mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-10-24 05:47:32 +00:00
548b08561e
* refactor: generalize decision models and add opt-in context compaction * chore: remove compaction-specific license metadata * test: add live decision compaction scenarios and strategy guides * docs: describe current decision model configuration directly * refactor: preserve recoverable tool evidence and add compaction benchmarks * docs: visualize compaction benchmark results with English charts * docs: fix compaction benchmark links with verified permalinks * benchmark: evaluate fixed-summary evidence additions and summary-aware selection * docs: report summary-aware incremental evidence results * docs: unify compaction strategy comparison * refactor: replace compaction studies with one matched-input benchmark * docs: pin matched-input results links * bench: evaluate gold-labelled HotpotQA trajectories collected with Hermes * docs: pin gold-labelled benchmark results * bench: focus on frozen-summary Jev Top-N payment evaluation * docs: pin frozen-summary benchmark results * bench: evaluate fixed-summary fusion across Hermes fixture tasks * docs: pin compaction study references to reviewed results * bench: compare Jev fusion across frozen summary strategies * docs: pin dual-summary benchmark and figure references * docs: specify reproducible compaction settings and Hermes summary scope * docs: plot Jev token overhead by retained Top N * docs: pin reproducibility settings and revised cost figure * docs: price total compaction and answering cost across Top N * docs: pin final cost accounting and reproduction references * docs: explain compaction experiment background setup and conclusions inline * docs: compare compaction-only costs and omit Full from cost panel * docs: pin compaction-only cost references * docs: retain only quality and context-length experiment comparisons * docs: pin streamlined experiment references * docs: add Chinese counterparts for all compaction benchmark guides * docs: link benchmark guides in the matching language * docs: consolidate bilingual compaction benchmark guides * docs: point compaction references to consolidated benchmark * docs: reference Hermes Jev compaction evaluation results * fix(benchmark): validate cached native summary provenance
83 lines
3.4 KiB
Python
83 lines
3.4 KiB
Python
"""JSON contracts for recoverable, tool-only context compaction."""
|
|
|
|
from typing import Literal
|
|
|
|
from pydantic import BaseModel, ConfigDict, Field, JsonValue, field_validator
|
|
|
|
|
|
class CompactionOptions(BaseModel):
|
|
"""Decision request limits and optional host-counted output budget."""
|
|
|
|
model_config = ConfigDict(extra="forbid", allow_inf_nan=False)
|
|
|
|
drop_threshold: float = Field(default=0.1, ge=0, le=1)
|
|
preserve_recent_messages: int = Field(default=6, ge=0, strict=True)
|
|
max_state_tokens: int = Field(default=25000, gt=0, strict=True)
|
|
max_request_tokens: int = Field(default=30000, gt=0, strict=True)
|
|
evidence_chars: int = Field(default=2000, gt=0, strict=True)
|
|
preview_chars: int = Field(default=300, ge=0, strict=True)
|
|
max_output_tokens: int | None = Field(default=None, gt=0, strict=True)
|
|
max_concurrency: int = Field(default=4, ge=1, le=32, strict=True)
|
|
total_timeout_seconds: float = Field(default=30, gt=0)
|
|
|
|
|
|
class CompactionRequest(BaseModel):
|
|
"""The host supplies immutable AgentScope snapshots and resolvable archive references."""
|
|
|
|
model_config = ConfigDict(extra="forbid", allow_inf_nan=False)
|
|
|
|
messages: list[dict[str, JsonValue]]
|
|
goal: str = ""
|
|
next_action: str = ""
|
|
source_refs: dict[str, str] = Field(default_factory=dict)
|
|
protected_message_ids: list[str] = Field(default_factory=list)
|
|
protected_call_ids: list[str] = Field(default_factory=list)
|
|
eligible_tool_names: list[str] = Field(default_factory=list)
|
|
options: CompactionOptions = Field(default_factory=CompactionOptions)
|
|
|
|
@field_validator("source_refs")
|
|
@classmethod
|
|
def validate_refs(cls, refs):
|
|
"""References are opaque host identifiers, not paths ReMe opens."""
|
|
if any(not key.strip() or not value.strip() for key, value in refs.items()):
|
|
raise ValueError("Source references need non-empty call IDs and values.")
|
|
return refs
|
|
|
|
@field_validator("messages")
|
|
@classmethod
|
|
def validate_messages(cls, messages):
|
|
"""Reject ambiguous envelopes while retaining unknown block fields."""
|
|
for message in messages:
|
|
if message.get("role") not in ("user", "assistant", "system"):
|
|
raise ValueError("Each message needs a user, assistant, or system role.")
|
|
content = message.get("content")
|
|
if not isinstance(content, list) or any(not isinstance(block, dict) for block in content):
|
|
raise ValueError("Each message needs a list of content block objects.")
|
|
return messages
|
|
|
|
|
|
class CallDecision(BaseModel):
|
|
"""Every replacement identifies its original tool pair and recoverable source."""
|
|
|
|
model_config = ConfigDict(extra="forbid", allow_inf_nan=False)
|
|
|
|
id: str
|
|
call_id: str
|
|
action: Literal["keep", "preview"]
|
|
reason: str
|
|
probability: float | None = Field(default=None, ge=0, le=1)
|
|
source_ref: str | None = None
|
|
|
|
|
|
class CompactionResult(BaseModel):
|
|
"""A proposed snapshot; the host owns archiving, recovery, and commit."""
|
|
|
|
model_config = ConfigDict(extra="forbid", allow_inf_nan=False)
|
|
|
|
schema_version: Literal[2] = 2
|
|
messages: list[dict[str, JsonValue]]
|
|
decisions: list[CallDecision] = Field(default_factory=list)
|
|
changed: bool
|
|
reason: Literal["compacted", "no_candidates", "no_change", "budget_exceeded"]
|
|
budget_met: bool | None = None
|
|
stats: dict[str, JsonValue] = Field(default_factory=dict)
|