feat: refresh Workers AI model handling#11
Merged
Merged
Conversation
Replace the deprecated Workers AI default model with @cf/zai-org/glm-4.7-flash and update staging to use the same model. Add JSON mode, disable model thinking, and pass both token limit fields for ingest and location extraction so newer chat models keep returning parseable JSON within the existing budgets. Also accept OpenAI-compatible `choices` responses in AI text extraction for summaries, ingest, and location enrichment. Upgrade Wrangler and the generated lockfile to the current Workers runtime tooling required by the refreshed model/runtime stack. Behavior change: AI extraction and summary calls now default to GLM 4.7 Flash, so outputs may differ slightly from the previous Llama model. Risk is mainly in JSON extraction quality and token-budget behavior; staging should be smoke tested before production rollout. Follow-up: watch ingest/location proposal quality and add model-specific regression fixtures if output drift appears.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace the deprecated Workers AI default model with @cf/zai-org/glm-4.7-flash and update staging to use the same model.
Add JSON mode, disable model thinking, and pass both token limit fields for ingest and location extraction so newer chat models keep returning parseable JSON within the existing budgets. Also accept OpenAI-compatible
choicesresponses in AI text extraction for summaries, ingest, and location enrichment.Upgrade Wrangler and the generated lockfile to the current Workers runtime tooling required by the refreshed model/runtime stack.
Behavior change: AI extraction and summary calls now default to GLM 4.7 Flash, so outputs may differ slightly from the previous Llama model. Risk is mainly in JSON extraction quality and token-budget behavior; staging should be smoke tested before production rollout. Follow-up: watch ingest/location proposal quality and add model-specific regression fixtures if output drift appears.