tau-coding-agent 0.3.1__tar.gz → 0.3.9__tar.gz

{tau_coding_agent-0.3.1/tau_coding_agent.egg-info → tau_coding_agent-0.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tau-coding-agent
-Version: 0.3.1
+Version: 0.3.9
 Summary: A self-extensible agent CLI with terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools and commands
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -26,6 +26,8 @@ Requires-Dist: pygments==2.20.0
 Requires-Dist: pathspec==1.1.1
 Requires-Dist: gitpython==3.1.50
 Requires-Dist: grapheme==0.6.0
+Provides-Extra: tools
+Requires-Dist: ripgrep>=14.0.0; extra == "tools"
 Dynamic: license-file
 
 # Tau (τ)

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/docs/auth.md

@@ -143,6 +143,7 @@ The provider ID used as the key in `auth.json` and the `{PROVIDER}_API_KEY` env
 | OpenAI | `openai` | `OPENAI_API_KEY` |
 | Google | `google` | `GOOGLE_API_KEY` |
 | Mistral | `mistral` | `MISTRAL_API_KEY` |
+| Fireworks AI | `fireworks` | `FIREWORKS_API_KEY` |
 | Ollama | `ollama` | `OLLAMA_API_KEY` |
 
 ## Next Steps

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/docs/extensions.md

@@ -30,9 +30,11 @@ A subdirectory under `extensions/` is loaded if it has either:
 
 Before the entry file is executed, these specs are installed into the project or
 global packages venv (`uv pip install`, falling back to `pip` when `uv` isn't on
-PATH) and the venv's site-packages directory is added to `sys.path`. The install
-only runs once — a hash of the dependency list is cached, so unchanged manifests
-are a no-op on subsequent launches.
+PATH) and the venv's site-packages directory is appended to `sys.path`. Tau's
+runtime environment keeps precedence, so an extension cannot replace Tau's own
+dependencies with incompatible versions. The install only runs once — a hash of
+the dependency list is cached, so unchanged manifests are a no-op on subsequent
+launches.
 
 ## Entry point
 
@@ -625,29 +627,6 @@ session working directory; pass an explicit `cwd=` to override.
 
 ---
 
-## Cross-extension event bus
-
-Extensions can communicate with each other via `tau.events`:
-
-```python
-# producer.py
-def register(tau):
-    @tau.on("session_start")
-    async def on_start(event, ctx):
-        await tau.events.emit("producer:ready", {"version": "1.0"})
-
-# consumer.py
-def register(tau):
-    @tau.events.on("producer:ready")
-    async def on_ready(data):
-        print(f"producer ready — version {data['version']}")
-```
-
-This is separate from the hooks bus: `tau.events` is for extension-to-extension
-messages; `tau.on(...)` is for system lifecycle events.
-
----
-
 ## Editor autocomplete providers
 
 Extensions can inject custom autocomplete suggestions into the editor. When the user
@@ -740,7 +719,6 @@ def register(tau):
 | `tau.register_flag(name, type, env, default)` | Declare an env-backed flag |
 | `tau.get_flag(name)` | Read a registered flag's value |
 | `await tau.exec(cmd, args, cwd)` | Run a shell command |
-| `tau.events` | Cross-extension `EventBus` |
 | `tau.config` | Per-extension settings dict from `settings.json` |
 | `tau.cwd` | `Path` — working directory at session start |
 | `tau.model_id` | Active model identifier |

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/docs/inference-providers.md

@@ -12,6 +12,7 @@ Tau supports the following inference providers:
 | OpenAI | API Key | No | [Link](#openai) |
 | Google Gemini | API Key | Yes | [Link](#google-gemini) |
 | Mistral AI | API Key | Limited | [Link](#mistral-ai) |
+| Fireworks AI | API Key | No | [Link](#fireworks-ai) |
 | Ollama | None | Yes | [Link](#ollama-local) |
 | Azure OpenAI | API Key | No | [Link](#azure-openai) |
 
@@ -103,11 +104,51 @@ export MISTRAL_API_KEY=...
 tau --model mistral/mistral-large -p "Say hello"
 ```
 
+## Fireworks AI
+
+Fireworks AI provides fast, cost-efficient inference for open-source models including Llama, DeepSeek, Qwen, and Mixtral — with OpenAI-compatible APIs.
+
+**Text models**:
+
+| Model | Context | Pricing (in/out per M tokens) |
+|-------|---------|-------------------------------|
+| `accounts/fireworks/models/llama-v3p3-70b-instruct` | 131K | $0.90 / $0.90 |
+| `accounts/fireworks/models/llama-v3p1-405b-instruct` | 131K | $3.00 / $3.00 |
+| `accounts/fireworks/models/deepseek-r1` *(thinking)* | 160K | $3.00 / $7.00 |
+| `accounts/fireworks/models/deepseek-v3` | 131K | $0.90 / $0.90 |
+| `accounts/fireworks/models/qwen3-235b-a22b` *(thinking)* | 131K | $0.22 / $0.88 |
+| `accounts/fireworks/models/qwen3-30b-a3b` *(thinking)* | 131K | $0.15 / $0.60 |
+| `accounts/fireworks/models/mixtral-8x22b-instruct` | 65K | $0.90 / $0.90 |
+| `accounts/fireworks/models/gemma2-9b-it` | 8K | $0.20 / $0.20 |
+
+**Image models**: Flux 1 Schnell FP8, Flux 1 Dev FP8
+
+### Setup
+
+1. Create an account at [Fireworks AI](https://fireworks.ai)
+2. Generate an API key in your account settings
+3. Set the environment variable:
+
+```bash
+export FIREWORKS_API_KEY=fw_...
+```
+
+### Verify
+
+```bash
+tau --model fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct -p "Say hello"
+```
+
+### Notes
+
+- Uses the OpenAI-compatible completions API under the hood
+- Session affinity is maintained automatically via a per-request `x-session-affinity` header
+
 ## Ollama (Local)
 
 Run open-source models locally without API keys or internet.
 
-**Models**: `llama2`, `mistral`, `neural-chat`, and [others](https://ollama.ai/library)
+**Models**: `llama2`, `mistral`, `neural-chat`, `qwen3.5:cloud` (262K context, thinking), and [others](https://ollama.ai/library)
 
 ### Setup
 

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/docs/settings.md

@@ -187,6 +187,10 @@ When your conversation grows long, tau automatically summarizes older messages t
 - **`reserve_tokens`**: How many tokens to keep available for the LLM's response (default 16,384 ≈ 4K-5K words)
 - **`keep_recent_tokens`**: How many recent message tokens to preserve word-for-word before summarization kicks in (default 20,000 ≈ 5K-6K words)
 
+#### Mid-turn (threshold) compaction
+
+In addition to compaction triggered at the start of a turn, tau can compact **mid-turn** when the context hits the configured limit while the agent is already running. When this happens the engine stops cleanly so you can review the compacted context and continue — no partial output is lost. Tool output lines are truncated before sending to the LLM to help prevent hitting the threshold in the first place.
+
 Example configurations:
 
 ```json
@@ -284,6 +288,10 @@ These settings are applied to the LLM client at startup:
 
 Changes take effect on the next session start or after `/reload`.
 
+#### Adaptive retry delay
+
+When a provider responds with a `Retry-After` or `Retry-After-Ms` header (common on rate-limit responses), tau uses that value as the retry delay instead of the configured `base_delay_ms`. The delay is capped at **60 seconds** so a provider that returns an extreme value (e.g. "retry in 16 days") doesn't stall the agent indefinitely. When no header is present, `base_delay_ms` is used.
+
 ```json
 {
   "retry": {
@@ -442,11 +450,11 @@ All retry settings are **fully implemented and wired to the LLM client at startu
 All thinking budget settings are **fully implemented and configurable**:
 
 - **`thinking_budgets.minimal`**: Token budget for "minimal" level (default: `1024`)
-- **`thinking_budgets.low`**: Token budget for "low" level (default: `2048`)
-- **`thinking_budgets.medium`**: Token budget for "medium" level (default: `4096`)
-- **`thinking_budgets.high`**: Token budget for "high" level (default: `8192`)
-- **`thinking_budgets.xhigh`**: Token budget for "xhigh" level (default: `16384`)
-- **`thinking_budgets.max`**: Token budget for "max" level (default: `32768`)
+- **`thinking_budgets.low`**: Token budget for "low" level (default: `4096`)
+- **`thinking_budgets.medium`**: Token budget for "medium" level (default: `8192`)
+- **`thinking_budgets.high`**: Token budget for "high" level (default: `16384`)
+- **`thinking_budgets.xhigh`**: Token budget for "xhigh" level (default: `32768`)
+- **`thinking_budgets.max`**: Token budget for "max" level (default: `65536`)
 
 Override these to customize extended thinking token allocations for your workflow.
 

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/docs/usage.md

@@ -102,8 +102,8 @@ Prints session info inline in the chat. Shows:
 
 - **Session Info** — Name (if set), File path, ID
 - **Messages** — User, Assistant, Tool calls, Tool results, Total
-- **Tokens** — Input, Output, Cache read (if any), Cache write (if any), Total
-- **Cost** — Total USD cost (only shown if non-zero)
+- **Tokens** — Input, Output, Cache read (if any), Cache write (if any), Total — counts use human-readable suffixes (e.g. `1.2K`, `3.4M`); each line shows an inline cost estimate in USD
+- **Cost** — Total USD cost with inline estimate (only shown if non-zero)
 
 ### `/copy`
 

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tau-coding-agent"
-version = "0.3.1"
+version = "0.3.9"
 description = "A self-extensible agent CLI with terminal UI, multi-provider LLM support, session management with branching, and a plugin system for tools and commands"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -64,3 +64,17 @@ include = ["tau*"]
 tau = [
     "builtins/**/*",
 ]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[project.optional-dependencies]
+tools = ["ripgrep>=14.0.0"]
+
+[dependency-groups]
+dev = [
+    "pytest>=9.1.1",
+    "ruff>=0.4.0",
+    "mypy>=1.10.0",
+    "pyright>=1.1.360",
+]

tau_coding_agent-0.3.9/tau/agent/__init__.py

@@ -0,0 +1,11 @@
+from tau.agent.service import Agent
+from tau.agent.types import AgentConfig, AgentContext, AgentPhase, ContextUsage, PromptOptions
+
+__all__ = [
+    "Agent",
+    "AgentConfig",
+    "AgentContext",
+    "AgentPhase",
+    "PromptOptions",
+    "ContextUsage",
+]

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/tau/agent/prompt/__init__.py

@@ -1,10 +1,10 @@
 """System prompt assembly for the coding agent."""
 
-from tau.agent.prompt.types import PromptOptions
 from tau.agent.prompt.builder import PromptBuilder, build_prompt
+from tau.agent.prompt.types import PromptOptions
 
 __all__ = [
-    'PromptOptions',
-    'PromptBuilder',
-    'build_prompt',
+    "PromptOptions",
+    "PromptBuilder",
+    "build_prompt",
 ]

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/tau/agent/prompt/builder.py

@@ -8,10 +8,11 @@ from pathlib import Path
 
 from tau.agent.prompt.types import PromptOptions
 from tau.settings.paths import (
-    get_system_prompt_path,
     get_append_system_prompt_path,
     get_docs_dir,
+    get_examples_path,
     get_readme_path,
+    get_system_prompt_path,
 )
 
 
@@ -32,14 +33,84 @@ def load_project_context_file(cwd: Path) -> tuple[str, Path] | None:
                 pass
     return None
 
+
+def _find_git_root(cwd: Path) -> Path | None:
+    """Walk up from cwd and return the first directory containing .git, or None."""
+    current = cwd.resolve()
+    while True:
+        if (current / ".git").exists():
+            return current
+        parent = current.parent
+        if parent == current:
+            return None
+        current = parent
+
+
+def load_project_context_files(cwd: Path) -> list[tuple[str, Path]]:
+    """Walk from git root (or cwd if not in a repo) down to cwd, collecting context files.
+
+    Returns (content, path) tuples ordered root-first so cwd instructions appear
+    last and take highest precedence when the model reads top-to-bottom.
+    """
+    candidates = ["AGENTS.md", "AGENTS.MD", "CLAUDE.md", "CLAUDE.MD"]
+
+    def _load(directory: Path) -> tuple[str, Path] | None:
+        for filename in candidates:
+            path = directory / filename
+            if path.is_file():
+                try:
+                    content = path.read_text(encoding="utf-8").strip()
+                    return (content, path) if content else None
+                except OSError:
+                    pass
+        return None
+
+    resolved = cwd.resolve()
+    git_root = _find_git_root(resolved)
+    stop_at = git_root if git_root else resolved
+
+    # Collect directories from stop_at down to cwd
+    dirs: list[Path] = []
+    current = resolved
+    while True:
+        dirs.append(current)
+        if current == stop_at:
+            break
+        parent = current.parent
+        if parent == current:
+            break
+        current = parent
+
+    seen: set[Path] = set()
+    results: list[tuple[str, Path]] = []
+    for directory in reversed(dirs):
+        entry = _load(directory)
+        if entry and entry[1] not in seen:
+            seen.add(entry[1])
+            results.append(entry)
+
+    return results
+
+
 _DEFAULT_IDENTITY = """\
-You are a coding agent. You help users understand, write, and modify code and files.
+You are a coding agent operating inside Tau, a coding agent harness. You help users by
+reading files, executing commands, editing code, and writing new files.
 
 You have strong software engineering skills. You think carefully before making changes,
 and follow the existing style and conventions of the project.
-If a task is ambiguous, ask a clarifying question before proceeding.\
 """
 
+_GENERAL_GUIDELINES = [
+    "If a task is ambiguous, ask a precise, clarifying question before proceeding.",
+    ("Do only what the task asks; don't add features, refactors, or abstractions beyond scope."),
+    "Write comments when the *why* is non-obvious — well-named code explains itself.",
+    "Keep responses short, concise, and direct; don't summarize what you just did.",
+    (
+        "Prioritize accuracy over agreement — investigate before confirming, and "
+        "disagree when the evidence calls for it."
+    ),
+]
+
 
 _GIT_STATUS_MAX_LINES = 30
 _GIT_LOG_COUNT = 5
@@ -136,7 +207,8 @@ class PromptBuilder:
     Assembles the system prompt from layered sources.
 
     Layers in order:
-      Identity              — SYSTEM.md if present, else built-in identity; --system bypasses entirely
+      Identity              — SYSTEM.md if present, else built-in identity;
+                              --system bypasses entirely
       Tools section         — auto-generated from tool list (descriptions + guidelines)
       Tau docs              — tau documentation and examples
       Project Instructions  — AGENTS.md or CLAUDE.md from project (if present)
@@ -155,6 +227,7 @@ class PromptBuilder:
     def build(self) -> str:
         """Build the complete system prompt."""
         identity = self._identity()
+        guidelines = self._guidelines_section()
         tools = self._tools_section()
         docs = self._docs_section()
         project_context = self._project_context_section()
@@ -162,7 +235,9 @@ class PromptBuilder:
         append = self._append()
         git = self._git_section()
         footer = self._footer()
-        return identity + tools + docs + project_context + skills + append + git + footer
+        return (
+            identity + guidelines + tools + docs + project_context + skills + append + git + footer
+        )
 
     # ------------------------------------------------------------------
     # Layers
@@ -178,6 +253,10 @@ class PromptBuilder:
 
         return _DEFAULT_IDENTITY
 
+    def _guidelines_section(self) -> str:
+        bullets = "\n".join(f"- {g}" for g in _GENERAL_GUIDELINES)
+        return f"\n\n# Guidelines\n\n{bullets}"
+
     def _tools_section(self) -> str:
         tools = self._opts.tools
         if not tools:
@@ -194,6 +273,10 @@ class PromptBuilder:
             if guideline:
                 guidelines.append(f"- **{t.name}**: {guideline.strip()}")
         section = "\n\n# Available Tools\n\n" + "\n".join(lines)
+        section += (
+            "\nIn addition to the tools above, you may have access to other custom "
+            "tools depending on the project."
+        )
         if guidelines:
             section += "\n\n## Tool Guidelines\n\n" + "\n".join(guidelines)
         return section
@@ -201,6 +284,10 @@ class PromptBuilder:
     def _project_context_section(self) -> str:
         """Include project-specific context from AGENTS.md or CLAUDE.md if present.
 
+        Walks from git root down to cwd, loading one file per directory.
+        Each file is wrapped in <project_instructions path="..."> so the model
+        knows which directory each set of rules comes from.
+
         Skipped if:
         - disable_context_files is True (--no-context-files flag)
         - project is not trusted (--no-approve flag or trust store)
@@ -209,36 +296,50 @@ class PromptBuilder:
             return ""
         if self._opts.project_trusted is False:
             return ""
-        context = load_project_context_file(self._opts.cwd)
-        if not context:
+        files = load_project_context_files(self._opts.cwd)
+        if not files:
             return ""
-        content, path = context
+        blocks = "".join(
+            f'<project_instructions path="{path}">\n{content}\n</project_instructions>\n\n'
+            for content, path in files
+        )
         return (
-            f"\n\n# Project Instructions\n\n"
-            f"Project-specific guidelines and rules (from {path.name}):\n\n"
-            f"{content}\n\n"
-            "Follow project-specific instructions before general Tau guidelines."
+            "\n\n# Project Instructions\n\n"
+            "Project-specific guidelines (follow before general Tau guidelines):\n\n"
+            "<project_context>\n\n" + blocks + "</project_context>"
         )
 
     def _docs_section(self) -> str:
         readme = get_readme_path()
         docs = get_docs_dir()
+        examples = get_examples_path()
         return (
             "\n\nTau documentation (read only when the user asks about Tau itself, its"
             " settings, extensions, themes, skills, tools, sessions, or keybindings):\n"
             f"- README: {readme}\n"
             f"- Docs directory: {docs}\n"
-            "- When asked about: settings (docs/settings.md), tools (docs/tools.md),"
+            f"- Examples directory: {examples} (extensions, custom tools, themes, skills)\n"
+            "- When asked about: quickstart (docs/quickstart.md),"
+            " installation (docs/installation.md),"
+            " usage (docs/usage.md), CLI flags (docs/cli-reference.md),"
+            " architecture (docs/architecture.md),"
+            " settings (docs/settings.md), tools (docs/tools.md),"
             " extensions (docs/extensions.md), themes (docs/themes.md),"
-            " skills (docs/skills.md), keybindings (docs/keybindings.md),"
-            " sessions (docs/sessions.md), usage (docs/usage.md),"
-            " Python API (docs/python-api.md), inference providers (docs/inference-providers.md)\n"
-            "- Resolve all doc paths under the Docs directory above, not the current working directory\n"
+            " skills (docs/skills.md), prompts (docs/prompts.md),"
+            " keybindings (docs/keybindings.md),"
+            " sessions (docs/sessions.md), messages (docs/messages.md),"
+            " Python API (docs/python-api.md),"
+            " inference providers (docs/inference-providers.md),"
+            " auth (docs/auth.md)\n"
+            "- Resolve all doc paths under the Docs directory above,"
+            " not the current working directory\n"
+            "- Resolve all example paths under the Examples directory above\n"
             "- Read .md files completely and follow cross-references before answering"
         )
 
     def _skills_section(self) -> str:
         from tau.skills.registry import skill_registry
+
         block = skill_registry.format_for_system_prompt(self._opts.skills)
         return f"\n\n{block}" if block else ""
 

{tau_coding_agent-0.3.1 → tau_coding_agent-0.3.9}/tau/agent/prompt/types.py

@@ -2,13 +2,16 @@ from __future__ import annotations
 
 from pathlib import Path
 from typing import Any
+
 from pydantic import BaseModel, Field
+
 from tau.tool.types import Tool
 
 
 class PromptOptions(BaseModel):
     """Options for constructing the system prompt."""
-    model_config = {'arbitrary_types_allowed': True}
+
+    model_config = {"arbitrary_types_allowed": True}
 
     cwd: Path
     tools: list[Tool] = Field(default_factory=list)