mirror of
https://github.com/openprose/prose.git
synced 2026-09-19 05:55:05 +08:00
dan
012650a201
* Document native runtime skill semantics * Rename native runtime to responsibility runtime * Add responsibility runtime compiler skeleton * Add responsibility compilation IR * Compile Forme manifests into repository IR * Serve static repository IR * Tighten responsibility runtime review gaps * Introduce OpenProse root model * Harden OpenProse root resolution * Add responsibility judge activation * Add responsibility pressure fulfillment path * Add repository status inspection * Make triggers concrete gateway registrations * Add live responsibility trigger adapters * Refine responsibility runtime validation * Harden responsibility runtime freshness * Tighten responsibility runtime guardrails * docs: replace skill examples with native repositories * chore: release v0.12.0 * fix: tighten release review gaps
1.2 KiB
1.2 KiB
name, kind
| name | kind |
|---|---|
| diagnose | system |
Services
- investigator
- classifier
- fixer
Requires
- run-path: path to the failed or problematic run (e.g.
<openprose-root>/runs/20260408-...) - focus: focus area -- "host-runtime", "system", "context", or "external" (optional, default: auto-detect)
Ensures
- report: diagnostic analysis with timeline, root cause, causal chain, and prioritized fix recommendations (immediate, permanent, prevention)
Errors
- no-run: run directory does not exist or is missing vm.log.md
- incomplete-run: run is still in progress (no
---endor---errormarker)
Strategies
- read the run's
vm.log.mdexecution log to identify the failure point from event markers - examine
workspace/directories for__error.mdfiles and intermediate artifacts - examine
bindings/directories for missing or malformed outputs - read
sources/*.prose.mdservice definitions to understand what each service was supposed to do - read
root.prose.md(the root source snapshot) to understand the system's intent - classify the root cause by asking "why" iteratively until reaching the earliest intervention point
- propose concrete fixes: show diffs for system errors, describe process changes for external errors