aria-code 0.76.0__tar.gz → 0.78.0__tar.gz

{aria_code-0.76.0 → aria_code-0.78.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: aria-code
-Version: 0.76.0
-Summary: Open-source AI agent for logistics and finance work: numbers you can check, client data kept apart, actions a person approves
+Version: 0.78.0
+Summary: Open-source AI agent for coding, financial analysis and logistics operations: numbers you can check, client data kept apart, actions a person approves
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/artheras/aria-code
 Project-URL: Repository, https://github.com/artheras/aria-code
@@ -163,7 +163,7 @@ Dynamic: license-file
 
 <h1 align="center">Aria Code</h1>
 
-<p align="center">An open-source AI agent for logistics and finance work.<br>
+<p align="center">An open-source AI agent for coding, financial analysis and logistics operations.<br>
 Numbers you can check, client data kept apart, actions a person approves.</p>
 
 <p align="center"><a href="README_CN.md">简体中文</a> · English</p>
@@ -175,20 +175,33 @@ Numbers you can check, client data kept apart, actions a person approves.</p>
   <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-64748b?style=flat-square" alt="Apache License 2.0"></a>
 </p>
 
-<p align="center"><img src="docs/assets/demo-logistics.gif" alt="Real Aria Code terminal recording: reorder points for one shipper, a refusal to mix two shippers' data, and a carrier scorecard with a saving and two anomalies" width="860"></p>
-<p align="center"><sub>Recorded from a real Aria Code session on the sample 3PL data in <code>evals/fixtures</code>. No model is called, so every number on screen comes from the tools; pauses are shortened. <a href="docs/assets/demo-logistics.png">Still screenshot</a> · <a href="scripts/record_logistics_demo.py">Recorder</a> · <a href="scripts/render_logistics_demo.py">Renderer</a>.</sub></p>
+<p align="center"><img src="docs/assets/demo-coding.gif" alt="Real Aria Code session: Gemini 2.5 Pro writes fx.py and its tests, runs them after each step is approved, then /review checks the change" width="860"></p>
+<p align="center"><sub>A real session on Gemini 2.5 Pro (Vertex AI): Aria writes <code>fx.py</code> and its tests, runs them once each step is approved, then <code>/review</code> checks the change and gives its verdict. Waiting is shortened; nothing else is changed. <a href="docs/assets/demo-coding.png">Still</a> · <a href="scripts/record_demo.py">Recorder</a> · <a href="scripts/render_demo.py">Renderer</a></sub></p>
 
 ## What Aria Code does
 
-A general-purpose assistant aims for an answer that reads well. In logistics and finance the number gets acted on — one purchase order left out of a reorder quantity and the stock is bought twice. Aria Code is built around three things that follow from that.
+**Writes code and builds projects.** Describe the task in plain words. Aria reads the project, writes and edits files, runs commands and tests, and shows every change before it lands — nothing is written or run until you say yes. [`/review`](docs/code-review.md) reviews a change the way a careful colleague would: prioritised findings (P0–P3) with file and line, and a verdict; `aria-code review --base main --fail-on P1` gates a pull request in CI. Use a local Ollama model, Gemini on Google Cloud (Vertex AI, with nothing more than a `gcloud` login), or another supported provider.
 
-**Numbers you can check.** Reorder points, safety stock and carrier rankings come from stated formulas, with the formula and every assumption in the result — as does stablecoin settlement reconciliation, from the [Artheras skills](https://github.com/artheras/skills) Aria Code can install. When the data cannot support an answer — under 14 days of demand history, rows that name no shipper — it says so instead of estimating. The [`operations` eval suite](docs/verifiable-evals.md) checks exactly these traps.
+**Analyses markets and finances.** Quotes, technical indicators, backtests with an HTML report, risk and factor analysis, SEC filings, and US, Hong Kong, A-share and crypto data. Results name their data source, period and any gaps.
+
+<p align="center"><img src="docs/assets/demo-finance.gif" alt="Real Aria Code session: technical indicators for AAPL and a one-year momentum backtest on SPY, with data source, period and completeness stated" width="760"></p>
+
+**Runs logistics operations.** For third-party logistics: reorder points, safety stock, ABC/XYZ classes, dead stock, carrier scorecards and freight anomalies — and in Feishu, a daily digest per shipper with approval cards.
+
+<p align="center"><img src="docs/assets/demo-logistics.gif" alt="Real Aria Code session: a refusal to mix two shippers' data, reorder points for one shipper, and a carrier scorecard with a saving and two anomalies" width="760"></p>
+<p align="center"><sub>Both recorded from real sessions — market data from yfinance; the logistics data is the sample 3PL in <code>evals/fixtures</code>, with no model call.</sub></p>
+
+## How it works
+
+A general-purpose assistant aims for an answer that reads well. In code, markets and warehouses the result gets acted on — a rounding rule in a currency function, one purchase order left out of a reorder quantity. Three rules follow from that.
+
+**Numbers you can check.** Reorder points, safety stock, carrier rankings and backtests come from stated formulas and named data, with the formula and every assumption in the result — as does stablecoin settlement reconciliation, from the [Artheras skills](https://github.com/artheras/skills) Aria Code can install. When the data cannot support an answer — under 14 days of demand history, rows that name no shipper — it says so instead of estimating. The [`operations` eval suite](docs/verifiable-evals.md) checks exactly these traps.
 
 **Client data kept apart.** A third-party logistics provider holds many clients' stock side by side. A chat group bound to one shipper confines every analysis to that shipper, and the logistics tools themselves refuse another shipper's data or an unattributable file — the rule holds below the prompt, whatever the model asks for.
 
-**Actions a person approves.** In Feishu, each shipper's group gets a daily digest of reorders, dead stock and freight anomalies. `/补货` turns the reorder list into a purchase-order draft card; nothing happens until an authorised approver presses approve, and what runs is exactly what was shown. The draft is a file for your own purchasing system — Aria Code places no orders.
+**Actions a person approves.** In the terminal, every file write and command waits for your yes, with the diff in front of you. In Feishu, `/补货` turns the reorder list into a purchase-order draft card; nothing happens until an authorised approver presses approve, and what runs is exactly what was shown. The draft is a file for your own purchasing system — Aria Code places no orders.
 
-Underneath is a terminal coding agent: it inspects project files, applies edits, runs commands and tests, and explains the changes ([recording](docs/assets/demo-coding-workflow.gif)), with a local Ollama model or a supported cloud provider. A fresh install has no live business data; the logistics tools read your exports (CSV or JSON), and the chat features need a Feishu app or the Aria relay.
+A fresh install has no live business data: the logistics tools read your exports (CSV or JSON), market data comes from public sources, and the chat features need a Feishu app or the Aria relay.
 
 ## Quick start
 
@@ -210,6 +223,19 @@ The installer downloads the binary for your OS from the latest [GitHub release](
 
 Alternative package-manager installs: `npm install -g @artheras/aria-code` (requires npm) or `python3 -m pip install --upgrade "aria-code<4"` (requires Python 3.10+; the `<4` skips an older 4.x numbering that PyPI still lists). For development from source, see [CONTRIBUTING.md](CONTRIBUTING.md).
 
+### Updates
+
+Aria checks for a newer stable version in the background at startup, at most once per day. Cached notices appear immediately; network checks never delay the prompt. It checks GitHub Releases, or scoped npm for npm installs. Pip updates pin the GitHub version and verify that version is available on PyPI, avoiding the older 4.x numbering still listed as PyPI's latest. Source checkouts receive Git update instructions.
+
+```bash
+aria update --check  # check without installing
+aria update          # install the newest stable version for this install channel
+```
+
+In an interactive session, use `/update --check` or `/update`, then restart Aria. Native updates verify SHA-256 and the downloaded binary's version before switching the command; a failed download or verification leaves the existing command in place. Startup checks only notify. To disable them, set `check_for_update_on_startup` to `false` in `~/.aria-code/config.json`.
+
+For GitHub notifications, open [this repository](https://github.com/artheras/aria-code), select **Watch → Custom → Releases**, and save. Notifications follow your GitHub notification settings. Published stable releases appear on the [release page](https://github.com/artheras/aria-code/releases/latest) once the platform assets and package publishing have completed.
+
 To use a local model, install [Ollama](https://ollama.com/download), pull a coding model, and start Aria in local-only mode:
 
 ```bash
@@ -231,7 +257,7 @@ Aria may request approval before editing files or running commands, according to
 | --- | --- |
 | Local Ollama | An installed and running Ollama model; no cloud account for local inference. |
 | Direct cloud provider | That provider's API credentials and network access. |
-| Direct Google Cloud Vertex AI | `aria-code[google]`, Google Cloud Application Default Credentials, `GOOGLE_CLOUD_PROJECT`, and `GOOGLE_CLOUD_LOCATION`. |
+| Direct Google Cloud Vertex AI | `GOOGLE_CLOUD_PROJECT` and either a `gcloud auth login` (Aria uses Vertex AI's OpenAI-compatible endpoint with that login's token) or Application Default Credentials with `aria-code[google]`. `GOOGLE_CLOUD_LOCATION` defaults to `global`. |
 | Arthera hosted service | Install `aria-code[google]` and sign in through `/login` in the CLI. Arthera account sign-in does not grant Vertex AI credentials to your own machine. |
 
 Install extras only for features you use; see [pyproject.toml](pyproject.toml) for the current package options. Local inference can work offline, but live market data, remote integrations, sign-in, and cloud models cannot.

aria_code-0.78.0/README.md

@@ -0,0 +1,126 @@
+<p align="center">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="docs/assets/aria-code-icon.png">
+    <img src="docs/assets/aria-code-icon-light.png" alt="Aria Code icon" width="88">
+  </picture>
+</p>
+
+<h1 align="center">Aria Code</h1>
+
+<p align="center">An open-source AI agent for coding, financial analysis and logistics operations.<br>
+Numbers you can check, client data kept apart, actions a person approves.</p>
+
+<p align="center"><a href="README_CN.md">简体中文</a> · English</p>
+
+<p align="center">
+  <a href="https://www.npmjs.com/package/@artheras/aria-code"><img src="https://img.shields.io/npm/v/@artheras/aria-code?style=flat-square&logo=npm&label=npm" alt="npm version"></a>
+  <a href="https://pypi.org/project/aria-code/"><img src="https://img.shields.io/pypi/v/aria-code?style=flat-square&logo=pypi&label=PyPI" alt="PyPI version"></a>
+  <a href="https://github.com/artheras/aria-code/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/artheras/aria-code/ci.yml?branch=main&style=flat-square&logo=githubactions&label=CI" alt="CI status"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-64748b?style=flat-square" alt="Apache License 2.0"></a>
+</p>
+
+<p align="center"><img src="docs/assets/demo-coding.gif" alt="Real Aria Code session: Gemini 2.5 Pro writes fx.py and its tests, runs them after each step is approved, then /review checks the change" width="860"></p>
+<p align="center"><sub>A real session on Gemini 2.5 Pro (Vertex AI): Aria writes <code>fx.py</code> and its tests, runs them once each step is approved, then <code>/review</code> checks the change and gives its verdict. Waiting is shortened; nothing else is changed. <a href="docs/assets/demo-coding.png">Still</a> · <a href="scripts/record_demo.py">Recorder</a> · <a href="scripts/render_demo.py">Renderer</a></sub></p>
+
+## What Aria Code does
+
+**Writes code and builds projects.** Describe the task in plain words. Aria reads the project, writes and edits files, runs commands and tests, and shows every change before it lands — nothing is written or run until you say yes. [`/review`](docs/code-review.md) reviews a change the way a careful colleague would: prioritised findings (P0–P3) with file and line, and a verdict; `aria-code review --base main --fail-on P1` gates a pull request in CI. Use a local Ollama model, Gemini on Google Cloud (Vertex AI, with nothing more than a `gcloud` login), or another supported provider.
+
+**Analyses markets and finances.** Quotes, technical indicators, backtests with an HTML report, risk and factor analysis, SEC filings, and US, Hong Kong, A-share and crypto data. Results name their data source, period and any gaps.
+
+<p align="center"><img src="docs/assets/demo-finance.gif" alt="Real Aria Code session: technical indicators for AAPL and a one-year momentum backtest on SPY, with data source, period and completeness stated" width="760"></p>
+
+**Runs logistics operations.** For third-party logistics: reorder points, safety stock, ABC/XYZ classes, dead stock, carrier scorecards and freight anomalies — and in Feishu, a daily digest per shipper with approval cards.
+
+<p align="center"><img src="docs/assets/demo-logistics.gif" alt="Real Aria Code session: a refusal to mix two shippers' data, reorder points for one shipper, and a carrier scorecard with a saving and two anomalies" width="760"></p>
+<p align="center"><sub>Both recorded from real sessions — market data from yfinance; the logistics data is the sample 3PL in <code>evals/fixtures</code>, with no model call.</sub></p>
+
+## How it works
+
+A general-purpose assistant aims for an answer that reads well. In code, markets and warehouses the result gets acted on — a rounding rule in a currency function, one purchase order left out of a reorder quantity. Three rules follow from that.
+
+**Numbers you can check.** Reorder points, safety stock, carrier rankings and backtests come from stated formulas and named data, with the formula and every assumption in the result — as does stablecoin settlement reconciliation, from the [Artheras skills](https://github.com/artheras/skills) Aria Code can install. When the data cannot support an answer — under 14 days of demand history, rows that name no shipper — it says so instead of estimating. The [`operations` eval suite](docs/verifiable-evals.md) checks exactly these traps.
+
+**Client data kept apart.** A third-party logistics provider holds many clients' stock side by side. A chat group bound to one shipper confines every analysis to that shipper, and the logistics tools themselves refuse another shipper's data or an unattributable file — the rule holds below the prompt, whatever the model asks for.
+
+**Actions a person approves.** In the terminal, every file write and command waits for your yes, with the diff in front of you. In Feishu, `/补货` turns the reorder list into a purchase-order draft card; nothing happens until an authorised approver presses approve, and what runs is exactly what was shown. The draft is a file for your own purchasing system — Aria Code places no orders.
+
+A fresh install has no live business data: the logistics tools read your exports (CSV or JSON), market data comes from public sources, and the chat features need a Feishu app or the Aria relay.
+
+## Quick start
+
+Install the standalone CLI on macOS or Linux without Python, Node.js, or npm:
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/artheras/aria-code/main/scripts/install.sh | sh
+~/.local/bin/aria
+```
+
+On Windows x64, run this in PowerShell:
+
+```powershell
+irm https://raw.githubusercontent.com/artheras/aria-code/main/scripts/install.ps1 | iex
+aria
+```
+
+The installer downloads the binary for your OS from the latest [GitHub release](https://github.com/artheras/aria-code/releases/latest), checks its SHA-256 digest, and installs it in your user account. Open a new terminal to start the interactive CLI with `aria`, `aria code`, or `aria-code`. Set `ARIA_CODE_VERSION=v0.55.0` to pin a release.
+
+Alternative package-manager installs: `npm install -g @artheras/aria-code` (requires npm) or `python3 -m pip install --upgrade "aria-code<4"` (requires Python 3.10+; the `<4` skips an older 4.x numbering that PyPI still lists). For development from source, see [CONTRIBUTING.md](CONTRIBUTING.md).
+
+### Updates
+
+Aria checks for a newer stable version in the background at startup, at most once per day. Cached notices appear immediately; network checks never delay the prompt. It checks GitHub Releases, or scoped npm for npm installs. Pip updates pin the GitHub version and verify that version is available on PyPI, avoiding the older 4.x numbering still listed as PyPI's latest. Source checkouts receive Git update instructions.
+
+```bash
+aria update --check  # check without installing
+aria update          # install the newest stable version for this install channel
+```
+
+In an interactive session, use `/update --check` or `/update`, then restart Aria. Native updates verify SHA-256 and the downloaded binary's version before switching the command; a failed download or verification leaves the existing command in place. Startup checks only notify. To disable them, set `check_for_update_on_startup` to `false` in `~/.aria-code/config.json`.
+
+For GitHub notifications, open [this repository](https://github.com/artheras/aria-code), select **Watch → Custom → Releases**, and save. Notifications follow your GitHub notification settings. Published stable releases appear on the [release page](https://github.com/artheras/aria-code/releases/latest) once the platform assets and package publishing have completed.
+
+To use a local model, install [Ollama](https://ollama.com/download), pull a coding model, and start Aria in local-only mode:
+
+```bash
+ollama pull qwen2.5-coder:7b
+aria-code --local
+```
+
+Or run a single task in an existing project:
+
+```bash
+aria-code -p "Inspect this project, fix the failing tests, run them, and summarize the diff."
+```
+
+Aria may request approval before editing files or running commands, according to the configured permission mode. Review changes and test results before committing them.
+
+## Models and accounts
+
+| Route | What it needs |
+| --- | --- |
+| Local Ollama | An installed and running Ollama model; no cloud account for local inference. |
+| Direct cloud provider | That provider's API credentials and network access. |
+| Direct Google Cloud Vertex AI | `GOOGLE_CLOUD_PROJECT` and either a `gcloud auth login` (Aria uses Vertex AI's OpenAI-compatible endpoint with that login's token) or Application Default Credentials with `aria-code[google]`. `GOOGLE_CLOUD_LOCATION` defaults to `global`. |
+| Arthera hosted service | Install `aria-code[google]` and sign in through `/login` in the CLI. Arthera account sign-in does not grant Vertex AI credentials to your own machine. |
+
+Install extras only for features you use; see [pyproject.toml](pyproject.toml) for the current package options. Local inference can work offline, but live market data, remote integrations, sign-in, and cloud models cannot.
+
+## Explore the project
+
+| Topic | Start here |
+| --- | --- |
+| Architecture and runtime | [Architecture](docs/architecture.md) |
+| Tool permissions and data boundaries | [Safety notes](docs/aria-code-safety.md) |
+| Warehouse agents and their read-only data contract | [Warehouse ERP agents](docs/warehouse-erp-agents.md) |
+| Strategy and backtesting workflows | [Strategy workspace](docs/strategy_workspace.md) |
+| More examples | [Examples](examples/README.md) |
+| Releases and changes | [Changelog](CHANGELOG.md) |
+
+For the current command-line flags, run `aria-code --help`. For help inside the interactive CLI, run `/help`. These are preferable to a copied command inventory that can drift from the product.
+
+## Contributing and license
+
+Contributions are welcome; see [CONTRIBUTING.md](CONTRIBUTING.md). Aria Code is open source under the [Apache License, Version 2.0](LICENSE).
+
+Releases 4.2.0 through 4.4.5 were published under the Business Source License 1.1 and remain available under those terms; releases up to and including 4.1.2 were MIT. A license grant cannot be withdrawn from someone who already has it, so each version keeps the license it shipped with — see [NOTICE](NOTICE).

{aria_code-0.76.0 → aria_code-0.78.0}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "aria-code"
-version = "0.76.0"
-description = "Open-source AI agent for logistics and finance work: numbers you can check, client data kept apart, actions a person approves"
+version = "0.78.0"
+description = "Open-source AI agent for coding, financial analysis and logistics operations: numbers you can check, client data kept apart, actions a person approves"
 readme = "README.md"
 license = { text = "Apache-2.0" }
 # Upper bound is real, not defensive: the core dep pandas_ta pulls numba, and

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/_version.py

@@ -17,4 +17,4 @@ from __future__ import annotations
 
 __all__ = ["__version__"]
 
-__version__ = "0.76.0"
+__version__ = "0.78.0"

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/bootstrap.py

@@ -58,6 +58,33 @@ def disable_broken_proxy(timeout: float = 1.5) -> None:
             os.environ.pop(name, None)
 
 
+_LOOPBACK = ("localhost", "127.0.0.1", "::1")
+
+
+def ensure_loopback_bypasses_proxy() -> None:
+    """With a proxy set, keep local services (Ollama, LM Studio, the API) off it.
+
+    HTTP clients honour HTTP(S)_PROXY, so a machine with a system proxy and no
+    NO_PROXY would send requests for localhost:11434 to the proxy and fail.
+    """
+    if not any(os.environ.get(name) for name in ("HTTP_PROXY", "HTTPS_PROXY", "http_proxy", "https_proxy",
+                                                 "ALL_PROXY", "all_proxy")):
+        return
+    current = os.environ.get("NO_PROXY") or os.environ.get("no_proxy") or ""
+    entries = [item.strip() for item in current.split(",") if item.strip()]
+    missing = [host for host in _LOOPBACK if host not in entries]
+    if missing:
+        value = ",".join(entries + missing)
+        os.environ["NO_PROXY"] = value
+        os.environ["no_proxy"] = value
+
+
+def prepare_network() -> None:
+    """Proxy settings every entry point needs before its first request."""
+    disable_broken_proxy()
+    ensure_loopback_bypasses_proxy()
+
+
 def use_system_trust_store() -> bool:
     """Verify TLS against the OS trust store instead of certifi's bundle.
 
@@ -105,7 +132,7 @@ def use_macos_ca_bundle() -> bool:
 def initialize_cli_environment() -> None:
     os.environ.setdefault("TQDM_DISABLE", "1")
     load_aria_env()
-    disable_broken_proxy()
+    prepare_network()
     if not use_system_trust_store():
         use_macos_ca_bundle()
 

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/commands/auth_cmds.py

@@ -99,7 +99,7 @@ class AuthCommandsMixin:
             self.context.console.print("[dim]Authenticating...[/dim]")
 
         try:
-            async with aiohttp.ClientSession() as session:
+            async with aiohttp.ClientSession(trust_env=True) as session:
                 async with session.post(
                     f"{self.terminal.api_url}/auth/login",
                     json={"email": email, "password": password},

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/commands/backtest_cmds.py

@@ -81,11 +81,15 @@ def _bt_volume_summary(data: dict) -> dict:
     return summary if isinstance(summary, dict) else {}
 
 
-def _bt_result_summary(data: dict) -> str:
+def _bt_result_summary(data: dict, lang: str = "zh") -> str:
     total = _bt_num(data.get("total_return"))
     benchmark = _bt_num(_bt_value(data, "buy_hold_return", "benchmark_return", default=0))
     sharpe = _bt_num(data.get("sharpe_ratio"))
     max_dd = _bt_num(data.get("max_drawdown"))
+    if not str(lang).lower().startswith("zh"):
+        relation = "above" if total > benchmark else "below" if total < benchmark else "level with"
+        return (f"Result: the strategy returned {_bt_pct(total)}, {relation} buy-and-hold at {_bt_pct(benchmark)}; "
+                f"Sharpe {sharpe:.2f}, max drawdown {_bt_pct(max_dd)}.")
     relation = "高于" if total > benchmark else "低于" if total < benchmark else "持平"
     return (
         f"结论：策略收益 {_bt_pct(total)}，{relation}买入持有 {_bt_pct(benchmark)}；"
@@ -475,7 +479,7 @@ class BacktestCommandsMixin:
                 "include_monte_carlo": False,
             }
             try:
-                async with aiohttp.ClientSession() as sess:
+                async with aiohttp.ClientSession(trust_env=True) as sess:
                     async with sess.post(f"{api_url}/api/v1/backtest", json=payload, timeout=aiohttp.ClientTimeout(total=60)) as resp:
                         if resp.status == 200:
                             body = await resp.json()
@@ -542,7 +546,8 @@ class BacktestCommandsMixin:
                 for r in rows:
                     tbl.add_row(*r)
                 self.context.console.print(tbl)
-                self.context.console.print(f"  [bold]{self._bt_result_summary(d)}[/bold]")
+                self.context.console.print(
+                    f"  [bold]{self._bt_result_summary(d, lang=self.terminal.config.get('ui_lang', 'en') or 'en')}[/bold]")
 
                 actual_start = self._bt_value(d, "start", "start_date", default=start_date)
                 actual_end = self._bt_value(d, "end", "end_date", default=end_date)
@@ -579,7 +584,11 @@ class BacktestCommandsMixin:
                         else "  [#57606a]volume:[/#57606a] unavailable"
                     )
                 if d.get("report_path"):
-                    self.context.console.print(f"  [#57606a]report:[/#57606a] {d['report_path']}")
+                    _report = str(d["report_path"])
+                    _home = str(pathlib.Path.home())
+                    if _report.startswith(_home + os.sep):
+                        _report = "~" + _report[len(_home):]
+                    self.context.console.print(f"  [#57606a]report:[/#57606a] {_report}")
                 if trades == 0:
                     self.context.console.print(
                         "  [yellow]注意:[/yellow] # Trades 为 0，表示本次规则没有触发入场；"
@@ -675,7 +684,7 @@ class BacktestCommandsMixin:
                 "end_date": __import__("datetime").date.today().isoformat(),
                 "train_period_days": 252, "test_period_days": 63, "step_days": 21,
             }
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.post(f"{api_url}/api/v1/backtest/walk-forward", json=payload, timeout=aiohttp.ClientTimeout(total=90)) as resp:
                     if resp.status != 200:
                         raise RuntimeError(f"HTTP {resp.status}")

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/commands/business_workflow_cmds.py

@@ -61,7 +61,7 @@ class BusinessWorkflowCommandsMixin:
         api_url = self.terminal.config.get("api_url", "http://localhost:8000")
         try:
             import aiohttp
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.get(
                     f"{api_url}/api/realty/assets/{asset_id}",
                     timeout=aiohttp.ClientTimeout(total=5)
@@ -128,7 +128,7 @@ class BusinessWorkflowCommandsMixin:
         rules = {}
         try:
             import aiohttp
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.get(f"{api_url}/api/realty/contracts/{project_id}",
                                     timeout=aiohttp.ClientTimeout(total=5)) as resp:
                     if resp.status == 200:
@@ -153,7 +153,7 @@ class BusinessWorkflowCommandsMixin:
         api_url = self.terminal.config.get("api_url", "http://localhost:8000")
         try:
             import aiohttp
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.get(
                     f"{api_url}/api/realty/risks/scan/{project_id}",
                     timeout=aiohttp.ClientTimeout(total=10)
@@ -174,7 +174,7 @@ class BusinessWorkflowCommandsMixin:
         marketing_data = {}
         try:
             import aiohttp
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.get(
                     f"{api_url}/api/realty/assets/{project_id}",
                     timeout=aiohttp.ClientTimeout(total=5)
@@ -224,7 +224,7 @@ class BusinessWorkflowCommandsMixin:
                       "prepayment_received": 0, "renovation_cost": 0}
         try:
             import aiohttp
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.get(
                     f"{api_url}/api/realty/contracts/{project_id}",
                     timeout=aiohttp.ClientTimeout(total=5)

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/commands/core_cmds.py

@@ -39,6 +39,12 @@ from typing import Dict, Any, Optional
 
 
 class CoreCommandsMixin:
+    async def cmd_update(self, args: str):
+        """Use the same updater from the REPL and the shell."""
+        from aria_code.apps.cli.updater import main
+
+        await asyncio.to_thread(main, shlex.split(args))
+
     def _cmd_rewind_unavailable(self, args: str):
         # cmd_rewind lands with the checkpoint store (runtime/checkpoints.py,
         # still a separate, uncommitted change) — degrade instead of crashing
@@ -194,7 +200,7 @@ class CoreCommandsMixin:
                 ("Session", ["/help","/clear","/compact","/cost","/status","/health",
                              "/regen","/undo","/rewind","/copy","/recap","/btw",
                              "/save","/load","/sessions","/export","/export-pdf"]),
-                ("Config",  ["/model","/thinking","/config","/privacy","/local",
+                ("Config",  ["/model","/thinking","/config","/privacy","/local","/update",
                              "/setup","/apikey","/doctor","/mcp"]),
                 ("Data",    ["/alert","/journal","/watch","/note","/todo","/memory",
                              "/artifacts","/strategy","/accuracy"]),
@@ -869,15 +875,11 @@ class CoreCommandsMixin:
         else:
             print(f"Generating: {description}")
 
-        # Use best available model for code gen
-        original_model = self.terminal.config.get("model", "qwen2.5:7b")
-        self.terminal.config["model"] = "qwen2.5:7b"
-
+        # The configured model writes the code. This used to switch to
+        # qwen2.5:7b for the call, whatever the user had chosen — a Gemini or
+        # Claude user got a small local model, or an error without Ollama.
         await self.terminal.send_message(prompt)
 
-        # Restore model
-        self.terminal.config["model"] = original_model
-
         # Extract code from last AI response and save if requested
         if save_path or description:
             last_response = ""
@@ -986,7 +988,7 @@ class CoreCommandsMixin:
                     "response_id":   self.terminal.session_id,  # latest-in-session match
                     "value":         comment or None,
                 }
-                async with aiohttp.ClientSession() as session:
+                async with aiohttp.ClientSession(trust_env=True) as session:
                     async with session.post(
                         f"{self.terminal.api_url}/feedback",
                         json=payload,
@@ -2322,13 +2324,15 @@ class CoreCommandsMixin:
         from aria_cli import _generate_chart_sync, parse_technical_args, print_ta_result
         from aria_code.ui.render.output import display_path as _display_path
         from aria_code.apps.cli.helpers import _chart_period_from_ta_days, _display_value
+        zh = str(self.terminal.config.get("ui_lang", "en")).lower().startswith("zh")
+        T = (lambda zh_text, en_text: zh_text) if zh else (lambda zh_text, en_text: en_text)
         parsed = parse_technical_args(args)
         symbol = parsed.symbol
         days = parsed.days
 
         service_result = None
         if self.context.has_rich:
-            with self.context.console.status(f"[dim]计算 {symbol} 技术指标...[/dim]", spinner="dots"):
+            with self.context.console.status(f"[dim]{T(f'计算 {symbol} 技术指标', f'Calculating {symbol} indicators')}...[/dim]", spinner="dots"):
                 from packages.aria_services.data import DataService
                 service_result = DataService().technical_indicators(symbol, days=days)
         else:
@@ -2343,16 +2347,19 @@ class CoreCommandsMixin:
             # Show current price when we have partial data (e.g. new IPO with 1 bar)
             _price_line = ""
             if _ta_data.get("price"):
-                _price_line = f"  当前价格  [bold]{_display_value(_ta_data['price'])}[/bold]"
+                _price_line = f"  {T('当前价格', 'Price')}  [bold]{_display_value(_ta_data['price'])}[/bold]"
                 if _ta_data.get("history_bars"):
-                    _price_line += f"  [dim]({_ta_data['history_bars']} 个交易日数据)[/dim]"
+                    _price_line += f"  [dim]({_ta_data['history_bars']} {T('个交易日数据', 'trading days of data')})[/dim]"
                 _price_line += "\n"
             if "数据不足" in _all_msgs or "新上市" in _all_msgs:
-                _reason = f"[yellow]历史数据不足[/yellow] — {symbol} 上市时间较短（< 14 个交易日），TA 指标无法计算\n  [dim]可待更多交易日积累后重试，或运行 `/analyze {symbol}` 查看基本面[/dim]"
+                _reason = T(
+                    f"[yellow]历史数据不足[/yellow] — {symbol} 上市时间较短（< 14 个交易日），TA 指标无法计算\n  [dim]可待更多交易日积累后重试，或运行 `/analyze {symbol}` 查看基本面[/dim]",
+                    f"[yellow]Not enough history[/yellow] — {symbol} has fewer than 14 trading days, so indicators cannot be computed\n  [dim]Try again later, or run `/analyze {symbol}` for fundamentals[/dim]")
             elif "rate" in _all_msgs or "429" in _all_msgs or "too many" in _all_msgs:
-                _reason = "[yellow]数据源频率限制[/yellow] — 稍后重试，或用 `/apikey set finnhub <KEY>` 切换数据源"
+                _reason = T("[yellow]数据源频率限制[/yellow] — 稍后重试，或用 `/apikey set finnhub <KEY>` 切换数据源",
+                            "[yellow]Rate-limited by the data source[/yellow] — retry later, or switch sources with `/apikey set finnhub <KEY>`")
             else:
-                _err = "; ".join(_ta_errs or _ta_warns) or "数据源暂时不可用"
+                _err = "; ".join(_ta_errs or _ta_warns) or T("数据源暂时不可用", "data source temporarily unavailable")
                 _reason = f"[red]{_err[:120]}[/red]"
                 if _missing:
                     _reason += f"  [dim]missing: {_missing}[/dim]"
@@ -2372,6 +2379,7 @@ class CoreCommandsMixin:
             days=days,
             service_result=service_result,
             formatter=_display_value,
+            lang="zh" if zh else "en",
         )
 
         period = _chart_period_from_ta_days(days)
@@ -2383,12 +2391,12 @@ class CoreCommandsMixin:
         }
         chart_result = None
         if self.context.has_rich:
-            with self.context.console.status(f"[dim]生成 {symbol} 技术图表 HTML/PNG...[/dim]", spinner="dots"):
+            with self.context.console.status(f"[dim]{T(f'生成 {symbol} 技术图表', f'Drawing the {symbol} chart')} HTML/PNG...[/dim]", spinner="dots"):
                 chart_result = await asyncio.get_event_loop().run_in_executor(
                     None, lambda: _generate_chart_sync(symbol, period=period)
                 )
         else:
-            print(f"  生成 {symbol} 技术图表 HTML/PNG...")
+            print(f"  {T(f'生成 {symbol} 技术图表', f'Drawing the {symbol} chart')} HTML/PNG...")
             chart_result = await asyncio.get_event_loop().run_in_executor(
                 None, lambda: _generate_chart_sync(symbol, period=period)
             )
@@ -2407,27 +2415,27 @@ class CoreCommandsMixin:
             }
             if self.context.has_rich:
                 self.context.console.print()
-                self.context.console.print("  [green]✓[/green] 技术图表已生成")
+                self.context.console.print(f"  [green]✓[/green] {T('技术图表已生成', 'Chart saved')}")
                 if html_path:
                     self.context.console.print(f"  [dim]HTML:[/dim] [link={html_path}]{_display_path(html_path)}[/link]")
                 if png_path:
                     self.context.console.print(f"  [dim]PNG :[/dim] [link={png_path}]{_display_path(png_path)}[/link]")
                 elif png_error:
-                    self.context.console.print(f"  [yellow]PNG 跳过:[/yellow] {png_error[:90]}")
+                    self.context.console.print(f"  [yellow]{T('PNG 跳过', 'PNG skipped')}:[/yellow] {png_error[:90]}")
             else:
-                print("\n  技术图表已生成")
+                print(f"\n  {T('技术图表已生成', 'Chart saved')}")
                 if html_path:
                     print(f"  HTML: {_display_path(html_path)}")
                 if png_path:
                     print(f"  PNG : {_display_path(png_path)}")
                 elif png_error:
-                    print(f"  PNG 跳过: {png_error[:90]}")
+                    print(f"  {T('PNG 跳过', 'PNG skipped')}: {png_error[:90]}")
         elif chart_result:
-            err = chart_result.get("error") or "图表生成失败"
+            err = chart_result.get("error") or T("图表生成失败", "chart failed")
             if self.context.has_rich:
-                self.context.console.print(f"  [yellow]图表生成跳过:[/yellow] {err[:120]}")
+                self.context.console.print(f"  [yellow]{T('图表生成跳过', 'Chart skipped')}:[/yellow] {err[:120]}")
             else:
-                print(f"  图表生成跳过: {err[:120]}")
+                print(f"  {T('图表生成跳过', 'Chart skipped')}: {err[:120]}")
     def _extract_last_code(self) -> str:
         """从对话历史中提取最后一段 Python 代码块."""
         import re

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/commands/data_cmds.py

@@ -356,7 +356,7 @@ class DataCommandsMixin:
         async def _do():
             payload = {"symbol": symbol, "strategies": _STRATS,
                        "start_date": start, "end_date": end, "initial_capital": 100000, "commission_rate": 0.0003}
-            async with aiohttp.ClientSession() as sess:
+            async with aiohttp.ClientSession(trust_env=True) as sess:
                 async with sess.post(f"{api_url}/api/v1/backtest/compare-strategies", json=payload, timeout=aiohttp.ClientTimeout(total=90)) as resp:
                     if resp.status != 200:
                         raise RuntimeError(f"HTTP {resp.status}")

{aria_code-0.76.0 → aria_code-0.78.0}/src/aria_code/apps/cli/commands/diagnostic_cmds.py

@@ -238,7 +238,7 @@ class DiagnosticCommandsMixin:
                 print(f"  ? {message}")
         for label, url, path in urls:
             try:
-                async with aiohttp.ClientSession() as session:
+                async with aiohttp.ClientSession(trust_env=True) as session:
                     async with session.get(f"{str(url).rstrip('/')}{path}", timeout=aiohttp.ClientTimeout(total=5)) as resp:
                         resp.raise_for_status()
                         data = await resp.json()