mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-08-04 14:57:42 +00:00
a07c0e4ae8
Grades fast-model activity-label headers against a fixed corpus so instruction changes are measured rather than eyeballed on one conversation. This existed untracked while the continuity work was developed; committing it because it is the only reproducible record of WHY `ACTIVITY_INSTRUCTION` is ordered and capped the way it is. - captured.json: 9 real production payloads pulled verbatim from Langfuse with the headers that shipped. Irreplaceable — traces age out. - corpus.js: 17 cases / 28 steps. The captured run replays as one sequence, plus synthetic cases for the modes it never exercised (all-failed, partial, parallel batches, rapid near-duplicates, entry overflow, truncated output, error-shaped success). Multi-step cases chain each generated label into the next step's context, which is what makes cross-batch redundancy measurable at all. - prompt.js: faithful port of the SDK's buildActivityLabelPrompt so synthetic cases render the bytes production sends, plus a previousLabelCap knob for continuity-window experiments. - variants.js: single-factor instruction variants. The baseline is read from the BUILT package (workspace resolution, then dist, then LABEL_EVAL_DIST) so a variant can never be graded against a stale copy of the shipped instruction. - checks.js: length/punctuation/markdown/tool-echo/count-echo, plus overlap split into `restate` (adds nothing over an earlier header) vs `template` (same frame, new payload — often fine). - run.js / rescore.js: live runner on the production wire shape (max_tokens 256) and an offline re-grader, so metric fixes never require re-spending on the API. Results are gitignored — regenerable, and 292K of the 364K. A full sweep is ~$0.03 per variant and ~45s. Findings are recorded in the README, two of them counter-intuitive: enumerating acceptable opening verbs ANCHORED the model rather than diversifying it (Confirmed 18→23, opener diversity halved), and diverse examples alone changed nothing. Sentence order is load-bearing, so a tidying reshuffle of ACTIVITY_INSTRUCTION regresses real output.
186 lines
2.8 KiB
Text
186 lines
2.8 KiB
Text
### node etc ###
|
|
|
|
# Logs
|
|
data-node
|
|
meili_data*
|
|
data/
|
|
logs
|
|
*.log
|
|
|
|
# Runtime data
|
|
pids
|
|
*.pid
|
|
*.seed
|
|
.git
|
|
|
|
# CI/CD data
|
|
test-image*
|
|
dump.rdb
|
|
|
|
# Directory for instrumented libs generated by jscoverage/JSCover
|
|
lib-cov
|
|
|
|
# Coverage directory used by tools like istanbul
|
|
coverage
|
|
|
|
# Grunt intermediate storage (http://gruntjs.com/creating-plugins#storing-task-files)
|
|
.grunt
|
|
|
|
# translation services
|
|
config/translations/stores/*
|
|
client/src/localization/languages/*_missing_keys.json
|
|
|
|
# Turborepo
|
|
.turbo
|
|
|
|
# Compiled Dirs (http://nodejs.org/api/addons.html)
|
|
build/
|
|
dist/
|
|
public/main.js
|
|
public/main.js.map
|
|
public/main.js.LICENSE.txt
|
|
client/public/images/
|
|
client/public/main.js
|
|
client/public/main.js.map
|
|
client/public/main.js.LICENSE.txt
|
|
|
|
# Azure Blob Storage Emulator (Azurite)
|
|
__azurite**
|
|
__blobstorage__/**/*
|
|
|
|
# Dependency directorys
|
|
# Deployed apps should consider commenting these lines out:
|
|
# see https://npmjs.org/doc/faq.html#Should-I-check-my-node_modules-folder-into-git
|
|
node_modules/
|
|
.node_modules-*
|
|
meili_data/
|
|
api/node_modules/
|
|
client/node_modules/
|
|
bower_components/
|
|
*.d.ts
|
|
!vite-env.d.ts
|
|
|
|
# AI
|
|
.clineignore
|
|
.cursor
|
|
.aider*
|
|
.bg-shell/
|
|
|
|
# Floobits
|
|
.floo
|
|
.floobit
|
|
.floo
|
|
.flooignore
|
|
|
|
#config file
|
|
librechat.yaml
|
|
librechat.yml
|
|
|
|
# Environment
|
|
.npmrc
|
|
.env*
|
|
my.secrets
|
|
!**/.env.example
|
|
!**/.env.test.example
|
|
cache.json
|
|
api/data/
|
|
owner.yml
|
|
archive
|
|
.vscode/settings.json
|
|
src/style - official.css
|
|
/e2e/specs/.test-results/
|
|
/e2e/benchmarks/.test-results/
|
|
/e2e/.generated/
|
|
/e2e/playwright-report/
|
|
/playwright/.cache/
|
|
.DS_Store
|
|
*.code-workspace
|
|
.idx
|
|
monospace.json
|
|
.idea
|
|
*.iml
|
|
*.pem
|
|
config.local.ts
|
|
**/storageState.json
|
|
junit.xml
|
|
**/.venv/
|
|
**/venv/
|
|
|
|
# docker override file
|
|
docker-compose.override.yaml
|
|
docker-compose.override.yml
|
|
|
|
# meilisearch
|
|
meilisearch
|
|
meilisearch.exe
|
|
data.ms/*
|
|
auth.json
|
|
|
|
/packages/ux-shared/
|
|
/images
|
|
|
|
!client/src/components/Nav/SettingsTabs/Data/
|
|
|
|
# User uploads
|
|
uploads/
|
|
|
|
# owner
|
|
release/
|
|
|
|
# Helm
|
|
helm/librechat/Chart.lock
|
|
helm/**/charts/
|
|
helm/**/.values.yaml
|
|
|
|
!/client/src/@types/i18next.d.ts
|
|
!/client/src/@types/react.d.ts
|
|
|
|
# SAML Idp cert
|
|
*.cert
|
|
|
|
# AI Assistants
|
|
/.claude/
|
|
/.codex/
|
|
/.cursor/
|
|
/.copilot/
|
|
/.aider/
|
|
/.openai/
|
|
/.tabnine/
|
|
/.codeium
|
|
/.pi/
|
|
*.local.md
|
|
|
|
# Removed Windows wrapper files per user request
|
|
hive-mind-prompt-*.txt
|
|
|
|
# Claude Flow generated files
|
|
.claude/settings.local.json
|
|
.mcp.json
|
|
claude-flow.config.json
|
|
.swarm/
|
|
.hive-mind/
|
|
.claude-flow/
|
|
/memory/
|
|
/coordination/
|
|
/memory/claude-flow-data.json
|
|
/memory/sessions/*
|
|
!/memory/sessions/README.md
|
|
/memory/agents/*
|
|
!/memory/agents/README.md
|
|
/coordination/memory_bank/*
|
|
/coordination/subtasks/*
|
|
/coordination/orchestration/*
|
|
*.db
|
|
*.db-journal
|
|
*.db-wal
|
|
*.sqlite
|
|
*.sqlite-journal
|
|
*.sqlite-wal
|
|
claude-flow
|
|
.playwright-mcp/*
|
|
# Removed Windows wrapper files per user request
|
|
hive-mind-prompt-*.txt
|
|
CLAUDE.md
|
|
.gsd
|
|
codedb.snapshot
|
|
scripts/activity-labels/results/
|