ctxprotocol 0.14.0__tar.gz → 0.16.0__tar.gz

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ctxprotocol
-Version: 0.14.0
+Version: 0.16.0
 Summary: Official Python SDK for the Context Protocol - Discover and execute AI tools programmatically
 Project-URL: Homepage, https://ctxprotocol.com
 Project-URL: Documentation, https://docs.ctxprotocol.com
@@ -42,7 +42,7 @@ Description-Content-Type: text/markdown
 
 Give your agent the live facts it's missing. Context is a pay-per-response data marketplace: your agent discovers tools at runtime, buys the data its question needs, and drops it straight into its context window — no API keys, no servers, no per-source integration work.
 
-Context Protocol is **pip for AI capabilities**. Just as you install packages to add functionality to your code, use the Context SDK to give your Agent instant access to thousands of live data sources and actions—from DeFi and Gas Oracles to Weather and Search.
+Context Protocol is **pip for AI capabilities**. Just as you install packages to add functionality to your code, use the Context SDK to give your Agent instant access to premium data feeds and live tools: the market intelligence usually locked behind steep monthly or annual subscriptions, unbundled into pay-per-response, from crypto and on-chain analytics to gas oracles, weather, and search.
 
 [![PyPI version](https://img.shields.io/pypi/v/ctxprotocol.svg)](https://pypi.org/project/ctxprotocol/)
 [![Python versions](https://img.shields.io/pypi/pyversions/ctxprotocol.svg)](https://pypi.org/project/ctxprotocol/)
@@ -65,7 +65,7 @@ Grant batches open periodically — see [Developer Grants](https://docs.ctxproto
 ## Why use Context?
 
 - **🔌 One Interface, Everything:** Stop integrating APIs one by one. Use a single SDK to access any tool in the marketplace.
-- **🧠 Zero-Ops:** We're a gateway to the best MCP tools. Just send the JSON and get the result.
+- **🧠 Zero-Ops:** We're the gateway to premium data feeds usually locked behind steep subscriptions. We host the connections; you just send the JSON and get the result.
 - **⚡️ Agentic Discovery:** Your Agent can search the marketplace at runtime to find tools it didn't know it needed.
 - **💸 Dual-Surface Economics:** Use Query for pay-per-response intelligence or Execute for session-budgeted method calls.
 
@@ -125,12 +125,12 @@ result = await client.tools.execute(
 print(result.session)  # method_price, spent, remaining, max_spend, ...
 ```
 
-**Query mode** gives you a managed librarian contract — the server runs the live pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with model-aware context budgeting and can return plain answers or structured evidence packages for one flat fee:
+**Query mode** gives you a managed librarian contract — the server runs the live pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with model-aware context budgeting and returns structured evidence packages for one flat fee:
 ```python
 answer = await client.query.run(
     query="What are the top whale movements on Base?",
     answer_model_id="glm-model",  # optional: choose the final synthesis model
-    response_shape="answer_with_evidence",  # optional: answer | answer_with_evidence | evidence_only
+    response_shape="answer_with_evidence",  # optional: answer_with_evidence (default) | evidence_only
     include_data_url=True,     # optional: persist full execution data to blob
     include_developer_trace=True,  # optional: include runtime developer trace
 )
@@ -156,9 +156,8 @@ print(answer.orchestration_metrics)  # Optional first-pass / rediscovery metrics
 
 `response_shape` options:
 
-- `answer`: backward-compatible prose answer
-- `answer_with_evidence`: prose plus `summary`, `evidence`, `artifacts`, `freshness`, `confidence`, `usage`, `outcome`, and `controller`
-- `evidence_only`: machine-friendly summary plus the same evidence package for downstream agents
+- `answer_with_evidence` (default): prose plus `summary`, `evidence`, `artifacts`, `freshness`, `confidence`, `usage`, `outcome`, and `controller`
+- `evidence_only`: raw fetched data, computed artifacts, and provenance for downstream agents (no prose synthesis)
 
 Premium wedge answers can also expose `evidence.market_intelligence`, `view.rows`, `view.columns`, and the top-level controller fields `stop_reason`, `issue_class`, and `actions_taken`.
 
@@ -300,7 +299,7 @@ closed = await client.tools.close_session("sess_123")
 
 #### `client.query.run(query, tools?, answer_model_id?, include_data?, include_data_url?, include_developer_trace?, idempotency_key?)`
 
-Run an agentic query. The server applies the live librarian pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with up to 100 MCP calls per response turn, then returns the selected Query response contract (`answer`, `answer_with_evidence`, or `evidence_only`).
+Run an agentic query. The server applies the live librarian pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with up to 100 MCP calls per response turn, then returns the selected Query response contract (`answer_with_evidence` or `evidence_only`, default `answer_with_evidence`).
 
 `client.query.run()` buffers the same SSE transport used by `client.query.stream()` and returns the final `done` result. This keeps Python aligned with the TypeScript SDK and the live query runtime.
 

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/README.md

@@ -4,7 +4,7 @@
 
 Give your agent the live facts it's missing. Context is a pay-per-response data marketplace: your agent discovers tools at runtime, buys the data its question needs, and drops it straight into its context window — no API keys, no servers, no per-source integration work.
 
-Context Protocol is **pip for AI capabilities**. Just as you install packages to add functionality to your code, use the Context SDK to give your Agent instant access to thousands of live data sources and actions—from DeFi and Gas Oracles to Weather and Search.
+Context Protocol is **pip for AI capabilities**. Just as you install packages to add functionality to your code, use the Context SDK to give your Agent instant access to premium data feeds and live tools: the market intelligence usually locked behind steep monthly or annual subscriptions, unbundled into pay-per-response, from crypto and on-chain analytics to gas oracles, weather, and search.
 
 [![PyPI version](https://img.shields.io/pypi/v/ctxprotocol.svg)](https://pypi.org/project/ctxprotocol/)
 [![Python versions](https://img.shields.io/pypi/pyversions/ctxprotocol.svg)](https://pypi.org/project/ctxprotocol/)
@@ -27,7 +27,7 @@ Grant batches open periodically — see [Developer Grants](https://docs.ctxproto
 ## Why use Context?
 
 - **🔌 One Interface, Everything:** Stop integrating APIs one by one. Use a single SDK to access any tool in the marketplace.
-- **🧠 Zero-Ops:** We're a gateway to the best MCP tools. Just send the JSON and get the result.
+- **🧠 Zero-Ops:** We're the gateway to premium data feeds usually locked behind steep subscriptions. We host the connections; you just send the JSON and get the result.
 - **⚡️ Agentic Discovery:** Your Agent can search the marketplace at runtime to find tools it didn't know it needed.
 - **💸 Dual-Surface Economics:** Use Query for pay-per-response intelligence or Execute for session-budgeted method calls.
 
@@ -87,12 +87,12 @@ result = await client.tools.execute(
 print(result.session)  # method_price, spent, remaining, max_spend, ...
 ```
 
-**Query mode** gives you a managed librarian contract — the server runs the live pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with model-aware context budgeting and can return plain answers or structured evidence packages for one flat fee:
+**Query mode** gives you a managed librarian contract — the server runs the live pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with model-aware context budgeting and returns structured evidence packages for one flat fee:
 ```python
 answer = await client.query.run(
     query="What are the top whale movements on Base?",
     answer_model_id="glm-model",  # optional: choose the final synthesis model
-    response_shape="answer_with_evidence",  # optional: answer | answer_with_evidence | evidence_only
+    response_shape="answer_with_evidence",  # optional: answer_with_evidence (default) | evidence_only
     include_data_url=True,     # optional: persist full execution data to blob
     include_developer_trace=True,  # optional: include runtime developer trace
 )
@@ -118,9 +118,8 @@ print(answer.orchestration_metrics)  # Optional first-pass / rediscovery metrics
 
 `response_shape` options:
 
-- `answer`: backward-compatible prose answer
-- `answer_with_evidence`: prose plus `summary`, `evidence`, `artifacts`, `freshness`, `confidence`, `usage`, `outcome`, and `controller`
-- `evidence_only`: machine-friendly summary plus the same evidence package for downstream agents
+- `answer_with_evidence` (default): prose plus `summary`, `evidence`, `artifacts`, `freshness`, `confidence`, `usage`, `outcome`, and `controller`
+- `evidence_only`: raw fetched data, computed artifacts, and provenance for downstream agents (no prose synthesis)
 
 Premium wedge answers can also expose `evidence.market_intelligence`, `view.rows`, `view.columns`, and the top-level controller fields `stop_reason`, `issue_class`, and `actions_taken`.
 
@@ -262,7 +261,7 @@ closed = await client.tools.close_session("sess_123")
 
 #### `client.query.run(query, tools?, answer_model_id?, include_data?, include_data_url?, include_developer_trace?, idempotency_key?)`
 
-Run an agentic query. The server applies the live librarian pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with up to 100 MCP calls per response turn, then returns the selected Query response contract (`answer`, `answer_with_evidence`, or `evidence_only`).
+Run an agentic query. The server applies the live librarian pipeline (`discover -> select -> iterative execute -> synthesize -> settle`) with up to 100 MCP calls per response turn, then returns the selected Query response contract (`answer_with_evidence` or `evidence_only`, default `answer_with_evidence`).
 
 `client.query.run()` buffers the same SSE transport used by `client.query.stream()` and returns the final `done` result. This keeps Python aligned with the TypeScript SDK and the live query runtime.
 

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/ctxprotocol/__init__.py

@@ -31,7 +31,7 @@ Example:
 For more information, visit: https://ctxprotocol.com
 """
 
-__version__ = "0.14.0"
+__version__ = "0.15.0"
 
 # Re-export everything from client module
 from ctxprotocol.client import (

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/ctxprotocol/client/resources/query.py

@@ -216,7 +216,8 @@ class Query:
             tools: Optional tool IDs to use (auto-discover if not provided)
             favorites_only: Restrict auto-discovery to favorite tools for this request
             answer_model_id: Optional answer model ID for final synthesis
-            response_shape: Structured response mode for query answers
+            response_shape: Structured response mode (`answer_with_evidence` or
+                `evidence_only`; server default `answer_with_evidence`)
             include_data: Include execution data inline in the query response
             include_data_url: Persist execution data to blob and return URL
             include_developer_trace: Include machine-readable Developer Mode traces
@@ -304,7 +305,8 @@ class Query:
             tools: Optional tool IDs to use (auto-discover if not provided)
             favorites_only: Restrict auto-discovery to favorite tools for this request
             answer_model_id: Optional answer model ID for final synthesis
-            response_shape: Structured response mode for query answers
+            response_shape: Structured response mode (`answer_with_evidence` or
+                `evidence_only`; server default `answer_with_evidence`)
             include_data: Include execution data inline in the query response
             include_data_url: Persist execution data to blob and return URL
             include_developer_trace: Include machine-readable Developer Mode traces

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/ctxprotocol/client/types.py

@@ -601,7 +601,7 @@ class ExecuteSessionResult(BaseModel):
 # from the query; this is a soft hint rather than a hard switch.
 QueryDepth = Literal["fast", "auto", "deep"]
 QueryOutcomeType = Literal["answer", "capability_miss"]
-QueryResponseShape = Literal["answer", "answer_with_evidence", "evidence_only"]
+QueryResponseShape = Literal["answer_with_evidence", "evidence_only"]
 QueryAttemptForkReason = Literal[
     "manual_fork",
     "bounded_rediscovery",
@@ -712,13 +712,14 @@ class QueryOptions(BaseModel):
         default=None,
         alias="responseShape",
         description=(
-            "Structured response mode. The runtime always produces a grounded "
-            "result (raw data + computed artifacts + provenance); this controls "
-            "whether a prose synthesis layer is added on top. "
+            "Structured response mode. Defaults to `answer_with_evidence` on the "
+            "server when omitted. The runtime always produces a grounded result "
+            "(raw data + computed artifacts + provenance); this controls whether "
+            "a prose synthesis layer is added on top. "
             "`answer_with_evidence` returns prose plus the structured grounding "
             "(chat parity); `evidence_only` returns grounding only with no prose "
             "(the agent-harness shape, with raw data + computed_artifacts + "
-            "grounding by default); `answer` is the legacy prose-only shape."
+            "grounding by default)."
         ),
     )
     include_data: bool | None = Field(

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/ctxprotocol/context/hyperliquid.py

@@ -212,6 +212,7 @@ class HyperliquidContext(BaseModel):
 
     Attributes:
         wallet_address: The wallet address this context is for
+        active_wallet_address: The single EOA actually connected to Hyperliquid
         perp_positions: Perpetual positions
         open_orders: Open orders
         spot_balances: Spot balances
@@ -224,6 +225,18 @@ class HyperliquidContext(BaseModel):
         alias="walletAddress",
         description="The wallet address this context is for",
     )
+    active_wallet_address: str | None = Field(
+        default=None,
+        alias="activeWalletAddress",
+        description=(
+            "The active wallet address for querying/signing. When multiple EOAs "
+            "are linked, this is the single externally-owned account actually "
+            "connected to Hyperliquid (determined by activity detection on the "
+            "client). Contributors should prefer this over wallet_address when "
+            "issuing Hyperliquid API calls, since wallet_address may be "
+            "comma-joined across multiple linked wallets."
+        ),
+    )
     perp_positions: list[HyperliquidPerpPosition] = Field(
         ...,
         alias="perpPositions",

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/ctxprotocol/context/polymarket.py

@@ -72,7 +72,8 @@ class PolymarketContext(BaseModel):
     This is what gets passed to MCP tools for personalized analysis.
 
     Attributes:
-        wallet_address: The wallet address this context is for
+        wallet_address: The wallet address this context is for (may be comma-separated if multiple)
+        active_wallet_address: The active wallet address for signing (the one with Polymarket activity)
         positions: All open positions
         open_orders: All open orders
         total_value: Total portfolio value in USD (sum of position values)
@@ -82,7 +83,17 @@ class PolymarketContext(BaseModel):
     wallet_address: str = Field(
         ...,
         alias="walletAddress",
-        description="The wallet address this context is for",
+        description="The wallet address this context is for (may be comma-separated if multiple)",
+    )
+    active_wallet_address: str | None = Field(
+        default=None,
+        alias="activeWalletAddress",
+        description=(
+            "The active wallet address for signing (the one with Polymarket "
+            "activity). When multiple wallets are linked, this is the wallet that "
+            "should be used for placing orders. Determined by activity detection "
+            "on the client."
+        ),
     )
     positions: list[PolymarketPosition] = Field(..., description="All open positions")
     open_orders: list[PolymarketOrder] = Field(

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/examples/server/hummingbot-contributor/requirements.txt

@@ -14,7 +14,7 @@ uvicorn[standard]>=0.30.0
 hummingbot-api-client>=1.2.6
 
 # Context Protocol SDK for payment verification
-ctxprotocol>=0.8.3
+ctxprotocol>=0.16.0
 
 # Environment management
 python-dotenv>=1.0.0

{ctxprotocol-0.14.0 → ctxprotocol-0.16.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ctxprotocol"
-version = "0.14.0"
+version = "0.16.0"
 description = "Official Python SDK for the Context Protocol - Discover and execute AI tools programmatically"
 readme = "README.md"
 license = "MIT"