Repository navigation
feat(entities): let the decision model type names the rules leave as terms - #513
Merged
Merged
Conversation
…terms Analysis asks the decision model (Jev or Laya, when set up) what each new Term of a recording is, in one call, and keeps the types it is sure of. Settings > Analysis > Names the rules can't type (analysis.typing) can let the language model answer too, or turn it off. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
…model types names Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
…-qfebqj Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
…-qfebqj Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT # Conflicts: # CHANGELOG.md # README.md # threat-model.yaml
…-qfebqj Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT # Conflicts: # CHANGELOG.md # threat-model.yaml
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
The changelog entry moves to the end of Unreleased, where pull requests adding at the top of the list don't conflict with it. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT
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.
Requested by Adeel · project thread
Description
Before: after #395 the rules type most names, but a name nothing around it explains (a single unknown word such as a brand, a product or a project, "Quillmark") still came out as a Term, even with a decision model set up.
After: when Jev or Laya is set up, analysis asks it what each new Term of a recording is, with the first two lines it's said in, and keeps the type when it is sure (
decisions.act_above, 0.8). A model that isn't sure, or can't be reached, leaves the name a Term.decide.choose_allasks several routine questions at once (up to 20 names a call, 40 a recording); Laya, which reads less, is asked one name at a time.analysis.typing):auto(default: the decision model when one is set up, never the language model),model(the language model answers when there's no decision model),rules(no model).decide, so they are in Activity and count toward budgets; at the hard limit nothing is asked.Motivation and Context
Adeel: "every entity comes as term? why!!" #395 fixed the rules; this covers the names the rules can't tell, with the decision model AGENTS.md asks routine calls to use.
Steps to reproduce (if appropriate):
With Jev set up, a transcript line "Then Quillmark came up, and Sarah Johnson said the Acme Corp deal is done." gave Quillmark as a Term. It is now a Product (
test_the_decision_model_types_what_the_rules_cant).Types of changes
!in the title)Checklist:
make hookschecks it on commit).tests/domain/test_name_types.py: Jev types an unknown name in one call and isn't asked again, unsure answers and failures stay Terms, the language model isn't asked by default,typing: modelandtyping: rules, Laya one at a time, Custom vocabulary terms aren't asked,choose_all).docs/accordingly (processing.md "Names the rules can't type", assistant.md routine choices).## UnreleasedinCHANGELOG.md.Done questions (AGENTS.md)
PUT /api/v1/settings/analysisand the assistant's change_settings tool like every other.analysis.typingin Settings › Analysis, defaultauto, not in the setup wizard.rulesas the way to keep them local.autolets the decision model people already set up for routine choices make it, only when it is sure; installs without one see no change,rulesturns it off, and types people set are never asked about or changed.decide(engines, confidence, budgets),entity_setup's built-in type help and the existing settings UI.Local CI (
ci/local-ci.sh): all six jobs (FastAPI embedded and server, Next.js, pre-commit, title, upgrade from the last release) pass on this change over main at #518 (cc07979).🤖 Generated with Claude Code
https://claude.ai/code/session_018MeaEgM8m7rTjbkKVQVsrT