docs(skill): scope inactive visibility to what a source can attest (#36)

`inactive` is populated only by Pi. The skill described it as a Pi
capability but never said what its absence means elsewhere, so an agent
querying a Claude Code session with `includeInactive: true` reads an empty
result as "nothing was abandoned here". Across 43 local Claude transcripts,
20 contained branches off the surviving path, so that reading is wrong far
more often than it is right.

Claude Code and Codex transcripts record no supersession event to attest
from; Kimi records one but the adapter drops those messages while indexing.
The added sentence covers all three without naming them, so it stays correct
if Kimi later marks retracted history instead of discarding it.

skill-doc/references/schema.md

@@ -80,7 +80,7 @@ Core evidence table.
 | `text` | Extracted text, truncated to 10k chars |
 | `content_type` | `text`, `thinking`, `tool_use`, `tool_result`, or `unknown` |
 | `is_meta` | 1 for injected/control-plane messages |
-| `visibility` | `visible` for current evidence, `inactive` for provider-attested superseded history, `hidden` for display-suppressed or transport-only material |
+| `visibility` | `visible` for current evidence, `inactive` for provider-attested superseded history, `hidden` for display-suppressed or transport-only material. Only Pi emits `inactive` |
 | `model` | Assistant model name |
 | `is_sidechain` | Retry/branch marker |
 | `agent_id` | Subagent/workflow agent ID |