You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Control flow: conditional edges, branches, loops/cycles & parallel execution #278
Real orchestration needs routing. Add conditional edges (router nodes), parallel branches that fan out and join, and bounded loops/cycles — the LangGraph control-flow surface.
Scope
Conditional/router edges that pick the next node from state
Parallel branches with fan-out + join (barrier) semantics
Loops/cycles with a max-iteration / termination guard
Cycle detection and clear errors for malformed graphs
Acceptance criteria
A graph can branch on a predicate, run two branches in parallel, and join
A loop terminates on condition and respects the iteration cap
Tests cover branch, parallel-join and loop-with-exit
I would like to work on this! I have an implementation ready that covers the complete control-flow specification:
Conditional / router edges with safe AST expression evaluation and callable predicates
Parallel branch fan-out and join (barrier synchronization) with isolated state copies and reducer merging
Bounded loops / cycles with termination guards and configurable iteration limits
Cycle detection that distinguishes between valid guarded loops and malformed infinite cycles
Since #278 builds directly on the graph/state runtime core (#277), I've implemented both in a clean dynavec.agents module with zero regressions to the existing ReActAgent/Planner primitives, accompanied by a comprehensive offline test suite.
Could you please assign this to me? Let me know if you would like this submitted as a combined dynaflow engine PR (#277 + #278) or split into two sequential PRs.
Activity
Ashishds commentedon Oct 7, 2026
Hi @codeforstartups / @abhishekkrthakur,
I would like to work on this! I have an implementation ready that covers the complete control-flow specification:
Since #278 builds directly on the graph/state runtime core (#277), I've implemented both in a clean
dynavec.agentsmodule with zero regressions to the existing ReActAgent/Planner primitives, accompanied by a comprehensive offline test suite.Could you please assign this to me? Let me know if you would like this submitted as a combined dynaflow engine PR (#277 + #278) or split into two sequential PRs.
feat(agents): add dynaflow graph orchestration engine and control flow (
feat(agents): add dynaflow graph orchestration engine and control flow (
Kaap10 commentedon Oct 13, 2026
Resolved by #344.