Compaction: the model's notes replace the middle of a long run (#158)

Before each driver call, over compact_at (0.6) of the prompt budget, the
same model is asked for notes over the very request it was about to get,
plus one message, so the server's cache covers all but the notes. The notes,
with code's list of the calls they replace, become a compaction event that
renders in place of its range, keeping word for word what started the work
and the last few turns. Rare, large steps keep the prompt's start unchanged
between them. A later compaction folds in the earlier; one from an earlier
run's view is hidden.

Failed notes are logged and fitting takes over. Fitting now applies
compactions before it measures, records what it cuts (Trim) and logs each
cut as context.trimmed. Wired into both agents' drivers and the benchmark;
nisse-dev's helper loop is a follow-up.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk

nisse-dev/src/nisse_dev/bench/runner.py

@@ -22,6 +22,7 @@ from nisse_core.log.canonical import (
 )
 from nisse_core.loop.driver import Driver, RunOutcome
 from nisse_core.models.catalog import ModelFacts
+from nisse_core.models.compact import Compactor
 from nisse_core.oplog import OpLog
 from nisse_dev.bench.tasks import Task
 from nisse_dev.config import Tuning
@@ -78,10 +79,13 @@ class MeteringClient:
         tools: list[dict[str, Any]] | None,
         model: str,
         system: str | None = None,
+        **options: Any,
     ) -> list[CanonicalEvent]:
         self.calls += 1
         try:
-            produced = self._inner.complete(events, tools, model, system=system)
+            produced = self._inner.complete(
+                events, tools, model, system=system, **options
+            )
         finally:
             # Counted even when the call fails: a rate limit that never
             # cleared still cost the run its wait.
@@ -95,10 +99,16 @@ class MeteringClient:
         answered = getattr(self._inner, "last_model", None)
         if not self._facts.answered(answered):
             self.fallbacks.append(str(answered))
-        if not any(isinstance(e, ToolCall) for e in produced):
+        # Compaction's notes are prose by request, not a broken turn.
+        asked_for_prose = options.get("require_tool_call") is False
+        if not asked_for_prose and not any(isinstance(e, ToolCall) for e in produced):
             self.prose_turns += 1
         return produced
 
+    def __getattr__(self, name: str) -> Any:
+        # The budget (budget_for, estimate) compaction reads.
+        return getattr(self._inner, name)
+
 
 @dataclass
 class RunRecord:
@@ -222,6 +232,8 @@ def run_task(
             model,
             max_turns=tuning.driver.max_turns,
             failure_limit=tuning.driver.failure_limit,
+            # As the agent runs it, so a long task measures the same thing.
+            compactor=Compactor(meter, tuning.context.compaction()),
         )
         system = SYSTEM.format(
             repo=f"bench/{task.name}",

nisse-dev/src/nisse_dev/config.py

@@ -34,6 +34,7 @@ from nisse_core.config import (
     resolve,
 )
 from nisse_core.conversation.matrix import MatrixConfig
+from nisse_core.models.compact import CompactionTuning, check_tuning
 from nisse_core.models.llm import (
     DEFAULT_MAX_OUTPUT_TOKENS,
     DEFAULT_REQUEST_TIMEOUT_S,
@@ -134,6 +135,19 @@ class ToolsTuning:
 class ContextTuning:
     keep_recent_turns: int = 6
     safety_margin: float = 0.1
+    # Compaction (L6): over compact_at of the prompt budget, the model's
+    # notes replace the middle of the run, keeping at most compact_keep_turns
+    # recent turns, in compact_to of it. compact_at 0: never.
+    compact_at: float = field(default=0.6, metadata={"zero": True})
+    compact_to: float = 0.25
+    compact_keep_turns: int = 3
+
+    def compaction(self) -> CompactionTuning:
+        return CompactionTuning(
+            compact_at=self.compact_at,
+            compact_to=self.compact_to,
+            keep_turns=self.compact_keep_turns,
+        )
 
 
 @dataclass(frozen=True)
@@ -182,6 +196,7 @@ def _parse_tuning(raw: Any, errors: list[str]) -> Tuning:
     )
     if tuning.context.safety_margin >= 1:
         errors.append("tuning.context.safety_margin: must be less than 1")
+    check_tuning(tuning.context.compaction(), "tuning.context", errors)
     return tuning
 
 

nisse-dev/src/nisse_dev/loop/build.py

@@ -15,6 +15,7 @@ from nisse_core.knowledge.memory import Memory
 from nisse_core.knowledge.vault import Vault
 from nisse_core.loop.driver import Driver
 from nisse_core.models.catalog import ModelCatalog, select_client
+from nisse_core.models.compact import Compactor
 from nisse_core.models.context import BudgetedClient
 from nisse_core.models.llm import AnthropicPassthroughClient, LiteLLMClient
 from nisse_core.oplog import OpLog
@@ -110,7 +111,7 @@ class RunningLoop:
 
 
 def make_llm_clients(
-    config: AgentConfig, catalog: ModelCatalog
+    config: AgentConfig, catalog: ModelCatalog, oplog: OpLog | None = None
 ) -> tuple[BudgetedClient, BudgetedClient]:
     """The two LLM routes, as every model call in the agent uses them.
 
@@ -136,6 +137,7 @@ def make_llm_clients(
             enforces_tool_choice=lambda m: (
                 catalog.facts(m).supports_tool_choice is True
             ),
+            oplog=oplog,  # a cut that fitting has to make is logged
         )
 
     normalized = budgeted(
@@ -276,7 +278,7 @@ def build_loop_agent(
         project_runtime(config, entry, store, gitea, account)
         for entry in config.projects
     ]
-    normalized, passthrough = make_llm_clients(config, catalog)
+    normalized, passthrough = make_llm_clients(config, catalog, oplog)
     cancel = Cancel()
     # The configured driver; each work item runs on the one it pinned (L9).
     driver = Driver(
@@ -285,6 +287,9 @@ def build_loop_agent(
         max_turns=config.tuning.driver.max_turns,
         cancel=cancel,
         failure_limit=config.tuning.driver.failure_limit,
+        compactor=Compactor(
+            normalized, config.tuning.context.compaction(), oplog=oplog
+        ),
     )
     tuning = config.tuning
     helpers = Helpers(

nisse-dev/tests/test_config.py

@@ -354,6 +354,18 @@ def test_context_tuning_is_read_and_checked() -> None:
         build(tuning={"context": {"safety_margin": 1}})
 
 
+def test_compaction_tuning_is_read_and_checked() -> None:
+    compaction = build().tuning.context.compaction()
+    assert (compaction.compact_at, compaction.compact_to) == (0.6, 0.25)
+    assert compaction.keep_turns == 3
+    off = build(tuning={"context": {"compact_at": 0}}).tuning.context
+    assert off.compaction().compact_at == 0
+    with pytest.raises(ConfigError, match="compact_to must be less than compact_at"):
+        build(tuning={"context": {"compact_at": 0.3, "compact_to": 0.5}})
+    with pytest.raises(ConfigError, match="compact_to must be less than compact_at"):
+        build(tuning={"context": {"compact_at": 1.5}})
+
+
 def test_the_build_host_is_required_and_defaults_to_root_on_22() -> None:
     host = only(build()).build_host
     assert (host.address, host.user) == ("build.test", "root")