crewforge 0.2.1__tar.gz → 0.3.0__tar.gz

{crewforge-0.2.1/src/crewforge.egg-info → crewforge-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crewforge
-Version: 0.2.1
+Version: 0.3.0
 Summary: One crew of LLM agents, five recipes: code review, document Q&A, API scaffolding, content and honest academic-writing help — on any OpenAI-compatible provider.
 Author: Muhammad Aiman
 License-Expression: MIT
@@ -56,15 +56,21 @@ Requires-Dist: fastapi>=0.110; extra == "dev"
 Requires-Dist: httpx>=0.27; extra == "dev"
 Dynamic: license-file
 
-# crewforge
+<p align="center"><img src="https://raw.githubusercontent.com/aimanmalib/crewforge/main/brand/logo-512.png" width="112" height="112" alt="crewforge"></p>
 
-**One crew of LLM agents, five recipes — code review, document Q&A, API scaffolding, content and honest academic-writing help — on any OpenAI-compatible provider, and it fails loudly instead of pretending.**
+<h1 align="center">crewforge</h1>
 
-[![CI](https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml/badge.svg)](https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml)
-[![PyPI](https://img.shields.io/pypi/v/crewforge)](https://pypi.org/project/crewforge/)
-[![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/aimanmalib/crewforge/badge)](https://scorecard.dev/viewer/?uri=github.com/aimanmalib/crewforge)
-![Python 3.10–3.14](https://img.shields.io/badge/python-3.10%E2%80%933.14-blue)
-![License: MIT](https://img.shields.io/badge/license-MIT-green)
+<p align="center"><a href="https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml"><img src="https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://pypi.org/project/crewforge/"><img src="https://img.shields.io/pypi/v/crewforge" alt="PyPI"></a> <a href="https://scorecard.dev/viewer/?uri=github.com/aimanmalib/crewforge"><img src="https://api.scorecard.dev/projects/github.com/aimanmalib/crewforge/badge" alt="OpenSSF Scorecard"></a> <img src="https://img.shields.io/badge/python-3.10%E2%80%933.14-blue" alt="Python 3.10–3.14"> <a href="https://github.com/aimanmalib/crewforge/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="License: MIT"></a></p>
+
+<p align="center"><b>One crew of LLM agents, five recipes, any OpenAI-compatible provider.</b> · <i>Satu kru ejen LLM, lima resipi, mana-mana penyedia serasi OpenAI.</i><br>
+<a href="https://pypi.org/project/crewforge/">PyPI</a> · <a href="https://github.com/aimanmalib/crewforge/blob/main/CHANGELOG.md">changelog</a> · <a href="https://github.com/aimanmalib/crewforge/blob/main/docs/porting.md">porting notes</a> · Built in Malaysia by <a href="https://aimanmalib.com">Aiman Malib</a></p>
+
+crewforge is a command-line tool and Python library that runs a crew of LLM agents through five recipes: code
+review, document Q&A, API scaffolding, content writing and honest academic-writing help. It works with any
+OpenAI-compatible provider, reads API keys only from the environment, and fails loudly instead of pretending: a run
+in which an agent produced nothing exits with code 1 and names that agent.
+
+[Bahasa Melayu ↓](#bahasa-melayu)
 
 ```bash
 crewforge review src/                                  # six reviewers + a summary
@@ -81,7 +87,7 @@ crewforge academic feedback draft.md --brief brief.md --language ms
 
 ## Why one crew, many recipes
 
-crewforge started as four separate command-line tools —
+crewforge started as four separate command-line tools:
 [codeguard](https://github.com/aimanmalib/codeguard),
 [documind](https://github.com/aimanmalib/documind),
 [apiforge](https://github.com/aimanmalib/apiforge) and
@@ -95,7 +101,7 @@ showed the copies had drifted and that each hid its failures differently:
 - apiforge scored a spec with **no endpoints** 100/100;
 - contentforge wrote the real API key into its YAML file, and sent `${OPENAI_API_KEY}` literally as the key.
 
-crewforge keeps one core — so a fix lands once — and turns each tool into a
+crewforge keeps one core, so a fix lands once, and turns each tool into a
 *recipe*: a set of agents plus the steps that connect them. The same core rules
 apply to every recipe: non-streaming requests, bounded retries, usage numbers
 taken only from the provider, keys only from the environment, and no run that
@@ -139,7 +145,7 @@ tables are trimmed to their totals.
 
 | Command | Agents | What you get |
 |---|---|---|
-| `review PATH` | security, style, complexity, logic, testing, documentation (parallel) → summary | Findings by severity, a decision and a score; `-f json` for CI |
+| `review PATH` | security, style, complexity, logic, testing, documentation (parallel) → summary | Findings by severity, a decision and a score; `-f json` for CI, `-f sarif` for GitHub code scanning |
 | `ingest FILES` | ingester, indexer (no LLM) | How each file was parsed and chunked |
 | `ask FILES -q Q [--verify] [--rerank]` | retriever → answerer → fact-checker | An answer with `[Source N]` citations and a claim-by-claim verdict |
 | `summarize FILES` | summarizer | Summary and key points per document |
@@ -171,6 +177,30 @@ $ crewforge review app.py -f markdown -o review.md      # app.py builds SQL with
 total   7 calls   22,366 tokens (provider-reported)
 ```
 
+`-f sarif` writes a [Static Analysis Results Interchange Format 2.1.0](https://docs.oasis-open.org/sarif/sarif/v2.1.0/sarif-v2.1.0.html)
+log (`sarif`), the format GitHub code scanning reads, so findings can appear in a repository's Security tab. Each finding becomes one
+result: `critical` and `error` map to level `error`, `warning` to `warning`, `info` to `note`; the rule is the
+finding's CWE when it has one, otherwise the reviewer's name. When you review a directory, the line a reviewer
+reports is mapped back to the file it came from. A finding whose line is missing or outside the code points at the
+reviewed path without a line. Reviewers that fail are listed in `invocations`, and the exit code is the same as for
+the other formats.
+
+```yaml
+# .github/workflows/review.yml (needs an API key secret, e.g. OPENAI_API_KEY)
+permissions:
+  contents: read
+  security-events: write
+steps:
+  - uses: actions/checkout@v4
+  - run: pipx run crewforge review src/ -f sarif -o crewforge.sarif
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  - uses: github/codeql-action/upload-sarif@v3
+    if: always()
+    with:
+      sarif_file: crewforge.sarif
+```
+
 ### `ask` and `summarize`
 
 <p align="center">
@@ -290,13 +320,13 @@ Saya menggunakan crewforge academic (versi 0.1.0), sebuah alat berbantukan AI, d
 - 22 Oktober 2026: Perancangan: alat ini menukar taklimat tugasan (brief-ms.md) kepada 3 soalan kajian, rangka 5 bahagian dan peruntukan perkataan. ...
 ```
 
-How sources are labelled — there is no "verified" status, because the tool
+How sources are labelled: there is no "verified" status, because the tool
 cannot check that a source exists:
 
 | Source | Label |
 |---|---|
 | You supplied it | *supplied by you (not checked online)* |
-| The model proposed it, with a DOI, URL or valid ISBN | **UNVERIFIED** — check it |
+| The model proposed it, with a DOI, URL or valid ISBN | **UNVERIFIED**: check it |
 | The model proposed it with none of those | **LIKELY FABRICATED** |
 | The model added a DOI/URL/ISBN to a reference you supplied | **UNVERIFIED**, naming the added identifier |
 
@@ -335,16 +365,16 @@ An unknown provider name is a configuration error, not a silent fallback.
 
 <sub>Source: [docs/architecture.mmd](https://github.com/aimanmalib/crewforge/blob/main/docs/architecture.mmd) (re-render with `scripts/render_architecture.py`).</sub>
 
-- **`core/client.py`** — one async client. It always sends `"stream": false`,
+- **`core/client.py`**: one async client. It always sends `"stream": false`,
   retries only HTTP 429, 5xx and network/timeout errors (with capped exponential
   backoff that honours `Retry-After`), and fails on the first 401/403/4xx with a
   message naming the variable to fix. The key is only ever a request header.
-- **`core/agent.py`** — an agent is a role, a system prompt and per-agent
+- **`core/agent.py`**: an agent is a role, a system prompt and per-agent
   sampling defaults. `ask()` records usage and raises if the reply is blank;
   `ask_json()` additionally requires parseable JSON (optionally a pydantic schema).
-- **`core/crew.py`** — runs agents as sequential steps or parallel stages and
+- **`core/crew.py`**: runs agents as sequential steps or parallel stages and
   turns any failure into a `CrewFailedError` that lists every failed agent.
-- **`core/usage.py`** — per-agent calls, tokens, retries and latency, taken from
+- **`core/usage.py`**: per-agent calls, tokens, retries and latency, taken from
   the provider's `usage` object. Calls without usage are counted as "not reported",
   never estimated.
 
@@ -409,10 +439,10 @@ watching them fail; see [docs/porting.md](https://github.com/aimanmalib/crewforg
 
 crewforge was built with AI coding assistance (Claude Code) under the
 direction of its author, Muhammad Aiman. It consolidates four earlier tools by
-the same author — [codeguard](https://github.com/aimanmalib/codeguard),
+the same author ([codeguard](https://github.com/aimanmalib/codeguard),
 [documind](https://github.com/aimanmalib/documind),
 [apiforge](https://github.com/aimanmalib/apiforge) and
-[contentforge](https://github.com/aimanmalib/contentforge) — whose test suites
+[contentforge](https://github.com/aimanmalib/contentforge)), whose test suites
 were carried over into this repository (see [docs/porting.md](https://github.com/aimanmalib/crewforge/blob/main/docs/porting.md)
 for what was ported, re-targeted at the shared core, or dropped and why).
 
@@ -435,10 +465,56 @@ Please report vulnerabilities privately through
 See [SECURITY.md](https://github.com/aimanmalib/crewforge/blob/main/SECURITY.md) for scope notes (what is sent to your provider,
 and what `validate` executes).
 
-## License
+## Bahasa Melayu
+
+crewforge ialah alat baris arahan dan pustaka Python yang menjalankan satu kru ejen LLM melalui lima resipi:
+semakan kod (`review`), soal jawab dokumen (`ask`, `summarize`), penjanaan projek API FastAPI (`scaffold`,
+`validate`), penulisan kandungan (`write`) dan bantuan penulisan akademik yang jujur (`academic`). Ia berfungsi
+dengan mana-mana penyedia serasi OpenAI, termasuk model tempatan melalui Ollama atau llama.cpp. Kunci API hanya
+dibaca dari pemboleh ubah persekitaran, tidak pernah ditulis ke fail.
+
+**Mengapa satu kru.** crewforge menggabungkan empat alat lama (codeguard, documind, apiforge, contentforge) yang
+masing-masing menyimpan salinan sendiri bagi rangka yang sama. Salinan itu sudah berbeza dan setiap satu
+menyembunyikan kegagalan dengan cara sendiri. Kini teras dikongsi: pembaikan dibuat sekali, dan setiap alat menjadi
+resipi di atas teras itu.
+
+**Gagal dengan jelas.** Larian yang ejennya memulangkan jawapan kosong atau tidak boleh dihurai, atau pengesah
+yang tidak menyemak apa-apa, keluar dengan kod 1 dan menamakan ejen itu. Kod keluar: `0` berjaya, `1` larian
+gagal, `2` ralat penggunaan atau konfigurasi. Bilangan token diambil daripada laporan penyedia sahaja, tidak
+dianggar.
+
+**Resipi `academic`.** Membantu pelajar dan penyelidik dengan kerja mereka **sendiri**: merancang dari taklimat
+tugasan, memberi ulasan atas draf tanpa menulis semula, memformat rujukan yang diberi pengguna (APA 7, IEEE,
+Harvard) tanpa menambah rujukan baharu, dan menulis pernyataan penggunaan AI daripada rekod langkah yang
+dijalankan. Output dalam bahasa Inggeris atau Bahasa Melayu (`--language ms`); output BM disemak untuk bentuk
+Indonesia seperti *karena* atau *kualitas*. Sumber yang dicadangkan model dilabel UNVERIFIED, atau LIKELY
+FABRICATED jika tiada DOI, URL atau ISBN. Tiada ciri "humanise" atau mengelak pengesan AI.
+
+**Pasang dan guna.**
+
+```bash
+pip install crewforge                 # Python 3.10 hingga 3.14
+pip install "crewforge[docs,api]"     # pilihan: PDF/DOCX dan semakan aplikasi FastAPI
+export OPENAI_API_KEY=sk-...          # atau penyedia lain, lihat `crewforge providers`
+crewforge review src/
+crewforge review src/ -f sarif -o crewforge.sarif   # untuk GitHub code scanning
+crewforge academic feedback draf.md --brief taklimat.md --language ms
+```
+
+`review -f sarif` menulis laporan `SARIF` 2.1.0 yang dibaca GitHub code scanning: setiap dapatan menjadi satu
+keputusan dalam tab Security, dan baris dalam semakan folder dipetakan kembali ke fail asalnya.
+
+Senarai penyedia, contoh setiap resipi dan seni bina ada dalam bahagian bahasa Inggeris di atas
+([Providers](https://github.com/aimanmalib/crewforge#providers), [Recipes](https://github.com/aimanmalib/crewforge#recipes)).
+
+## Licence
+
+[MIT](https://github.com/aimanmalib/crewforge/blob/main/LICENSE) © Muhammad Aiman. Made by [Aiman Malib](https://aimanmalib.com), Malaysia.
+
+## Work with Sasa Teguh
 
-[MIT](https://github.com/aimanmalib/crewforge/blob/main/LICENSE) © Muhammad Aiman
+[![Work with Sasa Teguh: book a call](https://raw.githubusercontent.com/sasateguh/.github/main/assets/work-with-sasa-teguh.png)](https://sasateguh.com/book)
 
----
+I built this project. I run [Sasa Teguh](https://sasateguh.com), a studio in Malaysia that builds websites found on Google and in AI answers, and sets up systems like this one for businesses.
 
-Built by [Sasa Teguh](https://sasateguh.com) · Malaysia
+[Book a call](https://sasateguh.com/book) · hello@sasateguh.com · [More from Sasa Teguh](https://github.com/sasateguh)

{crewforge-0.2.1 → crewforge-0.3.0}/README.md

@@ -1,12 +1,18 @@
-# crewforge
+<p align="center"><img src="https://raw.githubusercontent.com/aimanmalib/crewforge/main/brand/logo-512.png" width="112" height="112" alt="crewforge"></p>
 
-**One crew of LLM agents, five recipes — code review, document Q&A, API scaffolding, content and honest academic-writing help — on any OpenAI-compatible provider, and it fails loudly instead of pretending.**
+<h1 align="center">crewforge</h1>
 
-[![CI](https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml/badge.svg)](https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml)
-[![PyPI](https://img.shields.io/pypi/v/crewforge)](https://pypi.org/project/crewforge/)
-[![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/aimanmalib/crewforge/badge)](https://scorecard.dev/viewer/?uri=github.com/aimanmalib/crewforge)
-![Python 3.10–3.14](https://img.shields.io/badge/python-3.10%E2%80%933.14-blue)
-![License: MIT](https://img.shields.io/badge/license-MIT-green)
+<p align="center"><a href="https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml"><img src="https://github.com/aimanmalib/crewforge/actions/workflows/ci.yml/badge.svg" alt="CI"></a> <a href="https://pypi.org/project/crewforge/"><img src="https://img.shields.io/pypi/v/crewforge" alt="PyPI"></a> <a href="https://scorecard.dev/viewer/?uri=github.com/aimanmalib/crewforge"><img src="https://api.scorecard.dev/projects/github.com/aimanmalib/crewforge/badge" alt="OpenSSF Scorecard"></a> <img src="https://img.shields.io/badge/python-3.10%E2%80%933.14-blue" alt="Python 3.10–3.14"> <a href="https://github.com/aimanmalib/crewforge/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="License: MIT"></a></p>
+
+<p align="center"><b>One crew of LLM agents, five recipes, any OpenAI-compatible provider.</b> · <i>Satu kru ejen LLM, lima resipi, mana-mana penyedia serasi OpenAI.</i><br>
+<a href="https://pypi.org/project/crewforge/">PyPI</a> · <a href="https://github.com/aimanmalib/crewforge/blob/main/CHANGELOG.md">changelog</a> · <a href="https://github.com/aimanmalib/crewforge/blob/main/docs/porting.md">porting notes</a> · Built in Malaysia by <a href="https://aimanmalib.com">Aiman Malib</a></p>
+
+crewforge is a command-line tool and Python library that runs a crew of LLM agents through five recipes: code
+review, document Q&A, API scaffolding, content writing and honest academic-writing help. It works with any
+OpenAI-compatible provider, reads API keys only from the environment, and fails loudly instead of pretending: a run
+in which an agent produced nothing exits with code 1 and names that agent.
+
+[Bahasa Melayu ↓](#bahasa-melayu)
 
 ```bash
 crewforge review src/                                  # six reviewers + a summary
@@ -23,7 +29,7 @@ crewforge academic feedback draft.md --brief brief.md --language ms
 
 ## Why one crew, many recipes
 
-crewforge started as four separate command-line tools —
+crewforge started as four separate command-line tools:
 [codeguard](https://github.com/aimanmalib/codeguard),
 [documind](https://github.com/aimanmalib/documind),
 [apiforge](https://github.com/aimanmalib/apiforge) and
@@ -37,7 +43,7 @@ showed the copies had drifted and that each hid its failures differently:
 - apiforge scored a spec with **no endpoints** 100/100;
 - contentforge wrote the real API key into its YAML file, and sent `${OPENAI_API_KEY}` literally as the key.
 
-crewforge keeps one core — so a fix lands once — and turns each tool into a
+crewforge keeps one core, so a fix lands once, and turns each tool into a
 *recipe*: a set of agents plus the steps that connect them. The same core rules
 apply to every recipe: non-streaming requests, bounded retries, usage numbers
 taken only from the provider, keys only from the environment, and no run that
@@ -81,7 +87,7 @@ tables are trimmed to their totals.
 
 | Command | Agents | What you get |
 |---|---|---|
-| `review PATH` | security, style, complexity, logic, testing, documentation (parallel) → summary | Findings by severity, a decision and a score; `-f json` for CI |
+| `review PATH` | security, style, complexity, logic, testing, documentation (parallel) → summary | Findings by severity, a decision and a score; `-f json` for CI, `-f sarif` for GitHub code scanning |
 | `ingest FILES` | ingester, indexer (no LLM) | How each file was parsed and chunked |
 | `ask FILES -q Q [--verify] [--rerank]` | retriever → answerer → fact-checker | An answer with `[Source N]` citations and a claim-by-claim verdict |
 | `summarize FILES` | summarizer | Summary and key points per document |
@@ -113,6 +119,30 @@ $ crewforge review app.py -f markdown -o review.md      # app.py builds SQL with
 total   7 calls   22,366 tokens (provider-reported)
 ```
 
+`-f sarif` writes a [Static Analysis Results Interchange Format 2.1.0](https://docs.oasis-open.org/sarif/sarif/v2.1.0/sarif-v2.1.0.html)
+log (`sarif`), the format GitHub code scanning reads, so findings can appear in a repository's Security tab. Each finding becomes one
+result: `critical` and `error` map to level `error`, `warning` to `warning`, `info` to `note`; the rule is the
+finding's CWE when it has one, otherwise the reviewer's name. When you review a directory, the line a reviewer
+reports is mapped back to the file it came from. A finding whose line is missing or outside the code points at the
+reviewed path without a line. Reviewers that fail are listed in `invocations`, and the exit code is the same as for
+the other formats.
+
+```yaml
+# .github/workflows/review.yml (needs an API key secret, e.g. OPENAI_API_KEY)
+permissions:
+  contents: read
+  security-events: write
+steps:
+  - uses: actions/checkout@v4
+  - run: pipx run crewforge review src/ -f sarif -o crewforge.sarif
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  - uses: github/codeql-action/upload-sarif@v3
+    if: always()
+    with:
+      sarif_file: crewforge.sarif
+```
+
 ### `ask` and `summarize`
 
 <p align="center">
@@ -232,13 +262,13 @@ Saya menggunakan crewforge academic (versi 0.1.0), sebuah alat berbantukan AI, d
 - 22 Oktober 2026: Perancangan: alat ini menukar taklimat tugasan (brief-ms.md) kepada 3 soalan kajian, rangka 5 bahagian dan peruntukan perkataan. ...
 ```
 
-How sources are labelled — there is no "verified" status, because the tool
+How sources are labelled: there is no "verified" status, because the tool
 cannot check that a source exists:
 
 | Source | Label |
 |---|---|
 | You supplied it | *supplied by you (not checked online)* |
-| The model proposed it, with a DOI, URL or valid ISBN | **UNVERIFIED** — check it |
+| The model proposed it, with a DOI, URL or valid ISBN | **UNVERIFIED**: check it |
 | The model proposed it with none of those | **LIKELY FABRICATED** |
 | The model added a DOI/URL/ISBN to a reference you supplied | **UNVERIFIED**, naming the added identifier |
 
@@ -277,16 +307,16 @@ An unknown provider name is a configuration error, not a silent fallback.
 
 <sub>Source: [docs/architecture.mmd](https://github.com/aimanmalib/crewforge/blob/main/docs/architecture.mmd) (re-render with `scripts/render_architecture.py`).</sub>
 
-- **`core/client.py`** — one async client. It always sends `"stream": false`,
+- **`core/client.py`**: one async client. It always sends `"stream": false`,
   retries only HTTP 429, 5xx and network/timeout errors (with capped exponential
   backoff that honours `Retry-After`), and fails on the first 401/403/4xx with a
   message naming the variable to fix. The key is only ever a request header.
-- **`core/agent.py`** — an agent is a role, a system prompt and per-agent
+- **`core/agent.py`**: an agent is a role, a system prompt and per-agent
   sampling defaults. `ask()` records usage and raises if the reply is blank;
   `ask_json()` additionally requires parseable JSON (optionally a pydantic schema).
-- **`core/crew.py`** — runs agents as sequential steps or parallel stages and
+- **`core/crew.py`**: runs agents as sequential steps or parallel stages and
   turns any failure into a `CrewFailedError` that lists every failed agent.
-- **`core/usage.py`** — per-agent calls, tokens, retries and latency, taken from
+- **`core/usage.py`**: per-agent calls, tokens, retries and latency, taken from
   the provider's `usage` object. Calls without usage are counted as "not reported",
   never estimated.
 
@@ -351,10 +381,10 @@ watching them fail; see [docs/porting.md](https://github.com/aimanmalib/crewforg
 
 crewforge was built with AI coding assistance (Claude Code) under the
 direction of its author, Muhammad Aiman. It consolidates four earlier tools by
-the same author — [codeguard](https://github.com/aimanmalib/codeguard),
+the same author ([codeguard](https://github.com/aimanmalib/codeguard),
 [documind](https://github.com/aimanmalib/documind),
 [apiforge](https://github.com/aimanmalib/apiforge) and
-[contentforge](https://github.com/aimanmalib/contentforge) — whose test suites
+[contentforge](https://github.com/aimanmalib/contentforge)), whose test suites
 were carried over into this repository (see [docs/porting.md](https://github.com/aimanmalib/crewforge/blob/main/docs/porting.md)
 for what was ported, re-targeted at the shared core, or dropped and why).
 
@@ -377,10 +407,56 @@ Please report vulnerabilities privately through
 See [SECURITY.md](https://github.com/aimanmalib/crewforge/blob/main/SECURITY.md) for scope notes (what is sent to your provider,
 and what `validate` executes).
 
-## License
+## Bahasa Melayu
+
+crewforge ialah alat baris arahan dan pustaka Python yang menjalankan satu kru ejen LLM melalui lima resipi:
+semakan kod (`review`), soal jawab dokumen (`ask`, `summarize`), penjanaan projek API FastAPI (`scaffold`,
+`validate`), penulisan kandungan (`write`) dan bantuan penulisan akademik yang jujur (`academic`). Ia berfungsi
+dengan mana-mana penyedia serasi OpenAI, termasuk model tempatan melalui Ollama atau llama.cpp. Kunci API hanya
+dibaca dari pemboleh ubah persekitaran, tidak pernah ditulis ke fail.
+
+**Mengapa satu kru.** crewforge menggabungkan empat alat lama (codeguard, documind, apiforge, contentforge) yang
+masing-masing menyimpan salinan sendiri bagi rangka yang sama. Salinan itu sudah berbeza dan setiap satu
+menyembunyikan kegagalan dengan cara sendiri. Kini teras dikongsi: pembaikan dibuat sekali, dan setiap alat menjadi
+resipi di atas teras itu.
+
+**Gagal dengan jelas.** Larian yang ejennya memulangkan jawapan kosong atau tidak boleh dihurai, atau pengesah
+yang tidak menyemak apa-apa, keluar dengan kod 1 dan menamakan ejen itu. Kod keluar: `0` berjaya, `1` larian
+gagal, `2` ralat penggunaan atau konfigurasi. Bilangan token diambil daripada laporan penyedia sahaja, tidak
+dianggar.
+
+**Resipi `academic`.** Membantu pelajar dan penyelidik dengan kerja mereka **sendiri**: merancang dari taklimat
+tugasan, memberi ulasan atas draf tanpa menulis semula, memformat rujukan yang diberi pengguna (APA 7, IEEE,
+Harvard) tanpa menambah rujukan baharu, dan menulis pernyataan penggunaan AI daripada rekod langkah yang
+dijalankan. Output dalam bahasa Inggeris atau Bahasa Melayu (`--language ms`); output BM disemak untuk bentuk
+Indonesia seperti *karena* atau *kualitas*. Sumber yang dicadangkan model dilabel UNVERIFIED, atau LIKELY
+FABRICATED jika tiada DOI, URL atau ISBN. Tiada ciri "humanise" atau mengelak pengesan AI.
+
+**Pasang dan guna.**
+
+```bash
+pip install crewforge                 # Python 3.10 hingga 3.14
+pip install "crewforge[docs,api]"     # pilihan: PDF/DOCX dan semakan aplikasi FastAPI
+export OPENAI_API_KEY=sk-...          # atau penyedia lain, lihat `crewforge providers`
+crewforge review src/
+crewforge review src/ -f sarif -o crewforge.sarif   # untuk GitHub code scanning
+crewforge academic feedback draf.md --brief taklimat.md --language ms
+```
+
+`review -f sarif` menulis laporan `SARIF` 2.1.0 yang dibaca GitHub code scanning: setiap dapatan menjadi satu
+keputusan dalam tab Security, dan baris dalam semakan folder dipetakan kembali ke fail asalnya.
+
+Senarai penyedia, contoh setiap resipi dan seni bina ada dalam bahagian bahasa Inggeris di atas
+([Providers](https://github.com/aimanmalib/crewforge#providers), [Recipes](https://github.com/aimanmalib/crewforge#recipes)).
+
+## Licence
+
+[MIT](https://github.com/aimanmalib/crewforge/blob/main/LICENSE) © Muhammad Aiman. Made by [Aiman Malib](https://aimanmalib.com), Malaysia.
+
+## Work with Sasa Teguh
 
-[MIT](https://github.com/aimanmalib/crewforge/blob/main/LICENSE) © Muhammad Aiman
+[![Work with Sasa Teguh: book a call](https://raw.githubusercontent.com/sasateguh/.github/main/assets/work-with-sasa-teguh.png)](https://sasateguh.com/book)
 
----
+I built this project. I run [Sasa Teguh](https://sasateguh.com), a studio in Malaysia that builds websites found on Google and in AI answers, and sets up systems like this one for businesses.
 
-Built by [Sasa Teguh](https://sasateguh.com) · Malaysia
+[Book a call](https://sasateguh.com/book) · hello@sasateguh.com · [More from Sasa Teguh](https://github.com/sasateguh)

{crewforge-0.2.1 → crewforge-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "crewforge"
-version = "0.2.1"
+version = "0.3.0"
 description = "One crew of LLM agents, five recipes: code review, document Q&A, API scaffolding, content and honest academic-writing help — on any OpenAI-compatible provider."
 readme = "README.md"
 license = "MIT"

{crewforge-0.2.1 → crewforge-0.3.0}/src/crewforge/__init__.py

@@ -1,3 +1,3 @@
 """crewforge — one crew of LLM agents, five recipes, any OpenAI-compatible provider."""
 
-__version__ = "0.2.1"
+__version__ = "0.3.0"

{crewforge-0.2.1 → crewforge-0.3.0}/src/crewforge/recipes/review/cli.py

@@ -22,8 +22,14 @@ from ...cli_support import (
 from ...core.config import LLMConfig
 from .agents import REVIEW_AGENTS
 from .pipeline import CodeReviewCrew, ReviewResult
-from .report import report_dict, report_markdown
-from .sources import DEFAULT_MAX_FILE_BYTES, SourceError, collect, detect_language
+from .report import report_dict, report_markdown, report_sarif
+from .sources import (
+    DEFAULT_MAX_FILE_BYTES,
+    SourceError,
+    Sources,
+    collect,
+    detect_language,
+)
 
 # Kept under the old private name: codeguard's tests and users imported it.
 _detect_language = detect_language
@@ -60,7 +66,8 @@ async def _run_review(
     "fmt",
     default="text",
     show_default=True,
-    type=click.Choice(["text", "json", "markdown"]),
+    type=click.Choice(["text", "json", "markdown", "sarif"]),
+    help="sarif = SARIF 2.1.0 for GitHub code scanning.",
 )
 @click.option("--output", "-o", default="", help="Write the report to this file.")
 @click.option(
@@ -77,6 +84,7 @@ def review(ctx, path, path_opt, language, fmt, output, allow_partial):
     Example:
       crewforge review app.py
       crewforge review src/ -f json -o review.json
+      crewforge review src/ -f sarif -o review.sarif
     """
     target = path or path_opt
     if not target:
@@ -116,11 +124,18 @@ def review(ctx, path, path_opt, language, fmt, output, allow_partial):
             allow_partial=allow_partial,
         )
     )
-    _display_results(result, fmt, output)
+    _display_results(result, fmt, output, sources, target)
 
 
-def _display_results(result: ReviewResult, fmt: str, output: str) -> None:
-    text = json.dumps(report_dict(result), indent=2) if fmt == "json" else report_markdown(result)
+def _display_results(
+    result: ReviewResult, fmt: str, output: str, sources: Sources, target: str
+) -> None:
+    if fmt == "json":
+        text = json.dumps(report_dict(result), indent=2)
+    elif fmt == "sarif":
+        text = json.dumps(report_sarif(result, sources, target), indent=2)
+    else:
+        text = report_markdown(result)
     if output:
         Path(output).write_text(text, encoding="utf-8")
         err_console.print(f"[green]Report written to {output}[/]")