tokenbee-sdk 2.0.0__tar.gz → 2.1.0__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.
Files changed (11) hide show
  1. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/PKG-INFO +9 -8
  2. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/README.md +8 -7
  3. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/pyproject.toml +1 -1
  4. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/setup.py +1 -1
  5. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee/__init__.py +16 -6
  6. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee_sdk.egg-info/PKG-INFO +9 -8
  7. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/setup.cfg +0 -0
  8. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee_sdk.egg-info/SOURCES.txt +0 -0
  9. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee_sdk.egg-info/dependency_links.txt +0 -0
  10. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee_sdk.egg-info/requires.txt +0 -0
  11. {tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee_sdk.egg-info/top_level.txt +0 -0
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tokenbee-sdk
3
- Version: 2.0.0
3
+ Version: 2.1.0
4
4
  Summary: Official Python SDK for TokenBee LLM inference gateway and observability.
5
5
  Author: TokenBee Inc.
6
6
  Author-email: "TokenBee Inc." <founders@tokenbee.io>
@@ -18,13 +18,13 @@ Dynamic: requires-python
18
18
 
19
19
  # TokenBee Python SDK
20
20
 
21
- Official Python SDK for [TokenBee](https://tokenbee.io) - The Intelligent LLM Inference Gateway with Observability, Compression, and Privacy.
21
+ Official Python SDK for [TokenBee](https://tokenbee.io) — AI interaction capture, audit, replay, and optimization.
22
22
 
23
23
  ## Features
24
24
 
25
25
  - **Unified API**: Access multiple LLM providers (OpenAI, Anthropic, Google, Mistral, etc.) through a single interface.
26
26
  - **Intelligent Compression**: Reduce token usage and latency with context-aware compression.
27
- - **Privacy Guard**: Automatic PII masking and privacy-preserving inference.
27
+ - **Configurable Capture**: Retain interaction content when you need it; turn capture off per request or globally.
28
28
  - **Built-in Observability**: Automatic tracking of latency, costs, and token usage.
29
29
 
30
30
  ## Links
@@ -82,7 +82,7 @@ response = client.send(
82
82
  "messages": [...],
83
83
  "compression": "auto", # "auto" (default), "on", or "off"
84
84
  "rate": CompressionRate.HIGH, # MEDIUM (0.5), HIGH (0.33), etc.
85
- "privacy": True
85
+ "capture": False # per-request: do not retain message/response bodies
86
86
  }
87
87
  )
88
88
  ```
@@ -91,15 +91,16 @@ response = client.send(
91
91
  - **`rate`**: Controls the aggressiveness of compression. `HIGH` aims for ~67% token reduction.
92
92
  - **`sessionId`**: (Optional) String ID to group multiple requests into a single replayable session in the dashboard.
93
93
  - **`userId`**: (Optional) String ID to track usage and costs per unique end-user.
94
- - **`privacy`**: (Optional) Set to `True` to disable payload logging and session replays for this request. Metadata (latency, tokens) will still be recorded for observability.
94
+ - **`capture`**: (Optional) Per-request override. `False` does not retain messages/responses (metadata like tokens/cost/latency can still be recorded). Precedence: per-request → project setting → default on.
95
95
 
96
96
  ### Supported Models
97
97
 
98
98
  The SDK provides a `TokenBeeModel` enum with popular models:
99
99
 
100
- - `TokenBeeModel.ANTHROPIC_CLAUDE_SONNET_4`
101
- - `TokenBeeModel.OPENAI_GPT_5_MINI`
102
- - `TokenBeeModel.GROQ_GPT_OSS_20B`
100
+ - `TokenBeeModel.OPENAI_GPT_6_ASTRA`
101
+ - `TokenBeeModel.ANTHROPIC_CLAUDE_FABLE_5_1`
102
+ - `TokenBeeModel.GEMINI_3_8_FLASH`
103
+ - `TokenBeeModel.XAI_GROK_4_6`
103
104
  - ... and many others.
104
105
 
105
106
  ## License
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/README.md RENAMED
@@ -1,12 +1,12 @@
1
1
  # TokenBee Python SDK
2
2
 
3
- Official Python SDK for [TokenBee](https://tokenbee.io) - The Intelligent LLM Inference Gateway with Observability, Compression, and Privacy.
3
+ Official Python SDK for [TokenBee](https://tokenbee.io) — AI interaction capture, audit, replay, and optimization.
4
4
 
5
5
  ## Features
6
6
 
7
7
  - **Unified API**: Access multiple LLM providers (OpenAI, Anthropic, Google, Mistral, etc.) through a single interface.
8
8
  - **Intelligent Compression**: Reduce token usage and latency with context-aware compression.
9
- - **Privacy Guard**: Automatic PII masking and privacy-preserving inference.
9
+ - **Configurable Capture**: Retain interaction content when you need it; turn capture off per request or globally.
10
10
  - **Built-in Observability**: Automatic tracking of latency, costs, and token usage.
11
11
 
12
12
  ## Links
@@ -64,7 +64,7 @@ response = client.send(
64
64
  "messages": [...],
65
65
  "compression": "auto", # "auto" (default), "on", or "off"
66
66
  "rate": CompressionRate.HIGH, # MEDIUM (0.5), HIGH (0.33), etc.
67
- "privacy": True
67
+ "capture": False # per-request: do not retain message/response bodies
68
68
  }
69
69
  )
70
70
  ```
@@ -73,15 +73,16 @@ response = client.send(
73
73
  - **`rate`**: Controls the aggressiveness of compression. `HIGH` aims for ~67% token reduction.
74
74
  - **`sessionId`**: (Optional) String ID to group multiple requests into a single replayable session in the dashboard.
75
75
  - **`userId`**: (Optional) String ID to track usage and costs per unique end-user.
76
- - **`privacy`**: (Optional) Set to `True` to disable payload logging and session replays for this request. Metadata (latency, tokens) will still be recorded for observability.
76
+ - **`capture`**: (Optional) Per-request override. `False` does not retain messages/responses (metadata like tokens/cost/latency can still be recorded). Precedence: per-request → project setting → default on.
77
77
 
78
78
  ### Supported Models
79
79
 
80
80
  The SDK provides a `TokenBeeModel` enum with popular models:
81
81
 
82
- - `TokenBeeModel.ANTHROPIC_CLAUDE_SONNET_4`
83
- - `TokenBeeModel.OPENAI_GPT_5_MINI`
84
- - `TokenBeeModel.GROQ_GPT_OSS_20B`
82
+ - `TokenBeeModel.OPENAI_GPT_6_ASTRA`
83
+ - `TokenBeeModel.ANTHROPIC_CLAUDE_FABLE_5_1`
84
+ - `TokenBeeModel.GEMINI_3_8_FLASH`
85
+ - `TokenBeeModel.XAI_GROK_4_6`
85
86
  - ... and many others.
86
87
 
87
88
  ## License
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/pyproject.toml RENAMED
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "tokenbee-sdk"
7
- version = "2.0.0"
7
+ version = "2.1.0"
8
8
  authors = [
9
9
  { name="TokenBee Inc.", email="founders@tokenbee.io" },
10
10
  ]
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/setup.py RENAMED
@@ -6,7 +6,7 @@ long_description = (this_directory / "README.md").read_text()
6
6
 
7
7
  setup(
8
8
  name="tokenbee-sdk",
9
- version="2.0.0",
9
+ version="2.1.0",
10
10
  packages=find_packages(),
11
11
  install_requires=["httpx>=0.23.0"],
12
12
  author="TokenBee Inc.",
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee/__init__.py RENAMED
@@ -1,6 +1,7 @@
1
1
  import os
2
2
  import httpx
3
3
  from enum import Enum
4
+ from typing import Optional
4
5
 
5
6
  class CompressionRate(str, Enum):
6
7
  LOW = "0.75"
@@ -20,7 +21,8 @@ class TokenBeeContext(str, Enum):
20
21
  CODE = "code"
21
22
 
22
23
  class TokenBeeModel(str, Enum):
23
- # OpenAI — current GPT-5.6 / GPT-5 family
24
+ # OpenAI — GPT-6 / GPT-5.6 family
25
+ OPENAI_GPT_6_ASTRA = "openai/gpt-6-astra"
24
26
  OPENAI_GPT_5_6_SOL = "openai/gpt-5.6-sol"
25
27
  OPENAI_GPT_5_6_TERRA = "openai/gpt-5.6-terra"
26
28
  OPENAI_GPT_5_6_LUNA = "openai/gpt-5.6-luna"
@@ -42,6 +44,10 @@ class TokenBeeModel(str, Enum):
42
44
  OPENAI_O1_MINI = "openai/o1-mini"
43
45
 
44
46
  # Anthropic
47
+ ANTHROPIC_CLAUDE_FABLE_5_1 = "anthropic/claude-fable-5-1"
48
+ ANTHROPIC_CLAUDE_OPUS_5 = "anthropic/claude-opus-5"
49
+ ANTHROPIC_CLAUDE_SONNET_5 = "anthropic/claude-sonnet-5"
50
+ ANTHROPIC_CLAUDE_HAIKU_4_5 = "anthropic/claude-haiku-4-5"
45
51
  ANTHROPIC_CLAUDE_SONNET_4 = "anthropic/claude-sonnet-4-latest"
46
52
  ANTHROPIC_CLAUDE_OPUS_4 = "anthropic/claude-opus-4-latest"
47
53
  ANTHROPIC_CLAUDE_HAIKU_4 = "anthropic/claude-haiku-4-latest"
@@ -50,6 +56,8 @@ class TokenBeeModel(str, Enum):
50
56
  ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic/claude-3-5-haiku-latest"
51
57
 
52
58
  # Google
59
+ GEMINI_3_8_FLASH = "google/gemini-3.8-flash"
60
+ GEMINI_3_1_PRO = "google/gemini-3.1-pro-preview"
53
61
  GEMINI_2_5_PRO = "google/gemini-2.5-pro"
54
62
  GEMINI_2_5_FLASH = "google/gemini-2.5-flash"
55
63
  GEMINI_2_0_FLASH = "google/gemini-2.0-flash"
@@ -75,6 +83,7 @@ class TokenBeeModel(str, Enum):
75
83
  GROQ_COMPOUND_MINI = "groq/groq/compound-mini"
76
84
 
77
85
  # xAI
86
+ XAI_GROK_4_6 = "xai/grok-4.6"
78
87
  XAI_GROK_3 = "xai/grok-3"
79
88
  XAI_GROK_2 = "xai/grok-2-1212"
80
89
  XAI_GROK_2_MINI = "xai/grok-2-mini-1212"
@@ -90,7 +99,7 @@ class TokenBee:
90
99
  context: str = TokenBeeContext.AUTO,
91
100
  model: str = "",
92
101
  provider: str = "",
93
- privacy: bool = False
102
+ capture: Optional[bool] = None
94
103
  ):
95
104
  self.api_key = api_key
96
105
  self.llm_key = llm_key
@@ -104,8 +113,9 @@ class TokenBee:
104
113
  "X-TokenBee-Rate": rate,
105
114
  "X-TokenBee-Strategy": strategy,
106
115
  "X-TokenBee-Context": context,
107
- "X-TokenBee-Privacy": str(privacy).lower()
108
116
  }
117
+ if capture is not None:
118
+ self.headers["X-TokenBee-Capture"] = str(capture).lower()
109
119
  if model:
110
120
  self.headers["X-TokenBee-Model"] = model
111
121
  if provider:
@@ -130,8 +140,8 @@ class TokenBee:
130
140
  headers["X-TokenBee-Strategy"] = str(input["strategy"])
131
141
  if "context" in input:
132
142
  headers["X-TokenBee-Context"] = str(input["context"])
133
- if "privacy" in input:
134
- headers["X-TokenBee-Privacy"] = str(input["privacy"]).lower()
143
+ if "capture" in input:
144
+ headers["X-TokenBee-Capture"] = str(input["capture"]).lower()
135
145
  if "sessionId" in input:
136
146
  headers["X-TB-Session-Id"] = str(input["sessionId"])
137
147
  if "userId" in input:
@@ -143,7 +153,7 @@ class TokenBee:
143
153
  payload.pop("rate", None)
144
154
  payload.pop("strategy", None)
145
155
  payload.pop("context", None)
146
- payload.pop("privacy", None)
156
+ payload.pop("capture", None)
147
157
  payload.pop("sessionId", None)
148
158
  payload.pop("userId", None)
149
159
 
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/tokenbee_sdk.egg-info/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: tokenbee-sdk
3
- Version: 2.0.0
3
+ Version: 2.1.0
4
4
  Summary: Official Python SDK for TokenBee LLM inference gateway and observability.
5
5
  Author: TokenBee Inc.
6
6
  Author-email: "TokenBee Inc." <founders@tokenbee.io>
@@ -18,13 +18,13 @@ Dynamic: requires-python
18
18
 
19
19
  # TokenBee Python SDK
20
20
 
21
- Official Python SDK for [TokenBee](https://tokenbee.io) - The Intelligent LLM Inference Gateway with Observability, Compression, and Privacy.
21
+ Official Python SDK for [TokenBee](https://tokenbee.io) — AI interaction capture, audit, replay, and optimization.
22
22
 
23
23
  ## Features
24
24
 
25
25
  - **Unified API**: Access multiple LLM providers (OpenAI, Anthropic, Google, Mistral, etc.) through a single interface.
26
26
  - **Intelligent Compression**: Reduce token usage and latency with context-aware compression.
27
- - **Privacy Guard**: Automatic PII masking and privacy-preserving inference.
27
+ - **Configurable Capture**: Retain interaction content when you need it; turn capture off per request or globally.
28
28
  - **Built-in Observability**: Automatic tracking of latency, costs, and token usage.
29
29
 
30
30
  ## Links
@@ -82,7 +82,7 @@ response = client.send(
82
82
  "messages": [...],
83
83
  "compression": "auto", # "auto" (default), "on", or "off"
84
84
  "rate": CompressionRate.HIGH, # MEDIUM (0.5), HIGH (0.33), etc.
85
- "privacy": True
85
+ "capture": False # per-request: do not retain message/response bodies
86
86
  }
87
87
  )
88
88
  ```
@@ -91,15 +91,16 @@ response = client.send(
91
91
  - **`rate`**: Controls the aggressiveness of compression. `HIGH` aims for ~67% token reduction.
92
92
  - **`sessionId`**: (Optional) String ID to group multiple requests into a single replayable session in the dashboard.
93
93
  - **`userId`**: (Optional) String ID to track usage and costs per unique end-user.
94
- - **`privacy`**: (Optional) Set to `True` to disable payload logging and session replays for this request. Metadata (latency, tokens) will still be recorded for observability.
94
+ - **`capture`**: (Optional) Per-request override. `False` does not retain messages/responses (metadata like tokens/cost/latency can still be recorded). Precedence: per-request → project setting → default on.
95
95
 
96
96
  ### Supported Models
97
97
 
98
98
  The SDK provides a `TokenBeeModel` enum with popular models:
99
99
 
100
- - `TokenBeeModel.ANTHROPIC_CLAUDE_SONNET_4`
101
- - `TokenBeeModel.OPENAI_GPT_5_MINI`
102
- - `TokenBeeModel.GROQ_GPT_OSS_20B`
100
+ - `TokenBeeModel.OPENAI_GPT_6_ASTRA`
101
+ - `TokenBeeModel.ANTHROPIC_CLAUDE_FABLE_5_1`
102
+ - `TokenBeeModel.GEMINI_3_8_FLASH`
103
+ - `TokenBeeModel.XAI_GROK_4_6`
103
104
  - ... and many others.
104
105
 
105
106
  ## License
{tokenbee_sdk-2.0.0 → tokenbee_sdk-2.1.0}/setup.cfg RENAMED
File without changes