fix(nano-banana-pro): remove space after MEDIA: token by QuantDeveloperUSA · Pull Request #18706 · openclaw/openclaw

QuantDeveloperUSA · 2026-02-17T00:18:26Z

Summary

The generate_image.py script in the nano-banana-pro skill prints MEDIA: /path (with a space after the colon), which does not match the canonical MEDIA:/path format used by all other skills and tested throughout the codebase.

Problem

OpenClaw's splitMediaFromOutput parser (in src/media/parse.ts) and extractToolResultMediaPaths (in src/agents/pi-embedded-subscribe.tools.ts) extract media file paths from lines starting with MEDIA:. While the regex MEDIA:\s* tolerates an optional space, every other skill and test uses the no-space format:

openai-image-gen outputs paths without the space
pi-embedded-subscribe.tools.media.test.ts tests MEDIA:/tmp/screenshot.png (no space)
media/parse.test.ts tests MEDIA:/Users/pete/My File.png (no space)

The space caused inconsistency and could interact poorly with downstream consumers that expect the canonical format.

Changes

skills/nano-banana-pro/scripts/generate_image.py: Changed print(f"MEDIA: {full_path}") to print(f"MEDIA:{full_path}")
Updated the comment to clarify the no-space, line-start format constraint

Testing

Verified the change matches the format in SKILL.md ("The script prints a MEDIA: line")
Confirmed alignment with all existing tests in the codebase

Greptile Summary

Fixes the MEDIA: token format in nano-banana-pro's generate_image.py by removing the space after the colon, aligning it with the canonical MEDIA:{path} format used by every other media token producer in the codebase (tts-tool.ts, nodes-tool.ts, common.ts) and expected by all tests.

Removed trailing space in print(f"MEDIA: {full_path}") → print(f"MEDIA:{full_path}") in generate_image.py:174
Updated the inline comment to document the no-space, line-start format constraint
The MEDIA_TOKEN_RE regex in src/media/parse.ts tolerates optional whitespace via \s*, so the old format worked but was inconsistent with all other producers and tests

Confidence Score: 5/5

This PR is safe to merge — it's a minimal one-line format fix that aligns with all existing conventions.
The change is a trivial, well-motivated format fix: removing a single space in a print statement to match the canonical MEDIA token format used everywhere else. The parser already handles both formats, so there is zero risk of breakage. The comment update is accurate and helpful.
No files require special attention.

_{Last reviewed commit: 80174c8}

_{(2/5) Greptile learns from your feedback when you react with thumbs up/down!}

…ge.py The MEDIA: output token must appear at line start with no space after the colon for OpenClaw's splitMediaFromOutput parser to extract the file path and auto-attach media on outbound chat channels (Discord, Telegram, WhatsApp, etc.). The script was printing 'MEDIA: /path' (with space), which while tolerated by the regex, does not match the canonical 'MEDIA:/path' format used by all other skills (e.g. openai-image-gen) and tested in the codebase (pi-embedded-subscribe.tools.media.test.ts, media/parse.test.ts). Also updated the comment to clarify the format constraint.

Copilot

Pull request overview

Aligns the nano-banana-pro skill’s stdout media directive with the repo’s canonical MEDIA:<path> format so downstream media extraction and consumers see consistent output.

Changes:

Remove the space after MEDIA: when printing the generated image path.
Update the inline comment to document the expected MEDIA: line format.

Copilot · 2026-02-17T00:20:22Z

skills/nano-banana-pro/scripts/generate_image.py

+            # OpenClaw parses MEDIA: tokens (line-start, no space after colon)
+            # and will attach the file on supported chat providers.


The new comment implies OpenClaw’s parser requires “no space after colon”, but the parser is whitespace-tolerant (e.g. MEDIA_TOKEN_RE = /\bMEDIA:\s*/ in src/media/parse.ts, and tests cover MEDIA: ./image.png). Consider rewording this comment to describe the canonical output format (prefer MEDIA:<path>), rather than a strict parsing constraint.

Suggested change

# OpenClaw parses MEDIA: tokens (line-start, no space after colon)

# and will attach the file on supported chat providers.

# OpenClaw parses MEDIA: tokens and will attach the file on supported chat providers.

# This script emits the canonical MEDIA:<path> format.

Copilot · 2026-02-17T00:20:22Z

skills/nano-banana-pro/scripts/generate_image.py

+            # OpenClaw parses MEDIA: tokens (line-start, no space after colon)
+            # and will attach the file on supported chat providers.
+            print(f"MEDIA:{full_path}")


PR description says “every other skill and test uses the no-space format”, but the repo includes tests/events that use a spaced form like MEDIA: ./image.png / MEDIA: https://... (e.g. src/auto-reply/reply.block-streaming.test.ts:261, src/infra/outbound/message-action-runner.test.ts:572, src/agents/pi-embedded-subscribe.subscribe-embedded-pi-session.subscribeembeddedpisession.e2e.test.ts:283). Please update the PR description to reflect that whitespace is currently tolerated in some places, even if this skill should emit the canonical no-space form.

openclaw-barnacle · 2026-02-22T04:03:24Z

This pull request has been automatically marked as stale due to inactivity.
Please add updates or it will be closed.

…ge.py (openclaw#18706) The MEDIA: output token must appear at line start with no space after the colon for OpenClaw's splitMediaFromOutput parser to extract the file path and auto-attach media on outbound chat channels (Discord, Telegram, WhatsApp, etc.). The script was printing 'MEDIA: /path' (with space), which while tolerated by the regex, does not match the canonical 'MEDIA:/path' format used by all other skills (e.g. openai-image-gen) and tested in the codebase (pi-embedded-subscribe.tools.media.test.ts, media/parse.test.ts). Also updated the comment to clarify the format constraint.

* main: Mattermost: harden interaction callback binding (openclaw#38057) WhatsApp: honor outbound mediaMaxMb (openclaw#38097) openai-image-gen: validate --background and --style options (openclaw#36762) Docs: align BlueBubbles media cap wording Telegram/Discord: honor outbound mediaMaxMb uploads (openclaw#38065) CI: run changed-scope on main pushes Skills/nano-banana-pro: clarify MEDIA token comment (openclaw#38063) nano-banana-pro: respect explicit --resolution when editing images (openclaw#36880) CI: drop unused install-smoke bootstrap fix(nano-banana-pro): remove space after MEDIA: token in generate_image.py (openclaw#18706) docs: context engine docs(config): list the context engine plugin slot docs(plugins): add context-engine manifest kind example docs(plugins): document context engine slots and registration docs(protocol): document slash-delimited schema lookup plugin ids docs(tools): document slash-delimited config schema lookup paths fix(session): tighten direct-session webchat routing matching (openclaw#37867) feature(context): extend plugin system to support custom context management (openclaw#22201) Gateway: allow slash-delimited schema lookup paths

…ge.py (openclaw#18706) The MEDIA: output token must appear at line start with no space after the colon for OpenClaw's splitMediaFromOutput parser to extract the file path and auto-attach media on outbound chat channels (Discord, Telegram, WhatsApp, etc.). The script was printing 'MEDIA: /path' (with space), which while tolerated by the regex, does not match the canonical 'MEDIA:/path' format used by all other skills (e.g. openai-image-gen) and tested in the codebase (pi-embedded-subscribe.tools.media.test.ts, media/parse.test.ts). Also updated the comment to clarify the format constraint.

Copilot AI review requested due to automatic review settings February 17, 2026 00:18

openclaw-barnacle bot added the size: XS label Feb 17, 2026

Copilot started reviewing on behalf of QuantDeveloperUSA February 17, 2026 00:18 View session

Copilot AI reviewed Feb 17, 2026

View reviewed changes

openclaw-barnacle bot added stale Marked as stale due to inactivity and removed stale Marked as stale due to inactivity labels Feb 22, 2026

vincentkoc merged commit 86a89d9 into openclaw:main Mar 6, 2026
31 of 32 checks passed

github-actions bot mentioned this pull request Mar 6, 2026

📡 Upstream Digest — 2026-03-06 16:31 UTC curtismercier/openclaw-mods#193

Open

alexyyyander mentioned this pull request Mar 7, 2026

fix/gateway token mismatch 38617 #38676

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(nano-banana-pro): remove space after MEDIA: token#18706

fix(nano-banana-pro): remove space after MEDIA: token#18706
vincentkoc merged 1 commit intoopenclaw:mainfrom
ABFS-Inc:fix/nano-banana-pro-media-token-space

QuantDeveloperUSA commented Feb 17, 2026 •

edited by greptile-apps bot

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Feb 17, 2026

Uh oh!

Copilot AI Feb 17, 2026

Uh oh!

openclaw-barnacle bot commented Feb 22, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		# OpenClaw parses MEDIA: tokens (line-start, no space after colon)
		# and will attach the file on supported chat providers.

Uh oh!

Conversation

QuantDeveloperUSA commented Feb 17, 2026 • edited by greptile-apps bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Problem

Changes

Testing

Greptile Summary

Confidence Score: 5/5

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

openclaw-barnacle bot commented Feb 22, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

QuantDeveloperUSA commented Feb 17, 2026 •

edited by greptile-apps bot

Loading