feat: add MiniMax image generation tool - #495
Merged
calesthio merged 3 commits intoAug 13, 2026
Merged
Conversation
|
Вообще ничего не понял, о чём тут говорят!??! Я пробовал что-то сделать,
мне ничего не понятно. Зачем с меня списали 30 €? Я не хотел подписываться
на это дерьмо! Извините.
Com os melhores
cumprimentos,
Vladimir Akulov
ср, 12 авг. 2026 г., 15:47 Octopus ***@***.***>:
… Reason: The repository has a provider-discovered image generation registry
and multiple first-party text-to-image tools, but no MiniMax image tool or
related PR implements the target global/CN image_generation endpoints,
current image models, request fields, or URL/base64 response parsing.
Summary:
- Add a provider-discovered MiniMax image generation tool with global
and mainland China endpoint routing.
- Support the current image models, documented request controls, URL
downloads, and base64 image responses.
- Add focused contract tests for discovery, availability, routing,
payloads, output parsing, and provider errors.
Checks:
- uv run --with-requirements requirements-dev.txt pytest
tests/tools/test_minimax_image.py -v
- uv run --with-requirements requirements-dev.txt python -m py_compile
tools/graphics/minimax_image.py tests/tools/test_minimax_image.py
- uv run --with-requirements requirements-dev.txt pytest
tests/tools/test_provider_model_defaults.py
tests/tools/test_google_imagen_multi_output.py
tests/tools/test_openai_image_multi_output.py -q
------------------------------
You can view, comment on, or merge this pull request online at:
#495
Commit Summary
- 9c2850f
<9c2850f>
feat: add MiniMax image generation tool
File Changes
(2 files <https://github.com/calesthio/OpenMontage/pull/495/files>)
- *A* tests/tools/test_minimax_image.py
<https://github.com/calesthio/OpenMontage/pull/495/files#diff-8467b52bd3cca41f3050de015e60ff9265f40fd2fcba87cbe480b9a833b7f4b1>
(222)
- *A* tools/graphics/minimax_image.py
<https://github.com/calesthio/OpenMontage/pull/495/files#diff-b50106ec75855a59cccc8d7e5679bc793df39a20552c814a97811187a4172234>
(290)
Patch Links:
- https://github.com/calesthio/OpenMontage/pull/495.patch
- https://github.com/calesthio/OpenMontage/pull/495.diff
—
Reply to this email directly, view it on GitHub
<#495?email_source=notifications&email_token=BKJWYYTQVZQTC2A234J4OC35JR7PHA5CNFSNUABEM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UF42DENRTGMZTANJZHCTHEZLBONXW5KTTOVRHGY3SNFRGKZFFMV3GK3TUVRTG633UMVZF6Y3MNFRWW>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/BKJWYYT4RURUY46VX6JD7SL5JR7PHAVCNFSNUABGKJSXA33TNF2G64TZHMYTCOJVGM3DANJSGU5US43TOVSTWNJRGMZDCNJZGM3TLILWAI>
.
Triage notifications, keep track of coding agent tasks and review pull
requests on the go with GitHub Mobile for iOS
<https://github.com/notifications/mobile/ios/BKJWYYQ4MJUM2QIGNYV4W5L5JR7PHA5CNFSNUABEM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UF42DENRTGMZTANJZHCTHEZLBONXW5KTTOVRHGY3SNFRGKZFFMV3GK3TUVJTG633UMVZF62LPOM>
and Android
<https://github.com/notifications/mobile/android/BKJWYYTRWCRISKPDAJZSSYD5JR7PHA5CNFSNUABEM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UF42DENRTGMZTANJZHCTHEZLBONXW5KTTOVRHGY3SNFRGKZFFMV3GK3TUVZTG633UMVZF6YLOMRZG62LE>.
Download it today!
You are receiving this because you are subscribed to this thread.Message
ID: ***@***.***>
|
calesthio
requested changes
Aug 13, 2026
calesthio
left a comment
Owner
There was a problem hiding this comment.
Thanks for the focused MiniMax image integration. The mocked URL/base64 paths, region routing, status gating, registry registration, multi-output handling, and existing image regressions all pass locally (22 passed).
I found merge-readiness blockers under the provider review guide:
- This is a paid network provider, but the tool does not implement
estimate_cost()and returns nocost_usd. Through the BaseTool default it will be presented as zero-cost during planning, which can lead to ungoverned spend. Please add a documented, model/output-count-aware estimate (or explicitly return unknown when MiniMax does not publish a stable rate) and test it. - The PR adds a user-visible provider without updating
docs/PROVIDERS.md/.env.examplewith setup, global-vs-CN routing, pricing/quota caveats, supported models, and limitations. - The review guide's minimum provider coverage requires selector routing. The current test registers the module directly, but does not prove that
image_selectordiscovers, selects, and routes a normal request tominimax_image. Please add a fully mocked selector-level test; no live endpoint should be involved. agent_skills = ["flux-best-practices"]is provider-inaccurate: FLUX prompting guidance does not describe MiniMax Image-01. Please add appropriate MiniMax guidance or leave this empty until such a skill exists rather than directing agents to the wrong vendor contract.
The provider itself is useful and the implementation is nicely scoped. Thank you?once cost governance, docs, selector coverage, and skill metadata are corrected, it should be ready for another review.
calesthio
approved these changes
Aug 13, 2026
calesthio
left a comment
Owner
There was a problem hiding this comment.
Thank you for the MiniMax image provider. Provider contracts, selector routing, cost reporting, docs, and tests are complete; the branch is current and CI is green. This is merge-ready.
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
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.
Reason: The repository has a provider-discovered image generation registry and multiple first-party text-to-image tools, but no MiniMax image tool or related PR implements the target global/CN image_generation endpoints, current image models, request fields, or URL/base64 response parsing.
Summary:
Checks:
uv run --with-requirements requirements-dev.txt pytest tests/tools/test_minimax_image.py -vuv run --with-requirements requirements-dev.txt python -m py_compile tools/graphics/minimax_image.py tests/tools/test_minimax_image.pyuv run --with-requirements requirements-dev.txt pytest tests/tools/test_provider_model_defaults.py tests/tools/test_google_imagen_multi_output.py tests/tools/test_openai_image_multi_output.py -q