drydock-cli 3.0.75__tar.gz → 3.0.76__tar.gz

{drydock_cli-3.0.75/drydock_cli.egg-info → drydock_cli-3.0.76}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: drydock-cli
-Version: 3.0.75
+Version: 3.0.76
 Summary: Drydock — a local, provider-agnostic terminal coding agent for local LLMs
 Author: Frank Bobe III
 License-Expression: Apache-2.0

{drydock_cli-3.0.75 → drydock_cli-3.0.76}/drydock/providers.py

@@ -56,6 +56,36 @@ PROVIDERS: dict[str, dict] = {
 }
 
 
+def probe_server_context(base_url: str, *, timeout: float = 4.0) -> int | None:
+    """Best-effort: ask the model server its REAL context window (tokens).
+    llama.cpp exposes it on `/props` (n_ctx); vLLM puts `max_model_len` on
+    `/v1/models`. Returns None if unknown/unreachable — never raises. This is the
+    definitive diagnostic for a "stuck at N tokens" cap that isn't drydock's
+    config (it's the server's own `-c` / `--ctx-size` / `max_model_len`)."""
+    import json
+    import urllib.request
+
+    root = base_url.rstrip("/")
+    base_no_v1 = root[:-3].rstrip("/") if root.endswith("/v1") else root
+
+    def _n_ctx(d):
+        return (d.get("default_generation_settings") or {}).get("n_ctx") or d.get("n_ctx")
+
+    def _max_model_len(d):
+        return next((m.get("max_model_len") for m in d.get("data", []) if m.get("max_model_len")), None)
+
+    for url, pick in ((base_no_v1 + "/props", _n_ctx), (root + "/models", _max_model_len)):
+        try:
+            with urllib.request.urlopen(url, timeout=timeout) as r:  # noqa: S310 (user's own server)
+                data = json.loads(r.read().decode("utf-8", "ignore"))
+            val = pick(data)
+            if isinstance(val, int) and val > 0:
+                return val
+        except Exception:  # noqa: BLE001 — best-effort probe
+            continue
+    return None
+
+
 class LLMUnreachable(RuntimeError):
     """The configured LLM endpoint could not be reached. Carries a
     user-facing message with remediation steps (shown verbatim in the TUI)."""

{drydock_cli-3.0.75 → drydock_cli-3.0.76}/drydock/tui/app.py

@@ -758,12 +758,12 @@ class DrydockApp(App):
         arg = (arg or "").strip()
         if not arg:
             self._info(
-                f"context_limit: {limit:,} tokens (the '/{limit // 1024}k' in the ctx gauge).\n"
+                f"context_limit (drydock): {limit:,} tokens (the '/{limit // 1024}k' in the ctx gauge).\n"
                 "Source order: built-in default 65536 < ~/.drydock/config.toml < --context-limit.\n"
-                "If you're stuck below this, your MODEL SERVER's context is smaller — raise its\n"
-                "`-c`/`--ctx-size`/`max_model_len` to match. To change drydock's budget:\n"
-                "  /context <tokens>      e.g. /context 65536   (saved to config.toml)"
+                "Probing your model server for its REAL context window…\n"
+                "  To change drydock's budget:  /context <tokens>   (saved to config.toml)"
             )
+            self.run_worker(lambda: self._probe_server_context(limit), thread=True)
             return
         try:
             n = int(arg.replace(",", "").replace("k", "000").replace("K", "000"))
@@ -781,6 +781,30 @@ class DrydockApp(App):
             "least this, or the server will still cap you below it."
         )
 
+    def _probe_server_context(self, limit: int) -> None:
+        """Worker: ask the model server its real context window and report whether
+        IT (not drydock's config) is the thing capping you — the definitive answer
+        to 'stuck at N tokens'."""
+        from drydock import providers
+
+        base_url = self.config.get("base_url") or providers.PROVIDERS.get(
+            self.config.get("provider") or "vllm", {}).get("base_url", "http://localhost:8000/v1")
+        n_ctx = providers.probe_server_context(base_url)
+        if n_ctx is None:
+            msg = (f"Model server ({base_url}) didn't report its context size "
+                   "(not llama.cpp /props or vLLM max_model_len, or unreachable). "
+                   f"Your effective cap is the smaller of drydock's {limit:,} and the "
+                   "server's own -c/--ctx-size.")
+        elif n_ctx < limit:
+            msg = (f"⚠ Model server reports n_ctx = {n_ctx:,} tokens — SMALLER than "
+                   f"drydock's {limit:,}. The SERVER is your real cap (you'll stick near "
+                   f"{n_ctx // 1024}k). Restart it with a larger -c/--ctx-size/max_model_len, "
+                   "or lower /context to match.")
+        else:
+            msg = (f"✓ Model server reports n_ctx = {n_ctx:,} tokens (≥ drydock's {limit:,}), "
+                   "so drydock's budget is the effective limit — no server-side cap.")
+        self.call_from_thread(self._info, msg)
+
     def _cmd_compact(self) -> None:
         """Manually compact the conversation to reclaim context NOW, without
         waiting for the automatic 60%-of-window threshold (agent.maybe_compact).

{drydock_cli-3.0.75 → drydock_cli-3.0.76/drydock_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: drydock-cli
-Version: 3.0.75
+Version: 3.0.76
 Summary: Drydock — a local, provider-agnostic terminal coding agent for local LLMs
 Author: Frank Bobe III
 License-Expression: Apache-2.0

{drydock_cli-3.0.75 → drydock_cli-3.0.76}/drydock_cli.egg-info/SOURCES.txt

@@ -79,6 +79,7 @@ tests/test_rmf.py
 tests/test_rmf_graph.py
 tests/test_rmf_stig_graph.py
 tests/test_runaway_repetition.py
+tests/test_server_probe.py
 tests/test_skills.py
 tests/test_stig.py
 tests/test_stop.py

{drydock_cli-3.0.75 → drydock_cli-3.0.76}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 # PyPI distribution name is drydock-cli (the established install name, continued
 # from the retired v2 fork); the import package + CLI command stay `drydock`.
 name = "drydock-cli"
-version = "3.0.75"
+version = "3.0.76"
 description = "Drydock — a local, provider-agnostic terminal coding agent for local LLMs"
 readme = "README.md"
 requires-python = ">=3.11"

drydock_cli-3.0.76/tests/test_server_probe.py

@@ -0,0 +1,39 @@
+"""Server context-window probe — the definitive 'what's capping me' diagnostic."""
+from __future__ import annotations
+
+import json
+
+from drydock import providers
+
+
+class _Resp:
+    def __init__(self, body): self._b = json.dumps(body).encode()
+    def read(self): return self._b
+    def __enter__(self): return self
+    def __exit__(self, *a): return False
+
+
+def test_probe_llamacpp_props_n_ctx(monkeypatch):
+    import urllib.request
+    def fake(url, timeout=0):
+        assert url.endswith("/props")      # llama.cpp endpoint, /v1 stripped
+        return _Resp({"default_generation_settings": {"n_ctx": 32768}})
+    monkeypatch.setattr(urllib.request, "urlopen", fake)
+    assert providers.probe_server_context("http://localhost:8000/v1") == 32768
+
+
+def test_probe_vllm_max_model_len(monkeypatch):
+    import urllib.request
+    def fake(url, timeout=0):
+        if url.endswith("/props"):
+            raise OSError("no props on vLLM")
+        return _Resp({"data": [{"id": "m", "max_model_len": 65536}]})
+    monkeypatch.setattr(urllib.request, "urlopen", fake)
+    assert providers.probe_server_context("http://localhost:8000/v1") == 65536
+
+
+def test_probe_unreachable_is_none(monkeypatch):
+    import urllib.request
+    def boom(url, timeout=0): raise OSError("offline")
+    monkeypatch.setattr(urllib.request, "urlopen", boom)
+    assert providers.probe_server_context("http://localhost:9999/v1") is None