update docs and tutorials to use new settlement mode names

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: balogh.adam@icloud.com

.claude/skills/opengradient/SKILL.md

@@ -68,9 +68,9 @@ client.llm.ensure_opg_approval(opg_amount=5)
 
 ## Settlement Modes (`og.x402SettlementMode`)
 
-- `SETTLE` — Hashes only (maximum privacy)
-- `SETTLE_METADATA` — Full data on-chain (maximum transparency)
-- `SETTLE_BATCH` — Aggregated hashes (most cost-efficient, default)
+- `PRIVATE` — Hashes only (maximum privacy)
+- `INDIVIDUAL_FULL` — Full data on-chain (maximum transparency)
+- `BATCH_HASHED` — Aggregated hashes (most cost-efficient, default)
 
 ## Core Patterns
 

.claude/skills/opengradient/api-reference.md

@@ -46,7 +46,7 @@ client.llm.chat(
     stream: bool = False,
     tools: list[dict] = None,      # Function definitions
     tool_choice: str = None,       # "auto", "none", or specific
-    x402_settlement_mode: og.x402SettlementMode = og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode: og.x402SettlementMode = og.x402SettlementMode.BATCH_HASHED,
 ) -> TextGenerationOutput | TextGenerationStream
 ```
 
@@ -137,9 +137,9 @@ Returned by `client.alpha.infer()`.
 
 | Mode | Value | Description |
 |------|-------|-------------|
-| `SETTLE` | `"private"` | Hashes only — maximum privacy |
-| `SETTLE_METADATA` | `"individual"` | Full data on-chain — maximum transparency |
-| `SETTLE_BATCH` | `"batch"` | Aggregated hashes — most cost-efficient (default) |
+| `PRIVATE` | `"private"` | Hashes only — maximum privacy |
+| `INDIVIDUAL_FULL` | `"individual"` | Full data on-chain — maximum transparency |
+| `BATCH_HASHED` | `"batch"` | Aggregated hashes — most cost-efficient (default) |
 
 ---
 
@@ -242,7 +242,7 @@ llm = og.agents.langchain_adapter(
     private_key: str,
     model_cid: og.TEE_LLM,
     max_tokens: int = 300,
-    x402_settlement_mode: og.x402SettlementMode = og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode: og.x402SettlementMode = og.x402SettlementMode.BATCH_HASHED,
 )
 ```
 

README.md

@@ -293,16 +293,16 @@ Manage, host, and execute models through the Model Hub with direct integration i
 
 OpenGradient supports multiple settlement modes through the x402 payment protocol:
 
-- **SETTLE**: Records cryptographic hashes only (maximum privacy)
-- **SETTLE_METADATA**: Records complete input/output data (maximum transparency)
-- **SETTLE_BATCH**: Aggregates multiple inferences (most cost-efficient)
+- **PRIVATE**: Payment only, no input/output data on-chain (maximum privacy)
+- **BATCH_HASHED**: Aggregates inferences into a Merkle tree with input/output hashes and signatures (most cost-efficient, default)
+- **INDIVIDUAL_FULL**: Records input, output, timestamp, and verification on-chain (maximum auditability)
 
 Specify settlement mode in your requests:
 ```python
 result = client.llm.chat(
     model=og.TEE_LLM.GPT_5,
     messages=[{"role": "user", "content": "Hello"}],
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
 )
 ```
 

docs/CLAUDE_SDK_USERS.md

@@ -59,7 +59,7 @@ result = client.llm.chat(
     tools: List[Dict] = [],            # Optional: function calling
     tool_choice: str = None,           # "auto", "none", or specific tool
     stop_sequence: List[str] = None,
-    x402_settlement_mode: x402SettlementMode = x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode: x402SettlementMode = x402SettlementMode.BATCH_HASHED,
     stream: bool = False,              # Enable streaming responses
 )
 # Returns: TextGenerationOutput (or TextGenerationStream if stream=True)
@@ -78,7 +78,7 @@ result = client.llm.completion(
     max_tokens: int = 100,
     temperature: float = 0.0,
     stop_sequence: List[str] = None,
-    x402_settlement_mode: x402SettlementMode = x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode: x402SettlementMode = x402SettlementMode.BATCH_HASHED,
 )
 # Returns: TextGenerationOutput
 #   - completion_output: str (raw text)
@@ -272,9 +272,9 @@ og.InferenceMode.TEE        # Trusted Execution Environment
 og.InferenceMode.ZKML       # Zero-knowledge proof
 
 # x402 Payment Settlement Modes (for LLM calls)
-og.x402SettlementMode.SETTLE           # Input/output hashes only (most private)
-og.x402SettlementMode.SETTLE_BATCH     # Batch hashes (most cost-efficient, default)
-og.x402SettlementMode.SETTLE_METADATA  # Full data and metadata on-chain
+og.x402SettlementMode.PRIVATE           # Input/output hashes only (most private)
+og.x402SettlementMode.BATCH_HASHED     # Batch hashes (most cost-efficient, default)
+og.x402SettlementMode.INDIVIDUAL_FULL  # Full data and metadata on-chain
 
 # Workflow data types
 og.CandleType.OPEN, .HIGH, .LOW, .CLOSE, .VOLUME

tutorials/01-verifiable-ai-agent.md

@@ -58,7 +58,7 @@ llm = og.agents.langchain_adapter(
     private_key=private_key,
     model_cid=og.TEE_LLM.GPT_4_1_2025_04_14,
     max_tokens=500,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
 )
 ```
 
@@ -223,9 +223,9 @@ is recorded on-chain:
 
 | Mode | What's Stored | Best For |
 |------|--------------|----------|
-| `SETTLE` | Hashes of input and output only | **Privacy** -- proves execution happened without revealing content |
-| `SETTLE_BATCH` | Batch hash of multiple inferences | **Cost efficiency** -- reduces per-call gas costs (default) |
-| `SETTLE_METADATA` | Full model info, input, output, and metadata | **Transparency** -- complete auditability for compliance |
+| `PRIVATE` | Hashes of input and output only | **Privacy** -- proves execution happened without revealing content |
+| `BATCH_HASHED` | Batch hash of multiple inferences | **Cost efficiency** -- reduces per-call gas costs (default) |
+| `INDIVIDUAL_FULL` | Full model info, input, output, and metadata | **Transparency** -- complete auditability for compliance |
 
 Choose based on your requirements:
 
@@ -234,21 +234,21 @@ Choose based on your requirements:
 llm_dev = og.agents.langchain_adapter(
     private_key=os.environ["OG_PRIVATE_KEY"],
     model_cid=og.TEE_LLM.GPT_4_1_2025_04_14,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
 )
 
 # For production financial applications -- full audit trail
 llm_prod = og.agents.langchain_adapter(
     private_key=os.environ["OG_PRIVATE_KEY"],
     model_cid=og.TEE_LLM.GPT_4_1_2025_04_14,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_METADATA,
+    x402_settlement_mode=og.x402SettlementMode.INDIVIDUAL_FULL,
 )
 
 # For privacy-sensitive applications -- minimal on-chain footprint
 llm_private = og.agents.langchain_adapter(
     private_key=os.environ["OG_PRIVATE_KEY"],
     model_cid=og.TEE_LLM.GPT_4_1_2025_04_14,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE,
+    x402_settlement_mode=og.x402SettlementMode.PRIVATE,
 )
 ```
 
@@ -299,7 +299,7 @@ llm = og.agents.langchain_adapter(
     private_key=private_key,
     model_cid=og.TEE_LLM.GPT_4_1_2025_04_14,
     max_tokens=500,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
 )
 
 # ── Standard tool ─────────────────────────────────────────────────────────
@@ -356,5 +356,5 @@ if __name__ == "__main__":
   models deployed on OpenGradient.
 - **Read workflow results**: Use `og.alphasense.create_read_workflow_tool` to read
   from scheduled on-chain workflows that run models automatically.
-- **Go to production**: Switch settlement mode to `SETTLE_METADATA` and store the
+- **Go to production**: Switch settlement mode to `INDIVIDUAL_FULL` and store the
   payment hashes and transaction hashes for your compliance records.

tutorials/02-streaming-multi-provider.md

@@ -163,17 +163,17 @@ privacy/cost/transparency trade-off:
 
 | Mode | On-Chain Data | Use Case |
 |------|--------------|----------|
-| `SETTLE` | Input/output hashes only | **Privacy** -- prove execution without revealing content |
-| `SETTLE_BATCH` | Batch digest of multiple calls | **Cost efficiency** -- lower gas per inference (default) |
-| `SETTLE_METADATA` | Full model, input, output, metadata | **Transparency** -- complete audit trail |
+| `PRIVATE` | Input/output hashes only | **Privacy** -- prove execution without revealing content |
+| `BATCH_HASHED` | Batch digest of multiple calls | **Cost efficiency** -- lower gas per inference (default) |
+| `INDIVIDUAL_FULL` | Full model, input, output, metadata | **Transparency** -- complete audit trail |
 
 ```python
 # Privacy-first: only hashes stored on-chain
 result_private = client.llm.chat(
     model=og.TEE_LLM.CLAUDE_SONNET_4_6,
     messages=[{"role": "user", "content": "Sensitive query here."}],
     max_tokens=100,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE,
+    x402_settlement_mode=og.x402SettlementMode.PRIVATE,
 )
 print(f"Payment hash (SETTLE): {result_private.payment_hash}")
 
@@ -182,18 +182,18 @@ result_batch = client.llm.chat(
     model=og.TEE_LLM.CLAUDE_SONNET_4_6,
     messages=[{"role": "user", "content": "Regular query."}],
     max_tokens=100,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
 )
-print(f"Payment hash (SETTLE_BATCH): {result_batch.payment_hash}")
+print(f"Payment hash (BATCH_HASHED): {result_batch.payment_hash}")
 
 # Full transparency: everything on-chain
 result_transparent = client.llm.chat(
     model=og.TEE_LLM.CLAUDE_SONNET_4_6,
     messages=[{"role": "user", "content": "Auditable query."}],
     max_tokens=100,
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_METADATA,
+    x402_settlement_mode=og.x402SettlementMode.INDIVIDUAL_FULL,
 )
-print(f"Payment hash (SETTLE_METADATA): {result_transparent.payment_hash}")
+print(f"Payment hash (INDIVIDUAL_FULL): {result_transparent.payment_hash}")
 ```
 
 All three calls return a `payment_hash` you can look up on-chain. The difference is
@@ -308,9 +308,9 @@ print("\n")
 
 # ── Settlement modes ──────────────────────────────────────────────────────
 for mode_name, mode in [
-    ("SETTLE",          og.x402SettlementMode.SETTLE),
-    ("SETTLE_BATCH",    og.x402SettlementMode.SETTLE_BATCH),
-    ("SETTLE_METADATA", og.x402SettlementMode.SETTLE_METADATA),
+    ("PRIVATE",          og.x402SettlementMode.PRIVATE),
+    ("BATCH_HASHED",    og.x402SettlementMode.BATCH_HASHED),
+    ("INDIVIDUAL_FULL", og.x402SettlementMode.INDIVIDUAL_FULL),
 ]:
     try:
         r = client.llm.chat(

tutorials/03-verified-tool-calling.md

@@ -179,7 +179,7 @@ result = client.llm.chat(
     # "auto" lets the model decide whether to call a tool or respond with text.
     # "none" forces a text-only response.
     tool_choice="auto",
-    x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+    x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
 )
 ```
 
@@ -225,7 +225,7 @@ def run_agent(client: og.Client, user_query: str) -> str:
                 temperature=0.0,
                 tools=TOOLS,
                 tool_choice="auto",
-                x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+                x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
             )
         except Exception as e:
             print(f"  LLM call failed: {e}")
@@ -376,7 +376,7 @@ def run_agent(user_query: str) -> str:
             result = client.llm.chat(
                 model=og.TEE_LLM.GPT_5, messages=messages, max_tokens=600,
                 temperature=0.0, tools=TOOLS, tool_choice="auto",
-                x402_settlement_mode=og.x402SettlementMode.SETTLE_BATCH,
+                x402_settlement_mode=og.x402SettlementMode.BATCH_HASHED,
             )
         except Exception as e:
             return f"Error: {e}"
@@ -409,5 +409,5 @@ if __name__ == "__main__":
   even during multi-turn tool loops. See **Tutorial 2** for streaming basics.
 - **Use different providers**: Swap `og.TEE_LLM.GPT_5` for `CLAUDE_SONNET_4_6` or
   `GEMINI_2_5_FLASH` -- tool calling works across all providers.
-- **Add settlement transparency**: Switch to `SETTLE_METADATA` to store the full
+- **Add settlement transparency**: Switch to `INDIVIDUAL_FULL` to store the full
   tool-calling reasoning chain on-chain for audit purposes.