common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix(insights): persist token usage for non-CLI sessions

Browse Source
This commit is contained in:
kshitijk4poor
2026-04-02 11:15:16 +05:30
committed by Teknium
parent 585855d2ca
commit 20441cf2c8
6 changed files with 73 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gateway/run.py
View File

@@ -2804,20 +2804,12 @@ class GatewayRunner:
skip_db=agent_persisted,
)
# Update session with actual prompt token count and model from the agent
# Token counts and model are now persisted by the agent directly.
# Keep only last_prompt_tokens here for context-window tracking and
# compression decisions.
self.session_store.update_session(
session_entry.session_key,
input_tokens=agent_result.get("input_tokens", 0),
output_tokens=agent_result.get("output_tokens", 0),
cache_read_tokens=agent_result.get("cache_read_tokens", 0),
cache_write_tokens=agent_result.get("cache_write_tokens", 0),
last_prompt_tokens=agent_result.get("last_prompt_tokens", 0),
model=agent_result.get("model"),
estimated_cost_usd=agent_result.get("estimated_cost_usd"),
cost_status=agent_result.get("cost_status"),
cost_source=agent_result.get("cost_source"),
provider=agent_result.get("provider"),
base_url=agent_result.get("base_url"),
)
# Auto voice reply: send TTS audio before the text response

50
gateway/session.py
View File

@@ -778,66 +778,18 @@ class SessionStore:
def update_session(
self,
session_key: str,
input_tokens: int = 0,
output_tokens: int = 0,
cache_read_tokens: int = 0,
cache_write_tokens: int = 0,
last_prompt_tokens: int = None,
model: str = None,
estimated_cost_usd: Optional[float] = None,
cost_status: Optional[str] = None,
cost_source: Optional[str] = None,
provider: Optional[str] = None,
base_url: Optional[str] = None,
) -> None:
"""Update a session's metadata after an interaction."""
db_session_id = None
"""Update lightweight session metadata after an interaction."""
with self._lock:
self._ensure_loaded_locked()
if session_key in self._entries:
entry = self._entries[session_key]
entry.updated_at = _now()
# Direct assignment — the gateway receives cumulative totals
# from the cached agent, not per-call deltas.
entry.input_tokens = input_tokens
entry.output_tokens = output_tokens
entry.cache_read_tokens = cache_read_tokens
entry.cache_write_tokens = cache_write_tokens
if last_prompt_tokens is not None:
entry.last_prompt_tokens = last_prompt_tokens
if estimated_cost_usd is not None:
entry.estimated_cost_usd = estimated_cost_usd
if cost_status:
entry.cost_status = cost_status
entry.total_tokens = (
entry.input_tokens
+ entry.output_tokens
+ entry.cache_read_tokens
+ entry.cache_write_tokens
)
self._save()
db_session_id = entry.session_id
if self._db and db_session_id:
try:
self._db.set_token_counts(
db_session_id,
input_tokens=input_tokens,
output_tokens=output_tokens,
cache_read_tokens=cache_read_tokens,
cache_write_tokens=cache_write_tokens,
estimated_cost_usd=estimated_cost_usd,
cost_status=cost_status,
cost_source=cost_source,
billing_provider=provider,
billing_base_url=base_url,
model=model,
absolute=True,
)
except Exception as e:
logger.debug("Session DB operation failed: %s", e)
def reset_session(self, session_key: str) -> Optional[SessionEntry]:
"""Force reset a session, creating a new session ID."""