ftgate 0.1.0__tar.gz

ftgate-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

ftgate-0.1.0/PKG-INFO

@@ -0,0 +1,167 @@
+Metadata-Version: 2.4
+Name: ftgate
+Version: 0.1.0
+Summary: Regression checks for small fine-tuned models on tool calling: do runtimes send the bytes the model was trained on?
+Author: Vitalii Bogachev
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/talhayme/ftgate
+Project-URL: Repository, https://github.com/talhayme/ftgate
+Project-URL: Issues, https://github.com/talhayme/ftgate/issues
+Keywords: fine-tuning,tool-calling,ollama,llama.cpp,gguf,evaluation,dataset,lint
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development :: Testing
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: transformers>=4.45
+Requires-Dist: requests>=2.31
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Dynamic: license-file
+
+# ftgate (working name)
+
+Regression checks for a small model you fine-tuned on tool calling: do the
+bytes the runtime sends match the bytes the model was trained on, and does
+it still call your tools correctly after export and quantisation?
+
+**Status: `ftgate template`, `ftgate data` and `ftgate tools` work.** The premise was
+checked before any tool code was written — the same way
+[pr-witness](https://github.com/talhayme/pr-witness) was built.
+
+## What has been measured so far
+
+- **llama-server reproduces the HF training bytes exactly** for a
+  tool-calling prompt (Qwen2.5-0.5B-Instruct, 250/250 tokens, text and ids
+  identical) — even though the GGUF's embedded template hashes differently
+  from HF's. Compare renderings, never hashes. → [`notes/day1-findings.md`](notes/day1-findings.md)
+- **Ollama 0.40.2 hands the model a Go struct dump instead of the tool
+  schema**: `{get_weather … {object <nil> <nil> [city] {…}}}`. Root cause
+  in `template/template.go` (`templateToolFunction` has no `String()`);
+  known upstream as ollama/ollama#14601 with open PRs #18318 and #18391.
+- **Qwen's official Qwen2.5 GGUFs embed the pre-fix chat template** —
+  doubled braces `{{"name": …}}` in the tool-call instruction, fixed on HF
+  on 2024-09-19 but never regenerated in the GGUF repos. Ollama's library
+  blobs are those files. Ollama never renders it; llama.cpp, vLLM or LM
+  Studio serving the file do. **The 0.5B model copies the braces into
+  every tool call** (invalid JSON; a strict parser gets 0/35 where the HF
+  template gets 22/35); the 1.5B model ignores them. llama-server's parser
+  forgives it, vLLM's `json.loads` would not.
+  → [`notes/day4-doubled-braces-impact.md`](notes/day4-doubled-braces-impact.md)
+  → [`notes/day3-template-command.md`](notes/day3-template-command.md)
+- **Ollama prepends the Modelfile SYSTEM** when a request has none — a
+  system prompt your training rows may never have had.
+- **It costs accuracy.** Same GGUF blob in every arm, temperature 0, 40
+  cases: Qwen2.5-0.5B gets exact arguments 39/40 with its own template and
+  31/40 with the prompt Ollama builds — every failure an invented
+  parameter `amount from_currency`, read off Go's `[amount from_currency
+  to_currency]` rendering of `required`. Qwen2.5-1.5B: 40/40 either way on
+  this easy set. → [`notes/day2-impact.md`](notes/day2-impact.md)
+
+## Use
+
+```
+uv pip install -e .
+ftgate template --model Qwen/Qwen2.5-0.5B-Instruct \
+                --llama http://localhost:8080 \
+                --ollama qwen2.5:0.5b-instruct \
+                --dataset train.jsonl --sample 20 --diff
+```
+
+`--model` is the HF checkpoint whose tokenizer and chat template the
+trainer used; `--dataset` is your own rows (`messages[, tools]` per line).
+Each runtime's prompt and token ids are compared with what SFT fed the
+model, and every difference is classified: `schema_not_json`,
+`injected_system`, `special_prefix`, `structural`, `spacing`, `tokenizer`.
+Ollama's column is rendered with Ollama's own `template` package (build
+`bin/` once) and cross-checked against the live `prompt_eval_count`.
+
+### `ftgate data` — lint the dataset with the model's own tokenizer and template
+
+```
+ftgate data train.jsonl --model Qwen/Qwen2.5-0.5B-Instruct --max-seq-len 2048 \
+            --eval eval.jsonl --fail-on error
+```
+
+Rows in `messages`, ShareGPT, Alpaca or preference (`chosen`/`rejected`)
+shape. Reports what the trainer will silently do to each row: an assistant
+turn that renders to zero target tokens, a conversation cut by
+`max_seq_len` before the answer (trains nothing) or inside it, a row that
+never ends with EOS, a template that raises on the row. Structural checks:
+empty or missing assistant target, role order, tool calls against the
+declared schema (missing required / unknown arguments / undeclared tool /
+`tool_call_id` with no call), `chosen == rejected`, length bias in
+preference pairs, exact duplicates, near-duplicates of the eval set.
+`--format json` for CI; `--fail-on error|warning` sets the exit code.
+
+### `ftgate tools` — does it still call *your* tools, on the backend it will run on?
+
+```
+ftgate tools --tools tools.json --cases cases.jsonl \
+             --provider ollama:my-finetune:q4_k_m \
+             --provider "openai:m@http://localhost:8080/v1" \
+             --min-exact 0.8
+ftgate tools --from-dataset train.jsonl --holdout 50 --provider ollama:my-finetune
+```
+
+Evaluation runs on [promptfoo](https://www.promptfoo.dev/) (installed
+once with `npm install --prefix .pfrunner promptfoo`, or set
+`FTGATE_PROMPTFOO`). ftgate writes the config — your tools, your cases
+(a file, or rows held out of your own training set), one provider per
+arm, temperature 0, one request in flight for local servers — and a
+deterministic judge that reports per case: the right tool, every expected
+argument present and equal (extra optional arguments allowed and counted),
+and two things a generic eval does not separate from "the model was
+wrong": **parser lost** — the model emitted a `<tool_call>` the provider
+did not surface — and **malformed** — the call's JSON does not parse.
+Failure reasons show the produced arguments next to the expected ones.
+
+### In CI, in tests, before commit
+
+```yaml
+# GitHub Actions
+- uses: talhayme/ftgate@main
+  with: { dataset: data/train.jsonl, model: Qwen/Qwen2.5-0.5B-Instruct, max-seq-len: "2048" }
+```
+
+```yaml
+# .pre-commit-config.yaml
+- repo: https://github.com/talhayme/ftgate
+  rev: main
+  hooks: [{ id: ftgate-data, args: [--fail-on, error] }]
+```
+
+```python
+# tests/test_data.py
+from ftgate.testing import assert_dataset_clean
+
+def test_training_data():
+    assert_dataset_clean("data/train.jsonl", model="Qwen/Qwen2.5-0.5B-Instruct", max_seq_len=2048)
+```
+
+or, with the plugin that installs alongside the package,
+`pytest --ftgate-dataset data/train.jsonl --ftgate-model Qwen/Qwen2.5-0.5B-Instruct`.
+
+## Reproduce the findings
+
+```
+uv venv --python 3.12 ~/.venvs/ftgate && uv pip install --python ~/.venvs/ftgate/bin/python torch transformers gguf requests
+# llama-server built from llama.cpp with --jinja support; Ollama ≥ 0.40 running on :11434
+python scripts/hf_side.py                       # training-side bytes
+python scripts/llama_side.py http://localhost:8089
+python scripts/ollama_side.py                   # needs bin/ollama-render (see bin/README.md)
+python scripts/day2_eval.py qwen2.5:0.5b-instruct   # three-arm accuracy comparison
+```
+
+## Plan
+
+`ftgate template` — the three-sided byte comparison as a command.
+`ftgate data` — a linter for SFT/DPO/tool-call datasets using the target
+model's tokenizer and template. Tool-call evaluation builds on promptfoo's
+`tool-call-f1` / `trajectory:tool-args-match` rather than duplicating them.
+
+Apache-2.0.

ftgate-0.1.0/README.md

@@ -0,0 +1,142 @@
+# ftgate (working name)
+
+Regression checks for a small model you fine-tuned on tool calling: do the
+bytes the runtime sends match the bytes the model was trained on, and does
+it still call your tools correctly after export and quantisation?
+
+**Status: `ftgate template`, `ftgate data` and `ftgate tools` work.** The premise was
+checked before any tool code was written — the same way
+[pr-witness](https://github.com/talhayme/pr-witness) was built.
+
+## What has been measured so far
+
+- **llama-server reproduces the HF training bytes exactly** for a
+  tool-calling prompt (Qwen2.5-0.5B-Instruct, 250/250 tokens, text and ids
+  identical) — even though the GGUF's embedded template hashes differently
+  from HF's. Compare renderings, never hashes. → [`notes/day1-findings.md`](notes/day1-findings.md)
+- **Ollama 0.40.2 hands the model a Go struct dump instead of the tool
+  schema**: `{get_weather … {object <nil> <nil> [city] {…}}}`. Root cause
+  in `template/template.go` (`templateToolFunction` has no `String()`);
+  known upstream as ollama/ollama#14601 with open PRs #18318 and #18391.
+- **Qwen's official Qwen2.5 GGUFs embed the pre-fix chat template** —
+  doubled braces `{{"name": …}}` in the tool-call instruction, fixed on HF
+  on 2024-09-19 but never regenerated in the GGUF repos. Ollama's library
+  blobs are those files. Ollama never renders it; llama.cpp, vLLM or LM
+  Studio serving the file do. **The 0.5B model copies the braces into
+  every tool call** (invalid JSON; a strict parser gets 0/35 where the HF
+  template gets 22/35); the 1.5B model ignores them. llama-server's parser
+  forgives it, vLLM's `json.loads` would not.
+  → [`notes/day4-doubled-braces-impact.md`](notes/day4-doubled-braces-impact.md)
+  → [`notes/day3-template-command.md`](notes/day3-template-command.md)
+- **Ollama prepends the Modelfile SYSTEM** when a request has none — a
+  system prompt your training rows may never have had.
+- **It costs accuracy.** Same GGUF blob in every arm, temperature 0, 40
+  cases: Qwen2.5-0.5B gets exact arguments 39/40 with its own template and
+  31/40 with the prompt Ollama builds — every failure an invented
+  parameter `amount from_currency`, read off Go's `[amount from_currency
+  to_currency]` rendering of `required`. Qwen2.5-1.5B: 40/40 either way on
+  this easy set. → [`notes/day2-impact.md`](notes/day2-impact.md)
+
+## Use
+
+```
+uv pip install -e .
+ftgate template --model Qwen/Qwen2.5-0.5B-Instruct \
+                --llama http://localhost:8080 \
+                --ollama qwen2.5:0.5b-instruct \
+                --dataset train.jsonl --sample 20 --diff
+```
+
+`--model` is the HF checkpoint whose tokenizer and chat template the
+trainer used; `--dataset` is your own rows (`messages[, tools]` per line).
+Each runtime's prompt and token ids are compared with what SFT fed the
+model, and every difference is classified: `schema_not_json`,
+`injected_system`, `special_prefix`, `structural`, `spacing`, `tokenizer`.
+Ollama's column is rendered with Ollama's own `template` package (build
+`bin/` once) and cross-checked against the live `prompt_eval_count`.
+
+### `ftgate data` — lint the dataset with the model's own tokenizer and template
+
+```
+ftgate data train.jsonl --model Qwen/Qwen2.5-0.5B-Instruct --max-seq-len 2048 \
+            --eval eval.jsonl --fail-on error
+```
+
+Rows in `messages`, ShareGPT, Alpaca or preference (`chosen`/`rejected`)
+shape. Reports what the trainer will silently do to each row: an assistant
+turn that renders to zero target tokens, a conversation cut by
+`max_seq_len` before the answer (trains nothing) or inside it, a row that
+never ends with EOS, a template that raises on the row. Structural checks:
+empty or missing assistant target, role order, tool calls against the
+declared schema (missing required / unknown arguments / undeclared tool /
+`tool_call_id` with no call), `chosen == rejected`, length bias in
+preference pairs, exact duplicates, near-duplicates of the eval set.
+`--format json` for CI; `--fail-on error|warning` sets the exit code.
+
+### `ftgate tools` — does it still call *your* tools, on the backend it will run on?
+
+```
+ftgate tools --tools tools.json --cases cases.jsonl \
+             --provider ollama:my-finetune:q4_k_m \
+             --provider "openai:m@http://localhost:8080/v1" \
+             --min-exact 0.8
+ftgate tools --from-dataset train.jsonl --holdout 50 --provider ollama:my-finetune
+```
+
+Evaluation runs on [promptfoo](https://www.promptfoo.dev/) (installed
+once with `npm install --prefix .pfrunner promptfoo`, or set
+`FTGATE_PROMPTFOO`). ftgate writes the config — your tools, your cases
+(a file, or rows held out of your own training set), one provider per
+arm, temperature 0, one request in flight for local servers — and a
+deterministic judge that reports per case: the right tool, every expected
+argument present and equal (extra optional arguments allowed and counted),
+and two things a generic eval does not separate from "the model was
+wrong": **parser lost** — the model emitted a `<tool_call>` the provider
+did not surface — and **malformed** — the call's JSON does not parse.
+Failure reasons show the produced arguments next to the expected ones.
+
+### In CI, in tests, before commit
+
+```yaml
+# GitHub Actions
+- uses: talhayme/ftgate@main
+  with: { dataset: data/train.jsonl, model: Qwen/Qwen2.5-0.5B-Instruct, max-seq-len: "2048" }
+```
+
+```yaml
+# .pre-commit-config.yaml
+- repo: https://github.com/talhayme/ftgate
+  rev: main
+  hooks: [{ id: ftgate-data, args: [--fail-on, error] }]
+```
+
+```python
+# tests/test_data.py
+from ftgate.testing import assert_dataset_clean
+
+def test_training_data():
+    assert_dataset_clean("data/train.jsonl", model="Qwen/Qwen2.5-0.5B-Instruct", max_seq_len=2048)
+```
+
+or, with the plugin that installs alongside the package,
+`pytest --ftgate-dataset data/train.jsonl --ftgate-model Qwen/Qwen2.5-0.5B-Instruct`.
+
+## Reproduce the findings
+
+```
+uv venv --python 3.12 ~/.venvs/ftgate && uv pip install --python ~/.venvs/ftgate/bin/python torch transformers gguf requests
+# llama-server built from llama.cpp with --jinja support; Ollama ≥ 0.40 running on :11434
+python scripts/hf_side.py                       # training-side bytes
+python scripts/llama_side.py http://localhost:8089
+python scripts/ollama_side.py                   # needs bin/ollama-render (see bin/README.md)
+python scripts/day2_eval.py qwen2.5:0.5b-instruct   # three-arm accuracy comparison
+```
+
+## Plan
+
+`ftgate template` — the three-sided byte comparison as a command.
+`ftgate data` — a linter for SFT/DPO/tool-call datasets using the target
+model's tokenizer and template. Tool-call evaluation builds on promptfoo's
+`tool-call-f1` / `trajectory:tool-args-match` rather than duplicating them.
+
+Apache-2.0.

ftgate-0.1.0/pyproject.toml

@@ -0,0 +1,45 @@
+[project]
+name = "ftgate"
+version = "0.1.0"
+description = "Regression checks for small fine-tuned models on tool calling: do runtimes send the bytes the model was trained on?"
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Vitalii Bogachev" }]
+keywords = ["fine-tuning", "tool-calling", "ollama", "llama.cpp", "gguf", "evaluation", "dataset", "lint"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3",
+  "Topic :: Software Development :: Testing",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = ["transformers>=4.45", "requests>=2.31"]
+
+[project.urls]
+Homepage = "https://github.com/talhayme/ftgate"
+Repository = "https://github.com/talhayme/ftgate"
+Issues = "https://github.com/talhayme/ftgate/issues"
+
+[project.optional-dependencies]
+dev = ["pytest"]
+
+[project.scripts]
+ftgate = "ftgate.cli:main"
+
+[project.entry-points.pytest11]
+ftgate = "ftgate.pytest_plugin"
+
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+ftgate = ["assets/*.js"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

ftgate-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

ftgate-0.1.0/src/ftgate/__init__.py

@@ -0,0 +1,2 @@
+"""ftgate — do runtimes send the bytes the model was trained on?"""
+__version__ = "0.1.0"

ftgate-0.1.0/src/ftgate/assets/assert_tools.js

@@ -0,0 +1,77 @@
+// ftgate: judge one tool-calling response against the expected calls.
+//
+// Written once by ftgate, run by promptfoo for every case. It reads the
+// model's output in whatever shape the provider produced — OpenAI
+// tool_calls JSON, a list of function_call items, or raw text with
+// <tool_call> blocks — and reports named scores rather than one pass/fail,
+// so the table can separate "wrong tool", "wrong arguments" and "the
+// call was there but the provider's parser lost it".
+module.exports = (output, context) => {
+  const expected = context.vars.__expected_calls;   // [{name, arguments}]
+  const norm = (v) => {
+    if (Array.isArray(v)) return v.map(norm);
+    if (v && typeof v === "object") { const o = {}; for (const k of Object.keys(v).sort()) o[k] = norm(v[k]); return o; }
+    if (typeof v === "number") return Number(v);
+    if (typeof v === "boolean") return v;
+    return String(v).trim().toLowerCase();
+  };
+  // Expected arguments must be present and equal; extra (optional) arguments
+  // are allowed and reported separately, so a model that adds unit="celsius"
+  // to a weather call is not marked wrong for being thorough.
+  const subsetKey = (c, exp) => {
+    const got = c.arguments || {}, want = exp.arguments || {};
+    const picked = {}; for (const k of Object.keys(want)) picked[k] = got[k];
+    return JSON.stringify([c.name, norm(picked)]);
+  };
+  const wantKey = (e) => JSON.stringify([e.name, norm(e.arguments || {})]);
+
+  let structured = [];
+  let text = typeof output === "string" ? output : JSON.stringify(output);
+  const takeCall = (c) => {
+    const fn = c.function || c;
+    let args = fn.arguments ?? fn.input ?? {};
+    if (typeof args === "string") { try { args = JSON.parse(args); } catch (e) { return { name: fn.name, arguments: null, malformed: true }; } }
+    return { name: fn.name, arguments: args };
+  };
+  try {
+    const o = typeof output === "string" ? JSON.parse(output) : output;
+    const list = Array.isArray(o) ? o : (o && o.tool_calls) ? o.tool_calls : (o && o.name) ? [o] : [];
+    structured = list.filter(c => c && (c.function || c.name)).map(takeCall);
+  } catch (e) { /* not JSON: raw text */ }
+
+  let fromText = [];
+  const re = /<tool_call>\s*([\s\S]*?)\s*<\/tool_call>/g; let m;
+  while ((m = re.exec(text)) !== null) {
+    try { const d = JSON.parse(m[1]); fromText.push({ name: d.name, arguments: d.arguments || {} }); }
+    catch (e) { fromText.push({ name: null, arguments: null, malformed: true }); }
+  }
+
+  const calls = structured.length ? structured : fromText;
+  const parserLost = structured.length === 0 && fromText.length > 0;   // the model called; the provider did not surface it
+  const malformed = calls.some(c => c.malformed);
+  const names = (a) => a.map(c => c.name).sort().join("|");
+  const namesOk = names(calls) === names(expected);
+  // Pair each expected call with a produced call of the same name (greedy).
+  let argsOk = namesOk && !malformed, extra = false;
+  if (argsOk) {
+    const pool = calls.slice();
+    for (const e of expected) {
+      const i = pool.findIndex(c => c.name === e.name && subsetKey(c, e) === wantKey(e));
+      if (i < 0) { argsOk = false; break; }
+      const got = pool[i].arguments || {};
+      if (Object.keys(got).some(k => !(k in (e.arguments || {})))) extra = true;
+      pool.splice(i, 1);
+    }
+  }
+
+  return {
+    pass: argsOk,
+    score: argsOk ? 1 : namesOk ? 0.5 : 0,
+    reason: argsOk ? (extra ? "ok, extra optional arguments" : "exact")
+      : !calls.length ? "no call"
+      : malformed ? "malformed arguments: " + text.slice(0, 160)
+      : !namesOk ? `tools ${names(calls) || "-"} vs expected ${names(expected)}`
+      : "arguments differ: got " + JSON.stringify(calls.map(c => c.arguments)) + " expected " + JSON.stringify(expected.map(e => e.arguments)),
+    namedScores: { called: calls.length ? 1 : 0, names: namesOk ? 1 : 0, args: argsOk ? 1 : 0, extra_args: extra ? 1 : 0, parser_lost: parserLost ? 1 : 0, malformed: malformed ? 1 : 0 },
+  };
+};