fix(compact): live-carrier for tool search pairs

.all-contributorsrc

@@ -1084,50 +1084,10 @@
       ]
     },
     {
-      "login": "shaqman",
-      "name": "Syakur Rahman",
-      "avatar_url": "https://avatars.githubusercontent.com/u/1113851?v=4",
-      "profile": "http://expressthisout.com/",
-      "contributions": [
-        "code",
-        "test"
-      ]
-    },
-    {
-      "login": "cigro-manager",
-      "name": "cigro-manager",
-      "avatar_url": "https://avatars.githubusercontent.com/u/219247995?v=4",
-      "profile": "https://github.com/cigro-manager",
-      "contributions": [
-        "code"
-      ]
-    },
-    {
-      "login": "lkraider",
-      "name": "Paul Eipper",
-      "avatar_url": "https://avatars.githubusercontent.com/u/52256?v=4",
-      "profile": "https://github.com/lkraider",
-      "contributions": [
-        "code",
-        "test",
-        "doc"
-      ]
-    },
-    {
-      "login": "ret2basic",
-      "name": "ret2basic.eth",
-      "avatar_url": "https://avatars.githubusercontent.com/u/59381775?v=4",
-      "profile": "https://github.com/ret2basic",
-      "contributions": [
-        "code",
-        "test"
-      ]
-    },
-    {
-      "login": "yeongjun-cigro",
-      "name": "유영준",
-      "avatar_url": "https://avatars.githubusercontent.com/u/260819931?v=4",
-      "profile": "https://github.com/yeongjun-cigro",
+      "login": "glopyglerky",
+      "name": "glopyglerky",
+      "avatar_url": "https://avatars.githubusercontent.com/u/189872235?v=4",
+      "profile": "https://github.com/glopyglerky",
       "contributions": [
         "code",
         "test"

app/core/balancer/__init__.py

@@ -11,6 +11,7 @@
     ROUTING_POLICY_PRESERVE,
     TRAFFIC_CLASS_FOREGROUND,
     TRAFFIC_CLASS_OPPORTUNISTIC,
+    USAGE_LIMIT_REACHED,
     AccountState,
     FailoverAction,
     ResetPreferenceWindow,
@@ -28,6 +29,7 @@
     handle_quota_exceeded,
     handle_rate_limit,
     plausible_rate_limit_reset_at,
+    pool_usage_exhaustion,
     select_account,
 )
 
@@ -52,6 +54,7 @@
     "RoutingStrategy",
     "TrafficClass",
     "SelectionResult",
+    "USAGE_LIMIT_REACHED",
     "UsageWeightedOrder",
     "account_status_for_permanent_failure",
     "configure_replica_salt",
@@ -61,5 +64,6 @@
     "handle_quota_exceeded",
     "handle_rate_limit",
     "plausible_rate_limit_reset_at",
+    "pool_usage_exhaustion",
     "select_account",
 ]

app/core/balancer/logic.py

@@ -145,6 +145,90 @@ class AccountState:
 class SelectionResult:
     account: AccountState | None
     error_message: str | None
+    error_code: str | None = None
+    resets_at: int | None = None
+
+
+USAGE_LIMIT_REACHED = "usage_limit_reached"
+
+
+def pool_usage_exhaustion(
+    states: Iterable[AccountState],
+    *,
+    current: float,
+    ignore_standard_quota: bool = False,
+    ignore_standard_quota_account_ids: Collection[str] | None = None,
+) -> SelectionResult | None:
+    """Describe pool-wide subscription exhaustion without parsing retry text."""
+    if ignore_standard_quota:
+        return None
+    ignored_account_ids = set(ignore_standard_quota_account_ids or ())
+
+    def _primary_usage_evidence(state: AccountState) -> float | None:
+        return state.priority_used_percent if state.priority_used_percent is not None else state.used_percent
+
+    def _secondary_usage_evidence(state: AccountState) -> float | None:
+        if state.limit_scoped_usage and state.priority_secondary_used_percent is None:
+            return _primary_usage_evidence(state)
+        return (
+            state.priority_secondary_used_percent
+            if state.priority_secondary_used_percent is not None
+            else state.secondary_used_percent
+        )
+
+    def _usage_exhausted(state: AccountState) -> bool:
+        if state.status not in (AccountStatus.QUOTA_EXCEEDED, AccountStatus.RATE_LIMITED):
+            return False
+        usage_values = (_primary_usage_evidence(state), _secondary_usage_evidence(state))
+        return any(value is not None and float(value) >= 100.0 for value in usage_values)
+
+    def _usage_exhausted_reset_at(state: AccountState) -> float | None:
+        if state.status not in (AccountStatus.QUOTA_EXCEEDED, AccountStatus.RATE_LIMITED):
+            return None
+        candidates: list[float] = []
+        primary_evidence = _primary_usage_evidence(state)
+        secondary_evidence = _secondary_usage_evidence(state)
+        if primary_evidence is not None and float(primary_evidence) >= 100.0 and state.primary_reset_at is not None:
+            candidates.append(float(state.primary_reset_at))
+        if (
+            secondary_evidence is not None
+            and float(secondary_evidence) >= 100.0
+            and state.secondary_reset_at is not None
+        ):
+            candidates.append(float(state.secondary_reset_at))
+        if not candidates:
+            return None
+        return max(candidates)
+
+    eligible = [
+        state
+        for state in states
+        if not state.ignore_standard_quota
+        and state.account_id not in ignored_account_ids
+        and state.status
+        not in (
+            AccountStatus.PAUSED,
+            AccountStatus.REAUTH_REQUIRED,
+            AccountStatus.DEACTIVATED,
+        )
+    ]
+    if not eligible or any(not _usage_exhausted(state) for state in eligible):
+        return None
+
+    # Only usage-proven exhausted accounts reach this branch; surface the
+    # earliest reset for an actually exhausted window so the structured 429
+    # does not retry a secondary-window exhaustion at the primary reset time.
+    reset_candidates = [reset_at for state in eligible if (reset_at := _usage_exhausted_reset_at(state)) is not None]
+    resets_at = int(min(reset_candidates)) if reset_candidates else None
+    message = "Usage limit reached"
+    if resets_at is not None:
+        message = _format_retry_hint(max(0.0, resets_at - current))
+    return SelectionResult(
+        account=None,
+        error_message=message,
+        error_code=USAGE_LIMIT_REACHED,
+        resets_at=resets_at,
+    )
 
 
 @dataclass(frozen=True, slots=True)
@@ -379,6 +463,8 @@ def select_account(
     primary_first_usage_weighted: bool = False,
     routing_costs: RoutingCostsByAccount | None = None,
     replica_salt: str | None = None,
+    allow_usage_exhaustion_error: bool = True,
+    usage_exhaustion_states: Iterable[AccountState] | None = None,
 ) -> SelectionResult:
     """Select an eligible account by applying availability checks and routing strategy.
 
@@ -446,6 +532,7 @@ def select_account(
     available: list[AccountState] = []
     in_error_backoff: list[AccountState] = []
     all_states = list(states)
+    usage_exhaustion_state_list = list(usage_exhaustion_states) if usage_exhaustion_states is not None else all_states
     bypass_account_ids = None if bypass_quota_exceeded_account_ids is None else set(bypass_quota_exceeded_account_ids)
 
     for state in all_states:
@@ -529,6 +616,15 @@ def _backoff_expires_at(s: AccountState) -> float:
                     return SelectionResult(None, f"opportunistic burn window closed: {reason}")
                 available = opportunistic_available
         else:
+            if allow_usage_exhaustion_error:
+                usage_exhaustion = pool_usage_exhaustion(
+                    usage_exhaustion_state_list,
+                    current=current,
+                    ignore_standard_quota=ignore_standard_quota or bypass_quota_exceeded,
+                    ignore_standard_quota_account_ids=bypass_account_ids,
+                )
+                if usage_exhaustion is not None:
+                    return usage_exhaustion
             reauth_required = [s for s in all_states if s.status == AccountStatus.REAUTH_REQUIRED]
             deactivated = [s for s in all_states if s.status == AccountStatus.DEACTIVATED]
             paused = [s for s in all_states if s.status == AccountStatus.PAUSED]

app/core/errors.py

@@ -47,8 +47,17 @@ class ResponseFailedEvent(TypedDict):
 PREVIOUS_RESPONSE_NOT_FOUND_MESSAGE = "Previous response was not found; retry without previous_response_id."
 
 
-def openai_error(code: str, message: str, error_type: str = "server_error") -> OpenAIErrorEnvelope:
-    return {"error": {"message": message, "type": error_type, "code": code}}
+def openai_error(
+    code: str,
+    message: str,
+    error_type: str = "server_error",
+    *,
+    resets_at: int | float | None = None,
+) -> OpenAIErrorEnvelope:
+    detail: OpenAIErrorDetail = {"message": message, "type": error_type, "code": code}
+    if resets_at is not None:
+        detail["resets_at"] = int(resets_at)
+    return {"error": detail}
 
 
 def dashboard_error(code: str, message: str) -> DashboardErrorEnvelope:
@@ -105,9 +114,10 @@ def response_failed_event(
     response_id: str | None = None,
     created_at: int | None = None,
     error_param: str | None = None,
+    resets_at: int | float | None = None,
     incomplete_details: dict[str, str] | None = None,
 ) -> ResponseFailedEvent:
-    error = openai_error(code, message, error_type)["error"]
+    error = openai_error(code, message, error_type, resets_at=resets_at)["error"]
     if error_param:
         error["param"] = error_param
     if created_at is None:

app/core/openai/requests.py

@@ -42,9 +42,9 @@
 _ASSISTANT_TEXT_PART_TYPES = frozenset({"text", "input_text", "output_text"})
 _TOOL_TEXT_PART_TYPES = frozenset({"text", "input_text", "output_text", "refusal"})
 _COMPACT_STATE_TOOL_NAMES = frozenset({"create_goal", "get_goal", "update_goal", "update_plan"})
-_COMPACT_TOOL_CALL_ITEM_TYPES = frozenset({"function_call", "custom_tool_call", "apply_patch_call"})
+_COMPACT_TOOL_CALL_ITEM_TYPES = frozenset({"function_call", "custom_tool_call", "apply_patch_call", "tool_search_call"})
 _COMPACT_TOOL_CALL_OUTPUT_ITEM_TYPES = frozenset(
-    {"function_call_output", "custom_tool_call_output", "apply_patch_call_output"}
+    {"function_call_output", "custom_tool_call_output", "apply_patch_call_output", "tool_search_output"}
 )
 _EXPLICIT_PROMPT_CACHE_CONTENT_TYPES = frozenset({"input_text", "input_image", "input_file"})
 _GOAL_CONTINUATION_CONTEXT_PREFIX = '<codex_internal_context source="goal">'