polanyi 0.3.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,17 @@
1
+ .env
2
+ .venv/
3
+ __pycache__/
4
+ *.py[cod]
5
+ .pytest_cache/
6
+ .mypy_cache/
7
+ .ruff_cache/
8
+ dist/
9
+ *.egg-info/
10
+ .DS_Store
11
+
12
+ # ignore raw dump, keep sample dataset outputs
13
+ output/browser_use_raw.json
14
+ !output/.gitkeep
15
+ !output/persona.json
16
+ !output/recsys_events.jsonl
17
+ !output/recsys_events.parquet
polanyi-0.3.0/LICENSE ADDED
@@ -0,0 +1,190 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ Copyright 2026 Polanyi Labs
179
+
180
+ Licensed under the Apache License, Version 2.0 (the "License");
181
+ you may not use this file except in compliance with the License.
182
+ You may obtain a copy of the License at
183
+
184
+ http://www.apache.org/licenses/LICENSE-2.0
185
+
186
+ Unless required by applicable law or agreed to in writing, software
187
+ distributed under the License is distributed on an "AS IS" BASIS,
188
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
189
+ See the License for the specific language governing permissions and
190
+ limitations under the License.
polanyi-0.3.0/PKG-INFO ADDED
@@ -0,0 +1,212 @@
1
+ Metadata-Version: 2.5
2
+ Name: polanyi
3
+ Version: 0.3.0
4
+ Summary: Synthetic shoppers hard-pinned to any website that emit recommendation-system event data.
5
+ Project-URL: Homepage, https://github.com/tmoula/polanyi_agent_harness
6
+ Project-URL: Repository, https://github.com/tmoula/polanyi_agent_harness
7
+ Project-URL: Issues, https://github.com/tmoula/polanyi_agent_harness/issues
8
+ Author: Polanyi Labs
9
+ License-Expression: Apache-2.0
10
+ License-File: LICENSE
11
+ Keywords: browser-agents,personas,recommendation-systems,recsys,synthetic-data
12
+ Classifier: Development Status :: 3 - Alpha
13
+ Classifier: Intended Audience :: Developers
14
+ Classifier: Intended Audience :: Science/Research
15
+ Classifier: License :: OSI Approved :: Apache Software License
16
+ Classifier: Programming Language :: Python :: 3
17
+ Classifier: Programming Language :: Python :: 3.11
18
+ Classifier: Programming Language :: Python :: 3.12
19
+ Classifier: Programming Language :: Python :: 3.13
20
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
21
+ Requires-Python: >=3.11
22
+ Requires-Dist: browser-use-sdk>=3.11.0
23
+ Requires-Dist: datasets>=3.0.0
24
+ Requires-Dist: httpx>=0.27.0
25
+ Requires-Dist: pandas>=2.2.0
26
+ Requires-Dist: pyarrow>=17.0.0
27
+ Requires-Dist: pydantic>=2.7.0
28
+ Requires-Dist: python-dotenv>=1.0.0
29
+ Provides-Extra: dev
30
+ Requires-Dist: fastapi>=0.115.0; extra == 'dev'
31
+ Requires-Dist: httpx>=0.27.0; extra == 'dev'
32
+ Requires-Dist: pytest>=8.0.0; extra == 'dev'
33
+ Requires-Dist: uvicorn[standard]>=0.30.0; extra == 'dev'
34
+ Provides-Extra: server
35
+ Requires-Dist: fastapi>=0.115.0; extra == 'server'
36
+ Requires-Dist: uvicorn[standard]>=0.30.0; extra == 'server'
37
+ Description-Content-Type: text/markdown
38
+
39
+ # Polanyi
40
+
41
+ **Synthetic shoppers hard-pinned to any website → recommendation-system event logs.**
42
+
43
+ Point Polanyi at a URL. It runs a diverse set of Nemotron personas as on-site shoppers (search, compare, select, stop before PII/payment) and emits privacy-safe `recsys_events` for offline experiments.
44
+
45
+ ## Install
46
+
47
+ ```bash
48
+ pip install polanyi
49
+ ```
50
+
51
+ From source:
52
+
53
+ ```bash
54
+ cd polanyi_agent_harness
55
+ python -m venv .venv
56
+ source .venv/bin/activate
57
+ pip install -e ".[dev]"
58
+ ```
59
+
60
+ ## Colab / product path (`POLANYI_API_KEY`)
61
+
62
+ ```python
63
+ import os
64
+ os.environ["POLANYI_API_KEY"] = "pk_live_..." # from Polanyi
65
+
66
+ from polanyi import Client
67
+
68
+ client = Client() # talks to https://api.polanyi.ai
69
+ result = client.simulate(site="https://www.nike.com", n=5, concurrency=5)
70
+ print(result.summary())
71
+ result.to_jsonl("nike_events.jsonl")
72
+ ```
73
+
74
+ While the hosted API is warming up, point the SDK at your own server:
75
+
76
+ ```python
77
+ os.environ["POLANYI_API_KEY"] = "pk_live_dev"
78
+ os.environ["POLANYI_API_BASE_URL"] = "http://127.0.0.1:8080"
79
+ ```
80
+
81
+ ## Local / power-user path (`BROWSER_USE_API_KEY`)
82
+
83
+ ```bash
84
+ cp .env.example .env
85
+ # BROWSER_USE_API_KEY=bu_...
86
+ ```
87
+
88
+ ```python
89
+ from polanyi import Client
90
+
91
+ client = Client() # uses Browser Use Cloud directly
92
+ result = client.simulate(
93
+ site="https://www.expedia.com",
94
+ n=10,
95
+ concurrency=5,
96
+ output_dir="runs/expedia",
97
+ )
98
+ print(result.summary())
99
+ result.to_jsonl("runs/expedia/merged.jsonl")
100
+ ```
101
+
102
+ Agents are **hard-pinned**: they start on your site and must not leave that domain. External “Book with…” handoffs stop with `checkout_boundary_stop` (first-party-shaped data).
103
+
104
+ ## Host your own Polanyi API
105
+
106
+ The server wraps Browser Use behind `POLANYI_API_KEY` auth so end users never see `bu_…` keys.
107
+
108
+ ```bash
109
+ pip install "polanyi[server]"
110
+
111
+ # mint a customer key
112
+ polanyi-serve --generate-key
113
+ # → pk_live_...
114
+
115
+ export POLANYI_API_KEYS=pk_live_...
116
+ export BROWSER_USE_API_KEY=bu_... # stays on the server only
117
+ polanyi-serve --host 0.0.0.0 --port 8080
118
+ ```
119
+
120
+ Docker:
121
+
122
+ ```bash
123
+ docker build -t polanyi-api .
124
+ docker run --rm -p 8080:8080 \
125
+ -e POLANYI_API_KEYS=pk_live_... \
126
+ -e BROWSER_USE_API_KEY=bu_... \
127
+ polanyi-api
128
+ ```
129
+
130
+ API surface:
131
+
132
+ | Method | Path | Purpose |
133
+ |--------|------|---------|
134
+ | `GET` | `/health` | Liveness |
135
+ | `POST` | `/v1/simulations` | Start a job (Bearer `pk_…`) |
136
+ | `GET` | `/v1/simulations/{id}` | Poll status + events |
137
+
138
+ ## CLI
139
+
140
+ ```bash
141
+ # Any site, N diverse personas
142
+ polanyi-sim --site https://www.nike.com --batch 5 --concurrency 5 \
143
+ --output-dir output/nike_run
144
+
145
+ # Optional journey brief
146
+ polanyi-sim --site expedia.com --batch 10 --concurrency 10 \
147
+ --prompt "Browse hotels and flights; pick what fits your budget." \
148
+ --output-dir output/expedia_run
149
+
150
+ # Dry-run (personas only, no Browser Use)
151
+ polanyi-sim --site example.com --batch 3 --dry-run-persona --output-dir output/dry
152
+ ```
153
+
154
+ Legacy (no `--site`) still works but is **not** hard-pinned.
155
+
156
+ ## Outputs
157
+
158
+ Each session directory contains:
159
+
160
+ | File | Purpose |
161
+ |------|---------|
162
+ | `persona.json` | Synthetic identity |
163
+ | `browser_use_raw.json` | Raw Browser Use run |
164
+ | `recsys_events.jsonl` / `.parquet` | Ordered recsys events |
165
+ | `simulate_meta.json` | Site + run config (SDK / `--site` runs) |
166
+ | `simulate_plan.json` | Inferred vertical + per-persona journey goals |
167
+
168
+ ## How journeys are planned
169
+
170
+ Live runs (`Client.simulate` / `polanyi-sim --site` without `--dry-run-persona`):
171
+
172
+ 1. **LLM diagnosis** — a Browser Use agent opens the real site and returns an accurate JSON profile (`site_name`, `vertical`, `description`, `journey_templates`)
173
+ 2. Saved to `simulate_diagnosis.json`
174
+ 3. Each persona gets a different template from that diagnosis, personalized with their location/budget
175
+
176
+ Dry-runs skip the LLM and fall back to URL heuristics only.
177
+
178
+ ```python
179
+ from polanyi import diagnose_site, plan_journeys
180
+ from polanyi.personas import load_personas
181
+
182
+ diagnosis = diagnose_site("https://www.ticketnetwork.com")
183
+ print(diagnosis.site_name, diagnosis.vertical)
184
+ print(diagnosis.description)
185
+ plan = plan_journeys("https://www.ticketnetwork.com", load_personas(count=3), diagnosis=diagnosis)
186
+ ```
187
+
188
+ ## Safety
189
+
190
+ - Synthetic actor IDs only (`syn_nmusa_*`)
191
+ - `training_use=offline_sandbox_only`
192
+ - Hard stop before identity / payment
193
+ - Hard site pin (first-party shaped)
194
+
195
+ ## Publish to PyPI
196
+
197
+ ```bash
198
+ pip install build twine
199
+ python -m build
200
+ twine upload dist/*
201
+ ```
202
+
203
+ The `polanyi` name is available on PyPI as of packaging time.
204
+
205
+ ## Roadmap
206
+
207
+ 1. ~~Schema, personas, Cloud runner, batch concurrency~~
208
+ 2. ~~Python SDK `Client.simulate(site=…)` + hard pin~~
209
+ 3. ~~LLM site diagnosis → diverse per-persona journeys~~
210
+ 4. ~~`POLANYI_API_KEY` + self-hostable API wrapping Browser Use~~
211
+ 5. Parse quality gates + JSON repair for agent output
212
+ 6. Hosted `api.polanyi.ai` + public PyPI release
@@ -0,0 +1,174 @@
1
+ # Polanyi
2
+
3
+ **Synthetic shoppers hard-pinned to any website → recommendation-system event logs.**
4
+
5
+ Point Polanyi at a URL. It runs a diverse set of Nemotron personas as on-site shoppers (search, compare, select, stop before PII/payment) and emits privacy-safe `recsys_events` for offline experiments.
6
+
7
+ ## Install
8
+
9
+ ```bash
10
+ pip install polanyi
11
+ ```
12
+
13
+ From source:
14
+
15
+ ```bash
16
+ cd polanyi_agent_harness
17
+ python -m venv .venv
18
+ source .venv/bin/activate
19
+ pip install -e ".[dev]"
20
+ ```
21
+
22
+ ## Colab / product path (`POLANYI_API_KEY`)
23
+
24
+ ```python
25
+ import os
26
+ os.environ["POLANYI_API_KEY"] = "pk_live_..." # from Polanyi
27
+
28
+ from polanyi import Client
29
+
30
+ client = Client() # talks to https://api.polanyi.ai
31
+ result = client.simulate(site="https://www.nike.com", n=5, concurrency=5)
32
+ print(result.summary())
33
+ result.to_jsonl("nike_events.jsonl")
34
+ ```
35
+
36
+ While the hosted API is warming up, point the SDK at your own server:
37
+
38
+ ```python
39
+ os.environ["POLANYI_API_KEY"] = "pk_live_dev"
40
+ os.environ["POLANYI_API_BASE_URL"] = "http://127.0.0.1:8080"
41
+ ```
42
+
43
+ ## Local / power-user path (`BROWSER_USE_API_KEY`)
44
+
45
+ ```bash
46
+ cp .env.example .env
47
+ # BROWSER_USE_API_KEY=bu_...
48
+ ```
49
+
50
+ ```python
51
+ from polanyi import Client
52
+
53
+ client = Client() # uses Browser Use Cloud directly
54
+ result = client.simulate(
55
+ site="https://www.expedia.com",
56
+ n=10,
57
+ concurrency=5,
58
+ output_dir="runs/expedia",
59
+ )
60
+ print(result.summary())
61
+ result.to_jsonl("runs/expedia/merged.jsonl")
62
+ ```
63
+
64
+ Agents are **hard-pinned**: they start on your site and must not leave that domain. External “Book with…” handoffs stop with `checkout_boundary_stop` (first-party-shaped data).
65
+
66
+ ## Host your own Polanyi API
67
+
68
+ The server wraps Browser Use behind `POLANYI_API_KEY` auth so end users never see `bu_…` keys.
69
+
70
+ ```bash
71
+ pip install "polanyi[server]"
72
+
73
+ # mint a customer key
74
+ polanyi-serve --generate-key
75
+ # → pk_live_...
76
+
77
+ export POLANYI_API_KEYS=pk_live_...
78
+ export BROWSER_USE_API_KEY=bu_... # stays on the server only
79
+ polanyi-serve --host 0.0.0.0 --port 8080
80
+ ```
81
+
82
+ Docker:
83
+
84
+ ```bash
85
+ docker build -t polanyi-api .
86
+ docker run --rm -p 8080:8080 \
87
+ -e POLANYI_API_KEYS=pk_live_... \
88
+ -e BROWSER_USE_API_KEY=bu_... \
89
+ polanyi-api
90
+ ```
91
+
92
+ API surface:
93
+
94
+ | Method | Path | Purpose |
95
+ |--------|------|---------|
96
+ | `GET` | `/health` | Liveness |
97
+ | `POST` | `/v1/simulations` | Start a job (Bearer `pk_…`) |
98
+ | `GET` | `/v1/simulations/{id}` | Poll status + events |
99
+
100
+ ## CLI
101
+
102
+ ```bash
103
+ # Any site, N diverse personas
104
+ polanyi-sim --site https://www.nike.com --batch 5 --concurrency 5 \
105
+ --output-dir output/nike_run
106
+
107
+ # Optional journey brief
108
+ polanyi-sim --site expedia.com --batch 10 --concurrency 10 \
109
+ --prompt "Browse hotels and flights; pick what fits your budget." \
110
+ --output-dir output/expedia_run
111
+
112
+ # Dry-run (personas only, no Browser Use)
113
+ polanyi-sim --site example.com --batch 3 --dry-run-persona --output-dir output/dry
114
+ ```
115
+
116
+ Legacy (no `--site`) still works but is **not** hard-pinned.
117
+
118
+ ## Outputs
119
+
120
+ Each session directory contains:
121
+
122
+ | File | Purpose |
123
+ |------|---------|
124
+ | `persona.json` | Synthetic identity |
125
+ | `browser_use_raw.json` | Raw Browser Use run |
126
+ | `recsys_events.jsonl` / `.parquet` | Ordered recsys events |
127
+ | `simulate_meta.json` | Site + run config (SDK / `--site` runs) |
128
+ | `simulate_plan.json` | Inferred vertical + per-persona journey goals |
129
+
130
+ ## How journeys are planned
131
+
132
+ Live runs (`Client.simulate` / `polanyi-sim --site` without `--dry-run-persona`):
133
+
134
+ 1. **LLM diagnosis** — a Browser Use agent opens the real site and returns an accurate JSON profile (`site_name`, `vertical`, `description`, `journey_templates`)
135
+ 2. Saved to `simulate_diagnosis.json`
136
+ 3. Each persona gets a different template from that diagnosis, personalized with their location/budget
137
+
138
+ Dry-runs skip the LLM and fall back to URL heuristics only.
139
+
140
+ ```python
141
+ from polanyi import diagnose_site, plan_journeys
142
+ from polanyi.personas import load_personas
143
+
144
+ diagnosis = diagnose_site("https://www.ticketnetwork.com")
145
+ print(diagnosis.site_name, diagnosis.vertical)
146
+ print(diagnosis.description)
147
+ plan = plan_journeys("https://www.ticketnetwork.com", load_personas(count=3), diagnosis=diagnosis)
148
+ ```
149
+
150
+ ## Safety
151
+
152
+ - Synthetic actor IDs only (`syn_nmusa_*`)
153
+ - `training_use=offline_sandbox_only`
154
+ - Hard stop before identity / payment
155
+ - Hard site pin (first-party shaped)
156
+
157
+ ## Publish to PyPI
158
+
159
+ ```bash
160
+ pip install build twine
161
+ python -m build
162
+ twine upload dist/*
163
+ ```
164
+
165
+ The `polanyi` name is available on PyPI as of packaging time.
166
+
167
+ ## Roadmap
168
+
169
+ 1. ~~Schema, personas, Cloud runner, batch concurrency~~
170
+ 2. ~~Python SDK `Client.simulate(site=…)` + hard pin~~
171
+ 3. ~~LLM site diagnosis → diverse per-persona journeys~~
172
+ 4. ~~`POLANYI_API_KEY` + self-hostable API wrapping Browser Use~~
173
+ 5. Parse quality gates + JSON repair for agent output
174
+ 6. Hosted `api.polanyi.ai` + public PyPI release
@@ -0,0 +1,75 @@
1
+ [build-system]
2
+ requires = ["hatchling"]
3
+ build-backend = "hatchling.build"
4
+
5
+ [project]
6
+ name = "polanyi"
7
+ version = "0.3.0"
8
+ description = "Synthetic shoppers hard-pinned to any website that emit recommendation-system event data."
9
+ readme = "README.md"
10
+ requires-python = ">=3.11"
11
+ license = "Apache-2.0"
12
+ authors = [
13
+ { name = "Polanyi Labs" },
14
+ ]
15
+ keywords = [
16
+ "synthetic-data",
17
+ "recsys",
18
+ "browser-agents",
19
+ "personas",
20
+ "recommendation-systems",
21
+ ]
22
+ classifiers = [
23
+ "Development Status :: 3 - Alpha",
24
+ "Intended Audience :: Developers",
25
+ "Intended Audience :: Science/Research",
26
+ "License :: OSI Approved :: Apache Software License",
27
+ "Programming Language :: Python :: 3",
28
+ "Programming Language :: Python :: 3.11",
29
+ "Programming Language :: Python :: 3.12",
30
+ "Programming Language :: Python :: 3.13",
31
+ "Topic :: Scientific/Engineering :: Artificial Intelligence",
32
+ ]
33
+ dependencies = [
34
+ "browser-use-sdk>=3.11.0",
35
+ "datasets>=3.0.0",
36
+ "httpx>=0.27.0",
37
+ "pandas>=2.2.0",
38
+ "pyarrow>=17.0.0",
39
+ "pydantic>=2.7.0",
40
+ "python-dotenv>=1.0.0",
41
+ ]
42
+
43
+ [project.optional-dependencies]
44
+ server = [
45
+ "fastapi>=0.115.0",
46
+ "uvicorn[standard]>=0.30.0",
47
+ ]
48
+ dev = [
49
+ "pytest>=8.0.0",
50
+ "fastapi>=0.115.0",
51
+ "uvicorn[standard]>=0.30.0",
52
+ "httpx>=0.27.0",
53
+ ]
54
+
55
+ [project.urls]
56
+ Homepage = "https://github.com/tmoula/polanyi_agent_harness"
57
+ Repository = "https://github.com/tmoula/polanyi_agent_harness"
58
+ Issues = "https://github.com/tmoula/polanyi_agent_harness/issues"
59
+
60
+ [project.scripts]
61
+ polanyi-sim = "polanyi.cli:main"
62
+ polanyi-serve = "polanyi.server.app:main"
63
+
64
+ [tool.hatch.build.targets.wheel]
65
+ packages = ["src/polanyi"]
66
+
67
+ [tool.hatch.build.targets.wheel.sources]
68
+ "src/polanyi" = "polanyi"
69
+
70
+ [tool.hatch.build.targets.sdist]
71
+ include = ["src/polanyi", "schemas", "README.md", "LICENSE"]
72
+
73
+ [tool.pytest.ini_options]
74
+ testpaths = ["tests"]
75
+ pythonpath = ["src"]