drydock-cli 2.6.145__tar.gz → 2.6.147__tar.gz

drydock_cli-2.6.147/.auto_release.lock

@@ -0,0 +1 @@
+2652274

drydock_cli-2.6.147/DEPLOYMENT.md

@@ -0,0 +1,223 @@
+# DryDock Deployment Guide
+
+The known-working configuration DryDock is developed and tested against.
+If you hit TUI loops, tool errors, or model hangs that look different
+from what the README describes, your setup is probably drifting from
+this baseline. This document is kept deliberately concrete — it mirrors
+a real working machine, not aspirational recommendations.
+
+## Hardware baseline
+
+| Component | What works |
+|---|---|
+| GPU | 2× NVIDIA RTX 4060 Ti 16 GB (32 GB total VRAM) |
+| Model | [Gemma-4-26B-A4B-it-AWQ-4bit](https://huggingface.co/casperhansen/gemma-4-26b-a4b-it-AWQ-4bit) |
+| RAM | 64 GB recommended (32 GB minimum) |
+| Disk | SSD, ≥100 GB free for model + session logs |
+| OS | Ubuntu 22.04, kernel 6.8 |
+
+A single 24 GB GPU can run the model with slightly reduced context.
+The AWQ quant is what makes 16 GB cards viable — non-quantized
+Gemma 4 26B needs ≥40 GB.
+
+## vLLM (model server)
+
+Run via Docker:
+
+```bash
+docker run -d \
+    --gpus all \
+    --name gemma4 \
+    -p 8000:8000 \
+    -v /path/to/models:/models \
+    --ipc=host \
+    vllm/vllm-openai:gemma4 \
+    --model /models/Gemma-4-26B-A4B-it-AWQ-4bit \
+    --quantization compressed-tensors \
+    --tensor-parallel-size 2 \
+    --max-model-len 131072 \
+    --max-num-seqs 2 \
+    --gpu-memory-utilization 0.95 \
+    --kv-cache-dtype fp8 \
+    --served-model-name gemma4 \
+    --trust-remote-code \
+    --tool-call-parser gemma4 \
+    --enable-auto-tool-choice \
+    --attention-backend TRITON_ATTN
+```
+
+**Don't omit** any of these flags — they're all load-bearing:
+
+| Flag | Why |
+|---|---|
+| `--tool-call-parser gemma4` | Without this, Gemma 4 emits tool calls in text that the OpenAI-compat layer can't route. Tool calling silently breaks. |
+| `--enable-auto-tool-choice` | Required so `tool_choice="auto"` actually works. Without it the model can't decide between text and tool call. |
+| `--attention-backend TRITON_ATTN` | The default backend has periodic OOM spikes on 16 GB cards. TRITON is stable. |
+| `--kv-cache-dtype fp8` | Halves KV cache memory; required to reach 131K context on 32 GB total VRAM. |
+| `--max-num-seqs 2` | Prevents OOM under concurrent load. Raise on larger cards. |
+| `--gpu-memory-utilization 0.95` | Squeezes the last bit of VRAM. Drop to 0.85 if you see allocator warnings. |
+
+Single-GPU variant: drop `--tensor-parallel-size 2` and lower
+`--max-model-len` to something like 65536.
+
+### Sanity-check
+
+```bash
+curl http://localhost:8000/v1/models
+# Should return: {"data": [{"id": "gemma4", ...}]}
+
+curl http://localhost:8000/v1/chat/completions \
+    -H "Content-Type: application/json" \
+    -d '{"model":"gemma4","messages":[{"role":"user","content":"hi"}]}'
+```
+
+## Optional: load balancer / failover
+
+For long sessions, a thin HTTP proxy in front of vLLM survives brief
+vLLM restarts. Point DryDock at the proxy, not vLLM directly. See
+`scripts/llm_balancer.py` for reference; typical setup is:
+
+- Proxy on port 8001 → vLLM on port 8000
+- Keepalive cron respawns the balancer if it dies
+- `scripts/vllm_failover.sh` on a 5-min cron restarts vLLM if it's unreachable
+
+The development machine uses this setup. Skip it for first-time setup;
+return to it when you start hitting multi-hour sessions.
+
+## `~/.drydock/config.toml`
+
+The known-working DryDock config. Copy into `~/.drydock/config.toml`
+after first run (DryDock creates a stub on first launch; overwrite it):
+
+```toml
+active_model = "local"
+auto_compact_threshold = 120000
+api_timeout = 600.0
+system_prompt_id = "ralph"           # Gemma 4's simplified prompt
+slim_system_prompt = true
+enable_telemetry = true
+enable_notifications = true
+
+[[providers]]
+name = "vllm"
+api_base = "http://localhost:8000/v1"   # or :8001 if using llm_balancer
+api_style = "openai"
+backend = "generic"
+reasoning_field_name = "reasoning_content"
+
+[[models]]
+name = "gemma4"
+provider = "vllm"
+alias = "local"                       # matches active_model above
+temperature = 0.2
+thinking = "high"
+
+[session_logging]
+save_dir = "~/.vibe/logs/session"     # drydock writes sessions here
+session_prefix = "session"
+enabled = true
+
+[project_context]
+max_chars = 40000
+max_doc_bytes = 32768
+max_files = 1000
+max_depth = 3
+timeout_seconds = 2.0
+
+[tools.bash]
+permission = "always"
+max_output_bytes = 16000
+default_timeout = 300
+# See repo config for the full allowlist/denylist.
+
+[tools.read_file]
+permission = "always"
+max_read_bytes = 64000
+
+[tools.write_file]
+permission = "always"
+max_write_bytes = 64000
+create_parent_dirs = true
+
+[tools.search_replace]
+permission = "always"
+max_content_size = 100000
+fuzzy_threshold = 0.9
+
+[tools.grep]
+permission = "always"
+max_output_bytes = 64000
+default_max_matches = 100
+default_timeout = 60
+
+[tools.todo]
+permission = "always"
+max_todos = 100
+
+[tools.task]
+permission = "always"
+allowlist = ["explore", "diagnostic", "planner", "builder"]
+
+[tools.web_fetch]
+permission = "ask"         # don't auto-approve network egress
+default_timeout = 30
+max_content_bytes = 512000
+
+[tools.web_search]
+permission = "ask"
+```
+
+Critical fields:
+
+- `temperature = 0.2` — Gemma 4 gets unstable above ~0.4. Don't raise.
+- `thinking = "high"` — required for planning. DryDock adaptively
+  lowers it per-turn; setting it here is the default ceiling.
+- `system_prompt_id = "ralph"` — the Gemma-4-tuned prompt. The default
+  cli prompt confuses Gemma 4 into planning instead of acting.
+- `auto_compact_threshold = 120000` — below Gemma 4's 131K max context,
+  with headroom for the response.
+- `api_timeout = 600.0` — Gemma 4's first-turn thinking can legitimately
+  take 60–120 s. The default timeout is too short.
+
+## Environment variables
+
+| Var | Default | Why you'd change it |
+|---|---|---|
+| `DRYDOCK_AUTO_CONTINUE_DISABLE` | unset | Set to `1` to stop the auto-"Continue." injection that keeps Gemma 4 chaining tool calls. Useful for **stress test runs** and any workflow where text-only turns should cleanly end the user turn. Leave unset for production use unless you see Continue-loops. |
+| `DRYDOCK_INSECURE` | unset | Set to `1` to accept self-signed TLS (local LAN deployments). |
+| `DRYDOCK_LOCAL_URL` | `http://localhost:8000/v1` | Override the default local endpoint. |
+| `DRYDOCK_LOCAL_MODEL` | `local` | Model alias to target. |
+
+## Known-good network topology
+
+```
+user        drydock TUI           llm_balancer         vLLM
+cli   ───►  :stdin           ───►  :8001      ────►  :8000
+                                  │                    │
+                                  └── keepalive cron   └── keeps one
+                                       (5-min)              container up
+```
+
+## Diagnosing bad installs
+
+If DryDock acts up, compare your runtime to this baseline before
+filing an issue:
+
+1. **`curl localhost:8000/v1/models`** returns Gemma 4? If not, vLLM
+   isn't running or isn't on the expected port.
+2. **`python3 -c "from drydock.core.agent_loop import AgentLoop; import inspect; print('aafa090' in inspect.getsource(AgentLoop._sanitize_message_ordering))"`** — checks the should_break_loop fix is in your install. If `False`, reinstall with `pip install --upgrade drydock-cli`.
+3. **Check the session log.** `tail ~/.vibe/logs/session/session_*/messages.jsonl` — look for `"user": "Continue."` repeating. If you see that, set `DRYDOCK_AUTO_CONTINUE_DISABLE=1`.
+4. **`docker logs gemma4 | tail -50`** — vLLM errors show up here. Common: `out of memory` (drop `--max-num-seqs` or `--max-model-len`), `unknown tool-call parser` (you're on an older vLLM image without the `gemma4` parser).
+
+## Tested versions
+
+Everything in this document was exercised on:
+
+- drydock-cli ≥ 2.6.145
+- vllm/vllm-openai:gemma4 Docker image (built from vLLM 0.7.x + Gemma 4 parser patch)
+- Python 3.12 (dev) / 3.14 (runtime)
+- Ubuntu 22.04, kernel 6.8, Docker 24.x with nvidia-container-toolkit
+- NVIDIA driver 550.x
+
+Older vLLM images may lack `--tool-call-parser gemma4`. Build from the
+gemma4 branch or wait for upstream.

drydock_cli-2.6.147/OVERNIGHT_PROGRESS.md

@@ -0,0 +1,159 @@
+# Overnight Progress — 2026-04-20 → 2026-04-21
+
+Drop-in status doc so a fresh Claude session (after disconnect) can
+resume without relearning the last 24 hours. **Read this first, then
+`git log --oneline -20` + `TaskList` for full picture.**
+
+## What landed today (in order)
+
+| Commit | What | Where it lives |
+|---|---|---|
+| 3cb957e | pexpect-buffer trim, banner detect, ESC+/clear, force-reset, checkpoint filter | scripts/ |
+| f363ae1 | `DRYDOCK_AUTO_CONTINUE_DISABLE` env gate for agent_loop auto-Continue | drydock/core/agent_loop.py |
+| 2e0431e | Admiral actuator via SIGUSR1 — watcher asks harness to recycle TUI | scripts/stress_watcher.py + stress_shakedown.py |
+| 5c76801 | Wipe cwd down to fixtures on fresh stress start | scripts/stress_shakedown.py |
+| aafa090 | **should_break_loop dead-code fix** — user turns actually end on text responses | drydock/core/agent_loop.py:876 |
+| 1508c1b | SessionWatcher reads drydock's configured save_dir (was hardcoded ~/.drydock) | scripts/shakedown_interactive.py |
+| c77c2e0 | Hourly stress_babysitter cron | scripts/stress_babysitter.sh + crontab |
+| 0ae9d07 | Karpathy-autoresearch scaffold | research/ (kernel.py, experimenter.py, config_base.toml, mini_*) |
+| 11cfe89 | Todo loop fix (#10) + Check 0 empty-result detector + realuser prompts + raw-md detector | drydock/core/tools/builtins/todo.py, agent_loop.py, scripts/ |
+| fd7a160 | v2.6.145 release | PyPI + GitHub |
+| aad7ac6 | Admiral sees raw-markdown leakage; DEPLOYMENT.md baseline | scripts/stress_watcher.py, DEPLOYMENT.md, README.md |
+| 553926a | v2.6.146 release | PyPI + GitHub |
+
+## Long-running processes (DO NOT KILL without checking)
+
+| PID | Process | Notes |
+|---|---|---|
+| 2625579 | stress_shakedown (v10 restart #1) | auto-restarted by babysitter at 02:00 UTC after original died. Resuming from step 866. |
+| child of 2625579 | drydock TUI | Recycled periodically by admiral actuator |
+| 2366908 or newer | stress_watcher (v10) | Paired with current stress PID |
+| 2251231 | admiral_probe on :8878 | Read-only dashboard endpoint |
+| 1230765 | llm_balancer on :8001 | DO NOT KILL — proxies to vLLM, shared |
+| cron | stress_babysitter.sh hourly | Auto-restarts stress if PID dies |
+
+**v10 progress summary** (as of ~03:00 UTC 2026-04-21):
+- Original run: reached idx 972/1658 (59%) with done=866, skip=105, recycle=72 — died at ~21:00 UTC
+- Restart #1: resumed from step 866, currently at idx ~921, done=50, skip=5, recycle=3
+- Net cumulative: ~920/1658, acceptance rate still ~95%
+- Babysitter fired once (telegram sent), admiral actuator firing per run
+
+## Meta-Harness integration — in progress
+
+User approved the scope at ~03:00 local and asked for overnight build.
+See `research/domain_spec.md` for the full design (just written).
+
+**Approved mutation surface:**
+- `drydock/core/prompts/gemma4.md` (system prompt)
+- `drydock/core/prompts/cli.md` (alternate prompt)
+- admiral knob TOML (existing 7 numerics in `config_base.toml`)
+- `scripts/stress_shakedown.py` threshold constants
+  (MAX_CONSECUTIVE_SKIPS_BEFORE_RESET, SESSION_RESET_EVERY, retry windows)
+- `drydock/admiral/detectors.py` thresholds + patterns
+
+**Approved frozen:**
+- `drydock/core/agent_loop.py` (just stabilized, too risky)
+- Tool implementations
+- Provider config
+- Core stress harness flow (pexpect loop, session tracking)
+
+**Approved budget:**
+- Per candidate: 20-min mini-stress (50 prompts) as search-set, 5-min kernel as held-out smoke
+- Per 24 hr: up to ~30 candidates
+- Full 1658-prompt stress is quarterly regression only
+
+**Remaining overnight tasks:**
+1. [in progress] Expand `config_base.toml` mutation surface (tasks #16)
+2. [pending] Trace capture in `kernel.py` — save per-run artifacts to `research/traces/<exp_id>/` (task #17)
+3. [pending] `research/proposer.py` — Opus-backed proposer (task #18)
+4. [pending] `--proposer opus` flag in `experimenter.py` (task #19)
+5. [pending] Commit + let auto_release ship (task #20)
+
+**NOT running the experimenter overnight** — it would share vLLM with
+v10 stress and starve both. Scaffolded ready-to-launch.
+
+## Known issues to investigate (user-reported, not yet fixed)
+
+### 2026-04-21 03:xx user reports drydock crash with 15+ API errors
+
+User's quote:
+```
+✓ Read 0 line from prepare.py (truncated)
+✓ Read 66 lines from prepare.py
+✓ Read 66 lines from prepare.py
+✓ Read 630 lines from train.py
+✓ Read 19 lines from AGENTS.md
+
+[6 consecutive API errors (round 1/3). Compacting and retrying. Last error: API error
+from vllm (model: gemma4): LLM backend error [vllm]
+status: 400 Bad Request
+...]
+
+[Stopping: 15+ API errors. The model cannot process this request.]
+```
+
+Plus drydock self-diagnoses: "You've written prepare.py 4 times this session.
+If the file is oscillating Fix this before moving to the next file."
+
+**This is the production version of the exact wedge pattern the stress
+harness fixes.** Production drydock hits 400s, auto-compacts 2-3 times,
+then gives up at 15+ errors. It DOES have recovery — the compaction
+fires — but 15 errors in a row means compaction isn't finding enough
+context to shrink.
+
+**Root cause hypothesis:**
+- User's session accumulated large read_file results (train.py 630 lines
+  is substantial), plus prepare.py written 4 times = 4 copies of the file
+  content in history.
+- Auto-compact at 120000 tokens doesn't fire because the issue isn't
+  raw token count, it's a single turn's payload exceeding vLLM's 131K
+  context limit.
+- Compaction per-attempt only truncates old tool results; doesn't
+  dedupe repeat writes to the same file.
+
+**Fix hypothesis (for tomorrow's session):**
+- `_prune_duplicate_writes` already exists in `drydock/core/agent_loop.py`
+  but only fires when the hard-block trips on a write_file call. Extend
+  it to fire on ANY `write_file` call where the target already has ≥3
+  prior write_file entries in history.
+- Lower emergency-compact aggressiveness: when a 400 arrives, drop
+  middle-of-history message runs even if recent, not just oldest
+  truncation. The "keep first user + last 5" fallback is already there
+  (lines 834-846 of agent_loop.py).
+- Consider: hard-cap read_file results at 32KB per call regardless of
+  `max_read_bytes` config when the session has had >50k tokens of
+  tool results already.
+
+**NOT fixing overnight** — this is in `agent_loop.py` which is marked
+frozen for the meta-harness integration AND just got stabilized
+yesterday. Investigate + propose fix in morning session.
+
+## Auto-release state
+
+**Paused flag:** NOT set. Auto-release cron fires at 0/6/12/18 UTC.
+Next fire: 06:00 UTC (~03:00 local). Any commits before then ship in
+v2.6.147.
+
+**Version:** local == v2.6.146 (tagged fd7a160, aad7ac6 shipped).
+
+## Monitoring for connection loss
+
+If this Claude session disconnects:
+
+1. **v10 stress continues** — babysitter cron handles restarts. Check
+   `/tmp/stress_babysitter.log` and `~/.drydock/logs/admiral_history.log`.
+2. **Meta-harness files** are committed incrementally. `git log --oneline`
+   shows progress. Any staged-but-uncommitted changes are lost, but the
+   `domain_spec.md` alone is enough to resume.
+3. **No orphan processes** — all long-running jobs are daemonized via
+   `nohup + disown`, they survive my death.
+
+## For the next session (morning handoff)
+
+- Read `research/domain_spec.md` for the full design.
+- `git log --oneline fd7a160..HEAD` for commits since v2.6.145.
+- Check v10 state: `tail /tmp/stress_babysitter.log`.
+- Check meta-harness progress: `ls research/`, look for `proposer.py`
+  and `traces/` — if both exist, the overnight build finished.
+- **Priority for morning:** investigate the prepare.py-loop / 400-error
+  wedge the user reported. Hypothesized fixes above.

{drydock_cli-2.6.145 → drydock_cli-2.6.147}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: drydock-cli
-Version: 2.6.145
+Version: 2.6.147
 Summary: Local-first CLI coding agent — tested with Gemma 4 26B via vLLM
 Project-URL: Homepage, https://github.com/fbobe321/drydock
 Project-URL: Repository, https://github.com/fbobe321/drydock
@@ -156,6 +156,13 @@ Or with uv:
 uv tool install drydock-cli
 ```
 
+> [!TIP]
+> **New install hitting weird behavior?** See [DEPLOYMENT.md](DEPLOYMENT.md)
+> for the exact known-working vLLM launch flags, `~/.drydock/config.toml`,
+> env vars, and a diagnostic checklist. Most "DryDock doesn't work" issues
+> trace back to missing vLLM flags (`--tool-call-parser gemma4`,
+> `--enable-auto-tool-choice`) or temperature/thinking config drift.
+
 ## Quick Start
 
 ```bash

{drydock_cli-2.6.145 → drydock_cli-2.6.147}/README.md

@@ -100,6 +100,13 @@ Or with uv:
 uv tool install drydock-cli
 ```
 
+> [!TIP]
+> **New install hitting weird behavior?** See [DEPLOYMENT.md](DEPLOYMENT.md)
+> for the exact known-working vLLM launch flags, `~/.drydock/config.toml`,
+> env vars, and a diagnostic checklist. Most "DryDock doesn't work" issues
+> trace back to missing vLLM flags (`--tool-call-parser gemma4`,
+> `--enable-auto-tool-choice`) or temperature/thinking config drift.
+
 ## Quick Start
 
 ```bash

{drydock_cli-2.6.145 → drydock_cli-2.6.147}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "drydock-cli"
-version = "2.6.145"
+version = "2.6.147"
 description = "Local-first CLI coding agent — tested with Gemma 4 26B via vLLM"
 readme = "README.md"
 requires-python = ">=3.12"

drydock_cli-2.6.147/research/config_base.toml

@@ -0,0 +1,209 @@
+# Baseline for the research experimenter.
+#
+# The knob array defines which admiral tunables the experimenter is
+# allowed to mutate. Bounds mirror drydock/admiral/tuning.py::KNOB_BOUNDS
+# exactly — if that file changes, mirror the change here. The kernel
+# validates bounds before writing admiral_tuning.json, so malformed
+# mutations fail fast rather than silently hitting admiral's clip.
+#
+# The experimenter NEVER edits this file. It writes to
+# research/config_best.toml on improvement. Swap this file's values
+# manually when you want to re-seed the search from a new baseline.
+#
+# FROZEN (NOT mutable — verified by experimenter before apply):
+#   - drydock/core/agent_loop.py (just stabilized 2026-04-19; untouchable)
+#   - Tool implementations (drydock/core/tools/)
+#   - Provider config
+#   - Core stress harness flow (scripts/stress_shakedown.py::run main loop)
+#
+# MUTABLE surface (what the Opus proposer may change):
+#   - Admiral knobs (the [[knob]] array below)
+#   - Env flags (the [env_flags] section below)
+#   - Stress harness thresholds (the [harness_thresholds] section below)
+#   - Admiral detector thresholds (the [admiral_detectors] section below)
+#   - System prompts (the [prompts] section below — paths to override files)
+#
+# The experimenter writes prompt overrides to:
+#     research/candidates/<exp_id>/prompts/<name>.md
+# and the kernel mounts them under the isolated HOME's prompt dir.
+
+[target]
+# admiral_tuning.json keys off (model, task). The kernel writes an entry
+# under this tuple when spawning drydock. Pick values that match what
+# admiral will classify stress-harness runs as.
+model = "mistral-vibe-cli-latest"
+task  = "unknown"
+
+# -----------------------------------------------------------------
+# Admiral knobs — bounded numeric tunables that affect agent_loop.
+# -----------------------------------------------------------------
+
+[[knob]]
+name    = "per_prompt_budget_sec"
+default = 300
+min     = 300
+max     = 3600
+mutable = true
+why     = "Hard ceiling on a single user turn. Too low wastes work; too high lets loops run wild."
+
+[[knob]]
+name    = "hard_stop_tool_calls"
+default = 100
+min     = 30
+max     = 250
+mutable = true
+why     = "HARD_STOP_CALLS in agent_loop. Cap on tool-call depth per user turn."
+
+[[knob]]
+name    = "wrap_up_warn_at"
+default = 40
+min     = 10
+max     = 100
+mutable = true
+why     = "First progressive nudge. Earlier = tighter turns, may lose quality."
+
+[[knob]]
+name    = "stop_now_warn_at"
+default = 60
+min     = 20
+max     = 150
+mutable = true
+why     = "Second progressive nudge. Gemma often ignores the wrap-up; this is the harder prod."
+
+[[knob]]
+name    = "temperature"
+default = 0.3
+min     = 0.0
+max     = 0.9
+mutable = true
+why     = "Sampling temperature. Lower = more deterministic; higher = more exploration."
+
+[[knob]]
+name    = "loop_detector_window"
+default = 3
+min     = 2
+max     = 6
+mutable = true
+why     = "How many consecutive identical tool calls trigger the loop advisor."
+
+[[knob]]
+name    = "struggle_threshold"
+default = 20
+min     = 10
+max     = 40
+mutable = true
+why     = "Reads-without-a-write before admiral fires the struggle directive."
+
+# -----------------------------------------------------------------
+# Environment flags — binary toggles the kernel sets in the TUI env.
+# -----------------------------------------------------------------
+
+[env_flags]
+DRYDOCK_AUTO_CONTINUE_DISABLE = "1"  # options: "0", "1"
+
+# -----------------------------------------------------------------
+# System prompt overrides. When `source_path` is set, the kernel
+# copies that file into the isolated HOME's prompt dir. When the
+# proposer mutates a prompt it writes to
+#     research/candidates/<exp_id>/prompts/<name>.md
+# and points the corresponding source_path here.
+# -----------------------------------------------------------------
+
+[prompts.gemma4]
+# Leave source_path empty to use the production gemma4.md shipped in
+# the installed drydock package. Opus proposer may replace this with
+# a candidate-local path.
+source_path = ""
+mutable = true
+why     = "Single highest-leverage mutable target. Governs how Gemma 4 interprets every turn."
+
+[prompts.cli]
+source_path = ""
+mutable = true
+why     = "Alternate non-Gemma system prompt. Rarely the right target but available for cross-model experiments."
+
+# -----------------------------------------------------------------
+# Stress harness threshold constants. These are hardcoded in
+# scripts/stress_shakedown.py today. The kernel reads them from here
+# via env overrides (DRYDOCK_STRESS_*) and the harness respects the
+# overrides if set, falling back to the source defaults otherwise.
+# -----------------------------------------------------------------
+
+[[harness_threshold]]
+name    = "MAX_CONSECUTIVE_SKIPS_BEFORE_RESET"
+default = 2
+min     = 1
+max     = 5
+mutable = true
+why     = "Force ESC+/clear after N consecutive SKIPs. Lower = aggressive recycling; higher = tolerant of transient wedges."
+
+[[harness_threshold]]
+name    = "SESSION_RESET_EVERY"
+default = 15
+min     = 5
+max     = 50
+mutable = true
+why     = "Periodic /clear cadence in prompts. Tight cadence bounds context but costs reset overhead every N prompts."
+
+[[harness_threshold]]
+name    = "SEND_PROMPT_RETRY_COUNT"
+default = 3
+min     = 1
+max     = 6
+mutable = true
+why     = "How many times send_prompt_and_confirm re-types before marking SKIP. Each retry is ~120s."
+
+[[harness_threshold]]
+name    = "SEND_PROMPT_WAIT_PER_RETRY_SEC"
+default = 120
+min     = 30
+max     = 300
+mutable = true
+why     = "Seconds to wait for user-msg confirmation before retyping. Tighter = faster SKIP, may miss slow prompts."
+
+# -----------------------------------------------------------------
+# Admiral detector thresholds. Currently hardcoded in
+# drydock/core/agent_loop.py and drydock/admiral/detectors.py.
+# Surface as env vars (DRYDOCK_ADMIRAL_*) that the detectors check
+# at init.
+# -----------------------------------------------------------------
+
+[[admiral_detector]]
+name    = "REPEAT_WARNING_THRESHOLD"
+default = 4
+min     = 2
+max     = 8
+mutable = true
+why     = "Consecutive identical tool calls before a WARNING. Lower = early nudge; higher = tolerant of legit repetition."
+
+[[admiral_detector]]
+name    = "REPEAT_FORCE_STOP_THRESHOLD"
+default = 8
+min     = 4
+max     = 20
+mutable = true
+why     = "Consecutive identical tool calls before FORCE_STOP. Must be >= REPEAT_WARNING_THRESHOLD."
+
+[[admiral_detector]]
+name    = "EMPTY_RESULT_THRESHOLD"
+default = 3
+min     = 2
+max     = 6
+mutable = true
+why     = "Check 0 (empty-result loop). Fire FORCE_STOP after N identical-call + empty-result in a row."
+
+[[admiral_detector]]
+name    = "SAME_TOOL_NAME_REPEAT_LIMIT_BASH"
+default = 5
+min     = 3
+max     = 10
+mutable = true
+why     = "Same-tool repetition limit for bash. Different from read/grep which need more headroom."
+
+[[admiral_detector]]
+name    = "SAME_TOOL_NAME_REPEAT_LIMIT_READ"
+default = 7
+min     = 4
+max     = 12
+mutable = true
+why     = "Same-tool repetition limit for read_file + grep. Investigation tools legitimately repeat more."