Add an optional requestMetadata field to BedrockOptions that forwards
key-value pairs to the Bedrock Converse API ConverseStreamCommand. Tags
appear in AWS Cost Explorer split cost allocation data, enabling callers
to attribute inference costs to specific applications or contexts.
Changes:
- Add requestMetadata?: Record<string, string> to BedrockOptions with
JSDoc documenting AWS constraints (max 50 pairs, key 64 chars, value
256 chars, no aws: prefix)
- Pass requestMetadata to commandInput via conditional spread to avoid
sending undefined when omitted
- Export BedrockOptions from package root (consistent with other
provider option types)
- Add E2E tests: metadata forwarded to SDK payload, and omitted when
not provided
closes#2510
cli-highlight's auto-detection misidentifies prose as AppleScript,
LiveCodeServer, etc., coloring random English words (if, but, and, the,
that, is) as keywords. This happens when code blocks have no language
specified: fenced blocks without a language tag, indented code blocks,
or unclosed fences during streaming.
Skip auto-detection entirely and apply plain mdCodeBlock styling instead.
Update the coding-agent default model picks for ZAI, Cerebras,
and MiniMax so new sessions prefer the current model lineup.
Add the missing MiniMax-M2.1-highspeed direct provider entries
and normalize MiniMax Anthropic-compatible context limits so the
catalog matches the provider's supported model set.
When auto-retry fires after a retryable error (e.g. overloaded_error) and the
retry response includes tool_use, session.prompt() returned prematurely because
_resolveRetry() was called on the first successful message_end — while the
agent loop was still executing tools via the fire-and-forget agent.continue().
This caused callers to observe isStreaming=true after prompt() returned, and
follow-up session.prompt() calls threw 'Agent is already processing'. The
tool execution results were silently lost.
Fix: move _resolveRetry() from the message_end handler to the agent_end
handler. The _retryAttempt counter reset stays on message_end (preventing
accumulation across LLM calls within a turn), but the promise that unblocks
waitForRetry() now only resolves when the full agent loop completes.
After updating models.json, the scoped model selector still shows the
old values when opened. Switching to the "all" scope, however, shows
updated model definitions.
