avatar.context

ContextBuilder — the compact per-turn working packet (§9).

Assembles only what the model needs this turn: goal, phase, recent evidence (summaries, most-recent-first-budgeted), and the tools allowed for the current phase. The model discovers the repo incrementally through tools; it never receives the whole repository by default.

Classes

ContextBuilder

Builds the per-turn ContextPacket from TaskState under a fixed budget (§9).

Evidence is compacted less-lossily (Phase 2.5): recent items keep full detail until a char budget is spent, older items degrade to their summary line (not dropped), the last N verifier outputs are pinned verbatim, and adjacent duplicates collapse to one ... (xN) line. Action history is cheap (one line each) so it is kept on a longer horizon than evidence.

Args: detail_char_budget: Total chars of evidence detail shown verbatim before older items degrade to summary-only. max_detail_chars: Per-item detail truncation budget. max_evidence_lines: Hard cap on rendered evidence lines (newest kept). max_actions: Max prior-action lines to surface. verifier_pin_count: How many recent verifier outputs keep detail verbatim regardless of budget — a repair loop needs its recent failure history, not just the latest verdict.

ContextBuilder(detail_char_budget: int = 48000, max_detail_chars: int = 16000, max_evidence_lines: int = 40, max_actions: int = 25, verifier_pin_count: int = 2) -> None

ContextBuilder.build(self, state: TaskState, ws: Workspace, registry: ToolRegistry) -> ContextPacket

Assemble the working packet for the current turn from state (§9).

Args: state: The task state, source of truth for the packet. ws: The run-scoped Workspace handle. registry: The ToolRegistry, for phase-active tools.

Returns: The ContextPacket for this turn.

ContextPacket

The compact, per-turn working set assembled for one model decision (§9).

ContextPacket(*, goal: str, constraints: list[str] = <factory>, conversation: list[ConversationTurn] = <factory>, phase: str, task_kind: str = 'investigate', plan: list[str] = <factory>, files_read: list[str] = <factory>, files_modified: list[str] = <factory>, prior_actions: list[str] = <factory>, recent_evidence: list[str] = <factory>, allowed_tools: list[ToolSummary] = <factory>, latest_error: str | None = None, has_uncommitted_changes: bool = False) -> None

Fields

Field	Type	Required
goal	str	yes
constraints	list[str]	no
conversation	list[ConversationTurn]	no
phase	str	yes
task_kind	str	no
plan	list[str]	no
files_read	list[str]	no
files_modified	list[str]	no
prior_actions	list[str]	no
recent_evidence	list[str]	no
allowed_tools	list[ToolSummary]	no
latest_error	`str	None`	no
has_uncommitted_changes	bool	no

ToolSummary

A tool’s name, description, and input schema, as shown to the model.

ToolSummary(*, name: str, description: str, input_schema: dict = <factory>) -> None

Fields

Field	Type	Required
name	str	yes
description	str	yes
input_schema	dict	no