Gralkor.Interpret (gralkor_ex v2.1.4)

Filter retrieved graph facts down to those relevant to the conversation, using the configured LLM.

Two responsibilities, each its own tree:

build_interpretation_context/3 — pure: assemble the LLM prompt from conversation messages and a formatted facts string, dropping oldest messages until the prompt fits the configured char budget. Renders role labels using agent_name.
interpret_facts/4 — call the LLM with that prompt and a structured- output schema; return the list of relevant facts the LLM selected.

See ex-interpret and ex-interpret-context in gralkor/TEST_TREES.md.

Summary

interpret_fn()

Assemble the LLM prompt from conversation messages and the formatted facts.

Run the LLM over the conversation context + facts text, returning the filtered list of relevant facts.

Schema for the structured-output response the LLM returns.

@type interpret_fn() :: (String.t() -> {:ok, [String.t()]} | {:error, term()})

@spec build_interpretation_context(
  [Gralkor.Message.t()],
  String.t(),
  String.t(),
  keyword()
) ::
  String.t()

Assemble the LLM prompt from conversation messages and the formatted facts.

Drops oldest messages until the assembled prompt fits the char budget (opts[:budget], default 8000). Raises on blank agent_name.

@spec interpret_facts(
  [Gralkor.Message.t()],
  String.t(),
  interpret_fn(),
  String.t(),
  keyword()
) :: [
  String.t()
]

Run the LLM over the conversation context + facts text, returning the filtered list of relevant facts.

Raises if the LLM call returns {:error, _} or a non-list response. Raises if agent_name is missing or blank.

@spec interpret_schema() :: keyword()

Schema for the structured-output response the LLM returns.