rve/learning-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: phase 5 of AI pipeline hardening — R42 retrieval & telemetry #7

Merged
rve merged 1 commits from feat/ai-pipeline-hardening-phase-5 into main 2026-05-20 19:38:34 +00:00
Conversation 0 Commits 1 Files Changed 11 +753 -56
rve commented 2026-05-20 19:38:25 +00:00
Owner
Copy Link
  • Add dependency-free TF-IDF retrieval (src/lib/retrieval.js) with NL+EN
    stopwords and a WeakMap-cached index.
  • Rewrite buildKbContext to ship the top-K relevant topics + verbatim-
    mentioned ids only, filter relations to the included set, and append a
    [kb_hash: <8 hex>] suffix so the ephemeral prompt cache busts when the
    graph changes. Returns { context, retrievedTopics, allTopics }.
  • Add LOOKUP_TOPIC_TOOL and drive useChat through callLLM directly with a
    multi-hop tool_result loop capped at 3 hops; preserve Anthropic-provided
    tool_use ids through callLLM so the loop can echo correct tool_use_id.
  • Truncate R42 history to the last 12 turns and prepend a single
    "(earlier conversation truncated)" assistant message.
  • Set R42 chat defaults: temperature 0.3, maxTokens 2048.
  • Add pb_migrations/1780500002_created_llm_calls.js (the best-effort
    logger in callLLM was already wired) and a new Admin → Diagnostics
    view showing the last 100 calls with token usage, cache-hit rate, and
    USD cost from a local Anthropic price table.
  • Finalize AI_PIPELINE_HARDENING_PLAN.md: mark Phases 1–5 shipped and
    Phase 6 (eval harness) explicitly out of scope.

Co-Authored-By: Claude Opus 4.7 (1M context) noreply@anthropic.com

- Add dependency-free TF-IDF retrieval (src/lib/retrieval.js) with NL+EN stopwords and a WeakMap-cached index. - Rewrite buildKbContext to ship the top-K relevant topics + verbatim- mentioned ids only, filter relations to the included set, and append a [kb_hash: <8 hex>] suffix so the ephemeral prompt cache busts when the graph changes. Returns { context, retrievedTopics, allTopics }. - Add LOOKUP_TOPIC_TOOL and drive useChat through callLLM directly with a multi-hop tool_result loop capped at 3 hops; preserve Anthropic-provided tool_use ids through callLLM so the loop can echo correct tool_use_id. - Truncate R42 history to the last 12 turns and prepend a single "(earlier conversation truncated)" assistant message. - Set R42 chat defaults: temperature 0.3, maxTokens 2048. - Add pb_migrations/1780500002_created_llm_calls.js (the best-effort logger in callLLM was already wired) and a new Admin → Diagnostics view showing the last 100 calls with token usage, cache-hit rate, and USD cost from a local Anthropic price table. - Finalize AI_PIPELINE_HARDENING_PLAN.md: mark Phases 1–5 shipped and Phase 6 (eval harness) explicitly out of scope. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
rve added 1 commit 2026-05-20 19:38:25 +00:00
feat: phase 5 of AI pipeline hardening — R42 retrieval & telemetry
All checks were successful
On Pull Request to Main / test (pull_request) Successful in 32s
Details
On Pull Request to Main / publish (pull_request) Successful in 57s
Details
On Pull Request to Main / deploy-dev (pull_request) Successful in 1m34s
Details
229246f7b6 
- Add dependency-free TF-IDF retrieval (src/lib/retrieval.js) with NL+EN
  stopwords and a WeakMap-cached index.
- Rewrite buildKbContext to ship the top-K relevant topics + verbatim-
  mentioned ids only, filter relations to the included set, and append a
  [kb_hash: <8 hex>] suffix so the ephemeral prompt cache busts when the
  graph changes. Returns { context, retrievedTopics, allTopics }.
- Add LOOKUP_TOPIC_TOOL and drive useChat through callLLM directly with a
  multi-hop tool_result loop capped at 3 hops; preserve Anthropic-provided
  tool_use ids through callLLM so the loop can echo correct tool_use_id.
- Truncate R42 history to the last 12 turns and prepend a single
  "(earlier conversation truncated)" assistant message.
- Set R42 chat defaults: temperature 0.3, maxTokens 2048.
- Add pb_migrations/1780500002_created_llm_calls.js (the best-effort
  logger in callLLM was already wired) and a new Admin → Diagnostics
  view showing the last 100 calls with token usage, cache-hit rate, and
  USD cost from a local Anthropic price table.
- Finalize AI_PIPELINE_HARDENING_PLAN.md: mark Phases 1–5 shipped and
  Phase 6 (eval harness) explicitly out of scope.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
rve merged commit a38ad5d1e0 into main 2026-05-20 19:38:34 +00:00
Sign in to join this conversation.
Reviewers
No Reviewers
Labels
No items
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
eho lmi lpr not rdi rve
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: rve/learning-platform#7
Delete Branch "feat/ai-pipeline-hardening-phase-5"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?