Understanding how /workflows:compound captures learnings from sub-agent work
Los mantenedores suelen responder en 1 día
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 35/100
- Tipo de issue
- Nueva funcionalidad
- Claridad
- Bastante claro
- Estado de actividad
- Estancado
- Stack tecnológico
- typescript
- Área
- developer-experience
Línea de trabajo
Read the /workflows:compound and sub-agent workflow definitions in the repository to trace what context and artifacts they consume. Then inspect the relevant instructions for how agents report findings; compare them with the questions raised here. Done means documenting how context loss is handled and whether workflow changes or usage guidance are warranted.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Context
I've started using the compound engineering workflow and I'm trying to understand how the compound step works in practice, specifically around sub-agent context and information retention.
What I'm trying to understand
When work happens through sub-agents (via /workflows:work, /lfg, /slfg), each sub-agent has its own context where it may try multiple approaches, hit dead ends, discover codebase quirks, and eventually succeed. The sub-agent then returns a summary to the orchestrator.
By the time /workflows:compound runs at the end, several things may have happened:
- Sub-agents compressed their experience into summaries, potentially dropping the failed attempts and unexpected discoveries that are arguably the most valuable things to compound
- Multiple sub-agent summaries have accumulated in the orchestrator's context, with early ones potentially losing weight as later tasks push them further back
- On longer task lists, compaction may have occurred at least once before the compound step runs, which could mean early sub-agent summaries are gone entirely — not just far back in context, but actually removed
Questions
-
What does
/workflows:compoundactually read from? Does it work from the orchestrator's conversation context, the git diff, the PR, the plan file, or some combination? -
If it relies on the orchestrator's context, how does it handle the case where compaction has already occurred and early task summaries have been lost?
-
Do sub-agents currently have any instructions to report failed approaches and unexpected discoveries, or are they primarily reporting outcomes?
-
Is there a recommended task list size or session structure where the compound step works best? For example, should users be running compound more frequently on long feature branches rather than once at the end?
-
Has the team observed cases where the compound step produced thin or low-value
docs/solutions/entries, and if so, was context loss a contributing factor? -
Would it make sense to compound at the sub-agent level — having each sub-agent capture learnings while its full context is still fresh, right after completing its task? If so, is there a recommended way to achieve this today, or would it require changes to the workflow?
I want to make sure I'm getting full value from the compound step rather than just going through the motions. Any insight into how this actually works under the hood would be really helpful.
- Lenguaje dominante
- TypeScript
- Estrellas
- 25.6k
- Forks
- 2.1k
- Merge medio
- 3 h 57 min
- PR fusionados (30 d)
- 170
Preparar el entorno
Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de EveryInc/compound-engineering-plugin
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
EveryInc/compound-engineering-plugin#2085 ·
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 66/100
EveryInc/compound-engineering-plugin#795 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
Dificultad 3/5 1-2 días Aptitud para principiantes 80/100
EveryInc/compound-engineering-plugin#2084 ·
Los mantenedores suelen responder en 1 día
-
Dificultad 4/5 3-5 días Aptitud para principiantes 48/100
EveryInc/compound-engineering-plugin#2083 ·
Los mantenedores suelen responder en 1 día
-
Host support: DeepSeek Harness (dsh)Posiblemente ocupada Un pull request vinculado a esta issue está abierto o ya se fusionó. Abierto
Dificultad 3/5 1-2 días Aptitud para principiantes 48/100
EveryInc/compound-engineering-plugin#2072 ·
Los mantenedores suelen responder en 1 día
Todos los issues de EveryInc/compound-engineering-plugin
Issues similares
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
Los mantenedores suelen responder en 1 día
-
e2e-failure ready-to-code
Dificultad 1/5 Menos de una hora Aptitud para principiantes 72/100
redhat-developer/rhdh-plugin-export-overlays#4794 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 82/100
Los mantenedores suelen responder en 1 día
-
area: plugins documentation good first issue
Dificultad 2/5 1-3 horas Aptitud para principiantes 83/100
CatVinci-Studio/Textus#727 ·
Los mantenedores suelen responder en 1 día