dulus 0.2.22__tar.gz → 0.2.24__tar.gz

{dulus-0.2.22/dulus.egg-info → dulus-0.2.24}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dulus
-Version: 0.2.22
+Version: 0.2.24
 Summary: Spanish-first multi-provider AI CLI — 14 NVIDIA models free, Mesa Redonda, voice, TTS, RTK token reducer, MemPalace
 Author: KevRojo
 License: GPL-3.0
@@ -69,7 +69,7 @@ SET /sticky_input ON since the first run for the best experience!
   <a href="https://pypi.org/project/dulus/"><img src="https://static.pepy.tech/badge/dulus?style=flat-square" alt="downloads"/></a>
   <img src="https://img.shields.io/badge/python-3.11+-ff6b1f?style=flat-square&labelColor=07070a" alt="python"/>
   <img src="https://img.shields.io/badge/license-GPLv3-ff6b1f?style=flat-square&labelColor=07070a" alt="license"/>
-  <img src="https://img.shields.io/badge/version-v0.2.22-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
+  <img src="https://img.shields.io/badge/version-v0.2.24-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
   <img src="https://img.shields.io/badge/providers-11-ff6b1f?style=flat-square&labelColor=07070a" alt="providers"/>
   <img src="https://img.shields.io/badge/tools-27-ff6b1f?style=flat-square&labelColor=07070a" alt="tools"/>
   <img src="https://img.shields.io/badge/tests-263+-ff6b1f?style=flat-square&labelColor=07070a" alt="tests"/>

{dulus-0.2.22 → dulus-0.2.24}/README.md

@@ -22,7 +22,7 @@ SET /sticky_input ON since the first run for the best experience!
   <a href="https://pypi.org/project/dulus/"><img src="https://static.pepy.tech/badge/dulus?style=flat-square" alt="downloads"/></a>
   <img src="https://img.shields.io/badge/python-3.11+-ff6b1f?style=flat-square&labelColor=07070a" alt="python"/>
   <img src="https://img.shields.io/badge/license-GPLv3-ff6b1f?style=flat-square&labelColor=07070a" alt="license"/>
-  <img src="https://img.shields.io/badge/version-v0.2.22-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
+  <img src="https://img.shields.io/badge/version-v0.2.24-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
   <img src="https://img.shields.io/badge/providers-11-ff6b1f?style=flat-square&labelColor=07070a" alt="providers"/>
   <img src="https://img.shields.io/badge/tools-27-ff6b1f?style=flat-square&labelColor=07070a" alt="tools"/>
   <img src="https://img.shields.io/badge/tests-263+-ff6b1f?style=flat-square&labelColor=07070a" alt="tests"/>

{dulus-0.2.22 → dulus-0.2.24}/context.py

@@ -20,6 +20,7 @@ You are Dulus, an AI coding agent. Think in English; reply to KevRojo in Dominic
 # Autonomy: Background scripts (nohup/&) allowed | Never refuse monitoring/long tasks | Always wait for tool results before replying
 # Tools: SearchLastOutput → for [TRUNCATED] | WebFetch/WebSearch → web | TmuxOffload → tasks > 5s | ReadJob → background results
 # SleepTimer: ONLY for user-facing reminders/notifications (e.g. "remind me in 10min"). NEVER use it to wait between your own tool calls — it freezes the console. To pause inside a command sequence, put `sleep N` INSIDE the Bash command itself (e.g. Bash('cmd1 && sleep 2 && cmd2')).
+# Long-running tools: any tool whose `description` ends in `[long-running — wrap in TmuxOffload]` MUST be invoked via TmuxOffload (not directly), so the REPL stays responsive while it runs.
 # Multi-agent: Agent(subagent_type=...) | isolation="worktree" runs parallel | wait=false + name=... for fire-and-forget
 # Rules: Edit > Write | Use absolute paths + line numbers | Surface errors immediately, do not retry blindly
 # Input: "🎙 Transcribed:" prefix = voice input — tolerate typos/misspellings

{dulus-0.2.22 → dulus-0.2.24}/docs/news.md

@@ -3,6 +3,18 @@
 ## 🔥🔥🔥 News (Pacific Time)
 
 
+- May 09, 2026 (**v0.2.24**): **Auto-adapter prompt — 5 fixes from a sherlock postmortem**
+  - **Reconciled `limit` default** — the prompt had two contradictory rules ("default: 50, max: 200" vs "default: 10, NOT 50"). Models burned tokens reasoning about which to follow. Unified on `default: 10, hard max: 200` everywhere.
+  - **"READ the source first" rule** at the top of the wrapper guidelines. Adapters were inferring upstream function signatures from class names and shipping plugins that compile/import/export cleanly but crash at runtime due to type-shape mismatches. Now the prompt explicitly tells the model to read the consumer code (`param.get(...)` / `for x in param`) before guessing shapes.
+  - **Notifier/callback pattern hint** — when the upstream library has a notify/callback class, prefer collecting results via that callback over parsing the return value. Callbacks tend to stay stable; return shapes drift between versions.
+  - **`ADAPTATION_GUIDE.md` now requires a `## Type Contracts` section** documenting the exact shape of every non-trivial parameter. Read by the verifier and by future re-adaptations — eliminates blind re-guessing.
+  - **Verifier checklist explicitly flags the smoke test as THE BAR.** Compile / import / exports / ToolDef-shape are necessary but not sufficient. The new header in `ADAPTATION_TODO.md` warns the model not to celebrate after the syntactic checks — most real bugs are type-shape mismatches that only the smoke test catches.
+
+- May 09, 2026 (**v0.2.23**): **Auto-adapter teaches new plugins to declare TmuxOffload-worthy tools**
+  - **The adapter prompt now requires** the model to estimate per-tool runtime. Any tool that typically takes more than ~15 seconds (sherlock, holehe, OSINT crawls, video downloads, full-repo analysis, etc.) must end its `description` with the literal marker `[long-running — wrap in TmuxOffload]`.
+  - **System prompt now honors that marker** at runtime. When the agent sees a tool with that suffix, it wraps the call in TmuxOffload automatically instead of blocking the REPL. No more 90-second sherlock freezes pretending to be productive.
+  - **Why this matters.** New plugins adopted via `/plugin adapt` now self-declare their UX hints. The agent picks them up the moment they install — zero manual config, zero "oh I should have offloaded that" regrets.
+
 - May 09, 2026 (**v0.2.22**): **`/bg start` — one detached daemon for CLI + Web + Telegram**
   - **One command, three doors.** `/bg start` spawns a detached Dulus daemon that simultaneously listens on `127.0.0.1:5151` (IPC for `dulus "..."` from any shell), `127.0.0.1:5000` (WebChat in your browser), and the Telegram bridge if configured. All three entry points hit the SAME live session — same history, memory, plugins, tool state.
   - **`/bg status` / `stop` / `attach`** — small surface, big convenience. `attach` prints how to reach the running daemon (CLI, browser, tail the log).

{dulus-0.2.22 → dulus-0.2.24/dulus.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dulus
-Version: 0.2.22
+Version: 0.2.24
 Summary: Spanish-first multi-provider AI CLI — 14 NVIDIA models free, Mesa Redonda, voice, TTS, RTK token reducer, MemPalace
 Author: KevRojo
 License: GPL-3.0
@@ -69,7 +69,7 @@ SET /sticky_input ON since the first run for the best experience!
   <a href="https://pypi.org/project/dulus/"><img src="https://static.pepy.tech/badge/dulus?style=flat-square" alt="downloads"/></a>
   <img src="https://img.shields.io/badge/python-3.11+-ff6b1f?style=flat-square&labelColor=07070a" alt="python"/>
   <img src="https://img.shields.io/badge/license-GPLv3-ff6b1f?style=flat-square&labelColor=07070a" alt="license"/>
-  <img src="https://img.shields.io/badge/version-v0.2.22-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
+  <img src="https://img.shields.io/badge/version-v0.2.24-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
   <img src="https://img.shields.io/badge/providers-11-ff6b1f?style=flat-square&labelColor=07070a" alt="providers"/>
   <img src="https://img.shields.io/badge/tools-27-ff6b1f?style=flat-square&labelColor=07070a" alt="tools"/>
   <img src="https://img.shields.io/badge/tests-263+-ff6b1f?style=flat-square&labelColor=07070a" alt="tests"/>

{dulus-0.2.22 → dulus-0.2.24}/dulus.py

@@ -218,7 +218,7 @@ try:
     from importlib.metadata import version as _pkg_version
     VERSION = _pkg_version("dulus")
 except Exception:
-    VERSION = "0.2.22"  # dev fallback — keep in sync with pyproject.toml
+    VERSION = "0.2.24"  # dev fallback — keep in sync with pyproject.toml
 
 # ── ANSI helpers (used even with rich for non-markdown output) ─────────────
 from common import C, clr, info, ok, warn, err, stream_thinking, print_tool_start, print_tool_end, sanitize_text

{dulus-0.2.22 → dulus-0.2.24}/plugin/autoadapter.py

@@ -250,6 +250,13 @@ GOAL: Generate `plugin.json`, `plugin_tool.py`, and `ADAPTATION_GUIDE.md`.
 
 GUIDELINES FOR plugin_tool.py:
 
+0. READ THE SOURCE FIRST (critical — skip and you'll waste 10+ retry rounds):
+   - Before writing the wrapper, READ the actual function/class definitions you'll be calling.
+   - Note the EXACT shape each parameter expects: raw dict-of-dicts vs object-of-objects vs list of objects.
+   - DO NOT infer shapes from class names. Read the consumer code that does `param.get(...)` or `for x in param: ...`.
+   - When the upstream library has a notifier/callback/observer class, PREFER collecting results via that callback over parsing the return value — callbacks are usually consistent across versions, return shapes are not.
+   - Common gotcha: a class called `XInformation` often *wraps* the raw dict in `.information` or `.data`. The downstream function may expect the raw dict, not the wrapper. Verify by reading the function body.
+
 1. EXPORTS (mandatory):
    - `TOOL_DEFS`: list of `ToolDef(name, schema, func)` objects
    - `TOOL_SCHEMAS`: `[t.schema for t in TOOL_DEFS]`
@@ -272,7 +279,7 @@ GUIDELINES FOR plugin_tool.py:
 
 4. SCHEMA DESIGN:
    - Each param gets its own property. Never bundle into single "data" string
-   - Include `limit`/`max_results` (default: 10, NOT 50) and `verbose` (default: False) on every tool
+   - Include `limit`/`max_results` (default: 10, hard max: 200) and `verbose` (default: False) on every tool
 
 5. TOOL GRANULARITY:
    - Multiple specific tools > one mega-tool
@@ -352,9 +359,29 @@ CRITICAL:
 - plugin.json "dependencies" MUST be a simple LIST of strings
 - Include "ADAPTATION_GUIDE.md" in plugin.json "skills" list
 
+TMUX-OFFLOAD HINT (important for UX):
+- For each tool you generate, ESTIMATE its typical runtime.
+- If a tool typically runs > 15 seconds (network scans, sherlock, full holehe sweeps, large file ingestion, OSINT crawls, video downloads, full-repo analysis, etc.), APPEND the literal marker `[long-running — wrap in TmuxOffload]` at the END of the tool's `description` field in the JSON schema.
+- Tools that are fast (< 5s) do NOT need the marker. Don't be over-cautious — only mark tools where users will visibly wait.
+- The marker is read by Dulus's agent at runtime: when it sees a tool description ending in `[long-running — wrap in TmuxOffload]`, it knows to wrap that call in TmuxOffload instead of blocking the REPL.
+- Example: `"description": "Search for a username across hundreds of social networks. [long-running — wrap in TmuxOffload]"`
+
 Respond with the delimited format:
 ---FILE: ADAPTATION_GUIDE.md---
 (Overview, tool design decisions, error patterns, validation)
+
+The ADAPTATION_GUIDE.md MUST include a `## Type Contracts` section that documents,
+for each upstream function/class you call, the EXACT shape of every non-trivial
+parameter. Example:
+
+## Type Contracts
+- `sherlock(username, site_data, ...)` expects `site_data: Dict[str, Dict[str, Any]]`
+  (NOT `Dict[str, SiteInformation]` — extract `.information` from each SiteInformation first).
+- `notifier.update(result)` is called once per site with a `QueryResult` object.
+  Collect via a `_SilentNotify(QueryNotify)` subclass instead of parsing the return dict.
+
+This section is read by the verifier and by future re-adaptations, so be precise.
+
 ---FILE: plugin.json---
 (JSON manifest)
 ---FILE: plugin_tool.py---
@@ -392,7 +419,7 @@ Respond with the delimited format:
             "- Always encoding='utf-8', errors='replace' for file/subprocess I/O\n"
             "- Never lowercase true/false/null in Python — always True/False/None\n\n"
             "TOKEN OPTIMIZATION RULES — plugins MUST be efficient:\n"
-            "- Every tool MUST accept a 'limit' or 'max_results' parameter (default: 50, max: 200)\n"
+            "- Every tool MUST accept a 'limit' or 'max_results' parameter (default: 10, hard max: 200)\n"
             "- Every tool MUST accept a 'verbose' parameter (default: False)\n"
             "- When verbose=False, return ONLY essential data — no debug info, no banners\n"
             "- Lists/arrays MUST be truncated before returning — never return unlimited items\n"
@@ -800,6 +827,14 @@ def _write_todo_file(plugin_dir: Path, safe_name: str, items: list[dict]) -> Pat
         "Auto-generated checklist verifying the AI-generated plugin works.",
         "Each task is verified by the adapter worker; failures trigger a fix attempt.",
         "",
+        "⚠ THE BAR IS THE SMOKE TEST. Compile / import / exports / ToolDef-shape",
+        "checks are necessary but NOT sufficient — they only prove the file is",
+        "syntactically a Python module that exports something callable. They do",
+        "NOT prove the wrapper passes the right shapes to upstream functions.",
+        "If a smoke test fails after the syntactic checks pass, the bug is almost",
+        "always a TYPE-SHAPE mismatch (e.g. passing wrapper objects where the",
+        "function expected raw dicts). Re-read the source code before guessing.",
+        "",
     ]
     for item in items:
         lines.append(f"- [ ] {item['title']}")

{dulus-0.2.22 → dulus-0.2.24}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "dulus"
-version = "0.2.22"
+version = "0.2.24"
 description = "Spanish-first multi-provider AI CLI — 14 NVIDIA models free, Mesa Redonda, voice, TTS, RTK token reducer, MemPalace"
 readme = "README.md"
 requires-python = ">=3.11"