Repository navigation
Conversation
|
Windows compatibility review — PR #1261, reviewed at Scope: the full base ( Windows-specific findings: none. Checks:
Verification (native Windows 11 10.0.26300, python 3.12.13, detached worktree
Coverage gaps: no live MiniMax call (the tests use an httpx mock); the UI is not involved. |
66b90dc to
2b02e3b
Compare
|
Windows compatibility review — PR #1261, reviewed at Scope: the branch was rebased onto the new main tip Windows-specific findings: none. The delta adds no code; the earlier checks stand (SVG-free JSON schema text, provider predicate shared with Verification (native Windows 11 10.0.26300, python 3.12.13, detached worktree
Coverage gaps: no live MiniMax call; the UI is not involved. |
2b02e3b to
a86d067
Compare
|
Windows compatibility review — PR #1261, reviewed at Scope: the branch was rebased onto the new main tip Windows-specific findings: none. The delta adds no code; the earlier checks stand (SVG-free JSON schema text, provider predicate shared with Verification (native Windows 11 10.0.26300, python 3.12.13; detached worktree
Coverage gaps: no live MiniMax call; the UI is not involved. |
a86d067 to
616429f
Compare
|
Windows compatibility review — PR #1261, reviewed at Scope: the branch was rebased onto the new main tip Windows-specific findings: none. The earlier checks stand (SVG-free JSON schema text, provider predicate shared with Verification (native Windows 11 10.0.26300, python 3.12.13; detached worktree
Coverage gaps: no live MiniMax call; the UI is not involved. |
616429f to
3c2ca88
Compare
|
Windows compatibility review — PR #1261, reviewed at Scope: the branch was rebased onto the new main tip Windows-specific findings: none. The earlier checks stand (SVG-free JSON schema text, provider predicate shared with Verification (native Windows 11 10.0.26300, python 3.12.13; detached worktree
Coverage gaps: no live MiniMax call; the UI is not involved. |
|
Friendly ping for a review when someone has a moment. CI is fully green at the current head, including the coverage gates, and the branch sits on the latest |
LivXue
left a comment
There was a problem hiding this comment.
The execute-side half is right: on MiniMax, _one truncates references to the first and appends a note naming how many were left out, which is what the transport already sent, and the second test pins the wire body and the note. The schema half does not reach the model through the real registration path. The plugin factory returns a SessionTool, and SessionTool defines name, description and parameters but not to_schema. admit_tool therefore sees the inherited Tool.to_schema, records schema_dynamic as False, and get_definitions serves the frozen snapshot built from the prototype's static _DESCRIPTION and its Up to six reference text.
I confirmed this end to end: make_ppt_generate_image with a MiniMax ImageToolConfig returns a SessionTool, and registering that and calling get_definitions still serves Up to six with no character wording, schema_dynamic False. The new schema test registers the raw PptGenerateImageTool, so it exercises a seam production does not use and cannot catch this.
Please make the wrapper delegate, for example def to_schema(self): return self._prototype.to_schema(), so the registry marks the tool dynamic and serves the provider-aware schema, and add a test through make_ppt_generate_image rather than the bare tool. Targeted runs here: tests/test_ppt_engine_generate_image_tool.py, tests/test_ppt_engine_plugin.py and tests/_ppt_engine_skill_claims.py, 78 passed.
840a16a to
a2909a6
Compare
|
Addressed the review finding.
The test now goes through Pushed to the branch. The whole ppt-engine suite passes locally (3774 passed, 13 skipped). |
LivXue
left a comment
There was a problem hiding this comment.
No blockers in the reviewed scope.
Scope: both commits of c3be94a..b0e489a5 (3 files, +148/-2), read at b0e489a5.
The schema half was the open question, and it now reaches the model. I drove the production seam rather than the bare tool: make_ppt_generate_image(ctx) returns a SessionTool, the registry now reads that as schema_dynamic, and get_definitions() serves the character and one-picture wording once the image section names MiniMax, then flips back when it does not. Registering the prototype instead of the wrapper agrees with it. Reverting the new SessionTool.to_schema makes the new test fail on assert "character" in served["description"], so it covers the seam it claims to.
The execution side holds through the same wrapper: one subject_reference on the wire and the note on the result. refs[:1] sits at generate_image.py:344.
Two nonblocking items. The MiniMax wording rewrites parameters.properties.references only; prompts[].references carries no description at all, so a batched call still gets no guidance. And ppt-script-authoring/SKILL.md still says "up to six pictures" (line 1102), so a deployment that mounts that skill has the resident prompt contradicting the tool; whether the product mounts it is more than this diff can settle.
Verification: the targeted file 16 passed; the six-file set 206 passed (204 at base, so +2, not the 192 in the description); ruff check and format clean; all five repo checks pass. The head is 8 commits behind main and touches none of those files.
Windows compatibility review —
|
b0e489a to
7399659
Compare
Windows compatibility review —
|
|
Both non-blocking notes from the earlier review are addressed in this head:
The PR body also claimed 192 tests for the combined run where it measures 229; that is corrected, along with the two lines this head adds. On the coverage gap you name: the "host sends only the first reference" premise is read from the host's MiniMax route, and I have not exercised it against a live endpoint either -- the test drives the schema through |
7399659 to
6786dac
Compare
|
The branch is on the latest main (head The review on this PR still reads as a comment rather than an approval, so the branch shows review as required. If it was meant as an approval, submitting it with the Approve button is all this needs. |
Windows compatibility review —
|
|
One question on the hardcoded one-reference MiniMax wording: is there an API-level way to learn that limit, rather than baking What I can see today does not publish one. The docs type Did you find a signal for the count -- a validation error when more than one |
6786dac to
7378de2
Compare
Windows compatibility review —
|
Windows compatibility review —
|
|
Heads up on the red
The same flake hit the previous head as well (the head only adds an empty retrigger commit on top of |
Windows compatibility review —
|
|
Hi @LivXue, your Windows compatibility review at head |
31098f1 to
653590a
Compare
Windows compatibility review —
|
ppt_generate_image told every deployment that `references` carries up to six pictures to match or vary, but the transport underneath it does not: on MiniMax the host sends the first alone, as a character to keep, and drops the rest without a word. The deck's model, reading a schema that promised six, asked for several and got one -- and was never told the others were not sent. The tool now authors its own to_schema, the same way image_generate does, so the registry serves the answer live and a section changed between turns is read on the next one: on MiniMax the description and the references parameter say one picture, kept as the character it shows, with the manner in the prompt where a reference cannot carry it; off MiniMax both stay byte-identical to what they were. A second reference on MiniMax is now reported rather than swallowed: the first is the one sent, the file is named for what was sent, and the result carries a note saying how many were left out -- the host's own truncation, with the word the issue says was missing. Co-authored-by: Claude (claude-fable-5-1) <noreply@anthropic.com>
…ssion wrapper The deck's image tool is registered as a SessionTool, which inherited Tool.to_schema and so read as a static shape to the registry: the schema was frozen at admit time, and a section that later named MiniMax was still served the OpenRouter wording. The wrapper now delegates to its prototype, which authors the provider-aware schema, and the registry serves that answer live. The test goes through make_ppt_generate_image and a registry, so it covers the seam production registers on rather than the bare tool. Co-authored-by: Claude (claude-fable-5-1) <noreply@anthropic.com>
A picture asked for inside `prompts` is a request of its own, so the MiniMax wording that rewrote the single-picture `references` left the batched one with no description at all: the model planning several pictures in one call was offered no guidance where the single ask got it. The skill page said "up to six" with no provider caveat, which is the promise the MiniMax route cannot keep. Co-authored-by: Claude (claude-fable-5-1) <noreply@anthropic.com>
653590a to
75223ed
Compare
Windows compatibility review —
|
Summary
ppt_generate_imagetold every deployment thatreferencescarries up to six pictures to match or vary, but the transport underneath it does not keep that promise on MiniMax: the host's MiniMax route sends the first reference alone, as asubject_referenceoftype: "character", and drops the rest without a word. The deck's model, reading a schema that offered six, asked for several and got one -- and was never told the others were not sent.The tool now authors its own
to_schema, the same wayimage_generatedoes, so the registry serves the answer live and a section changed between turns is read on the next one rather than frozen at admission:referencesparameter say one picture, kept as the character it shows, with the manner in the prompt where a reference cannot carry it;origin/mainrenders, not just by eye.The issue left the second-reference behaviour to the PR: this sends the first (which is what the transport does anyway, so no request changes shape), names the file for what was sent, and puts a note on the result saying how many were left out. Refusing instead would fail a whole batch of pictures for one extra reference; the note keeps the batch moving and fixes the complaint, which was the silence.
The wording reaches every ask, not only the single-picture one: a picture asked for inside
promptsis a request of its own, so it carries the same one-reference description on MiniMax, and theppt-script-authoringskill page -- which an author reads where the schema is not in front of them -- says the deployment keeps the first picture only, so the character to stay consistent with goes in that one.Tests, in the shape the issue asked for: the registry-served schema with the section's provider switched between turns (the deck's counterpart of
test_the_image_tool_says_what_references_do_on_the_provider_it_runs_on), and the reference handling itself -- onesubject_referenceon the wire, and the note on the answer.Type
Verification
Relevant tests pass locally
Relevant lint / type checks pass locally
User-facing docs or screenshots are updated when needed
PYTHONUTF8=1 uv run pytest tests/test_ppt_engine_generate_image_tool.py -o addopts='' -p no:xdist -q- 16 passed (14 existing + 2 new)PYTHONUTF8=1 uv run pytest tests/test_ppt_engine_generate_image_tool.py tests/test_ppt_engine_image_search.py tests/test_ppt_engine_assembly.py tests/test_ppt_engine_plugin.py tests/test_agents_ppt_launcher.py tests/_ppt_engine_skill_claims.py -o addopts='' -p no:xdist -q- 229 passedPYTHONUTF8=1 uv run pytest tests/test_ppt_engine_prompt_claims.py tests/test_ppt_engine_assets_script_helpers.py -q- 142 passed, which is what checks the skill page against the code that has to back itBoth new tests were watched failing first: the schema one on
assert 'character' in served["description"](the served text did not follow the provider), the behaviour one on the missing note (the host had already been sending only the first reference)The default schema was checked byte-for-byte against the description
origin/mainrenders, extracted from the old source withast-- identical, withUp to sixpresent and no MiniMax textuv run ruff checkanduv run ruff format --checkon the two changed files - clean (the test file needed oneruff formatpass)uv run ty checkon the two changed files - cleanmake lint-imports- 10 contracts kept, 0 brokenmake coverage-diff- 100.00% (0/0 executable changed lines):coveragemeasuresraven/only, so aplugins-dist/change has no executable lines in the report; the gate passes the same way it did for a test-only PRuv run python scripts/check_source_language.py origin/main..HEAD,scripts/check_large_files.py origin/main..HEAD,scripts/check_commit_messages.py origin/main..HEAD- passThe doc change is the skill page the deck author reads; the schema itself is the documentation the model reads, and it is what changed
Risk
Off MiniMax nothing changes: the served schema is byte-identical to today's, verified as above, and no request on any other provider goes out differently. On MiniMax the schema now promises one reference instead of six -- which is what the transport already did -- and a picture that arrives with more than one gets a note instead of silence. The provider read is the same private
_runs_on_minimaxthe tool already reaches for in_model, so no host API was touched. Rollback is reverting the squash commit.Related Issues
Fixes #1014