docs: document advisor recent_log_lines byte cap [doc-updater]

docs/guides/pipeline-health-monitoring.md

@@ -243,6 +243,7 @@ Tripwire thresholds are configurable in `PipelineConfig`:
 | `overseer_heartbeat_failures_before_restart` | `3` | Consecutive heartbeat failures before the overseer triggers an agent restart (default: 3) |
 | `overseer_nudge_timeout_before_restart_minutes` | `5` | Minutes to wait after sending a nudge with no response before triggering an agent restart |
 | `overseer_advisor_model` | `"opus"` | LLM model used by the Tier-2 advisor when Haiku flags an anomaly that intersects with a Tier-1 health alert. The default is the canonical `opus` alias (resolved by `shared/egg_harness/config.py` to the latest pinned Opus ID, currently Opus 4.6) so cost telemetry resolves correctly. See [Advisor Gate](#advisor-gate). |
+| `overseer_advisor_recent_log_bytes_cap` | `256000` | Byte cap for the `recent_log_lines` block in the advisor prompt (issue #2120). When the joined block exceeds the cap, the prompt-builder drops oldest lines first so the most-recent lines (highest signal) survive, and prepends a marker so the advisor knows truncation happened. Set to `0` to disable (not recommended — leaves the prompt open to pathological log payloads). |
 | `overseer_auto_file_issues_mode` | `"shadow"` | Auto-issue-filing mode: `shadow` surfaces the advisor's `recommendation=file_issue` as an `OVERSEER_ALERT` + HITL decision (the human approves before any `gh issue create` runs); `live` runs the same HITL flow but allows the CLI verb to file once approval lands. The HITL approval is *never* bypassed. To disable issue filing entirely, set `overseer_enabled=false`. |
 | `overseer_owns_host_detection` | `false` | Calibration-window flag for the host → overseer migration. While `false` (the default), the `/sdlc` host skill keeps its stall / silent-agent / NACK / long-running-phase / stuck-pipeline rescue detectors live. While `true`, those host detectors short-circuit and the overseer is the sole source of these alerts. See [Host Detector Migration](#host-detector-migration). |
 | `overseer_stuck_phase_transition_seconds` | `180` | Threshold (seconds) for the existing overseer `stuck-phase-transition` trigger (orchestrator-level signal). Raised from the previous hardcoded ~60s default per operator feedback during long phase transitions. |

docs/reference/orchestrator-cli.md

@@ -39,7 +39,7 @@ Run `egg-orch --help` for full usage. All commands support `--json` for machine-
 | `egg-orch message send [<id>] --to <role\|all> --type <type> --subject "..." --body "..."` | Send directed or broadcast message. Types: `HANDOFF`, `STATUS`, `PROGRESS`, `HEARTBEAT`. (`QUESTION` was removed in [#1897](https://github.com/jwbron/egg/issues/1897).) |
 | `egg-orch overseer alert [<id>] --anomaly <type> --priority <low\|medium\|high> --summary "..." [--detail "..."] [--recommend "..."] [--recommendation file_issue] [--recommendation-payload-file <path>]` | Broadcast `OVERSEER_ALERT` to human operator (overseer use only — always sets `message_type=OVERSEER_ALERT` and `to_role=all`). `--recommendation file_issue` attaches a structured advisor verdict; requires `--recommendation-payload-file` (JSON path with `issue_title`/`issue_body`/`priority`/`anomaly_signature`). |
 | `egg-orch overseer file-issue [<id>] --anomaly-type <type> --priority <p0\|p1\|p2\|p3> --agent-role <role> --anomaly-signature <hex16> --issue-title-file <path> --issue-body-file <path> [--parent-alert-message-id <id>] [--dry-run] [--json]` | File a GitHub issue from the overseer role (advisor-gated). Checks `filed-issues.jsonl` + `gh issue list` for deduplication; skips filing if a matching open issue exists. Default stdout is plain text (`Filed issue #N (...)` or `Existing issue #N already covers ...`); with `--json`, prints JSON `{"issue_number": int, "filed": bool, "dedup_match": int\|null}`; with `--dry-run` (no `gh` invocation either way): if a dedup match is found, prints the same `--json` shape (with `issue_number`/`dedup_match` populated); otherwise prints `{"issue_number": null, "filed": false, "dedup_match": null, "dry_run": true, "argv": [...], "title": str, "body_bytes": int}`. Requires `EGG_PIPELINE_REPO` env var. |
-| `egg-orch overseer consult-advisor [<id>] --inputs-file <path> [--output-file <path>] [--json]` | Consult the Opus advisor for a structured `AdvisorVerdict` (sandbox-side LLM call). Reads a JSON inputs file with `classification`, `health_alerts`, `progress_events`, and `recent_log_lines`. Returns `decision` (`alert`\|`file_issue`\|`watch`), `priority`, `alert_summary`, `alert_detail`, `issue_title`, `issue_body`, and `reasoning`. Without `--output-file`, the JSON verdict is written to stdout; with `--output-file`, the verdict is written to that path and stdout shows a confirmation message (pass `--json` to additionally echo the verdict to stdout). |
+| `egg-orch overseer consult-advisor [<id>] --inputs-file <path> [--output-file <path>] [--recent-log-bytes-cap <n>] [--json]` | Consult the Opus advisor for a structured `AdvisorVerdict` (sandbox-side LLM call). Reads a JSON inputs file with `classification`, `health_alerts`, `progress_events`, and `recent_log_lines`. Returns `decision` (`alert`\|`file_issue`\|`watch`), `priority`, `alert_summary`, `alert_detail`, `issue_title`, `issue_body`, and `reasoning`. Without `--output-file`, the JSON verdict is written to stdout; with `--output-file`, the verdict is written to that path and stdout shows a confirmation message (pass `--json` to additionally echo the verdict to stdout). `--recent-log-bytes-cap` overrides the `PipelineConfig.overseer_advisor_recent_log_bytes_cap` value (default 256 KiB); oldest lines are dropped first when the block exceeds the cap. `0` disables the cap. |
 | `egg-orch message poll [<id>] [--since <id>] [--limit <n>]` | Poll for messages from other agents (concurrent mode) |
 | `egg-orch message wait [<id>] --for <TYPE>... [--timeout N] [--since <id>]` | Block until a **new** typed BRC event arrives (cursor-less calls start at stream tip — already-seen events are skipped). Pass `--since <id>` for zero-drop send→wait semantics. Exit 0 = matched, 1 = timeout, 2 = transient (retry-safe), 3 = permanent. See [Agent Wait Patterns §3](agent-wait-patterns.md#3-exit-code-contract-for-egg-orch-message-wait) |
 | `egg-orch message wait-loop [<id>] --for <TYPE>... [--since <id>]` | **Canonical STAY ALIVE idiom** — loops `message wait` server-side until a new matching event arrives (defaults to stream-tip; pass `--since <id>` for zero-drop send→wait). Do not wrap in an outer shell loop. See [Agent Wait Patterns §1](agent-wait-patterns.md#1-the-canonical-idiom) |