ducoterra
1374faf136
**Phase 112 — final verification pass (all 4 tasks already complete in `complete/`):** - Verified gate fix: `app/api/chat.py::plan_turn` — HIGH iff `best_cosine >= relevance_threshold` OR (`fts_hits > 0` AND `best_cosine >= lexical_support_floor`); `lexical_support_floor` (default 0.35, `BOR_LEXICAL_SUPPORT_FLOOR`, bounds-validated) in `app/config.py` + `.env.example`; A8 revision note (2026-09-14) in `.agents/PLAN.md`. - Verified prompt contract: `app/rag/prompts.py` diff is docstring-only (dated owner-decision-iii entry); `tests/unit/test_prompt_lock.py` byte-pins PERSONA/TOOLS_SECTION/DEFLECT body (sha256+length). - Verified README: L11 + L575 deflection copy refreshed; `grep "haven't done anything" README.md` → no hits; disclosed-answer behavior documented. - Tests: `uv run pytest --cov=app --cov-report=term-missing` → **2378 passed, 99% coverage (>90%)**; includes Mongolia-quadrant unit pins (fts>0 + cosine<floor → LOW). - E2E in isolation: `uv run pytest tests/e2e/test_honest_deflection.py -v --no-cov` → **4 passed** (out-of-KB question: `deflected=true`, `sources==[]`, 2–3 suggestions); regression `test_chat_rag.py` + `test_retrieval_quality.py` → **7 passed**. - Lint/types: `uv run ruff check .` → clean; `uv run pyright` → 0 errors. **Completion criteria:** weak-FTS→LOW unit-pinned ✅ · no false citations + 2–3 alternatives E2E ✅ · prompts byte-identical (test-pinned) + README matches ✅ · suite/coverage/e2e/lint all green ✅ · commit + phase move → left to harness (no `git commit` run, per rules; changes in working tree). **Deviations:** none. Next pending phase: `113_source_chip_quality`.
126 lines
7.7 KiB
Bash
126 lines
7.7 KiB
Bash
# Brain of Reese — environment configuration
|
|
# Copy to `.env` and adjust: cp .env.example .env
|
|
# (`.env` is gitignored; never commit secrets.)
|
|
|
|
# --- App ---
|
|
BOR_ENVIRONMENT=development
|
|
# BOR_APP_NAME=Brain of Reese # display name on all pages — titles, header brand, status labels, aria text (phase 39)
|
|
# BOR_INPUT_PLACEHOLDER=Ask me anything… # composer placeholder, chat page (phase 62)
|
|
# BOR_FOOTER_TEXT=Powered by self-hosted models # footer line on every page (phase 62)
|
|
# (Phase 91: the retired CSS-file theme env var is gone — the colors
|
|
# are set from the admin Theme tab, /theme.html; a leftover value in
|
|
# a local .env is ignored.)
|
|
# BOR_LOG_LEVEL=INFO
|
|
# BOR_STATIC_DIR=frontend # dev default; container sets /app/static
|
|
|
|
# --- Database (matches `podman compose` db service) ---
|
|
BOR_DATABASE_URL=postgresql+psycopg://reese:reese@localhost:5432/brain_of_reese
|
|
# BOR_DB_POOL_SIZE=5 # connection pool size (SEC-14-04, default 5)
|
|
# BOR_DB_POOL_MAX_OVERFLOW=10 # max overflow connections (SEC-14-04, default 10)
|
|
# BOR_DB_POOL_RECYCLE=3600 # recycle connections after N seconds (SEC-14-04, default 3600)
|
|
# BOR_CHAT_MAX_CONCURRENT=10 # max concurrent /api/chat turns (SEC-14-04, default 10)
|
|
|
|
# --- LLM (self-hosted, OpenAI-compatible "aipi") ---
|
|
BOR_LLM_BASE_URL=https://aipi.reeseapps.com/v1
|
|
BOR_LLM_API_KEY= # falls back to $AIPI_KEY, then "not-needed"
|
|
BOR_LLM_CHAT_MODEL=turbo
|
|
# BOR_LLM_RETRIES=3 # LLM retries: chat-turn stream before the first token (phase 67) + empty one-shot summary replies (phase 96); 0 = off
|
|
# BOR_LLM_TIMEOUT=300 # HTTP timeout for LLM API calls, seconds (default 120)
|
|
# BOR_LLM_RETRY_DELAY=5 # seconds between LLM retries (phase 67 chat-turn stream; phase 96 one-shot summary calls)
|
|
BOR_LLM_EMBED_MODEL=embed
|
|
BOR_LLM_SUMMARY_MODEL=lite # one-shot completions: document summaries (phase 30), KB overview (phase 31)
|
|
BOR_EMBEDDING_DIM=768 # verified 2026-08 via scripts/llm_probe.py
|
|
BOR_STREAM_THINKING=1 # stream the model's thinking as `thinking` SSE events (0 to suppress)
|
|
|
|
# --- RAG tuning ---
|
|
BOR_TOP_N_DOCS=2
|
|
BOR_RELEVANCE_THRESHOLD=0.62 # answer when best cosine >= this OR an FTS hit corroborated by cosine >= lexical_support_floor; else honest deflection
|
|
# BOR_LEXICAL_SUPPORT_FLOOR=0.35 # cosine floor for FTS hits to flip HIGH (A8 revised 2026-09-14); 0 <= floor <= relevance_threshold
|
|
BOR_MAX_OUTPUT_TOKENS=32768 # max answer length in tokens (answers must not be cut off)
|
|
BOR_STEERING_MAX_CHARS=8000 # char budget for the <tuning> (steering notes) prompt section
|
|
BOR_SUMMARY_MAX_CHARS=12000 # cap on document content sent to the lite summary model (phase 30)
|
|
BOR_KB_OVERVIEW_MAX_CHARS=4000 # char budget for the <knowledge_base> prompt section (phase 31)
|
|
BOR_OVERVIEW_INPUT_MAX_CHARS=40000 # cap on the document list sent to the lite model for the KB outline (phase 31)
|
|
BOR_FOLDER_SUMMARY_INPUT_MAX_CHARS=8000 # cap on a folder's document list sent to the lite model (phase 94)
|
|
BOR_CHUNK_TARGET_CHARS=2000
|
|
BOR_CHUNK_OVERLAP_CHARS=200
|
|
BOR_EMBED_BATCH_SIZE=16
|
|
|
|
# --- Hybrid retrieval (vector + Postgres FTS, RRF-fused) ---
|
|
BOR_HYBRID_VECTOR_CANDIDATES=100 # cosine list width for the fusion
|
|
BOR_HYBRID_LEXICAL_CANDIDATES=30 # FTS list width for the fusion
|
|
BOR_RRF_K=60 # Reciprocal Rank Fusion damping constant
|
|
BOR_RECENCY_BOOST=0.0007 # max additive fused-score bonus a zero-age doc gets (phase 106); 0 = off (pre-phase ranking byte-identical)
|
|
BOR_RECENCY_HALF_LIFE_DAYS=365 # recency decay timescale, days (phase 106); the boost decays by e^-1 (~0.37x) per timescale of age
|
|
|
|
# --- Agent document tools (grounded turns may extend context: ls / read / grep) ---
|
|
# BOR_AGENT_MAX_ROUNDS=10 # hard cap on agent tool rounds per turn (0 = no tools)
|
|
# BOR_READ_MAX_CHARS=128000 # cap on a `read` result (chars); over-cap reads truncate + a grep-pointer notice (phase 95)
|
|
|
|
# --- Import scope (A9 default; ANY well-formed extension is allowed) ---
|
|
# Comma-separated file extensions (lowercase, no dot) the importer reads.
|
|
# Any extension is allowed — the value below is the built-in default (the
|
|
# A9 family: the original seven + the quadlet family + jinja ``j2``); add
|
|
# your own (e.g. md,sh,toml,dockerfile,containerfile) or narrow it
|
|
# (e.g. md). A token also matches extensionless files whose lowercased
|
|
# full filename equals it exactly (dockerfile → Dockerfile — case-
|
|
# insensitive, no partial names — phase 102). A blank list or a
|
|
# malformed token (e.g. md,sh!) fails startup loudly, naming the value.
|
|
BOR_IMPORT_EXTENSIONS=md,markdown,txt,yaml,yml,json,py,container,network,volume,image,pod,kube,swap,os,endpoint,j2
|
|
# BOR_SUGGESTIONS=["How is my Kubernetes cluster set up?"] # JSON seed chips — shown only before any question has been saved (phase 80); after that the chips are the 3 newest chats' opening questions (phase 103)
|
|
|
|
# --- Import sources (git; phase 28, admin-managed since phase 35) ---
|
|
# Comma-separated git repo URLs; import_docs clones each (first run) or
|
|
# pulls it (subsequent runs) into BOR_SOURCES_DIR/<repo-name>/ and indexes
|
|
# the result. Auth via URL (e.g. an https token) or SSH keys.
|
|
#
|
|
# Phase 35 (owner permission 2026-08-26): the PRIMARY way to manage the
|
|
# list is the admin Git sources page (http://localhost:8000/git-sources.html)
|
|
# — rows stored in Postgres (git_sources table, migration 0006). This
|
|
# variable is the EMPTY-TABLE FALLBACK: it only applies while the admin
|
|
# list is empty; once the page has stored any source, this variable is
|
|
# ignored (the page is the source of truth). Empty table + empty variable
|
|
# + no local rows = no sources (import_docs falls back to --source / the
|
|
# old ~/Homelab + ~/Deployments defaults; the UI Sync button fails loudly
|
|
# with "no sources configured (git or local)").
|
|
#
|
|
# Phase 38: this env fallback is GIT-ONLY. Local directory sources (an
|
|
# existing, non-git directory on the server) have NO env var — the DB is
|
|
# the local-source registry: add them on the same admin page (the
|
|
# "Add a local directory" form, kind 'local' + path, migration 0007).
|
|
# BOR_GIT_SOURCES=https://github.com/user/homelab.git,https://github.com/user/deployments.git
|
|
# BOR_SOURCES_DIR=~/bor-sources
|
|
|
|
# Phase 49: uploaded source archives (the Sources page upload form).
|
|
# An uploaded .tar / .tar.gz / .tgz / .zip is unpacked to
|
|
# BOR_UPLOAD_DIR/<name>/ where <name> is the filename minus the archive
|
|
# suffix (homelab.tar.gz -> homelab/). Re-uploading the same name
|
|
# replaces the folder's content IN PLACE — one folder, one row, no
|
|
# missing window; a failed upload never touches the existing folder,
|
|
# row, or KB. Deliberately separate from BOR_SOURCES_DIR (git checkouts).
|
|
# BOR_UPLOAD_DIR=~/bor-sources/uploads
|
|
# BOR_UPLOAD_MAX_MB=512 # caps BOTH the compressed upload and the total
|
|
# extracted bytes (zip-bomb guard); must be > 0
|
|
|
|
# --- Docs push (phase 59: save a chat answer as documentation) ---
|
|
# The git repo chat answers can be committed to — any remote (URL or
|
|
# local path). While empty, the "Save as doc" action is hidden and the
|
|
# push endpoint 409s. Commits land on BOR_DOCS_BRANCH (push --ff-only);
|
|
# open the PR yourself.
|
|
# BOR_DOCS_REPO=/path/to/docs-repo
|
|
# BOR_DOCS_BRANCH=bor-docs
|
|
# BOR_DOCS_BASE_BRANCH=main
|
|
# BOR_DOCS_WORK_DIR=~/bor-docs
|
|
|
|
# --- Admin & sign-in (single-admin password login; BOTH required) ---
|
|
# The app refuses to start while either is empty (names the missing
|
|
# variable(s) — README "Admin & sign-in"). Generate the secret with:
|
|
# python -c 'import secrets;print(secrets.token_hex(32))'
|
|
BOR_ADMIN_PASSWORD=
|
|
BOR_SESSION_SECRET=
|
|
# BOR_SESSION_MAX_AGE=43200 # signed-cookie lifetime, seconds (default 12 h, sliding)
|
|
|
|
# --- Debugging (0/1 — 1 enables attach-on-demand debugpy on port 5678) ---
|
|
DEBUGPY=0
|
|
# DEBUGPY_PORT=5678
|