fix(runner): build a new message when saving input blobs, instead of writing into the caller's Content

[svetanis]

Please ensure you have read the contribution guide before creating a pull request.

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

• Closes: #1377

2. Or, if no issue exists, describe the change:

Problem:

With saveInputBlobsAsArtifacts(true), Runner.appendNewMessageToSession replaces each inline blob with
a placeholder by writing into the parts list of the Content the caller passed to runAsync
(Runner.java:376-382).
That list is never copied on the way in, so for an immutable one the set throws
UnsupportedOperationException — before the model is called, and before anything is appended:

Construction	Backing list	Result
builder().parts(List.of(text, blob))	caller's List.of, uncopied	throws
builder().parts(textBuilder, blobBuilder)	genai's own ImmutableList	throws
Content.fromParts(text, blob)	Arrays.asList	works

Solution:

Rewrite a copy of the parts list and build a new Content for the event. The loop moves into a
helper returning both the prepared message and the saves it scheduled:

private record OffloadedMessage(Content message, Completable artifactSaves) { ... }

private OffloadedMessage offloadInputBlobs(Session session, Content message, String invocationId) {
  // The runner directly saves the artifacts (if applicable) in the user message and replaces
  // the artifact data with a file name placeholder.
  List<Part> parts = new ArrayList<>(message.parts().get());
  ...
  return new OffloadedMessage(
      message.toBuilder().parts(ImmutableList.copyOf(parts)).build(), saveArtifactsFlow);
}

so appendNewMessageToSession becomes one decision:

OffloadedMessage offloaded =
    this.artifactService != null && saveInputBlobsAsArtifacts
        ? offloadInputBlobs(session, newMessage, invocationContext.invocationId())
        : OffloadedMessage.unchanged(newMessage);

The functional change is one line — new ArrayList<>(...), which always accepts set. Documented
behaviour is unchanged: the persisted message still carries the placeholder, the blob is still saved, and
the model still never sees it.

Testing Plan

Unit Tests:

• I have added or updated unit tests for my change.
• All unit tests pass locally.

Tests run: 94, Failures: 0, Errors: 0, Skipped: 0     # with the fix
Tests run: 94, Failures: 5                            # reverting only Runner.java

Nine tests added. Five fail without the fix (regression tests); four pass in both states (parity tests
pinning behaviour that must not change):

Test	Without fix
..._immutablePartsList_savesArtifactAndCompletes	fails
..._partBuilderPartsList_savesArtifactAndCompletes	fails
..._appendedEventReplacesBlobWithPlaceholder	fails
..._doesNotModifyCallerMessage	fails
..._storesBlobVerbatim	fails
..._fromPartsConstruction_savesArtifactAndCompletes	passes
..._disabled_keepsBlobAndSavesNothing	passes
..._textOnlyMessage_passesThroughUnchanged	passes
..._disabledWithTextOnlyMessage_passesThroughUnchanged	passes

The last two cover ordinary traffic: a text-only prompt with the option on (the runner still walks the
parts and, after the fix, copies them), and the default path with the option off (the rewrite is skipped
entirely and the caller's message passes through uncopied).

Manual End-to-End (E2E) Tests:

A demo drives one real agent turn per row through InMemoryRunner (no custom wiring) against
gemini-2.5-flash, varying only the construction and the flag, and reads back both the artifact store
and the session afterwards.

Before:

Run A (immutable List.of)      threw UnsupportedOperationException   model calls 0   nothing appended
Run B (Part.Builder varargs)   threw UnsupportedOperationException   model calls 0   nothing appended
Run C (Content.fromParts)      completed, blob offloaded, placeholder appended
Run D (immutable, flag off)    completed, blob reaches the model, no artifact
BUG REPRODUCED

After (same demo):

Run A (immutable List.of)      completed   model calls 1   payload back verbatim   placeholder appended
Run B (Part.Builder varargs)   completed   model calls 1   payload back verbatim   placeholder appended
Run C (Content.fromParts)      unchanged
Run D (immutable, flag off)    unchanged
Run E (text only, flag on)     completed, nothing stored, text through untouched
Run F (text only, flag off)    completed, nothing stored, text through untouched
FIXED

On every row where the offload ran, the payload came back out of storage verbatim, the model was never
shown the blob, and the model was shown the placeholder — so this is not merely "stopped crashing".

Checklist

• I have read the CONTRIBUTING.md document.
• My pull request contains a single commit.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• I have manually tested my changes end-to-end.
• Any dependent changes have been merged and published in downstream modules.

[hemasekhar-p]

Hi @svetanis, thank you for your contribution! We appreciate you taking the time to submit this pull request. Currently this PR is under review by our team, we will keep you posted if any additional information is required. thank you.

[MiloszSobczyk]

Hi @svetanis, thank you for your contribution. Please look into the comments I left within my review.

[svetanis]

Thanks for the review @MiloszSobczyk.
All three comments addressed:

1. Removed the OffloadedMessage record and offloadInputBlobs; the offload is inline in
   appendNewMessageToSession, as in your comment. The fix itself is unchanged:
   new ArrayList<>(newMessage.parts().get()).
2. Copyright year reverted to 2025.
3. The repeated setup in the new tests is now a single useRunnerWithArtifactService()
   helper, which points the existing runner and session fields at a runner backed by a
   fresh InMemoryArtifactService.

The branch has also been rebased against the latest main.

[MiloszSobczyk]

Thank you for addressing my comments @svetanis. I have two more suggestions regarding the test suite. Please consider following them.

1. saveInputBlobsAsArtifacts_doesNotModifyCallerMessage never asserts that the artifact was saved, so it would still pass if the feature silently became a no-op. Please add an assertThat(artifactNames()).hasSize(1);.

2. saveInputBlobsAsArtifacts_appendedEventReplacesBlobWithPlaceholder uses var unused = ... .test() with no assertComplete(). That contradicts the reasoning you wrote yourself in storesBlobVerbatim. Please assert completion here too.

[svetanis]

Thanks for the review, @MiloszSobczyk. Both applied.

Changes in the saveInputBlobsAsArtifacts_* tests:

• _doesNotModifyCallerMessage — asserts the artifact count.
• _appendedEventReplacesBlobWithPlaceholder — asserts completion, the role and the text part;
  placeholder matched exactly against the saved artifact name.
• _storesBlobVerbatim — asserts the artifact count and the mime type.
• _fromPartsConstruction_savesArtifactAndCompletes — placeholder matched exactly against the
  saved artifact name.
• _twoBlobs_namesEachArtifactAfterItsPartIndex — new test.
• All ten — completion now goes through one assertAgentReplied(...) helper, which also asserts
  the agent's reply event.