0.12.11
A patch release. All six packages move to 0.12.11 together. @silverprotocol/core and @silverprotocol/google-adk change. The spec revision stays 1.0.0-draft.8.
Who should upgrade
- You run Google ADK 2.4.0 in
StreamingMode.SSEwith a planner that writes state. The package’s peer range (>=1.0.0 <3) admits 2.4.0, though the 0.12 line is verified at 2.2.1. Streamed text rendered twice on 0.12.10; it now renders once. - You run Google ADK on the Interactions route (
useInteractionsApi) inStreamingMode.SSE. A response now renders once, where 0.12.10 rendered it again afterturn.done. - Anyone else gets the same output as from 0.12.10: all 103 replayed runs are byte-identical (see Wire version). Read “Upgrading from 0.12.10” first: the message-thread change applies to every framework package’s output.
Upgrading from 0.12.10
- A message lands on its turn’s thread. When a
message.startnames athreadIdother than the one its turn already has (from the turn’sturn.start, from its parent’s thread for a nested turn, or from an earliermessage.start), the reducer now creates the message on the turn’s thread. 0.12.10 kept themessage.start’s ownthreadId. The turn record’s thread doesn’t move, and the fold doesn’t resync. Amessage.startfor a turn that has no thread yet still gives the turn its thread. When a nested turn’s parent was never opened, the turn takes the thread of a turn the fold has already opened or, with none, the parent turn id itssubagent.startnames, as before; its messages now take the same thread. - Google ADK: an unmatched function response that holds credential material is no longer carried. A
functionResponsethat carries no id (or an empty one) and answers no pending call under its name ridesext.google.unparsedwhole. When it holds an ADK credential object or a response toadk_request_credential, at any depth, the package now emits one non-terminalerrorevent in its place, withcode"adk_orphan_credential_response"and a fixed message, and nothing of the response rides (spec §8.0, graceful degradation). 0.12.10 carried such a response whole, credential members included. Theerrordoesn’t close the turn. An unmatched response without credential material still rides whole, a reply namedadk_request_credentialkeeps its allowlisted carry, and a response that answers a call still maps totool.done. A credential an application keeps in a shape of its own isn’t recognised, and rides unchanged.
@silverprotocol/core
- The message-thread change above. No other fold rule changes.
Google ADK
- A planner’s state record no longer doubles streamed text. From
@google/adk2.4.0, with a planner that writes state, ADK yields an event that only records the state change inside a model call, between its streamed chunks and its repeat of them inStreamingMode.SSE. 0.12.10 read that event as the end of the call, so the repeat rendered the text a second time. On the 0.12 line the package matches streamed text per turn: the record still maps to itsstate.delta, and it holds the match open only when its own source streamed the match’s last chunk. While it holds, that source’s next chunk,partial: falserepeat or another such record keeps the match, and an event from any other source, or one without apartialflag, ends it first, as before. A record of another source ends the match, as before. The repeat renders nothing, as without the record. - A repeated close of an Interactions response maps once. On the Interactions route (
useInteractionsApi) inStreamingMode.SSE, any@google/adkfrom 2.2.1 through 2.4.0 closes a response atinteraction.completedand again when the stream ends, and acompletedstatus update can close it once more, each time with every part so far. 0.12.10 rendered the response again at the second close, afterturn.done. A close that maps to exactly what the response’s previous close mapped to, itsidandtimestampaside, with no other event of the response between them, now emits nothing. A close with any mapped difference maps as before, and apartial: falseevent ADK yields mid-response (a media part, a finished function call) is not a close and always maps. - The unmatched-response change under “Upgrading from 0.12.10”.
With @ai-sdk/openai 4.0.110 or later
- If your host resolves
@ai-sdk/openai4.0.110 or later, an OpenAI Responses refusal reaches the stream. From 4.0.110, the provider streams a refusal as the assistant’s text and finishes the step withcontent-filter. This package maps that finish, as before, toturn.donewithfinishReason"safety_blocked", and sets nofinishReasonRawfor it. With 4.0.109 or earlier, the refusal text never reached the stream: the host saw an empty assistant message, and the turn closed withfinishReason"stop". The change is in the provider; this package’s code doesn’t change, and the 0.12 line’s verified versions don’t include 4.0.110.
The other four packages change only their version.
Verified versions
Unchanged from 0.12.10. Each framework package is verified end to end, tool calls included, against a live run at:
@anthropic-ai/claude-agent-sdk0.3.292;@openai/agents0.21.0;@google/adk2.2.1;ai7.0.130.
Wire version
1.0.0-draft.8, unchanged. Replaying every recorded stream and the Google ADK pause fixtures in the release’s test corpus through the 0.12.10 and 0.12.11 packages, all 103 runs give byte-identical events. The replay compares the events each package emits, not a fold of them, and no recorded stream or fixture carries an unmatched credential response, a planner’s state record or a stream on the Interactions route; those changes rest on their own tests. A live capture on the Interactions route, recorded outside that corpus in StreamingMode.SSE at gemini-3.8-flash, shows the repeated-close fix: 0.12.10 renders the response twice, in 30 events, and 0.12.11 renders it once, in 19.
npm’s provenance for all six 0.12.11 packages attests typescript-sdk commit a0bf753e.