[FEATURE]: mechanism to keep critical rules visible against long-context dilution #41590

Checklist

• I have verified this feature has not been suggested before (searched existing issues before filing).

Not a duplicate of #37767 / #40474 (checked before filing):

• [FEATURE]:Performance: inefficient repository exploration and repeated static prompt context cause excessive inference and tool-call overhead #37767 covers repeated static prompt context across requests and context efficiency in long sessions.
• V2: agent/mode switches are invisible to the model — plan agent has no system prompt, no reminders in the request path (v1 parity gap) #40474 covers the missing reminder/re-injection mechanism in V2's request path (agent-switched messages dropped, no mode reminders).
  This request is wider: it asks for a first-class, verifiable mechanism whose injected content must actually reach the LLM context (verifiable in DB / request payload), not just logs or TUI rendering — plus optional "always-pinned" rules that survive any amount of context growth. Neither existing issue specifies the traceable-injection requirement.

Feature

Provide a supported, native mechanism so that important rules/instructions (e.g. from AGENTS.md) remain effective and visible to the LLM even when the conversation context grows very long.

Why (reason) — the "7-second fish" problem

Every AI agent is essentially a "7-second fish": high capability, but terrible memory. Each session/context boundary is a memory reset; it only survives on the current context window. In long sessions, rules injected early are diluted and forgotten as the conversation grows — so the agent drifts and violates its own golden rules (comment conventions, proxy usage, timeout discipline, role naming, etc.).

The user tried to counter this with a plugin (rules_reminder.js) that every N rounds console.logs a condensed rule card into the log stream. Verification showed this never entered the LLM context at all — it only printed a big text block over the TUI/interface, obscuring the actual conversation, and it had zero effect on the model's behavior. There is currently no reliable way for a plugin to inject text into the LLM context that the model actually reads, nor a way to verify it (plugin self-logs are not evidence).

Request details

1. A first-class mechanism to re-inject/highlight critical rules at a given interval (e.g. every N user turns), OR a way for plugins/AGENTS.md sections to be marked "always pinned" so they never get diluted.
2. The injected content must actually reach the LLM context (verifiable in the DB / request payload), not just logs or UI.
3. Optionally: context window management / automatic compaction info so rules survive.

Please iterate on this soon — context dilution is the single biggest reliability problem in long agent sessions.