Implement token-budget awareness (§4.4.7) and tool output pruning
(§4.4.8-9) for the multi-turn tool-call loop to prevent context-window
exhaustion.
Token budget: tracks estimated token count before each ainvoke(), emits
warning at 75% budget, injects synthesis prompt at exhaustion with one
final tool-call round. Estimation via chat_model.get_num_tokens() with
len(content)//4 heuristic fallback. Config key: token_budget_percent.
Tool output pruning: implicit LLM extraction pass scoped to file_read
calls. Schema augmentation injects output_prune (bool) and
output_prune_context (string) meta-arguments. Pruning model responds
with [PRUNE_INFO_START/END] and [PRUNE_OUTPUT_START/END] markers.
Config keys: allow_tool_output_pruning, pruning_model.
- Capture output_prune value in budget synthesis flow with proper guard
- Fix ADR D-4: synthesis prompt is HumanMessage not SystemMessage
- Fix Robot tests: replace /dev/null with temp file path
ADR-2031 documents all specification extensions. 21 new BDD scenarios,
5 Robot integration tests, 16 ASV benchmarks.
ISSUES CLOSED: #61
CoreRasurae