lkn
/
ollie
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Relocate Trial 1 research ideas to TRIAL_1.md under Future Work

This commit is contained in:
Levi Neely 2026-05-01 12:07:58 +02:00
parent d28ae139b6
commit d75c7a5cf0
2 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
doc/IDEAS.md
View File

@ -96,11 +96,3 @@ The script is the coordinator; agents have no knowledge of each other. Informati
Since agents have access to `execute_code`, a session can write and execute a workflow script without any human involvement. Given a task and knowledge of the filesystem layout, an agent can decompose the work, spawn sessions, write the coordination script, and run it — all in a single turn. The README you are reading is essentially its system prompt. Conductor functionality, for free.
### Next Steps & Research (derived from [TRIAL_1](../experiments/TRIAL_1.md))
- **Status Polling Mechanism**: Implement a mandatory `status` file for all agents that the orchestrator can poll. This would prevent having to tail `chat` files to estimate if an agent is stuck or done.
- **Verification of Premises**: Require agents to perform an "Environment Check" before acting on prompts to prevent fulfillment of hallucinated requirements (e.g., CMake in a Makefile-only project).
- **Administrative Handshake**: Force a "Sync" step at the end of every subagent task where they must receive an ACK from the parent before idling, reducing the "Done State Trap."
- **Purity Reviewers**: Introduce specialized reviewer scripts that look for "extraness" (extra files, unrelated changes, or phantom technical debt) rather than just functional correctness.
- **Post-Turn Environmental Hooks**: Implement hooks for sub-agents that automatically run environmental checks (e.g., build verification or linting) after every turn, ensuring that premises and system state remain valid without manual oversight.
- **Just-in-Time (JIT) Agent Generation**: Ollie could dynamically generate specialized JSON agent configs in `a/`, tailored to the immediate task (e.g., a "Makefile Purity Expert"). These ephemeral agents could be kept if they prove reusable or deleted immediately after the subagent session concludes to prevent configuration rot.

11
experiments/TRIAL_1.md
View File

@ -107,4 +107,13 @@ The following transitions required manual user intervention (the user prompting
- **Information Decay in Parallelism**: In a parallel spawn, context must be perfectly mirrored. Any discrepancy in the roster or instructions between concurrent agents can lead to deadlocks where one agent waits for a signal that another agent doesn't know it was supposed to send.
## Conclusion
The model is effective for multi-stage engineering tasks. However, notification protocols rely on agent autonomy which sometimes fails. Manual inspection of session files remains a critical fallback for the orchestrator. Future trials should experiment with a dedicated "Status File" per session that agents are required to update, allowing the orchestrator to poll health without reading full chat transcripts.
The model is effective for multi-stage engineering tasks. However, notification protocols rely on agent autonomy which sometimes fails. Manual inspection of session files remains a critical fallback for the orchestrator.
## Future Work
- **Status Polling Mechanism**: Implement a mandatory `status` file for all agents that the orchestrator can poll. This would prevent having to tail `chat` files to estimate if an agent is stuck or done.
- **Verification of Premises**: Require agents to perform an "Environment Check" before acting on prompts to prevent fulfillment of hallucinated requirements (e.g., CMake in a Makefile-only project).
- **Administrative Handshake**: Force a "Sync" step at the end of every subagent task where they must receive an ACK from the parent before idling, reducing the "Done State Trap."
- **Purity Reviewers**: Introduce specialized reviewer scripts that look for "extraness" (extra files, unrelated changes, or phantom technical debt) rather than just functional correctness.
- **Post-Turn Environmental Hooks**: Implement hooks for sub-agents that automatically run environmental checks (e.g., build verification or linting) after every turn, ensuring that premises and system state remain valid without manual oversight.
- **Just-in-Time (JIT) Agent Generation**: Ollie could dynamically generate specialized JSON agent configs in `a/`, tailored to the immediate task (e.g., a "Makefile Purity Expert"). These ephemeral agents could be kept if they prove reusable or deleted immediately after the subagent session concludes to prevent configuration rot.