docs(#3996): document verified generated-image behavior - #4030
Draft
aheritier wants to merge 2 commits into
Draft
Conversation
aheritier
added
area/docs
rumpl
requested changes
Aug 24, 2026
| Some models (e.g. Gemini image-output models) can generate an image as part | ||
| of a reply. Docker Agent saves each generated image into the session's | ||
| workspace — the directory the session was started in — as an ordinary, | ||
| untracked file, not into `session.db` or the data directory. The session |
Member
There was a problem hiding this comment.
We should keep it in the database, sessions should be portable
aheritier
force-pushed
the
generated-media-docs
branch
from
August 24, 2026 15:13
a5107cd to
962223a
Compare
aheritier
force-pushed
the
generated-media-docs
branch
from
August 25, 2026 08:01
962223a to
48a5f96
Compare
aheritier
force-pushed
the
generated-media-docs
branch
from
August 25, 2026 08:18
48a5f96 to
8c8e021
Compare
…nd validation walkthrough User-facing documentation for the generated-media feature across docs/features/tui/index.md (Generated Media section: storage location, naming and collision behavior, no-resend placeholders, bounded/sanitized warning and placeholder wording), docs/features/sessions/index.md (generated-media lifecycle), and docs/providers/google/index.md (image-output model guidance), plus a step-by-step manual validation walkthrough for contributors.
Document that image-output-capable models request TEXT+IMAGE on supported Google surfaces, with explicit output_capabilities values overriding automatic models.dev detection. Explain local rejection of unsupported tool and structured-output combinations, provider-controlled formats and text-only responses, generated-file naming and collision handling, workspace escape confirmation, and inline TUI rendering with safe fallbacks. Update the example and remove stale claims that image output is not requested or rendered, while keeping developer-only validation details out of user docs.
aheritier
force-pushed
the
generated-media-docs
branch
from
August 25, 2026 08:33
8c8e021 to
1445548
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Documents verified generated-image behavior across model configuration, sessions, TUI usage, Google provider guidance, and examples.
Why
Provides a concise, reproducible reference for configuring and using generated images safely.
Validation
Documentation/example review;
task testis unchanged by this docs-only PR.Test instructions
Run:
task testFollow
examples/gemini_image_output.yamland the generated-image provider, session, and TUI documentation using a supported Gemini image-output model. Expected: the documented configuration is valid and the workflow produces and displays generated media as described.