fix(compression): make the attempt cap config-driven and enforce it at every compression site

agent/agent_init.py

@@ -1781,6 +1781,34 @@ def _moa_reference_relay(event: str, **kwargs: Any) -> None:
     compression_enabled = str(_compression_cfg.get("enabled", True)).lower() in {"true", "1", "yes"}
     compression_target_ratio = float(_compression_cfg.get("target_ratio", 0.20))
     compression_protect_last = int(_compression_cfg.get("protect_last_n", 20))
+    # Cap on compression retry rounds before a turn gives up with "max
+    # compression attempts reached" (compression.max_attempts).  Hardcoding 3
+    # strands sessions that legitimately need more rounds — e.g. a restart
+    # history reload whose incompressible tool schemas keep the request
+    # estimate above the threshold even though the messages compress fine
+    # (the #62605 failure class).  Default 3 preserves current behavior, so
+    # an unset key is behavior-neutral; validated >= 1, hard-capped at 10,
+    # and any non-int-like value falls back to 3.  Booleans are rejected
+    # (bool subclasses int, so int(True) would silently become 1) and
+    # fractional floats are rejected rather than truncated — "4.7 attempts"
+    # is a config mistake, not a request for 4.
+    _raw_max_attempts = _compression_cfg.get("max_attempts", 3)
+    if isinstance(_raw_max_attempts, bool):
+        compression_max_attempts = 3
+    elif isinstance(_raw_max_attempts, int):
+        compression_max_attempts = _raw_max_attempts
+    elif isinstance(_raw_max_attempts, float):
+        compression_max_attempts = (
+            int(_raw_max_attempts) if _raw_max_attempts.is_integer() else 3
+        )
+    else:
+        try:
+            compression_max_attempts = int(str(_raw_max_attempts).strip())
+        except (TypeError, ValueError):
+            compression_max_attempts = 3
+    if compression_max_attempts < 1:
+        compression_max_attempts = 3
+    compression_max_attempts = min(compression_max_attempts, 10)
     # protect_first_n is the number of non-system messages to protect at
     # the head, in addition to the system prompt (which is always
     # implicitly protected by the compressor).  Floor at 0 — a value of
@@ -2224,6 +2252,7 @@ def _moa_reference_relay(event: str, **kwargs: Any) -> None:
     agent.compression_enabled = compression_enabled
     agent.compression_in_place = compression_in_place
     agent.codex_app_server_auto_compaction = codex_app_server_auto_compaction
+    agent.max_compression_attempts = compression_max_attempts
 
     # Reject models whose context window is below the minimum required
     # for reliable tool-calling workflows (64K tokens).

agent/conversation_loop.py

@@ -685,6 +685,13 @@ def run_conversation(
     truncated_tool_call_retries = 0
     truncated_response_parts: List[str] = []
     compression_attempts = 0
+    # One resolved per-turn compression attempt cap, shared by every site that
+    # consumes ``compression_attempts``: the pre-API pressure gate, the
+    # overflow/413 retry handlers, and the post-tool compaction gate.
+    # Config-driven via compression.max_attempts (parsed + validated in
+    # agent_init); default 3 preserves the prior hardcoded behavior for
+    # objects without the attribute (older pickles / minimal stubs).
+    max_compression_attempts = getattr(agent, "max_compression_attempts", 3)
     _last_preflight_pressure: Optional[int] = None
     _preflight_compression_blocked = _ctx.preflight_compression_blocked
     _turn_exit_reason = "unknown"  # Diagnostic: why the loop ended
@@ -1168,7 +1175,7 @@ def run_conversation(
         if (
             agent.compression_enabled
             and len(messages) > 1
-            and compression_attempts < 3
+            and compression_attempts < max_compression_attempts
             and not _preflight_compression_blocked
             and not _defer_preflight(request_pressure_tokens)
             and not _compression_cooldown
@@ -1177,12 +1184,13 @@ def run_conversation(
             compression_attempts += 1
             logger.info(
                 "Pre-API compression: ~%s request tokens >= %s threshold "
-                "(context=%s, attempt=%s/3)",
+                "(context=%s, attempt=%s/%s)",
                 f"{request_pressure_tokens:,}",
                 f"{int(getattr(_compressor, 'threshold_tokens', 0) or 0):,}",
                 f"{int(getattr(_compressor, 'context_length', 0) or 0):,}"
                 if getattr(_compressor, "context_length", 0) else "unknown",
                 compression_attempts,
+                max_compression_attempts,
             )
             agent._emit_status(
                 f"📦 Pre-API compression: ~{request_pressure_tokens:,} tokens "
@@ -1252,7 +1260,6 @@ def run_conversation(
         retry_count = 0
         max_retries = agent._api_max_retries
         _retry = TurnRetryState()
-        max_compression_attempts = 3
 
         finish_reason = "stop"
         response = None  # Guard against UnboundLocalError if all retries fail
@@ -5175,7 +5182,12 @@ def _perform_api_call(next_api_kwargs):
                         messages, tools=agent.tools or None
                     )
 
-                if agent.compression_enabled and _compressor.should_compress(_real_tokens):
+                if (
+                    agent.compression_enabled
+                    and compression_attempts < max_compression_attempts
+                    and _compressor.should_compress(_real_tokens)
+                ):
+                    compression_attempts += 1
                     agent._safe_print("  ⟳ compacting context…")
                     messages, active_system_prompt = agent._compress_context(
                         messages, system_message,

agent/turn_context.py

@@ -665,7 +665,13 @@ def build_turn_context(
                 f">= {_compressor.threshold_tokens:,} threshold. "
                 "This may take a moment."
             )
-            for _pass in range(3):
+            # Preflight passes honor the same configured per-turn cap
+            # (compression.max_attempts) as the loop's compression sites;
+            # default 3 preserves the prior hardcoded behavior.
+            _max_preflight_passes = max(
+                1, int(getattr(agent, "max_compression_attempts", 3) or 3)
+            )
+            for _pass in range(_max_preflight_passes):
                 _orig_len = len(messages)
                 _orig_tokens = _preflight_tokens
                 messages, active_system_prompt = agent._compress_context(

cli-config.yaml.example

@@ -429,6 +429,12 @@ compression:
   # compression of older turns.
   protect_last_n: 20
 
+  # Compression retry rounds before a turn gives up with "max compression
+  # attempts reached" (default: 3, same as the previous hardcoded value).
+  # Raise (e.g. 6) for tool-schema-heavy sessions where 3 rounds cannot bring
+  # the request estimate under the threshold. Validated >= 1, hard cap 10.
+  max_attempts: 3
+
   # Codex app-server (codex CLI runtime) thread-compaction mode. The codex
   # agent owns the real thread context on this runtime, so Hermes' summarizer
   # cannot shrink it — compaction goes through the app server instead.

contributors/emails/dominicbejar@gmail.com

@@ -0,0 +1 @@
+dombejar

hermes_cli/config.py

@@ -1471,6 +1471,11 @@ def _ensure_hermes_home_managed(home: Path):
                                       # set this above 0.75 to override the floor.
         "target_ratio": 0.20,         # fraction of threshold to preserve as recent tail
         "protect_last_n": 20,         # minimum recent messages to keep uncompressed
+        "max_attempts": 3,            # compression retry rounds before a turn gives up
+                                      # with "max compression attempts reached". Raise
+                                      # (e.g. 6) for tool-schema-heavy sessions where 3
+                                      # rounds cannot clear the request estimate.
+                                      # Validated >= 1, hard-capped at 10.
         "hygiene_hard_message_limit": 5000,  # gateway session-hygiene force-compress threshold by message count
         "protect_first_n": 3,         # non-system head messages always preserved
                                       # verbatim, in ADDITION to the system prompt

tests/agent/test_compression_max_attempts_config.py

@@ -0,0 +1,119 @@
+"""compression.max_attempts — config-driven compression retry cap.
+
+The conversation loop's compression retry cap was hardcoded to 3, stranding
+sessions that legitimately need more rounds — e.g. a restart history reload
+whose incompressible tool schemas keep the request estimate above the
+threshold while the messages themselves compress fine (the #62605 failure
+class).  The cap is now parsed from ``compression.max_attempts`` in
+``agent_init`` and read by the loop via
+``getattr(agent, "max_compression_attempts", 3)``.
+
+These tests pin the parse/validate/attach seam: default preserved, custom
+value honored, floor and ceiling enforced, garbage tolerated.
+"""
+
+from __future__ import annotations
+
+import contextlib
+import io
+from pathlib import Path
+
+from hermes_state import SessionDB
+from run_agent import AIAgent
+
+
+def _config(max_attempts=None) -> dict:
+    compression = {
+        "enabled": True,
+        "threshold": 0.50,
+        "target_ratio": 0.20,
+        "protect_first_n": 3,
+        "protect_last_n": 20,
+    }
+    if max_attempts is not None:
+        compression["max_attempts"] = max_attempts
+    return {
+        "compression": compression,
+        "prompt_caching": {"cache_ttl": "5m"},
+        "sessions": {},
+        "bedrock": {},
+    }
+
+
+def _make_agent(monkeypatch, tmp_path: Path, *, max_attempts=None):
+    from hermes_cli import config as config_mod
+
+    monkeypatch.setattr(
+        config_mod, "load_config", lambda: _config(max_attempts=max_attempts)
+    )
+    db = SessionDB(db_path=tmp_path / "state.db")
+    with contextlib.redirect_stdout(io.StringIO()):
+        agent = AIAgent(
+            base_url="https://chatgpt.com/backend-api/codex",
+            api_key="test-key",
+            provider="openai-codex",
+            model="gpt-5.5",
+            enabled_toolsets=[],
+            disabled_toolsets=[],
+            quiet_mode=True,
+            skip_memory=True,
+            session_db=db,
+            session_id="max-attempts-test",
+        )
+    return agent
+
+
+class TestCompressionMaxAttemptsConfig:
+    def test_default_is_three_when_unset(self, monkeypatch, tmp_path):
+        agent = _make_agent(monkeypatch, tmp_path)
+        assert agent.max_compression_attempts == 3
+
+    def test_custom_value_is_honored(self, monkeypatch, tmp_path):
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=6)
+        assert agent.max_compression_attempts == 6
+
+    def test_hard_capped_at_ten(self, monkeypatch, tmp_path):
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=25)
+        assert agent.max_compression_attempts == 10
+
+    def test_zero_and_negative_fall_back_to_default(self, monkeypatch, tmp_path):
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=0)
+        assert agent.max_compression_attempts == 3
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=-2)
+        assert agent.max_compression_attempts == 3
+
+    def test_non_integer_falls_back_to_default(self, monkeypatch, tmp_path):
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts="lots")
+        assert agent.max_compression_attempts == 3
+
+    def test_boolean_is_rejected_not_coerced(self, monkeypatch, tmp_path):
+        # bool subclasses int: int(True) == 1 would silently near-disable
+        # compression retries. YAML `max_attempts: true` must fall back to 3.
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=True)
+        assert agent.max_compression_attempts == 3
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=False)
+        assert agent.max_compression_attempts == 3
+
+    def test_fractional_float_is_rejected_not_truncated(self, monkeypatch, tmp_path):
+        # "4.7 attempts" is a config mistake, not a request for 4.
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=4.7)
+        assert agent.max_compression_attempts == 3
+
+    def test_integral_float_and_numeric_string_are_accepted(
+        self, monkeypatch, tmp_path
+    ):
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=5.0)
+        assert agent.max_compression_attempts == 5
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts="6")
+        assert agent.max_compression_attempts == 6
+
+    def test_loop_pickup_degrades_to_default_when_attribute_missing(
+        self, monkeypatch, tmp_path
+    ):
+        # The loop reads getattr(agent, "max_compression_attempts", 3): a
+        # configured agent exposes its value, and an object without the
+        # attribute (older pickle / minimal stub) degrades to the prior
+        # hardcoded behavior.
+        agent = _make_agent(monkeypatch, tmp_path, max_attempts=7)
+        assert getattr(agent, "max_compression_attempts", 3) == 7
+        assert getattr(object(), "max_compression_attempts", 3) == 3