The date hint sat at the end of each analyst's system prompt, after a long
indicator block, so weaker models anchored to their training cutoff when
generating tool-call date ranges. Lead each prompt with it instead.
Clear the deferred full-repo lint backlog so the whole tree passes the strict
ruff select (E,W,F,I,B,UP,C4,SIM). Mechanical fixes dominate: import sorting,
pep585/604 annotations, dropped dead imports, and whitespace. The few semantic
changes are behavior-preserving: declare __all__ on the agent_utils and
alpha_vantage re-export hubs; expand 'from x import *' to explicit names; use
immutable tuple defaults instead of mutable list defaults; contextlib.suppress
for try/except/pass; and narrow an over-broad assertRaises.
The market analyst could confabulate exact figures — citing a Bollinger
band or a "historically validated bounce" the data doesn't support (#830).
Add a deterministic get_verified_market_snapshot tool (latest OHLCV row,
common indicators, recent closes) the analyst must consult and treat as
the source of truth for any exact price/indicator claim, and instruct it
not to assert historical validation or support bounces without tool-backed
dates and prices.
#830
Agents had no ground-truth ticker→company mapping, so the market analyst
could pattern-match a price chart to the wrong company (e.g. TOTDY read as
"TotalEnergies"), and every downstream agent inherited the bad framing.
Resolve identity once at run start via a cached, fail-open yfinance lookup
and inject company/sector/exchange into the shared instrument context that
all twelve agents consume, with an explicit do-not-substitute instruction.
Resolution runs on both the propagate() and CLI entry points.
Also replaces the bare "Continue" message-clear placeholder, which some
OpenAI-compatible providers interpreted as the user task, with a
context-anchored placeholder carrying the resolved identity and date.
#814#888
Yijia-Xiao