Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

everalgo-boundary

Boundary detection for EverAlgo — cuts a conversation into coherent MemCell slices with an LLM, either in one batch call or one message at a time. Agent trajectories with tool calls and tool results go through the same class: only the chat messages reach the model, and the tool items stay in the cells.

See the umbrella project: EverAlgo monorepo and the architecture document at docs/concepts/architecture.md.

Install

pip install everalgo-boundary

everalgo-user-memory and everalgo-agent-memory both depend on this package and re-export BoundaryDetector unchanged.

What this distribution provides

Symbol Role
BoundaryDetector Class binding an LLM client: adetect / detect (batch, over ConversationItem), adetect_step / detect_step (incremental, over ChatMessage)
adetect_boundaries Async function behind BoundaryDetector.adetect: (Sequence[ConversationItem], *, llm, is_final, ...) → DetectionResult
detect_boundaries Sync bridge over adetect_boundaries (asgiref.async_to_sync); never call it inside a running event loop
adetect_boundary_step Async function behind BoundaryDetector.adetect_step: single-step boundary decision → BoundaryDecision
DetectionResult NamedTuple(cells: list[MemCell], tail: list[ConversationItem], tail_complete: bool | None)

Tool items

adetect_boundaries renders only the ChatMessage items for the model and carries its cuts back to the full list: tool items between two chat messages go with the earlier one, tool items ahead of the first chat message with the first cell, and trailing tool items into the tail (into the last cell when is_final=True). Every item lands exactly once. Without any ChatMessage no LLM is called and every item goes to the tail.

Hard limits

Both paths cut without the model once a window reaches a hard limit: 65536 tokens or 500 messages by default (hard_token_limit / hard_msg_limit on the batch path, hard_token_limit / hard_message_limit on adetect_step).

Prompts

Each model call sends two messages. The system message holds the rules — BATCH_BOUNDARY_DETECT_SYSTEM_PROMPT or STEP_BOUNDARY_DETECT_SYSTEM_PROMPT in everalgo.boundary.prompts.en.chat — and is the same text on every call, so a prompt cache can share all of it. The user message holds only the data, rendered from BATCH_BOUNDARY_DETECT_USER_PROMPT (<messages count="N">) or STEP_BOUNDARY_DETECT_USER_PROMPT (<conversation_history>, <time_gap>, <new_messages>). Each message line is [N] [YYYY-MM-DD HH:MM UTC (Weekday)] speaker: text on the batch path and the same without [N] on the step path.

custom_instructions= on adetect_boundaries, adetect_boundary_step and the BoundaryDetector methods adds the host's text to the bundled rules, never replacing them: it is placed verbatim, never rendered as a template, in a <custom_instructions> block that is always the system message's last, and None or a blank string leaves it out. The user message is unchanged and always rendered by the operator. There is no prompt=: the bundled rules cannot be replaced per call.

Quick start

import asyncio
import json

from everalgo.boundary import adetect_boundaries
from everalgo.testing.fake_llm import FakeLLMClient
from everalgo.types import ChatMessage

_BOUNDARY_JSON = json.dumps(
    {"reasoning": "single topic", "boundaries": [], "tail_complete": True}
)

async def main() -> None:
    # One scripted reply per LLM call; `llm.achat` returns the reply text (see `everalgo.llm.LLMClient`).
    fake = FakeLLMClient(responses=[_BOUNDARY_JSON, _BOUNDARY_JSON])
    messages = [
        ChatMessage(id="m1", role="user",   content="Let's talk about deployment.",     timestamp=1_700_000_000_000, sender_id="u_alice"),
        ChatMessage(id="m2", role="assistant", content="Sure — what's the target env?",  timestamp=1_700_000_001_000, sender_id="assistant"),
        ChatMessage(id="m3", role="user",   content="K8s. Switching topic: lunch?",     timestamp=1_700_000_002_000, sender_id="u_alice"),
    ]

    # Streaming: hold `tail` between calls; pass prior tail + new messages each time.
    result = await adetect_boundaries(messages, llm=fake)
    cells, tail, tail_complete = result  # NamedTuple unpacking

    # `tail_complete` is the LLM's verdict on the tail, not a restatement of it being non-empty: True
    # means the trailing segment already forms a complete episode, so it can be closed now; False
    # means it is not complete yet (it only opens a topic, or is only media placeholders, a bare "ok",
    # a system notification, an ambiguous 30-min-to-4-hour gap), so hold it for the next batch.
    # `None` means no path judged it — see the DetectionResult docstring.

    # End-of-session: tail is forced into the last cell.
    result = await adetect_boundaries(messages, llm=fake, is_final=True)
    assert result.tail == []
    for mc in result.cells:
        print(mc.timestamp, len(mc.items))


asyncio.run(main())

The streaming state machine

adetect_boundaries deliberately holds back trailing messages as tail — the LLM cannot know whether a conversation continues beyond the last seen message. The caller maintains state:

tail: list[ConversationItem] = []

for batch in incoming_batches:
    result = await adetect_boundaries(tail + batch, llm=client)
    await persist(result.cells)
    tail = result.tail

# Session ends — flush everything.
final = await adetect_boundaries(tail, llm=client, is_final=True)
await persist(final.cells)

Failures

Each call makes one LLM request and validates the reply against a strict pydantic model, which it also passes as response_format. A reply that does not fit — not JSON, a missing or extra key, a non-integer boundary — raises everalgo.llm.LLMOutputError; nothing is retried, and the client's own exceptions propagate unchanged. Retry policy belongs to the caller.

Tokenizer utilities

Boundary detection counts tokens with everalgo.utils.count_tokens (in everalgo-core), which uses OpenAI's o200k_base encoding via tiktoken.

Stubs

WorkspaceMemCellExtractor (Jira / Email / Confluence) is a placeholder in v0.x — all methods raise NotImplementedError. It is deliberately excluded from everalgo.boundary.__all__; import it from everalgo.boundary.workspace directly if you need the reserved name. Implementation lands in a future minor bump when the RawData contract is finalised.

Metadata

Release files for everalgo-boundary 0.4.0rc3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for everalgo-boundary 0.4.0rc3
File Size Uploaded Provenance Actions
everalgo_boundary-0.4.0rc3.tar.gz 46.9 kB Without provenance Details for everalgo_boundary-0.4.0rc3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for everalgo-boundary 0.4.0rc3
File Interpreter ABI Platform Actions
everalgo_boundary-0.4.0rc3-py3-none-any.whl Python 3 none any Details for everalgo_boundary-0.4.0rc3-py3-none-any.whl

Total release size: 69.9 kB

Release files / everalgo_boundary-0.4.0rc3.tar.gz

Download URL everalgo_boundary-0.4.0rc3.tar.gz
Size 46.9 kB
Tags Source
SHA-256 checksum
How to use checksums
852f5375d5513676efbca10a98fbb250584f1d985464274baedbe4eafb4d6b19
BLAKE2b-256 checksum
How to use checksums
de0d1ae021403ed51ab20aa4abaf8208bbb8505376ba67cf7d759f3f53081173
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.12.12

Release files / everalgo_boundary-0.4.0rc3-py3-none-any.whl

Download URL everalgo_boundary-0.4.0rc3-py3-none-any.whl
Size 23.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
414a8cc379315deeeba4a562a658317901f841837f384aee4345ad1de6dc1cf9
BLAKE2b-256 checksum
How to use checksums
614710294581ec7ae2a0f14ef6035dc14da8205913ea4c592825ae75136474b0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.12.12

Security for everalgo-boundary 0.4.0rc3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page