The refresh button had no effect because two independent gates blocked
the Codex probe:
1. isOpenAICodexSnapshotStale returned false for non-WS-v2 accounts even
when data was stale — this is correct for background auto-refresh (Codex
quota is only auto-tracked for Codex CLI / WS v2 accounts), so this
behavior is preserved.
2. shouldProbeOpenAICodexSnapshot had a 10-min in-memory rate limit with
no bypass for explicit user requests.
Fix: add a force parameter threaded from handler → GetUsage → getOpenAIUsage
→ shouldProbeOpenAICodexSnapshot. When force=true (manual refresh button),
both gates are bypassed and the probe always runs. Background auto-loads
continue to respect the original WS v2 logic and 10-min rate limit.
- AccountsView: display email under account name by checking extra.email
and credentials.email in addition to extra.email_address; OpenAI OAuth
stores email under the 'email' key while Anthropic uses 'email_address'
- AccountUsageCell: add per-account refresh button to the OpenAI OAuth
usage section, identical to the existing Anthropic OAuth pattern;
reuses loadActiveUsage, activeQueryLoading, and the activeQuery i18n key
Claude Code can send one assistant turn with multiple tool_use blocks followed by a user turn containing matching tool_result blocks. The OpenAI /v1/messages compatibility path trimmed continuation input to the last user turn plus adjacent tool outputs, which could leave a function_call_output without its earlier function_call when previous_response_id was attached.
This keeps all function_call items needed by retained function_call_output entries so the upstream Responses API can resolve every call_id.
Constraint: Applies only to the OpenAI /v1/messages -> Responses compatibility continuation path.
Rejected: Disable previous_response_id for all tool outputs | loses continuation and cache benefits for valid turns.
Confidence: high
Scope-risk: narrow
Directive: Do not trim function_call_output entries without preserving their matching function_call call_id context.
Tested: go test ./internal/service -run 'TestForwardAsAnthropic_(PreviousResponseIDKeepsMultiToolCallContext|AttachesPreviousResponseIDForCompatContinuation|OAuthPreservesClaudeCodeToolCallID)' -count=1
Tested: go test ./internal/service -run 'TestForwardAsAnthropic|TestApplyAnthropicCompatFullReplayGuard|TestOpenAICompat|Test.*ToolContinuation' -count=1
Tested: go test ./internal/pkg/apicompat -count=1
Related: #2337
The Claude Code mimic path rewrites tool names in tools[] (and
tool_choice) but left tool_use blocks in messages[] with their
original names. Anthropic validates that every tool referenced by
a tool_use block is declared in tools[], so the mismatch produces:
messages.N.content.M: Input tag 'original_name' not found in tools
(surfaced as HTTP 400 directly, or wrapped as 424 by upstream proxies
such as Bedrock gateways.)
The previous code comment asserted 'this matches Parrot; response-side
bytes.Replace will restore the names'. Parrot's behavior is fine for
Claude Code's own tool set, but breaks once the upstream client sends
additional tools (e.g. web_search) that are not part of Claude Code
and therefore get renamed here.
Fix: apply the same ToolNameRewrite to messages[].content[] blocks
where type == 'tool_use', keeping tools[], tool_choice and messages
self-consistent before the request reaches Anthropic. tool_result
blocks reference tools via tool_use_id, not name, so no change is
needed there.
A new unit test covers the full rewrite flow and guards against
server tools (type != '') being affected.
