Record context pressure signal requirement
This commit is contained in:
parent
aab3ae3334
commit
cc7fda08da
5 changed files with 11 additions and 3 deletions
|
|
@ -201,12 +201,17 @@ Current operating rule:
|
|||
|
||||
Future runtime behavior should:
|
||||
|
||||
- detect context pressure before the hard limit
|
||||
- expose context pressure as a real runtime signal before the hard limit
|
||||
- checkpoint at safe points when possible
|
||||
- preserve role-specific resume packets
|
||||
- distinguish what survived from what was discarded
|
||||
- make compaction visible instead of pretending continuity is magic
|
||||
|
||||
Until that signal exists, agents can only infer pressure from indirect cues:
|
||||
long transcripts, compaction warnings, quota pressure, and a shrinking safe
|
||||
landing zone. That is a scar, not a sensor. Automatic CRRC needs typed
|
||||
pressure/freshness telemetry instead of vibes with a clipboard.
|
||||
|
||||
Compaction should squeeze scratch, not the map.
|
||||
|
||||
## Persistent State Hygiene
|
||||
|
|
|
|||
|
|
@ -113,6 +113,7 @@ The next unknowns are:
|
|||
|
||||
- how to expose live long-running job progress without making the GUI authoritative
|
||||
- when watcher-driven invalidation becomes necessary instead of merely tempting
|
||||
- how to expose context pressure as a real runtime signal for automatic CRRC
|
||||
- how much automatic CRRC coordination belongs in runtime before it becomes ceremony machinery
|
||||
- what Phase 6 should prove before specialist scheduling begins
|
||||
|
||||
|
|
@ -139,7 +140,7 @@ These remain later work:
|
|||
- richer evidence and graph-shard inspection beyond the landed targeted context read
|
||||
- role-scoped specialist-agent registry and scheduling
|
||||
- mutation gates that warn or block broad writes when map freshness is stale
|
||||
- automatic CRRC runtime coordination
|
||||
- automatic CRRC runtime coordination with typed context-pressure telemetry
|
||||
- GUI workflows for graph, evidence, job, invariant, and frontier steering
|
||||
|
||||
Do not start these from vibes. Each one needs a source-grounded slice plan and a
|
||||
|
|
|
|||
|
|
@ -159,7 +159,7 @@ Live `thread/epiphany/scene`, `thread/epiphany/jobs`, and
|
|||
- automatic observation promotion
|
||||
- specialist-agent scheduling
|
||||
- GUI-as-source-of-truth
|
||||
- automatic runtime CRRC coordinator
|
||||
- automatic runtime CRRC coordinator with real context-pressure telemetry
|
||||
- live long-running job execution or `thread/epiphany/jobsUpdated`
|
||||
- broad event stream beyond the landed state update notification
|
||||
|
||||
|
|
|
|||
Reference in a new issue