release: v0.3.0 — tf.learning closed decision→outcome loop - #7
Merged
Conversation
Expose the engine's outcome-loop RPCs through the SDK as a new `learning` resource: recordDecision, recordOutcome, getOutcomes, getEffectiveness. Record a decision (with links to the patterns/predictions that informed it), record its realized outcome, and every informing pattern's calibrated confidence moves toward what actually happened. - src/resources/learning.ts: LearningResource + full types - registered on the client (tf.learning) and exported from index - proto + coverage.json synced (35 RPCs — 30 covered, 5 internal) typecheck + check:proto pass. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds the runnable next-best-offer example showcasing the tf.learning closed decision→outcome loop, wires demo:nbo, and pulls in the @anthropic-ai/sdk + zod dev deps it needs. Bumps to 0.3.0 for the new tf.learning + tf.behaviors public surface since 0.2.0. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
npm ci failed because the lock file was never regenerated after these deps were added to package.json. Co-Authored-By: Claude Opus 4.8 (1M context) <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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
v0.3.0
Lands the
tf.learningclosed decision→outcome loop onmainand cuts the 0.3.0 release.What's included
feat(learning):tf.learning— closed-loop decision→outcome primitive (recordDecision/recordOutcome/getEffectiveness), withinformedByprovenance so outcomes re-calibrate the patterns/predictions that drove each decision.chore(release): runnableexamples/next-best-offer.tsdemonstrating the loop end-to-end (which offer, when, and how it learns), wired asnpm run demo:nbo.@anthropic-ai/sdk+zodas dev deps for the example; bumps version to 0.3.0.Why 0.3.0
New public API surface (
tf.learning, andtf.behaviors.discoverfrom #5) since 0.2.0, no breaking changes → semver minor.Validation
npm run typechecknpm run build🤖 Generated with Claude Code