mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-29 06:31:32 +00:00
fix(compressor): propagate api_mode and fix root logger calls
- Add api_mode to 4 update_model() call sites: - conversation_loop.py: long_context failover and probe stepping - agent_runtime_helpers.py: rollback restore (also saves compressor_api_mode) - chat_completion_helpers.py: fallback activation - Fix 31 root-logger calls across 5 files (logging.warning/error/info -> logger.warning/error/info) to respect module-level log filtering
This commit is contained in:
0z1-ghb
Teknium
parent
8b2adead78
commit
dcbcdd6526
5 changed files with 36 additions and 31 deletions
|
|
@ -132,7 +132,7 @@ def convert_to_trajectory_format(agent, messages: List[Dict[str, Any]], user_que
|
|||
except json.JSONDecodeError:
|
||||
# This shouldn't happen since we validate and retry during conversation,
|
||||
# but if it does, log warning and use empty dict
|
||||
logging.warning(f"Unexpected invalid JSON in trajectory conversion: {tool_call['function']['arguments'][:100]}")
|
||||
logger.warning(f"Unexpected invalid JSON in trajectory conversion: {tool_call['function']['arguments'][:100]}")
|
||||
arguments = {}
|
||||
|
||||
tool_call_json = {
|
||||
|
|
@ -747,7 +747,7 @@ def try_recover_primary_transport(
|
|||
time.sleep(wait_time)
|
||||
return True
|
||||
except Exception as e:
|
||||
logging.warning("Primary transport recovery failed: %s", e)
|
||||
logger.warning("Primary transport recovery failed: %s", e)
|
||||
return False
|
||||
|
||||
# ── End provider fallback ──────────────────────────────────────────────
|
||||
|
|
@ -910,19 +910,20 @@ def restore_primary_runtime(agent) -> bool:
|
|||
base_url=rt["compressor_base_url"],
|
||||
api_key=rt["compressor_api_key"],
|
||||
provider=rt["compressor_provider"],
|
||||
api_mode=rt.get("compressor_api_mode", ""),
|
||||
)
|
||||
|
||||
# ── Reset fallback chain for the new turn ──
|
||||
agent._fallback_activated = False
|
||||
agent._fallback_index = 0
|
||||
|
||||
logging.info(
|
||||
logger.info(
|
||||
"Primary runtime restored for new turn: %s (%s)",
|
||||
agent.model, agent.provider,
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
logging.warning("Failed to restore primary runtime: %s", e)
|
||||
logger.warning("Failed to restore primary runtime: %s", e)
|
||||
return False
|
||||
|
||||
# Which error types indicate a transient transport failure worth
|
||||
|
|
@ -1093,7 +1094,7 @@ def dump_api_request_debug(
|
|||
return dump_file
|
||||
except Exception as dump_error:
|
||||
if agent.verbose_logging:
|
||||
logging.warning(f"Failed to dump API request debug payload: {dump_error}")
|
||||
logger.warning(f"Failed to dump API request debug payload: {dump_error}")
|
||||
return None
|
||||
|
||||
|
||||
|
|
@ -1478,6 +1479,7 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
|
|||
"compressor_api_key": getattr(_cc, "api_key", "") if _cc else "",
|
||||
"compressor_provider": getattr(_cc, "provider", agent.provider) if _cc else agent.provider,
|
||||
"compressor_context_length": _cc.context_length if _cc else 0,
|
||||
"compressor_api_mode": getattr(_cc, "api_mode", agent.api_mode) if _cc else agent.api_mode,
|
||||
"compressor_threshold_tokens": _cc.threshold_tokens if _cc else 0,
|
||||
}
|
||||
if api_mode == "anthropic_messages":
|
||||
|
|
@ -1509,7 +1511,7 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
|
|||
agent._fallback_chain = fallback_chain
|
||||
agent._fallback_model = fallback_chain[0] if fallback_chain else None
|
||||
|
||||
logging.info(
|
||||
logger.info(
|
||||
"Model switched in-place: %s (%s) -> %s (%s)",
|
||||
old_model, old_provider, new_model, new_provider,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -757,7 +757,7 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
|||
current_base_url = str(getattr(agent, "base_url", "") or "").rstrip("/").lower()
|
||||
fb_base_url_for_dedup = (fb.get("base_url") or "").strip().rstrip("/").lower()
|
||||
if fb_provider == current_provider and fb_model == current_model:
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"Fallback skip: chain entry %s/%s matches current provider/model",
|
||||
fb_provider, fb_model,
|
||||
)
|
||||
|
|
@ -768,7 +768,7 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
|||
and fb_base_url_for_dedup == current_base_url
|
||||
and fb_model == current_model
|
||||
):
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"Fallback skip: chain entry base_url %s matches current backend",
|
||||
fb_base_url_for_dedup,
|
||||
)
|
||||
|
|
@ -800,7 +800,7 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
|||
explicit_base_url=fb_base_url_hint,
|
||||
explicit_api_key=fb_api_key_hint)
|
||||
if fb_client is None:
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"Fallback to %s failed: provider not configured",
|
||||
fb_provider)
|
||||
return agent._try_activate_fallback() # try next in chain
|
||||
|
|
@ -940,19 +940,20 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
|
|||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""), # callable preserved → call_llm
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
|
||||
agent._emit_status(
|
||||
f"🔄 Primary model failed — switching to fallback: "
|
||||
f"{fb_model} via {fb_provider}"
|
||||
)
|
||||
logging.info(
|
||||
logger.info(
|
||||
"Fallback activated: %s → %s (%s)",
|
||||
old_model, fb_model, fb_provider,
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
logging.error("Failed to activate fallback %s: %s", fb_model, e)
|
||||
logger.error("Failed to activate fallback %s: %s", fb_model, e)
|
||||
return agent._try_activate_fallback() # try next in chain
|
||||
|
||||
|
||||
|
|
@ -1168,7 +1169,7 @@ def handle_max_iterations(agent, messages: list, api_call_count: int) -> str:
|
|||
final_response = "I reached the iteration limit and couldn't generate a summary."
|
||||
|
||||
except Exception as e:
|
||||
logging.warning(f"Failed to get summary response: {e}")
|
||||
logger.warning(f"Failed to get summary response: {e}")
|
||||
final_response = f"I reached the maximum iterations ({agent.max_iterations}) but couldn't summarize. Error: {str(e)}"
|
||||
|
||||
return final_response
|
||||
|
|
@ -1197,12 +1198,12 @@ def cleanup_task_resources(agent, task_id: str) -> None:
|
|||
_ra().cleanup_vm(task_id)
|
||||
except Exception as e:
|
||||
if agent.verbose_logging:
|
||||
logging.warning(f"Failed to cleanup VM for task {task_id}: {e}")
|
||||
logger.warning(f"Failed to cleanup VM for task {task_id}: {e}")
|
||||
try:
|
||||
_ra().cleanup_browser(task_id)
|
||||
except Exception as e:
|
||||
if agent.verbose_logging:
|
||||
logging.warning(f"Failed to cleanup browser for task {task_id}: {e}")
|
||||
logger.warning(f"Failed to cleanup browser for task {task_id}: {e}")
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -1183,7 +1183,7 @@ def run_conversation(
|
|||
else str(_codex_error_obj) if _codex_error_obj
|
||||
else f"Responses API returned status '{_codex_resp_status}'"
|
||||
)
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"Codex response status='%s' (error=%s). Routing to fallback. %s",
|
||||
_codex_resp_status, _codex_error_msg,
|
||||
agent._client_log_context(),
|
||||
|
|
@ -1335,7 +1335,7 @@ def run_conversation(
|
|||
primary_recovery_attempted = False
|
||||
continue
|
||||
agent._emit_status(f"❌ Max retries ({max_retries}) exceeded for invalid responses. Giving up.")
|
||||
logging.error(f"{agent.log_prefix}Invalid API response after {max_retries} retries.")
|
||||
logger.error(f"{agent.log_prefix}Invalid API response after {max_retries} retries.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
|
|
@ -1348,7 +1348,7 @@ def run_conversation(
|
|||
# Backoff before retry — jittered exponential: 5s base, 120s cap
|
||||
wait_time = jittered_backoff(retry_count, base_delay=5.0, max_delay=120.0)
|
||||
agent._vprint(f"{agent.log_prefix}⏳ Retrying in {wait_time:.1f}s ({_failure_hint})...", force=True)
|
||||
logging.warning(f"Invalid API response (retry {retry_count}/{max_retries}): {', '.join(error_details)} | Provider: {provider_name}")
|
||||
logger.warning(f"Invalid API response (retry {retry_count}/{max_retries}): {', '.join(error_details)} | Provider: {provider_name}")
|
||||
|
||||
# Sleep in small increments to stay responsive to interrupts
|
||||
sleep_end = time.time() + wait_time
|
||||
|
|
@ -2225,7 +2225,7 @@ def run_conversation(
|
|||
f"stripped all thinking blocks, retrying...",
|
||||
force=True,
|
||||
)
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"%sThinking block signature recovery: stripped "
|
||||
"reasoning_details from %d messages",
|
||||
agent.log_prefix, len(messages),
|
||||
|
|
@ -2250,7 +2250,7 @@ def run_conversation(
|
|||
from tools.schema_sanitizer import strip_pattern_and_format
|
||||
_, _stripped = strip_pattern_and_format(agent.tools)
|
||||
except Exception as _strip_exc: # pragma: no cover — defensive
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"%sllama.cpp grammar recovery: strip helper failed: %s",
|
||||
agent.log_prefix, _strip_exc,
|
||||
)
|
||||
|
|
@ -2261,7 +2261,7 @@ def run_conversation(
|
|||
f"stripped {_stripped} pattern/format keyword(s), retrying...",
|
||||
force=True,
|
||||
)
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"%sllama.cpp grammar recovery: stripped %d "
|
||||
"pattern/format keyword(s) from tool schemas",
|
||||
agent.log_prefix, _stripped,
|
||||
|
|
@ -2269,7 +2269,7 @@ def run_conversation(
|
|||
continue
|
||||
# No keywords found to strip — fall through to normal
|
||||
# retry path rather than loop forever on the same error.
|
||||
logging.warning(
|
||||
logger.warning(
|
||||
"%sllama.cpp grammar error but no pattern/format "
|
||||
"keywords to strip — falling through to normal retry",
|
||||
agent.log_prefix,
|
||||
|
|
@ -2370,6 +2370,7 @@ def run_conversation(
|
|||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""),
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
# Context probing flags — only set on built-in
|
||||
# compressor (plugin engines manage their own).
|
||||
|
|
@ -2483,7 +2484,7 @@ def run_conversation(
|
|||
error_context=error_context,
|
||||
)
|
||||
else:
|
||||
logging.info(
|
||||
logger.info(
|
||||
"Nous 429 looks like upstream capacity "
|
||||
"(no exhausted bucket in headers or "
|
||||
"last-known state) -- not tripping "
|
||||
|
|
@ -2543,7 +2544,7 @@ def run_conversation(
|
|||
if compression_attempts > max_compression_attempts:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached for payload-too-large error.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logging.error(f"{agent.log_prefix}413 compression failed after {max_compression_attempts} attempts.")
|
||||
logger.error(f"{agent.log_prefix}413 compression failed after {max_compression_attempts} attempts.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
|
|
@ -2574,7 +2575,7 @@ def run_conversation(
|
|||
else:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Payload too large and cannot compress further.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logging.error(f"{agent.log_prefix}413 payload too large. Cannot compress further.")
|
||||
logger.error(f"{agent.log_prefix}413 payload too large. Cannot compress further.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
|
|
@ -2627,7 +2628,7 @@ def run_conversation(
|
|||
if compression_attempts > max_compression_attempts:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logging.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
logger.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
|
|
@ -2679,6 +2680,7 @@ def run_conversation(
|
|||
base_url=agent.base_url,
|
||||
api_key=getattr(agent, "api_key", ""),
|
||||
provider=agent.provider,
|
||||
api_mode=agent.api_mode,
|
||||
)
|
||||
# Context probing flags — only set on built-in
|
||||
# compressor (plugin engines manage their own).
|
||||
|
|
@ -2700,7 +2702,7 @@ def run_conversation(
|
|||
if compression_attempts > max_compression_attempts:
|
||||
agent._vprint(f"{agent.log_prefix}❌ Max compression attempts ({max_compression_attempts}) reached.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 Try /new to start a fresh conversation, or /compress to retry compression.", force=True)
|
||||
logging.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
logger.error(f"{agent.log_prefix}Context compression failed after {max_compression_attempts} attempts.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
|
|
@ -2733,7 +2735,7 @@ def run_conversation(
|
|||
# Can't compress further and already at minimum tier
|
||||
agent._vprint(f"{agent.log_prefix}❌ Context length exceeded and cannot compress further.", force=True)
|
||||
agent._vprint(f"{agent.log_prefix} 💡 The conversation has accumulated too much content. Try /new to start fresh, or /compress to manually trigger compression.", force=True)
|
||||
logging.error(f"{agent.log_prefix}Context length exceeded: {approx_tokens:,} tokens. Cannot compress further.")
|
||||
logger.error(f"{agent.log_prefix}Context length exceeded: {approx_tokens:,} tokens. Cannot compress further.")
|
||||
agent._persist_session(messages, conversation_history)
|
||||
return {
|
||||
"messages": messages,
|
||||
|
|
@ -2826,7 +2828,7 @@ def run_conversation(
|
|||
agent._vprint(f"{agent.log_prefix} • Check credits: https://openrouter.ai/settings/credits", force=True)
|
||||
else:
|
||||
agent._vprint(f"{agent.log_prefix} 💡 This type of error won't be fixed by retrying.", force=True)
|
||||
logging.error(f"{agent.log_prefix}Non-retryable client error: {api_error}")
|
||||
logger.error(f"{agent.log_prefix}Non-retryable client error: {api_error}")
|
||||
# Skip session persistence when the error is likely
|
||||
# context-overflow related (status 400 + large session).
|
||||
# Persisting the failed user message would make the
|
||||
|
|
@ -2903,7 +2905,7 @@ def run_conversation(
|
|||
force=True,
|
||||
)
|
||||
|
||||
logging.error(
|
||||
logger.error(
|
||||
"%sAPI call failed after %s retries. %s | provider=%s model=%s msgs=%s tokens=~%s",
|
||||
agent.log_prefix, max_retries, _final_summary,
|
||||
_provider, _model, len(api_messages), f"{approx_tokens:,}",
|
||||
|
|
|
|||
|
|
@ -641,7 +641,7 @@ def fetch_model_metadata(force_refresh: bool = False) -> Dict[str, Dict[str, Any
|
|||
return cache
|
||||
|
||||
except Exception as e:
|
||||
logging.warning(f"Failed to fetch model metadata from OpenRouter: {e}")
|
||||
logger.warning(f"Failed to fetch model metadata from OpenRouter: {e}")
|
||||
return _model_metadata_cache or {}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -491,7 +491,7 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
|
|||
try:
|
||||
function_args = json.loads(tool_call.function.arguments)
|
||||
except json.JSONDecodeError as e:
|
||||
logging.warning(f"Unexpected JSON error after validation: {e}")
|
||||
logger.warning(f"Unexpected JSON error after validation: {e}")
|
||||
function_args = {}
|
||||
if not isinstance(function_args, dict):
|
||||
function_args = {}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue