Grounded chat turns now run the agent loop (app/rag/agent.py) instead
of a bare chat_stream: while the per-turn budgets last
(BOR_AGENT_LIST_CALLS / BOR_AGENT_READ_CALLS, default 1 each) the model
gets list_documents (the indexed catalog, /api/docs order) and
read_document (full text, never truncated — A7-revised contract); once
both budgets are spent the tools key is dropped from the request and
the model must answer. Rejected calls (unknown tool, unknown/missing
path, document already in context, spent budget) consume no budget.
Budgets 0/0 make exactly one tools=None request — byte-identical to
the pre-phase path (budgets-as-kill-switch). Deflected turns keep the
direct chat_stream (A8 unchanged; the LOW prompt never carries the
<tools> section).
SSE contract gains {"type":"tool","name":...,"argument":
"source/path"|null} frames ahead of the answer deltas (PLAN §4
extension, owner permission 2026-08-26); done.sources, query_log.sources
and the per-turn log line (gains tool_calls=N) report the retrieval
docs + read docs, deduped. The UI shows a "calling tool"
button/label state and one visible .tool-call line per call above the
answer; the lines persist with the chat record and re-render on
reload. chat_stream passes tools through and accumulates streaming
tool_calls deltas into ToolCallPiece (tools=None stays byte-identical).
E2E: deterministic mock tool flow ("use your tools" + <tools> marker:
list -> read first catalog line -> quoted answer) plus the story suite
(marker flow, reload re-render, plain/deflected no-tool regressions).
Docs: .env.example + README (the two tools, the budgets, the SSE tool
frame, the "calling tool" UI state).
probe: turbo tool_calls=supported 2026-08-26 (uv run python -m
scripts.llm_probe --tools — non-streaming + streaming
finish_reason=tool_calls, indexed delta.tool_calls partials)
Phase 33 (story: .agent/user_stories/cache-busting.md).
- app/core/caching.py: asset_version() — git short SHA (a commit is a
deploy), stable content-hash fallback for non-git checkouts, "dev"
for a missing static dir; computed once per process. CachingMiddleware
— the five HTML pages revalidate (no-cache) with ?v=<token> asset refs
rewritten in flight; /assets/* is public, max-age=31536000, immutable;
everything else (all /api/*, the SSE chat stream in particular) passes
through byte-identical.
- tests/e2e/test_cache_busting.py: fresh-Chromium wire assertions —
document no-cache, versioned CSS/JS request URLs sharing one token,
immutable asset headers, /api/health baseline headers, SSE chat to
done (mock LLM).
- README 'Caching / deploys' section + story file.
Also fixed two prod-image defects surfaced by this phase's podman smoke
(the full app would not boot):
- Containerfile: ship the scripts/ package — app/api/sync.py (phase 32)
imports scripts.git_sync / scripts.import_docs at module level, so the
container crashed on boot (ModuleNotFoundError: No module named
'scripts').
- compose.yaml: pass BOR_ADMIN_PASSWORD / BOR_SESSION_SECRET through to
the app service (:- defaults keep 'podman compose up -d db' working;
the app's own fail-loud gate still names missing admin auth).
Smoke: podman compose --profile prod up -d on a fresh image + a fresh
Chromium profile — /, /sources.html and /login.html all served
Cache-Control: no-cache; all 8 asset requests versioned with one shared
token (content-hash fallback inside the image — no .git there);
/assets/* immutable for a year.
ducoterra