drydock-cli 2.6.144__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-2.6.144 → drydock_cli-2.6.147}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: drydock-cli
-Version: 2.6.144
+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-2.6.144 → 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-2.6.144 → drydock_cli-2.6.147}/drydock/core/agent_loop.py

@@ -865,17 +865,31 @@ class AgentLoop:
                                     has_made_edit = True
                                     break
 
-                # Only break when the model emits TEXT and hasn't made
-                # any tool calls this turn. If tool_turns > 0 the model
-                # is mid-work — a text message is an intermediate summary
-                # ("Wrote __init__.py, now I'll write cli.py") that used
-                # to force the user to type "continue" after every step.
-                # Keeping the loop alive lets the model chain through
-                # its entire plan in one user turn. The per-prompt budget
-                # (50 tool calls / 15 min) still provides a hard stop.
+                # Break when the model emits a text-only assistant
+                # response (no tool calls). That means the model is done
+                # with this user turn — return control so the user sees
+                # the response and can send the next prompt.
+                #
+                # The previous condition `last_message.role != Role.tool
+                # and tool_turns == 0` was unreachable: tool_turns is
+                # incremented to ≥1 at the top of every iteration, so
+                # the equality is never true after the first call. With
+                # the auto-"Continue." injection in _sanitize_message_
+                # ordering, the model re-ran forever on text-only
+                # prompts; with that injection disabled (via
+                # DRYDOCK_AUTO_CONTINUE_DISABLE=1) the model regenerated
+                # the same text response until PER_PROMPT_BUDGET_SEC
+                # timed out. Either way user turns never closed on a
+                # "done" state. See stress_shakedown.py runs v3–v7 for
+                # the full wedge picture.
+                #
+                # If Gemma 4 emits intermediate summaries without tool
+                # calls ("Wrote X, now I'll write Y") the user will see
+                # partial progress and have to prompt "continue". That's
+                # an acceptable cost compared to the forever-loop.
                 should_break_loop = (
-                    last_message.role != Role.tool
-                    and tool_turns == 0
+                    last_message.role == Role.assistant
+                    and not last_message.tool_calls
                 )
 
                 # No circuit breakers, no loop detection, no forced nudges.
@@ -2277,6 +2291,41 @@ class AgentLoop:
         sigs.reverse()
         tool_names.reverse()
 
+        # Check 0: Same call + empty-pattern result 3+ times in a row.
+        # Lower threshold than Check 1 (8) or the WARNING path (4) for
+        # the specific case where the tool keeps saying "nothing's
+        # here" — more calls literally cannot change state. GitHub #10:
+        # model called todo_list 4× getting "Retrieved 0 todos"; the
+        # existing Check 1 wouldn't fire until 8, leaving the user
+        # staring at a blob of empty calls for ~half a minute.
+        #
+        # We only fire when the result LOOKS empty (total_count: 0,
+        # "no todos", "no tasks", "no results", or entirely blank).
+        # Same call with a non-empty result (e.g., model re-reading a
+        # file whose content hasn't changed) is left to Check 1/WARNING
+        # — those cases often have legitimate ambiguity.
+        def _looks_empty(c: str) -> bool:
+            s = (c or "").lower().strip()
+            if not s:
+                return True
+            for p in ('"total_count": 0', '"total_count":0',
+                      'total_count: 0', 'retrieved 0 todos',
+                      'no todos', '0 tasks', 'no tasks',
+                      'no results', 'no matches', '0 matches'):
+                if p in s:
+                    return True
+            return False
+        if len(sigs) >= 3 and all(s == sigs[-1] for s in sigs[-3:]):
+            recent_results: list[str] = []
+            for msg in reversed(self.messages):
+                if msg.role == Role.tool:
+                    recent_results.append(str(msg.content or ""))
+                    if len(recent_results) >= 3:
+                        break
+            if (len(recent_results) >= 3
+                    and all(_looks_empty(r) for r in recent_results)):
+                return "FORCE_STOP"
+
         # Check 1: Exact same tool call repeated (same name + same args)
         last_tool = tool_names[-1] if tool_names else ""
         if (

{drydock_cli-2.6.144 → drydock_cli-2.6.147}/drydock/core/tools/builtins/todo.py

@@ -119,6 +119,11 @@ class TodoConfig(BaseToolConfig):
 
 class TodoState(BaseToolState):
     todos: list[TodoItem] = Field(default_factory=list)
+    # Track consecutive empty reads so the tool can escalate its reply
+    # from "empty" to "stop calling me". GitHub #10: model asked to
+    # "review PRD and continue", read empty todos, and re-called the
+    # read 4× in a row hoping for a change.
+    consecutive_empty_reads: int = 0
 
 
 class Todo(
@@ -167,10 +172,36 @@ class Todo(
                 )
 
     def _read_todos(self) -> TodoResult:
+        count = len(self.state.todos)
+        if count == 0:
+            # Escalate the reply each consecutive empty read. GitHub #10:
+            # with a neutral "Retrieved 0 todos", the model kept calling
+            # read in a loop hoping for a change. Directive phrasing plus
+            # an explicit "stop re-reading" at attempt 2+ breaks the loop.
+            self.state.consecutive_empty_reads += 1
+            n = self.state.consecutive_empty_reads
+            if n == 1:
+                message = (
+                    "No todos yet. The list is empty because nothing has "
+                    "been written. If you want to track work items, call "
+                    "this tool with action='write' and a todos list. "
+                    "Do not call with action='read' again until you've "
+                    "written at least one."
+                )
+            else:
+                message = (
+                    f"Still no todos (this is read #{n} in a row with no "
+                    "write between them). Stop calling read. Either write "
+                    "a todos list, or proceed with the user's task "
+                    "directly — empty state will not change on its own."
+                )
+        else:
+            self.state.consecutive_empty_reads = 0
+            message = f"Retrieved {count} todos"
         return TodoResult(
-            message=f"Retrieved {len(self.state.todos)} todos",
+            message=message,
             todos=self.state.todos,
-            total_count=len(self.state.todos),
+            total_count=count,
         )
 
     def _write_todos(self, todos: list[TodoItem]) -> TodoResult:
@@ -182,6 +213,7 @@ class Todo(
             raise ToolError("Todo IDs must be unique")
 
         self.state.todos = todos
+        self.state.consecutive_empty_reads = 0
 
         return TodoResult(
             message=f"Updated {len(todos)} todos",

{drydock_cli-2.6.144 → drydock_cli-2.6.147}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "drydock-cli"
-version = "2.6.144"
+version = "2.6.147"
 description = "Local-first CLI coding agent — tested with Gemma 4 26B via vLLM"
 readme = "README.md"
 requires-python = ">=3.12"