revert(orchestration): remove HandoffContext and validation layer (#2076, #2078)#2082
Merged
revert(orchestration): remove HandoffContext and validation layer (#2076, #2078)#2082
Conversation
, #2078) The typed HandoffContext enum, RoleContext variants, and validation layer introduced in #2076 and #2078 are superseded by the rust-agent-handoff skill. Agents follow the handoff protocol via skill instructions injected into their system prompt — no compile-time struct enforcement is needed. Reverts: - handoff.rs (deleted) - typed HandoffConfig in zeph-config - handoff fields in TaskResult/TaskNode - handoff validation metrics in OrchestrationMetrics - scheduler.rs validation/verification wiring Closes #2023
github-actions
bot
added
rust
bug-ops
added a commit
that referenced
this pull request
Mar 21, 2026
Cover 14 new features across specs, mdbook, READMEs, and references: - Memory: SYNAPSE spreading activation, MAGMA typed edges, semantic response caching, anchored summarization, compaction probe, importance scoring - Tools: TAFC, schema filtering, result cache, dependency graph - Context: HiAgent subgoal-aware compaction - Orchestration: plan template caching - Self-learning: multi-language FeedbackDetector - Channels: feature parity across all 7 channels Rewrite why-zeph.md to reflect full value proposition. Add 7 new research references (SYNAPSE, MemOS, HiAgent, TAFC, APC, Less is More, Speculative Tool Calls, MAST). Rewrite handoff-skill-system spec to reflect current state after HandoffContext revert (#2082). Remove all stale HandoffContext references from documentation.
4 tasks
bug-ops
added a commit
that referenced
this pull request
Mar 21, 2026
Cover 14 new features across specs, mdbook, READMEs, and references: - Memory: SYNAPSE spreading activation, MAGMA typed edges, semantic response caching, anchored summarization, compaction probe, importance scoring - Tools: TAFC, schema filtering, result cache, dependency graph - Context: HiAgent subgoal-aware compaction - Orchestration: plan template caching - Self-learning: multi-language FeedbackDetector - Channels: feature parity across all 7 channels Rewrite why-zeph.md to reflect full value proposition. Add 7 new research references (SYNAPSE, MemOS, HiAgent, TAFC, APC, Less is More, Speculative Tool Calls, MAST). Rewrite handoff-skill-system spec to reflect current state after HandoffContext revert (#2082). Remove all stale HandoffContext references from documentation.
bug-ops
added a commit
that referenced
this pull request
Mar 21, 2026
….0 (#2085) Cover 14 new features across specs, mdbook, READMEs, and references: - Memory: SYNAPSE spreading activation, MAGMA typed edges, semantic response caching, anchored summarization, compaction probe, importance scoring - Tools: TAFC, schema filtering, result cache, dependency graph - Context: HiAgent subgoal-aware compaction - Orchestration: plan template caching - Self-learning: multi-language FeedbackDetector - Channels: feature parity across all 7 channels Rewrite why-zeph.md to reflect full value proposition. Add 7 new research references (SYNAPSE, MemOS, HiAgent, TAFC, APC, Less is More, Speculative Tool Calls, MAST). Rewrite handoff-skill-system spec to reflect current state after HandoffContext revert (#2082). Remove all stale HandoffContext references from documentation.
bug-ops
added a commit
that referenced
this pull request
Mar 21, 2026
* docs: comprehensive documentation update for all features since v0.16.0 Cover 14 new features across specs, mdbook, READMEs, and references: - Memory: SYNAPSE spreading activation, MAGMA typed edges, semantic response caching, anchored summarization, compaction probe, importance scoring - Tools: TAFC, schema filtering, result cache, dependency graph - Context: HiAgent subgoal-aware compaction - Orchestration: plan template caching - Self-learning: multi-language FeedbackDetector - Channels: feature parity across all 7 channels Rewrite why-zeph.md to reflect full value proposition. Add 7 new research references (SYNAPSE, MemOS, HiAgent, TAFC, APC, Less is More, Speculative Tool Calls, MAST). Rewrite handoff-skill-system spec to reflect current state after HandoffContext revert (#2082). Remove all stale HandoffContext references from documentation. * release: prepare v0.16.1
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
HandoffContext,RoleContextenum, and validation layer added in feat(orchestration): MAST-informed handoff hardening — Phase 1 (issue #2023) #2076 and feat(orchestration): implement Phase 2 handoff validation layer (issue #2023) #2078crates/zeph-orchestration/src/handoff.rs(1700+ lines)HandoffConfigfromzeph-configTaskResult/TaskNodeOrchestrationMetricsDagSchedulerReason
The
rust-agent-handoffskill (.zeph/skills/rust-agent-handoff/) is injected into every agent's system prompt and already solves the coordination problem. Agents follow the structured YAML handoff protocol via skill instructions — compile-time struct enforcement and runtime validation add complexity without meaningful benefit.Closes #2023
Test plan
cargo buildpasses