Alex 9df90ab9df Bind the log context for tool continuations ...

gen_continuation is not wrapped by @log_activity, so the llm_* log lines
from a resumed turn carried no user, agent, conversation or endpoint. Every
OpenAI-compatible /v1 client-tool round landed anonymous in the logs.

Add agent_log_context, which binds the same keys log_activity binds while
keeping any enclosing activity_id, and wrap gen_continuation in it. Both
now derive the keys from one helper.

2026-09-24 13:26:49 +01:00

..

tools

fix(agents): hand the graph tool's connection back, and gate it like the rest

2026-09-20 10:45:04 +01:00

workflows

Trace unexecuted tool calls in one place; tidy span lifecycles

2026-09-23 22:42:05 +01:00

__init__.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

agent_creator.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

agentic_agent.py

feat(agents): let agents walk a source's graph when they can search it

2026-09-19 14:07:41 +01:00

base.py

Bind the log context for tool continuations

2026-09-24 13:26:49 +01:00

classic_agent.py

feat(agents): let agents walk a source's graph when they can search it

2026-09-19 14:07:41 +01:00

default_tools.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

headless_runner.py

Give a scheduled run's trace to the user who scheduled it

2026-09-23 22:09:58 +01:00

research_agent.py

Trace unexecuted tool calls in one place; tidy span lifecycles

2026-09-23 22:42:05 +01:00

scheduler_utils.py

refactor: rename the application package to docsgpt

2026-09-07 10:20:43 +01:00

tool_executor.py

Trace unexecuted tool calls in one place; tidy span lifecycles

2026-09-23 22:42:05 +01:00

workflow_agent.py

refactor: read settings directly instead of getattr with a second default

2026-09-17 11:14:34 +01:00