Skip to content

[Bug] BaseRunOutputEvent.from_dict rebuilds images/videos/audio/response_audio with model_validate, so base64 media content becomes the base64 text #10205

Open

Description

@BlueX888

Description

BaseRunOutputEvent.from_dict (libs/agno/agno/run/base.py:268) rebuilds the media fields
with pydantic model_validate:

  • images -> Image.model_validate (line 268)
  • videos -> Video.model_validate (line 272)
  • audio -> Audio.model_validate (line 276)
  • response_audio -> Audio.model_validate (line 286)
  • image -> Image.model_validate (line 290)

to_dict/to_json writes base64-encoded content for these fields, and pydantic coerces a
str straight to bytes, so the deserialized content becomes the ASCII of the base64
text
instead of the decoded payload. An event carrying media therefore does not survive
to_dict -> from_dict.

Three lines above, in the same function, files is handled correctly with
agno.utils.media.reconstruct_files (lines 280-282). The sibling
RunOutput.from_dict (libs/agno/agno/run/agent.py) uses
reconstruct_images / reconstruct_videos / reconstruct_audio_list /
reconstruct_response_audio for exactly these fields and round-trips the same payload
losslessly.

Reachability: run_output_event_from_dict (libs/agno/agno/run/agent.py:609) dispatches to
BaseRunOutputEvent.from_dict, and it is the parser for the AgentOS client SSE stream
(libs/agno/agno/client/os.py:650, :736, and the team/workflow variants at :927, :1049,
:1235, :1336), as well as for stored/session-loaded runs via
RunOutput.from_dict (run/agent.py:879) and TeamRunOutput.from_dict (run/team.py:979).
Any run stored with stream_events=True whose model produced image/video/audio content, and
any AgentOS client consuming such a stream, is affected.

Steps to Reproduce

import json

from agno.media import Audio, Image, Video, File
from agno.run.agent import RunCompletedEvent, RunOutput, run_output_event_from_dict

RAW = b"\x00\x01\x02\xffhello-media"

event = RunCompletedEvent(
    run_id="r1",
    response_audio=Audio(id="a1", content=RAW, transcript="hi"),
    audio=[Audio(id="a2", content=RAW)],
    images=[Image(id="i1", content=RAW)],
    videos=[Video(id="v1", content=RAW)],
    files=[File(id="f1", filename="a.bin", content=RAW)],
)
restored = run_output_event_from_dict(json.loads(event.to_json()))

run_output = RunOutput(
    run_id="r1",
    response_audio=Audio(id="a1", content=RAW, transcript="hi"),
    audio=[Audio(id="a2", content=RAW)],
    images=[Image(id="i1", content=RAW)],
    videos=[Video(id="v1", content=RAW)],
    files=[File(id="f1", filename="a.bin", content=RAW)],
)
ro = RunOutput.from_dict(json.loads(run_output.to_json()))

print(f"response_audio | {restored.response_audio.content == RAW} | {ro.response_audio.content == RAW}")
print(f"audio[0]       | {restored.audio[0].content == RAW} | {ro.audio[0].content == RAW}")
print(f"images[0]      | {restored.images[0].content == RAW} | {ro.images[0].content == RAW}")
print(f"videos[0]      | {restored.videos[0].content == RAW} | {ro.videos[0].content == RAW}")
print(f"files[0]       | {restored.files[0].content == RAW} | {ro.files[0].content == RAW}")

The same script is the reproduction used by both verifiers below
(/tmp/repro_event_media_base64.py), plus an SSE round-trip through the AgentOS client.

  1. Create a RunCompletedEvent with bytes-typed image/video/audio/response_audio content.
  2. Serialize with to_json() and deserialize with run_output_event_from_dict.
  3. Compare content against the original bytes.

Agent Configuration (if applicable)

Not required to reproduce; the failure is in the event (de)serializer and shows up with any
agent or team whose model returns media, e.g. an audio/image/video-capable model streamed to
an AgentOS client or persisted with stream_events=True.

Expected Behavior

type(event).from_dict(json.loads(event.to_json())) should be lossless for media content, the
same way RunOutput.from_dict already is: base64 content strings must be decoded back to
bytes.

Concrete basis:

  • Sibling branch in the same function, libs/agno/agno/run/base.py:280-282, already uses
    agno.utils.media.reconstruct_files for files — the same situation, handled correctly.
  • RunOutput.from_dict (libs/agno/agno/run/agent.py, and likewise
    TeamRunOutput.from_dict run/team.py:1013-1026, WorkflowRunOutput.from_dict
    run/workflow.py:1033-1037) calls reconstruct_images / reconstruct_videos /
    reconstruct_audio_list / reconstruct_response_audio for exactly these fields.
  • agno/utils/media.py documents the contract: reconstruct_image_from_dict — "Handles media
    references (from external storage), base64-encoded content (from database) ... # If content
    is base64 string, decode it back to bytes" and then calls Image.from_base64 (same shape for
    video/audio/file at lines 294, 347, 394, 443), while Image.to_dict documents "Convert to
    dict, optionally including base64-encoded content" and emits self.to_base64(). The
    round-trip is symmetric by design.
  • The field annotations are images: Optional[List[Image]] and response_audio: Optional[Audio],
    i.e. bytes-typed media, not base64 text.

Actual Behavior

Media comes back as the ASCII bytes of the base64 text (length 344 instead of 256 for the test
payload; files — the one field using reconstruct_files — is correct):

Verifier 1 (run on the default branch, same script):

images[0]        equal=False len=344 head=b'AAECAwQFBgcICQoLDA0O'
videos[0]        equal=False len=344 head=b'AAECAwQFBgcICQoLDA0O'
audio[0]         equal=False len=344 head=b'AAECAwQFBgcICQoLDA0O'
response_audio   equal=False len=344 head=b'AAECAwQFBgcICQoLDA0O'
files[0]         equal=True  len=256 head=b'\x00\x01\x02\x03\x04\x05\x06\x07...'
SSE: server frame "content":"iVBORw0KGgoAAQID" -> client b'iVBORw0KGgoAAQID', PNG magic False

Verifier 2 (independent, same script, base64 content):

EVENT images          equal=False  got=b'iVBORw0KGgoAAQL/YmluYXJ5LW1lZGlhLWJ5dGVz'
EVENT videos          equal=False  got=b'iVBORw0KGgoAAQL/YmluYXJ5LW1lZGlhLWJ5dGVz'
EVENT audio           equal=False  got=b'iVBORw0KGgoAAQL/YmluYXJ5LW1lZGlhLWJ5dGVz'
EVENT response_audio  equal=False  got=b'iVBORw0KGgoAAQL/YmluYXJ5LW1lZGlhLWJ5dGVz'
EVENT files           equal=True   got=b'\x89PNG\r\n\x1a\n\x00\x01\x02\xffbinary-media-bytes'
SSE frame response_audio equal=False b'iVBORw0KGgoAAQL/YmluYXJ5LW1lZGlhLWJ5dGVz'

Downstream, the "image"/"audio" is no longer a valid media file: it is base64 text stored in a
bytes field, so any consumer writing it to disk or handing it to a model gets a corrupt file
(PNG magic check fails in the SSE case above).

Screenshots or Logs (if applicable)

Not applicable — the console output above is the full evidence.

Environment

- OS: macOS 26.6.2 (Darwin 25.6.0)
- Agno Version: 3.0.9 (editable install), commit 44219f8532e2fe6ce936850455f4b9a2567e4194 (main)
- External Dependency Versions: pydantic 2.13.5
- Additional Environment Details: Python 3.12.14

Possible Solutions (optional)

In BaseRunOutputEvent.from_dict use the same helpers the files branch and
RunOutput.from_dict already use: reconstruct_images(images), reconstruct_videos(videos),
reconstruct_audio_list(audio), reconstruct_response_audio(response_audio) (and
reconstruct_image(image) for the single image field at line 290), imported from
agno.utils.media. Those helpers already handle both the base64-string case and the
media_reference case, so behaviour would match RunOutput.from_dict.

Additional Context (optional)

Activity

  1. BlueX888 commented on Sep 16, 2026

    @BlueX888
    ContributorAuthor

    Reproduced this. Root cause: libs/agno/agno/run/base.py:268-290: images/videos/audio/response_audio/image are rebuilt with Image/Video/Audio.model_validate while files on the next branch uses agno.utils.media.reconstruct_files, and pydantic coerces the base64 text to bytes, so content becomes the ASCII of the base64 instead of the decoded payload; in the output above column 1 is run_output_event_from_dict and column 2 is RunOutput.from_dict.

    Minimal reproduction:

    import json
    
    from agno.media import Audio, Image, Video, File
    from agno.run.agent import RunCompletedEvent, RunOutput, run_output_event_from_dict
    
    RAW = b"\x00\x01\x02\xffhello-media"
    
    event = RunCompletedEvent(
        run_id="r1",
        response_audio=Audio(id="a1", content=RAW, transcript="hi"),
        audio=[Audio(id="a2", content=RAW)],
        images=[Image(id="i1", content=RAW)],
        videos=[Video(id="v1", content=RAW)],
        files=[File(id="f1", filename="a.bin", content=RAW)],
    )
    restored = run_output_event_from_dict(json.loads(event.to_json()))
    
    run_output = RunOutput(
        run_id="r1",
        response_audio=Audio(id="a1", content=RAW, transcript="hi"),
        audio=[Audio(id="a2", content=RAW)],
        images=[Image(id="i1", content=RAW)],
        videos=[Video(id="v1", content=RAW)],
        files=[File(id="f1", filename="a.bin", content=RAW)],
    )
    ro = RunOutput.from_dict(json.loads(run_output.to_json()))
    
    print(f"response_audio | {restored.response_audio.content == RAW} | {ro.response_audio.content == RAW}")
    print(f"audio[0]       | {restored.audio[0].content == RAW} | {ro.audio[0].content == RAW}")
    print(f"images[0]      | {restored.images[0].content == RAW} | {ro.images[0].content == RAW}")
    print(f"videos[0]      | {restored.videos[0].content == RAW} | {ro.videos[0].content == RAW}")
    print(f"files[0]       | {restored.files[0].content == RAW} | {ro.files[0].content == RAW}")
    

    Observed output:

    response_audio | False | True
    audio[0]       | False | True
    images[0]      | False | True
    videos[0]      | False | True
    files[0]       | True | True
    

    Happy to open a PR with this fix, or to be assigned if you prefer to take it.

  2. self-assigned this
    on Sep 16, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions