aboutsummaryrefslogtreecommitdiffstats
path: root/pkg/aflow/flow_test.go
Commit message (Collapse)AuthorAgeFilesLines
* pkg/aflow: ask LLM to call several tools at the same timeDmitry Vyukov2026-01-201-3/+3
| | | | This seems to help a bit with number of round-trips.
* pkg/aflow: handle common LLM mis-behaviors wrt tool callingDmitry Vyukov2026-01-201-1/+237
| | | | | | | | | | | | | Gracefully handle (reply to LLM with error): - incorrect tool name - incorrect tool arg type - missing tool arg Silently handle: - more than one call to set-results - excessive tool args Fixes #6604
* pkg/aflow: handle model quota errorsDmitry Vyukov2026-01-201-0/+22
| | | | | | | | Detect model quota violations (assumed to be RPD). Make syz-agent not request jobs that use the model until the next quota reset time. Fixes #6573
* pkg/aflow: make LLM model per-agent rather than per-flowDmitry Vyukov2026-01-201-7/+35
| | | | | | Having LLM model per-agent is even more flexible than per-flow. We can have some more complex tasks during patch generation with the most elaborate model, but also some simpler ones with less elaborate models.
* pkg/aflow: add ability to generate several candidate replies for LLM agentsDmitry Vyukov2026-01-191-57/+393
| | | | | | | | | Add LLMAgent.Candidates parameter. If set to a value N>1, then the agent is invoked N times, and all outputs become slices. The results can be later aggregated by another agent, as shown in the test.
* pkg/aflow: allow to specify model per-flowDmitry Vyukov2026-01-141-1/+3
| | | | | We may want to use a weaker model for some workflows. Allow to use different models for different workflows.
* pkg/aflow: add package for agentic workflowsDmitry Vyukov2026-01-091-0/+554
generated by ggit (джигит) mrf-deployment (git 2.46.0) at 2026-03-11 21:28:00 +0000