fix: normalize video duration per model rules via Zod schemas#194
Merged
SecurityQQ merged 1 commit intomainfrom Apr 4, 2026
Merged
fix: normalize video duration per model rules via Zod schemas#194SecurityQQ merged 1 commit intomainfrom
SecurityQQ merged 1 commit intomainfrom
Conversation
Contributor
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
📝 Walkthroughwalkthroughrefactored fal provider by extracting duration normalization into a new changes
sequence diagram(s)(skip — changes are modular and don't introduce a new multi-component flow) estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/ai-sdk/providers/model-rules.ts`:
- Around line 68-100: ModelInputSchemas is missing entries for several Falcon
video model variants so those IDs will bypass validation; add explicit schema
rules for "grok-imagine-edit", "grok-imagine-image", "grok-imagine-image/edit",
"kling-v2.6-motion", "kling-v2.6-motion-standard", and "sora-2-remix" into the
ModelInputSchemas map (or implement a clear fallback rule at the top of the map)
using the same helper validators used elsewhere (stringIntDuration,
enumDuration, rangeDuration, intDuration) to mirror the appropriate existing
variants (e.g., match "grok-imagine" rules for grok-imagine-* variants, match
"kling-v2.6" for kling-v2.6-motion*, and match "sora-2" for sora-2-remix) so
these IDs are validated consistently by the lookup.
- Around line 116-127: normalizeProviderInput currently silently applies schema
coercions via ModelInputSchemas and schema.safeParse, losing the previous
warning behavior; update normalizeProviderInput to detect when the
parsed/normalized value differs from the original (e.g., compare input.duration
to result.data.duration) and return the normalized input together with a
warnings array (or attach a warnings property) describing adjustments (for
example: "Duration Xs not supported. Using Ys"); ensure the function signature
and callers that consume normalizeProviderInput are updated to accept { input:
Record<string, unknown>, warnings?: string[] } (or similar) and emit a warning
only when the schema clamps or coerces values so callers regain observability of
changes.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 38e54a08-c86b-4122-8723-1b53b644d8f6
📒 Files selected for processing (2)
src/ai-sdk/providers/fal.tssrc/ai-sdk/providers/model-rules.ts
src/ai-sdk/providers/model-rules.ts
Outdated
Comment on lines
+68
to
+100
| const ModelInputSchemas: Record<string, z.ZodType> = { | ||
| // Kling O3 (v3): fal expects string integer "3"–"15" | ||
| "kling-v3": z.object({ duration: stringIntDuration(3, 15, 5) }), | ||
| "kling-v3-standard": z.object({ duration: stringIntDuration(3, 15, 5) }), | ||
|
|
||
| // Kling v2.6: same rules as v3 | ||
| "kling-v2.6": z.object({ duration: stringIntDuration(3, 15, 5) }), | ||
|
|
||
| // Kling legacy: exactly 5 or 10 | ||
| "kling-v2.5": z.object({ duration: enumDuration([5, 10], 5) }), | ||
| "kling-v2.1": z.object({ duration: enumDuration([5, 10], 5) }), | ||
| "kling-v2": z.object({ duration: enumDuration([5, 10], 5) }), | ||
|
|
||
| // Wan: 5 or 10 | ||
| "wan-2.5": z.object({ duration: enumDuration([5, 10], 5) }), | ||
| "wan-2.5-preview": z.object({ duration: enumDuration([5, 10], 5) }), | ||
|
|
||
| // Minimax: round to integer | ||
| minimax: z.object({ duration: intDuration(5) }), | ||
|
|
||
| // Grok Imagine: integer 1–15 | ||
| "grok-imagine": z.object({ duration: rangeDuration(1, 15, 6) }), | ||
|
|
||
| // Sora 2: only 4, 8, 12, 16, 20 | ||
| "sora-2": z.object({ duration: enumDuration([4, 8, 12, 16, 20], 4) }), | ||
| "sora-2-pro": z.object({ duration: enumDuration([4, 8, 12, 16, 20], 4) }), | ||
|
|
||
| // Seedance (piapi): 5, 10, or 15 | ||
| "seedance-2-preview": z.object({ duration: enumDuration([5, 10, 15], 5) }), | ||
| "seedance-2-fast-preview": z.object({ | ||
| duration: enumDuration([5, 10, 15], 5), | ||
| }), | ||
| }; |
Contributor
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# check if VIDEO_MODELS keys in fal.ts are all covered in ModelInputSchemas
# extract model ids from both files and compare
echo "=== VIDEO_MODELS in fal.ts ==="
rg -o '"[^"]+":' src/ai-sdk/providers/fal.ts | head -50 | grep -E 'kling|wan|minimax|grok|sora|seedance' | sort -u
echo ""
echo "=== ModelInputSchemas keys ==="
rg -o '"[^"]+":|^ [a-z].*:' src/ai-sdk/providers/model-rules.ts | grep -v '//' | sort -uRepository: vargHQ/sdk
Length of output: 712
add schema definitions for missing model variants - the lookup doesn't cover all video models from fal.ts. these ids are missing from ModelInputSchemas and will skip validation:
- grok-imagine-edit
- grok-imagine-image
- grok-imagine-image/edit
- kling-v2.6-motion
- kling-v2.6-motion-standard
- sora-2-remix
add explicit schema rules for each or define a fallback strategy meow
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/ai-sdk/providers/model-rules.ts` around lines 68 - 100, ModelInputSchemas
is missing entries for several Falcon video model variants so those IDs will
bypass validation; add explicit schema rules for "grok-imagine-edit",
"grok-imagine-image", "grok-imagine-image/edit", "kling-v2.6-motion",
"kling-v2.6-motion-standard", and "sora-2-remix" into the ModelInputSchemas map
(or implement a clear fallback rule at the top of the map) using the same helper
validators used elsewhere (stringIntDuration, enumDuration, rangeDuration,
intDuration) to mirror the appropriate existing variants (e.g., match
"grok-imagine" rules for grok-imagine-* variants, match "kling-v2.6" for
kling-v2.6-motion*, and match "sora-2" for sora-2-remix) so these IDs are
validated consistently by the lookup.
Comment on lines
+116
to
+127
| export function normalizeProviderInput( | ||
| model: string, | ||
| input: Record<string, unknown>, | ||
| ): Record<string, unknown> { | ||
| const schema = ModelInputSchemas[model]; | ||
| if (!schema) return input; | ||
|
|
||
| const result = schema.safeParse({ duration: input.duration }); | ||
| if (!result.success) return input; | ||
|
|
||
| return { ...input, ...(result.data as Record<string, unknown>) }; | ||
| } |
Contributor
There was a problem hiding this comment.
silent normalization loses observability from previous implementation
the old openai.ts and fal.ts code pushed warnings when duration was invalid or clamped (e.g., "Duration ${duration}s not supported. Using ${validSeconds}s"). this new approach silently transforms values without any indication to the caller.
if someone passes duration: 2.5 to kling-v3, it silently becomes "3" with no warning. might want to consider returning warnings alongside the normalized input for cases where values were adjusted.
💡 possible approach to add observability
+interface NormalizeResult {
+ input: Record<string, unknown>;
+ warnings: string[];
+}
+
export function normalizeProviderInput(
model: string,
input: Record<string, unknown>,
-): Record<string, unknown> {
+): NormalizeResult {
const schema = ModelInputSchemas[model];
- if (!schema) return input;
+ if (!schema) return { input, warnings: [] };
const result = schema.safeParse({ duration: input.duration });
- if (!result.success) return input;
+ if (!result.success) return { input, warnings: [] };
- return { ...input, ...(result.data as Record<string, unknown>) };
+ const normalized = { ...input, ...(result.data as Record<string, unknown>) };
+ const warnings: string[] = [];
+ if (input.duration !== undefined && normalized.duration !== input.duration) {
+ warnings.push(`Duration ${input.duration} normalized to ${normalized.duration} for ${model}`);
+ }
+ return { input: normalized, warnings };
}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@src/ai-sdk/providers/model-rules.ts` around lines 116 - 127,
normalizeProviderInput currently silently applies schema coercions via
ModelInputSchemas and schema.safeParse, losing the previous warning behavior;
update normalizeProviderInput to detect when the parsed/normalized value differs
from the original (e.g., compare input.duration to result.data.duration) and
return the normalized input together with a warnings array (or attach a warnings
property) describing adjustments (for example: "Duration Xs not supported. Using
Ys"); ensure the function signature and callers that consume
normalizeProviderInput are updated to accept { input: Record<string, unknown>,
warnings?: string[] } (or similar) and emit a warning only when the schema
clamps or coerces values so callers regain observability of changes.
Replace the scattered duration if/else chain in fal.ts with a centralised normalizeProviderInput() backed by per-model Zod schemas. Each model gets a .transform() schema that clamps, rounds, and type-converts duration values automatically. Fixes kling-v3/v2.6 failures when duration is a float (from speech segments) or outside the [3,15] range.
SecurityQQ
force-pushed
the
fix/normalize-provider-duration
branch
from
94fc438 to
0bea8a1
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
1 participant
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.
Summary
model-rules.tswith per-model Zod schemas that validate and transformdurationvalues via.transform()— rounding floats, clamping to valid ranges, and converting typesif/elsechain infal.tswith a singlenormalizeProviderInput()callresolution, Soradelete_video) preserved alongside the new normalizationProblem
All 6 clips failed with:
Input should be '3', '4', '5', ... '15'onfal-ai/kling-video/o3/pro/image-to-video.The SDK was doing
String(duration ?? 5)but never clamping range or rounding — floats like2.34from speech segments became"2.34"(rejected), and values outside [3,15] passed through.Model rules defined
kling-v3,kling-v3-standard,kling-v2.6stringkling-v2.5,kling-v2.1,kling-v2numberwan-2.5,wan-2.5-previewnumberminimaxnumbergrok-imaginenumbersora-2,sora-2-pronumberseedance-2-*numberCompanion gateway PR: https://github.com/vargHQ/gateway/pull/new/fix/normalize-provider-duration