ducoterra
b855d0aef9
Phase 45 (owner permission 2026-08-27, TODO.md L8: "allow the LLM
to make as many tool calls as it wants"): the phase-37 per-turn tool
budgets (BOR_AGENT_LIST_CALLS / BOR_AGENT_READ_CALLS, default 1 each)
and their exhaustion refusals are removed — a grounded turn now offers
list_documents / read_document for the whole turn (re-lists included),
bounded only by the round cap:
- app/config.py: agent_max_rounds (BOR_AGENT_MAX_ROUNDS, default 10,
negative rejected) replaces agent_list_calls / agent_read_calls;
.env.example + README document the single knob; app/rag/prompts.py
docstrings follow.
- app/rag/agent.py: the loop runs tools until the model answers or
rounds >= max_rounds, at which point it forces one final no-tools
answer (the cap is the only forced exit); 0 = no tools — exactly one
tools=None request, byte-identical to the pre-phase-37 path (the
kill switch). Rejected calls (unknown tool / missing args /
already-in-context / unknown path) still consume a round, so
pathological rejected-call streams are bounded by the cap. The
per-call log line is now tool/args/round=N/M; the per-turn
tool_calls=N field and the tool SSE event are unchanged.
- tests/e2e/mock_llm.py: MULTI_READ_TRIGGER ("read two documents") —
the deterministic list -> read #1 -> read #2 -> forced-answer flow
(byte-stable "I read <sp1> and <sp2>." line), classified by the
count of tool-role read results; the phase-37 single-read flow stays
byte-identical (unit-pinned in tests/unit/test_mock_tool_flow.py).
- tests/e2e/test_agent_unlimited_tools.py (new, story suite,
mock-only): three tool frames/lines in order (one list, two reads —
the second read is what the old read budget refused) + the
both-named non-deflected answer; done.sources + chips = retrieval
doc + both reads, deduped; no budget refusal rendered; the
single-read marker flow regression (exactly one read, single tool
pair).
- .agent/PLAN.md: the phase-45 SSE revision note (owner-locked, R2) —
the only PLAN edit this phase; the phase-37 note's budget clause is
marked removed.
Unit/integration rewrites (test_agent.py round-cap matrix incl. the
kill switch and rejected-call spam, test_config.py, test_chat_api.py
agent_max_rounds=0 fixtures) landed with the server core so every gate
stays green.
uv run pytest: 756 passed, app/ coverage 99%; ruff + pyright clean;
story E2E 4/4 in isolation (ran twice); regression E2E suites
(agent_document_tools unmodified, chat_rag, smoke) green in isolation.
Also records the 45_agent_unlimited_tools todo/ -> complete/ task-file
moves (00/01/02 pending in the working tree, task 03 moves on success).
80 lines
4.2 KiB
Bash
80 lines
4.2 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_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
|
|
|
|
# --- 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_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; else honest deflection
|
|
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_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
|
|
|
|
# --- Agent document tools (phase 37: grounded turns may list + read) ---
|
|
# BOR_AGENT_MAX_ROUNDS=10 # hard cap on agent tool rounds per turn (0 = no tools)
|
|
|
|
# --- Import scope (A9 formats; may only narrow, never widen) ---
|
|
# BOR_IMPORT_EXTENSIONS=md,markdown,txt,yaml,yml,json,py
|
|
# BOR_SUGGESTIONS=["How is my Kubernetes cluster set up?"] # JSON list of onboarding chips
|
|
|
|
# --- 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
|
|
|
|
# --- 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
|