Maniacs_Mansion/MealQuest
11
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

normalize_recipe skill #69

Merged
approver_agent merged 2 commits from task/normalize-recipe_9b4db226-9d8f-4251-a5de-adc45713c7bc into feature/cebed295-8c05-453b-807b-8078dcd8d250-recipe-grounding 2026-10-05 14:54:38 -04:00
Conversation 2 Commits 2 Files Changed 7
+983
dev_agent commented 2026-10-05 14:31:28 -04:00
Member
Copy Link
Copy Source

Maestro task: 9b4db226-9d8f-4251-a5de-adc45713c7bc (Feature 10 - Recipe Grounding and Photos).

Done-condition

internal/ai/skills implements normalize_recipe v1 (temperature 0): input title, raw ingredient lines, steps, JSON-LD times; output {ingredients:[{name,qty,unit,note}], method, difficulty, minutes_total}. Validators require exactly one output ingredient per input line, in order, non-empty name. Code-derived values win: minutes_total from JSON-LD when present; method crockpot on slow cooker/crock pot mentions; difficulty from step count and minutes when the model omits it. Golden Fake-provider tests: typical recipe, line-count mismatch repaired, slow-cooker forced to crockpot despite the model, JSON-LD minutes overriding the model. Go quality floor passes.

Evidence

  • New internal/ai/skills normalize_recipe + prompt template (checksum test passes); docs updated.
  • gofmt/vet/go test -race/build pass; no new dependency.
  • First concrete skill on the merged Feature 09 harness.
Maestro task: 9b4db226-9d8f-4251-a5de-adc45713c7bc (Feature 10 - Recipe Grounding and Photos). ## Done-condition internal/ai/skills implements normalize_recipe v1 (temperature 0): input title, raw ingredient lines, steps, JSON-LD times; output {ingredients:[{name,qty,unit,note}], method, difficulty, minutes_total}. Validators require exactly one output ingredient per input line, in order, non-empty name. Code-derived values win: minutes_total from JSON-LD when present; method crockpot on slow cooker/crock pot mentions; difficulty from step count and minutes when the model omits it. Golden Fake-provider tests: typical recipe, line-count mismatch repaired, slow-cooker forced to crockpot despite the model, JSON-LD minutes overriding the model. Go quality floor passes. ## Evidence - New internal/ai/skills normalize_recipe + prompt template (checksum test passes); docs updated. - gofmt/vet/go test -race/build pass; no new dependency. - First concrete skill on the merged Feature 09 harness.
dev_agent added 1 commit 2026-10-05 14:31:28 -04:00
Add normalize_recipe skill
CI / ci (push) Successful in 1m37s
Details
CI / ci (pull_request) Successful in 1m38s
Details
925eddfa24 
normalize_recipe v1 turns a recipe page's title, raw ingredient lines,
steps and JSON-LD times into {ingredients: [{name, qty, unit, note}],
method, difficulty, minutes_total}. skills.NormalizeRecipe always runs it
at temperature 0. Validation requires one named ingredient per input line,
in order, so a mismatch gets the harness's repair turn. Code-derived
values win over the model's: JSON-LD total minutes, crockpot for a slow
cooker or crock pot mention, and a derived difficulty when the model gives
none. Golden tests with the Fake provider cover a typical recipe, a
repaired line-count mismatch, a slow-cooker recipe forced to crockpot and
JSON-LD minutes overriding the model.

Maestro task 9b4db226-9d8f-4251-a5de-adc45713c7bc

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
review_agent requested changes 2026-10-05 14:33:05 -04:00
Dismissed
review_agent left a comment
Member
Copy Link
Copy Source

Independent Codex gpt-6-sol review: CHANGES_REQUIRED for this exact commit.

Independent Codex gpt-6-sol review: CHANGES_REQUIRED for this exact commit.
overseer added 1 commit 2026-10-05 14:43:17 -04:00
Tighten normalize_recipe output checks
CI / ci (push) Successful in 1m39s
Details
CI / ci (pull_request) Successful in 1m39s
Details
f4817f5189 
Address review findings on the normalize_recipe skill:

- Ingredient order: an ingredient is out of order when its name has more
  of its words in another line than in its own, not merely when it
  shares no word with its own line. Swapping "olive oil" and
  "sesame oil" now fails validation and triggers the repair turn.
- Required fields: Ingredient and NormalizedRecipe decode through
  UnmarshalJSON that requires every schema field and rejects unknown
  ones; qty, unit and note may not be omitted or null. Such a reply
  fails to decode and triggers the repair turn.
- Zero total: a present JSON-LD TotalMinutes that is not positive is
  rejected by PromptInput before any model call, instead of falling
  back to the model's minutes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
review_agent left a comment
Member
Copy Link
Copy Source

Independent Codex gpt-6-sol review: APPROVED for this exact commit.

Independent Codex gpt-6-sol review: APPROVED for this exact commit.
approver_agent merged commit 2a19e89e5a into feature/cebed295-8c05-453b-807b-8078dcd8d250-recipe-grounding 2026-10-05 14:54:38 -04:00
Sign in to join this conversation.
Reviewers
No Reviewers
review_agent
Labels
No items
No labels
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
approver_agent (The Approver) chatgpt claude-ai Claude-Code codex (Codex) dev_agent grok opencode orchestrator-agent overseer (Joshua) review_agent (The Reviewer)
No Assignees
3 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Maniacs_Mansion/MealQuest#69