feat: add AI Teammate training system with learn-by-example patterns#148

Merged

anandgupta42 merged 22 commits intomainfrom

claude/ai-teammate-interface-p8SO6

Mar 15, 2026

Commits on Mar 15, 2026

Add AI Teammate repositioning design document

claude
authored and
anandgupta42
committed
Enrich design doc with OpenClaw research and proactive behaviors

claude
authored and
anandgupta42
committed
Implement AI Teammate training system and Deep Research mode

claude
authored and
anandgupta42
committed
Polish AI Teammate training UX: auto-lowercase names, update detection, budget visibility

claude
authored and
anandgupta42
committed
Enhance training UX: attribution, correction detection, priority sorting

claude
authored and
anandgupta42
committed
Fix experience gaps from user journey simulations

claude
authored and
anandgupta42
committed
Add self-improvement loop: applied tracking, insights, staleness detection

claude
authored and
anandgupta42
committed
fix: add dedicated training feature flag and remove unused insight type

anandgupta42
and
claude
committed
fix: reset training session tracking, add error logging, fix list truncation

anandgupta42
and
claude
committed
fix: use `.altimate-code/memory` as primary storage path with `.opencode` fallback

anandgupta42
and
claude
committed
feat: add Trainer agent mode with pattern discovery and training validation

anandgupta42
and
claude
committed
docs: add comprehensive training guide with scenarios and limitations

anandgupta42
and
claude
committed
fix: increase training budget to 16K chars and rewrite docs as harness customization guide

anandgupta42
and
claude
committed
feat: merge training into memory with context-aware relevance scoring

anandgupta42
and
claude
committed
refactor: cut training_scan and training_validate, simplify docs

anandgupta42
and
claude
committed
fix: remove dead accepted/rejected fields, add training tips, expand limitations

anandgupta42
and
claude
committed
docs: update site-wide docs for training and new agent modes

anandgupta42
and
claude
committed
fix: address Sentry review findings — 7 bugs fixed

anandgupta42
and
claude
committed
fix: CI failure + new Sentry finding — orphaned headers and agent test

anandgupta42
and
claude
committed
fix: address multi-model code review findings

anandgupta42
and
claude
committed
fix: address new Sentry findings — regex m flag and off-by-one budget check

anandgupta42
and
claude
committed
fix: address 6-model consensus review — 4 remaining bugs

anandgupta42
and
claude
committed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: add AI Teammate training system with learn-by-example patterns#148

feat: add AI Teammate training system with learn-by-example patterns#148
anandgupta42 merged 22 commits intomainfrom
claude/ai-teammate-interface-p8SO6

Commits on Mar 15, 2026

Add AI Teammate repositioning design document

Enrich design doc with OpenClaw research and proactive behaviors

Implement AI Teammate training system and Deep Research mode

Polish AI Teammate training UX: auto-lowercase names, update detection, budget visibility

Enhance training UX: attribution, correction detection, priority sorting

Fix experience gaps from user journey simulations

Add self-improvement loop: applied tracking, insights, staleness detection

fix: add dedicated training feature flag and remove unused insight type

fix: reset training session tracking, add error logging, fix list truncation

fix: use `.altimate-code/memory` as primary storage path with `.opencode` fallback

feat: add Trainer agent mode with pattern discovery and training validation

docs: add comprehensive training guide with scenarios and limitations

fix: increase training budget to 16K chars and rewrite docs as harness customization guide

feat: merge training into memory with context-aware relevance scoring

refactor: cut training_scan and training_validate, simplify docs

fix: remove dead accepted/rejected fields, add training tips, expand limitations

docs: update site-wide docs for training and new agent modes

fix: address Sentry review findings — 7 bugs fixed

fix: CI failure + new Sentry finding — orphaned headers and agent test

fix: address multi-model code review findings

fix: address new Sentry findings — regex m flag and off-by-one budget check

fix: address 6-model consensus review — 4 remaining bugs