phase-40: Gemini + Claude provider adapters
Phase 40 PRD (docs/CONTROL_PLANE_PRD.md:82-83) listed: - crates/aibridge/src/providers/gemini.rs - crates/aibridge/src/providers/claude.rs Neither existed. Landing both now, in gateway/src/v1/ (matches the existing ollama.rs + openrouter.rs sibling pattern — aibridge's providers/ is for the adapter *trait* abstractions, v1/ holds the concrete /v1/chat dispatchers that know the wire format). gemini.rs: - POST https://generativelanguage.googleapis.com/v1beta/models/ {model}:generateContent?key=<API_KEY> - Auth: query-string key (not bearer) - Maps messages → contents+parts (Gemini's wire shape), extracts from candidates[0].content.parts[0].text - 3 tests: key resolution, body serialization (camelCase generationConfig + maxOutputTokens), prefix-strip claude.rs: - POST https://api.anthropic.com/v1/messages - Auth: x-api-key header + anthropic-version: 2023-06-01 - Carries system prompt in top-level `system` field (not messages[]). Extracts from content[0].text where type=="text" - 4 tests: key resolution, body serialization with/without system field, prefix-strip v1/mod.rs: + V1State.gemini_key + claude_key Option<String> + resolve_provider() strips "gemini/" and "claude/" prefixes + /v1/chat dispatcher handles "gemini" + "claude"/"anthropic" + 2 new resolve_provider tests (prefix + strip per adapter) main.rs: + Construct both keys at startup via resolve_*_key() helpers. Missing keys log at debug (not warn) since these are optional providers — unlike OpenRouter which is the rescue rung. Every /v1/chat error path mirrors the existing pattern: - 503 SERVICE_UNAVAILABLE when key isn't configured - 502 BAD_GATEWAY with the provider's error text when the upstream call fails - Response shape always the OpenAI-compatible ChatResponse Workspace warnings still at 0. 9 new tests pass. Pre-existing test failure `executor_prompt_includes_surfaced_ candidates` at execution_loop/mod.rs:1550 is unrelated (fails on pristine HEAD too — PR fixture divergence). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
root
@@ -0,0 +1,222 @@
|
||||
//! Claude (Anthropic) adapter.
|
||||
//!
|
||||
//! POST `https://api.anthropic.com/v1/messages`. Auth via `x-api-key`
|
||||
//! header (not bearer) + required `anthropic-version` header. Payload
|
||||
//! is NOT OpenAI-compatible — response text lives at
|
||||
//! `content[0].text`. Phase 40 deliverable. System prompts travel in
|
||||
//! a top-level `system` field, separate from the `messages` array.
|
||||
|
||||
use std::time::Duration;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::{ChatRequest, ChatResponse, Choice, Message, UsageBlock};
|
||||
|
||||
const CLAUDE_BASE_URL: &str = "https://api.anthropic.com/v1";
|
||||
const CLAUDE_API_VERSION: &str = "2023-06-01";
|
||||
const CLAUDE_TIMEOUT_SECS: u64 = 180;
|
||||
|
||||
pub fn resolve_claude_key() -> Option<String> {
|
||||
if let Ok(k) = std::env::var("ANTHROPIC_API_KEY") {
|
||||
if !k.trim().is_empty() { return Some(k.trim().to_string()); }
|
||||
}
|
||||
for path in ["/home/profit/.env", "/root/.env"] {
|
||||
if let Ok(raw) = std::fs::read_to_string(path) {
|
||||
for line in raw.lines() {
|
||||
if let Some(rest) = line.strip_prefix("ANTHROPIC_API_KEY=") {
|
||||
let k = rest.trim().trim_matches('"').trim_matches('\'');
|
||||
if !k.is_empty() { return Some(k.to_string()); }
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
pub async fn chat(
|
||||
key: &str,
|
||||
req: &ChatRequest,
|
||||
) -> Result<ChatResponse, String> {
|
||||
// Strip the "claude/" prefix if the caller used the namespaced form.
|
||||
let model = req.model.strip_prefix("claude/").unwrap_or(&req.model).to_string();
|
||||
|
||||
// Anthropic carries system prompts outside the messages array.
|
||||
// Concatenate any system-role messages into a single system string;
|
||||
// keep user + assistant messages in `messages`.
|
||||
let mut system_parts: Vec<String> = Vec::new();
|
||||
let mut msgs: Vec<AnMessage> = Vec::new();
|
||||
for m in &req.messages {
|
||||
if m.role == "system" {
|
||||
system_parts.push(m.content.clone());
|
||||
} else {
|
||||
// Anthropic expects strictly "user" or "assistant"; anything
|
||||
// else we normalize to "user".
|
||||
let role = if m.role == "assistant" { "assistant" } else { "user" };
|
||||
msgs.push(AnMessage { role: role.to_string(), content: m.content.clone() });
|
||||
}
|
||||
}
|
||||
let system = if system_parts.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(system_parts.join("\n\n"))
|
||||
};
|
||||
|
||||
let body = AnChatBody {
|
||||
model: model.clone(),
|
||||
messages: msgs,
|
||||
max_tokens: req.max_tokens.unwrap_or(800),
|
||||
temperature: req.temperature.unwrap_or(0.3),
|
||||
system,
|
||||
};
|
||||
|
||||
let client = reqwest::Client::builder()
|
||||
.timeout(Duration::from_secs(CLAUDE_TIMEOUT_SECS))
|
||||
.build()
|
||||
.map_err(|e| format!("build client: {e}"))?;
|
||||
|
||||
let t0 = std::time::Instant::now();
|
||||
let resp = client
|
||||
.post(format!("{}/messages", CLAUDE_BASE_URL))
|
||||
.header("x-api-key", key)
|
||||
.header("anthropic-version", CLAUDE_API_VERSION)
|
||||
.json(&body)
|
||||
.send()
|
||||
.await
|
||||
.map_err(|e| format!("api.anthropic.com unreachable: {e}"))?;
|
||||
|
||||
let status = resp.status();
|
||||
if !status.is_success() {
|
||||
let body = resp.text().await.unwrap_or_else(|_| "?".into());
|
||||
return Err(format!("claude {}: {}", status, body));
|
||||
}
|
||||
|
||||
let parsed: AnChatResponse = resp.json().await
|
||||
.map_err(|e| format!("invalid claude response: {e}"))?;
|
||||
|
||||
let latency_ms = t0.elapsed().as_millis();
|
||||
let text = parsed.content.into_iter()
|
||||
.find(|b| b.block_type == "text")
|
||||
.map(|b| b.text)
|
||||
.unwrap_or_default();
|
||||
|
||||
let prompt_tokens = parsed.usage.as_ref().map(|u| u.input_tokens).unwrap_or_else(|| {
|
||||
let chars: usize = req.messages.iter().map(|m| m.content.chars().count()).sum();
|
||||
((chars + 3) / 4) as u32
|
||||
});
|
||||
let completion_tokens = parsed.usage.as_ref().map(|u| u.output_tokens).unwrap_or_else(|| {
|
||||
((text.chars().count() + 3) / 4) as u32
|
||||
});
|
||||
|
||||
tracing::info!(
|
||||
target: "v1.chat",
|
||||
provider = "claude",
|
||||
model = %model,
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
latency_ms = latency_ms as u64,
|
||||
"claude chat completed",
|
||||
);
|
||||
|
||||
Ok(ChatResponse {
|
||||
id: format!("chatcmpl-{}", chrono::Utc::now().timestamp_nanos_opt().unwrap_or(0)),
|
||||
object: "chat.completion",
|
||||
created: chrono::Utc::now().timestamp(),
|
||||
model,
|
||||
choices: vec![Choice {
|
||||
index: 0,
|
||||
message: Message { role: "assistant".into(), content: text },
|
||||
finish_reason: parsed.stop_reason.unwrap_or_else(|| "stop".into()),
|
||||
}],
|
||||
usage: UsageBlock {
|
||||
prompt_tokens,
|
||||
completion_tokens,
|
||||
total_tokens: prompt_tokens + completion_tokens,
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
// -- Anthropic Messages API wire shapes --
|
||||
|
||||
#[derive(Serialize)]
|
||||
struct AnChatBody {
|
||||
model: String,
|
||||
messages: Vec<AnMessage>,
|
||||
max_tokens: u32,
|
||||
temperature: f64,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
system: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(Serialize)]
|
||||
struct AnMessage { role: String, content: String }
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct AnChatResponse {
|
||||
content: Vec<AnContentBlock>,
|
||||
#[serde(default, rename = "stop_reason")]
|
||||
stop_reason: Option<String>,
|
||||
#[serde(default)]
|
||||
usage: Option<AnUsage>,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct AnContentBlock {
|
||||
#[serde(rename = "type")]
|
||||
block_type: String,
|
||||
#[serde(default)]
|
||||
text: String,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct AnUsage { input_tokens: u32, output_tokens: u32 }
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn resolve_claude_key_does_not_panic() {
|
||||
let _ = resolve_claude_key();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn chat_body_serializes_with_separate_system() {
|
||||
let body = AnChatBody {
|
||||
model: "claude-3-5-sonnet-latest".into(),
|
||||
messages: vec![
|
||||
AnMessage { role: "user".into(), content: "hi".into() },
|
||||
],
|
||||
max_tokens: 800,
|
||||
temperature: 0.3,
|
||||
system: Some("You are helpful.".into()),
|
||||
};
|
||||
let json = serde_json::to_string(&body).unwrap();
|
||||
assert!(json.contains("\"system\":\"You are helpful.\""));
|
||||
assert!(json.contains("\"messages\""));
|
||||
assert!(json.contains("\"max_tokens\":800"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn body_omits_system_when_none() {
|
||||
let body = AnChatBody {
|
||||
model: "claude-3-5-sonnet-latest".into(),
|
||||
messages: vec![AnMessage { role: "user".into(), content: "hi".into() }],
|
||||
max_tokens: 800,
|
||||
temperature: 0.3,
|
||||
system: None,
|
||||
};
|
||||
let json = serde_json::to_string(&body).unwrap();
|
||||
assert!(!json.contains("\"system\""), "system field should be skipped when None: {json}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn model_prefix_strip_preserves_bare_names() {
|
||||
let cases = [
|
||||
("claude/claude-3-5-sonnet-latest", "claude-3-5-sonnet-latest"),
|
||||
("claude-3-5-sonnet-latest", "claude-3-5-sonnet-latest"),
|
||||
];
|
||||
for (input, expected) in cases {
|
||||
let out = input.strip_prefix("claude/").unwrap_or(input);
|
||||
assert_eq!(out, expected);
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user