From 52b2ca78aed7950af27d4865aee65da781514a99 Mon Sep 17 00:00:00 2001 From: T Date: Sun, 26 Apr 2026 11:09:37 -0600 Subject: Initial work, and name change to pantograph --- docs/phase-2.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'docs/phase-2.md') diff --git a/docs/phase-2.md b/docs/phase-2.md index 877f8bd..af45546 100644 --- a/docs/phase-2.md +++ b/docs/phase-2.md @@ -84,7 +84,7 @@ No inference needed — Anthropic gives us explicit boundaries. - Thinking → `{ "type": "thinking", "thinking": "..." }` - ToolUse → `{ "type": "tool_use", "id": "...", "name": "...", "input": {...} }` (phase 3+) -Note: Anthropic expects ToolUse's `input` as a parsed JSON object, not a string. Since we store `input` as raw bytes in a TextualBlock, we will need to parse it into a `std.json.Value` during Anthropic serialization. This is the one place where libawl does parse tool input JSON — it's a serialization requirement, not an interpretation of the tool schema. The round-trip guarantee is: the bytes we stored serialize back to equivalent JSON when sent to Anthropic. +Note: Anthropic expects ToolUse's `input` as a parsed JSON object, not a string. Since we store `input` as raw bytes in a TextualBlock, we will need to parse it into a `std.json.Value` during Anthropic serialization. This is the one place where libpanto does parse tool input JSON — it's a serialization requirement, not an interpretation of the tool schema. The round-trip guarantee is: the bytes we stored serialize back to equivalent JSON when sent to Anthropic. --- @@ -132,7 +132,7 @@ AnthropicConfig = struct { }; ``` -Separate from `OpenAIConfig`. The CLI and any higher-level config can unify them; libawl treats them as distinct. +Separate from `OpenAIConfig`. The CLI and any higher-level config can unify them; libpanto treats them as distinct. --- @@ -149,7 +149,7 @@ Separate from `OpenAIConfig`. The CLI and any higher-level config can unify them ### Integration test (manual) -- Run `awl` binary against Anthropic API with a real API key +- Run `panto` binary against Anthropic API with a real API key - Hold a multi-turn conversation with thinking model - Verify thinking and text stream correctly - Switch to OpenAI provider, verify same experience -- cgit v1.3