Empty text blocks ({"type":"text","text":""}) cause Anthropic upstream to
return 400: "text content blocks must be non-empty". This was not caught
by the existing error detection pattern in isThinkingBlockSignatureError,
nor handled by FilterThinkingBlocksForRetry.
- Add empty text block stripping to FilterThinkingBlocksForRetry
- Fix isThinkingBlockSignatureError to match new Anthropic error format
- Add fast-path byte patterns to avoid unnecessary JSON parsing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Propagate UpstreamModel through ForwardResult and OpenAIForwardResult in Anthropic direct, API-key passthrough, Bedrock, and OpenAI gateway flows. Extract optionalNonEqualStringPtr and optionalTrimmedStringPtr into usage_log_helpers.go. Store upstream_model only when it differs from the requested model.
Also introduces anthropicPassthroughForwardInput struct to reduce parameter count.
Extend RecordUsageInput and RecordUsageLongContextInput structs with InboundEndpoint and UpstreamEndpoint so that Claude, Gemini, and Sora handlers can record endpoint info alongside OpenAI handlers.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Add 5th error filter switch IgnoreInsufficientBalanceErrors to suppress
upstream insufficient balance / insufficient_quota errors from ops log
- Extract hardcoded error strings into package-level constants for
shouldSkipOpsErrorLog, normalizeOpsErrorType, classifyOpsPhase, and
classifyOpsIsBusinessLimited
- Define ErrNoAvailableAccounts sentinel error and replace all
errors.New("no available accounts") call sites
- Update tests to use require.ErrorIs with the sentinel error
- Add 5th error filter switch IgnoreInsufficientBalanceErrors to suppress
upstream insufficient balance / insufficient_quota errors from ops log
- Extract hardcoded error strings into package-level constants for
shouldSkipOpsErrorLog, normalizeOpsErrorType, classifyOpsPhase, and
classifyOpsIsBusinessLimited
- Define ErrNoAvailableAccounts sentinel error and replace all
errors.New("no available accounts") call sites
- Update tests to use require.ErrorIs with the sentinel error
Claude's output_config.effort parameter (low/medium/high/max) was not
being extracted from requests or logged in the reasoning_effort column
of usage logs. Only the OpenAI path populated this field.
Changes:
- Extract output_config.effort in ParseGatewayRequest
- Add ReasoningEffort field to ForwardResult
- Populate reasoning_effort in both RecordUsage and RecordUsageWithLongContext
- Guard against overwriting service-set effort values in handler
- Update stale comments that described reasoning_effort as OpenAI-only
- Add unit tests for extraction, normalization, and persistence
Consolidate two separate channel types (bedrock + bedrock-apikey) into
a single "AWS Bedrock" channel. Authentication mode is now distinguished
by credentials.auth_mode ("sigv4" | "apikey") instead of separate types.
Backend:
- Remove AccountTypeBedrockAPIKey constant
- IsBedrock() simplified; IsBedrockAPIKey() checks auth_mode
- Add IsAPIKeyOrBedrock() helper to eliminate repeated type checks
- Extend pool mode, quota scheduling, and billing to bedrock
- Add RetryableOnSameAccount to handleBedrockUpstreamErrors
- Add "bedrock" scope to Beta Policy for independent control
Frontend:
- Merge two buttons into one "AWS Bedrock" with auth mode radio
- Badge displays "Anthropic | AWS"
- Pool mode and quota limit UI available for bedrock
- Quota display in account list (usage bars, capacity badges, reset)
- Remove all bedrock-apikey type references
Recovers features lost during 0.1.91->0.1.95 merge (0.1.92-0.1.94
customizations were skipped because main branch was not updated).
Recovered features:
- Antigravity 403 forbidden/validation/ban status detection and display
- Subscription tier badge in account list
- Client affinity scheduling for Anthropic accounts
- Sora async task API and GDrive storage backend
- Swipe-to-select for admin tables
- OpenAI passthrough account selection fix
- Various quota and usage enhancements
Merge main (custom features) into release/custom-0.1.95 (upstream v0.1.95).
New upstream features: group subscription binding, multi-dimension quota (daily/weekly/total),
allow_messages_dispatch, default_mapped_model, recover state API.
Our customizations: simulate_claude_max_enabled, usage status detection, 403 validation handling.
The isModelSupportedByAccount function lost the OpenAI passthrough
check during the upstream merge, causing GPT-5.4 and other models
to be rejected for passthrough accounts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
4K image base64 data can exceed 40MB limit, causing "bufio.Scanner:
token too long" errors. Scanner is adaptive (starts at 64KB, grows
as needed), so increasing the cap has no impact on normal responses.
4K image base64 data can exceed 40MB limit, causing "bufio.Scanner:
token too long" errors. Scanner is adaptive (starts at 64KB, grows
as needed), so increasing the cap has no impact on normal responses.
pq driver treats []byte as bytea, not jsonb. Convert charJSON and
reqBody to *string before passing to ExecContext for character_info
and request_body JSONB columns.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extend the existing total quota limit with daily and weekly periodic
dimensions. Each dimension is independently configurable and uses lazy
reset — when the period expires, usage is automatically reset to zero on
the next increment. Any dimension exceeding its limit will pause the
account from scheduling.
Backend:
- Add GetQuotaDailyLimit/Used, GetQuotaWeeklyLimit/Used, HasAnyQuotaLimit
- Rewrite IncrementQuotaUsed with atomic CTE SQL for 3-dimension update
- Rewrite ResetQuotaUsed to clear all dimensions and period timestamps
- Update postUsageBilling to use HasAnyQuotaLimit()
- Preserve daily/weekly used values on account edit
Frontend:
- Refactor QuotaLimitCard from single v-model to 3-dimension props
- Add QuotaBadge component for compact D/W/$ display
- Update AccountCapacityCell with per-dimension badges
- Update Create/Edit modals with daily/weekly quota fields
- Update AccountActionMenu hasQuotaLimit to check all dimensions
- Add i18n strings for daily/weekly/total quota labels
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
classifyByAffinityZone was running before filterByMinPriority, causing
high-priority accounts in the red zone to be removed before priority
filtering, allowing low-priority accounts in the green zone to be
selected instead. Move zone classification into the priority loop so
it operates within same-priority groups, with fallback to next priority
group when current group is entirely in the red zone.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Backend: Add AffinityZone type with GetAffinityBase/GetAffinityBuffer/GetAffinityZone
methods. Integrate classifyByAffinityZone into Layer 2 scheduling and red zone
check into Layer 1.6 affinity hit path. 17 unit tests covering all zone boundaries.
Frontend: Add AffinityConfigCard for base/buffer configuration in EditAccountModal.
Move affinity badge from status column to capacity column with zone-based coloring
(count/limit format). Extract CapacityBadge and QuotaBadge components to reduce
AccountCapacityCell from 444 to 215 lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- New API: GET /accounts/:id/affinity-clients returns client list with
last_active timestamps from Redis ZSET scores
- New Lua script: get_affinity_clients_with_scores.lua uses ZREVRANGEBYSCORE
WITHSCORES to return both client IDs and their timestamps
- New frontend component: AffinityBadge.vue replaces inline badge with
hover popover that lazy-loads client details on first hover
- Shows client ID (monospace) + relative time (e.g. "3h ago")
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>