build: dspack-gen 0.4.0 across web/composer/agent - #76
Merged
Conversation
…loop + think:false) emit ^0.7.0 bump follows once its npm publish (owner-gated trusted-publisher setup) completes — gen 0.4.0's range admits both, one emitter copy either way. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Deploying with
|
| Status | Name | Latest Commit | Updated (UTC) |
|---|---|---|---|
| ✅ Deployment successful! View logs |
dspack-studio-composer | b54b60c | Aug 10 2026, 11:26 PM |
There was a problem hiding this comment.
Pull request overview
Bumps @aestheticfunction/dspack-gen to ^0.4.0 across the monorepo apps to ship the generator 0.4.0 behavior described in the PR (representability repair loop, casualty-free generation, and Ollama think:false) through the product surfaces (web/composer/agent).
Changes:
- Update
@aestheticfunction/dspack-gendependency from^0.3.2→^0.4.0inapps/web,apps/composer, andapps/agent. - Update
pnpm-lock.yamlto lock@aestheticfunction/dspack-gen@0.4.0(including snapshot entry) consistently for all importers.
Reviewed changes
Copilot reviewed 3 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| pnpm-lock.yaml | Locks @aestheticfunction/dspack-gen to 0.4.0 and updates the corresponding snapshot entry. |
| apps/web/package.json | Bumps @aestheticfunction/dspack-gen dependency to ^0.4.0 for the web app. |
| apps/composer/package.json | Bumps @aestheticfunction/dspack-gen dependency to ^0.4.0 for the composer app. |
| apps/agent/package.json | Bumps @aestheticfunction/dspack-gen dependency to ^0.4.0 for the agent app. |
Files not reviewed (1)
- pnpm-lock.yaml: Generated file
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
…r loop gen 0.4.0 makes emitter refusals repairable, so the one-entry script exhausted into failed-adapter instead of the demonstrated terminal refusal. Three identical entries replay the unprojectable surface through both repairs — the demo now shows a declared casualty staying refused (verbatim reason) even WITH repair turns, which is the truer story. break.spec.ts 8/8 locally. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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.
Ships the representability repair loop + casualty-free generation + Ollama think:false to the product (gen 0.4.0's emit range admits the installed 0.6.0 — one emitter copy). The emit ^0.7.0 bump follows once its npm publish (owner-gated trusted-publisher setup) completes. Corpus before/after on the exact merged code: shadcn 1→3 passed, Astryx 7→11, zero casualty refusals in 32 post-fix runs, zero regressions. qwen3.6:35b verified through the real agent /generate (was: empty model output).
🤖 Generated with Claude Code