context, agent=context.agent.as_approved()) async with limit: return await tools_service.run_tool( ctx, call["name"], call["arguments"], parsed=arguments[index] ) return list(await asyncio.gather(*(one(i, c) for i, c in enumerate(calls)))) def _pending_text(db, message: Message) -> str: """The user turn this reply is answering, for the size estimate.""" previous = db.scalars( select(Message) .where(Message.chat_id == message.chat_id, Message.created_at < message.created_at) .order_by(Message.created_at.desc()) .limit(1) ).first() return previous.content if previous is not None else "" def _question_from(payload: dict) -> str: """The last thing the user said, for auto-titling.""" for entry in reversed(payload.get("messages", [])): if entry.get("role") != ROLE_USER: continue content = entry.get("content") if isinstance(content, str): return content if isinstance(content, list): return " ".join( part.get("text", "") for part in content if isinstance(part, dict) and part.get("type") == "text" ).strip() return "" def _next_waiting(db, chat_id: str) -> Message | None: """The oldest prompt in this chat that has not been sent.""" return db.scalars( select(Message) .where( Message.chat_id == chat_id, Message.role == ROLE_USER, Message.queued.is_(True), ) .order_by(Message.created_at) .limit(1) ).first() def _drain(generation: Generation) -> None: """Hand the next waiting prompt to a reply of its own, if there is one. Exactly one, not all of them. Draining the lot would put two consecutive user turns into the next request, which several local chat templates refuse outright -- `build_messages` already goes to some trouble over that around the compaction lead. "One after another" is also what was asked for: the second waiting prompt is drained by the reply the first one starts, and so on down the chain. Three refusals, and none of them is a special case: - **Superseded.** The same test `_persist` makes, for the same reason: a regeneration cancels its predecessor and the predecessor's `finally:` still runs. Without this, regenerating would drain the queue *and* leave a third generation running. - **Stopped.** Stop means stop, and the queue stays visible and undelivered with Send now beside it. This is also what makes shutdown safe -- cancellation sets `stopped`, so a restart never fires off a reply with nobody watching. - **Errored.** The endpoint has just failed. Feeding the next prompt into it produces a second failure and spends somebody's words to do it. """ owner = _RUNNING.get(generation.message_id) if owner is not None and owner is not generation: return if generation.stopped or generation.error: return try: with session_scope() as db: chat = db.get(Chat, generation.chat_id) if chat is None: return waiting = _next_waiting(db, chat.id) if waiting is None: return waiting.queued = False assistant = chat_service.create_message( db, chat, ROLE_ASSISTANT, "", complete_=False, model_id=chat.model_id ) chat_id, assistant_id = chat.id, assistant.id except Exception: # noqa: BLE001 - the reply is over either way log.exception("could not drain the queue for chat %s", generation.chat_id) return # Outside the session: this starts a task, and a task is not something to # hold a database session open across. ensure(chat_id, assistant_id) generation.drained = True def _inject(generation: Generation, chat_id: str, vision: bool) -> dict | None: """Take the oldest waiting prompt into this reply, between two rounds. Marked delivered and committed *before* the request goes out, so this is at-most-once. A crash in between loses the turn, which is recoverable -- the words are still in the transcript with Send now beside them. The other way round would ask the same question twice and let an agent act on it twice, which is not. Sent verbatim, in the user role, with no framing. Everything else this codebase injects is quoted and attributed because it came out of a file, a page or a machine; this one genuinely *is* the person at the keyboard, authenticated by the session cookie and stored as a `Message` whose role says so. Wrapping it would teach a model that a user turn can be a quotation, which is the exact distinction the other two rely on. What the model needs -- that this can happen at all -- is one sentence in the harness, where authored wording lives. """ try: with session_scope() as db: waiting = _next_waiting(db, chat_id) if waiting is None: return None waiting.queued = False entry = chat_service.message_payload(waiting, vision=vision) # The reply that answers it must sort *before* it, or the next # turn's transcript reads "answer, then the question it answered" # and a small model dutifully answers again. Moving the placeholder # rather than the prompt keeps several interjections in the order # they were typed. placeholder = db.get(Message, generation.message_id) if placeholder is not None: placeholder.created_at = datetime.now(UTC) generation.injected_ids.append(waiting.id) except Exception: # noqa: BLE001 - a lost interjection is not a failed reply log.exception("could not take a queued prompt into chat %s", chat_id) return None generation.status = "Taking in what you just added…" generation.touch() return entry def _persist(generation: Generation, title: str, elapsed: float) -> None: """Write the finished reply, name the chat, and set the unread flag. A generation another one has replaced may not write. A regeneration cancels its predecessor, whose `finally:` then runs this on the same row -- and it would overwrite the fresh reply with the abandoned one. The test is "someone else owns this row now", not "this one is registered": an unregistered generation still writes, because that is a direct call rather than a superseded one. """ owner = _RUNNING.get(generation.message_id) if owner is not None and owner is not generation: log.debug("skipping persist for superseded generation %s", generation.message_id) return try: with session_scope() as db: message = db.get(Message, generation.message_id) chat = db.get(Chat, generation.chat_id) if message is None or chat is None: return message.content = generation.text message.reasoning = generation.thinking message.reasoning_ms = generation.reasoning_ms message.tool_calls_json = generation.tool_events message.plan_json = generation.plan or {} if generation.canvas.get("tabs"): # A union with whatever the row says *now*, not an overwrite: # the snapshot above was seeded when the reply began, and # somebody may have opened a tab by hand since. chat.canvas_json = canvas_service.merge(chat.canvas_json, generation.canvas) if generation.plan: # This bubble now carries the plan in force, and the chat points # at it so the harness can find it with one primary-key lookup # rather than a scan. Older bubbles keep the plan as it was then, # which is what a transcript is for -- the card is never # re-rendered in place. chat.plan_message_id = message.id message.usage_json = metrics_service.to_json( metrics_service.from_generation(generation) ) message.error = generation.error message.stopped = generation.stopped message.complete = True if title and not chat.title_generated: chat.title = title chat.title_generated = True # Nobody watching when it landed, so it is news. The chat page # clears this when it is next opened. Not for a temporary chat: # there is no sidebar row for the dot, and the toast would name a # chat nobody can navigate to. if generation.followers == 0 and not chat.temporary: chat.unread = True chat.unread_notified = False db.commit() log.debug( "chat %s finished: %d chars, %d reasoning, %.1fs", generation.chat_id, len(message.content), len(message.reasoning), elapsed, ) except Exception: # noqa: BLE001 - the task is ending either way log.exception("could not persist generation for chat %s", generation.chat_id) __all__ = [ "RENDER_INTERVAL", "Generation", "ROLE_ASSISTANT", "ensure", "get", "request_stop", "restart", "shutdown", ]