feat(ai): USER_NAME env + shared summary prompt + test-bin knobs

Introduces USER_NAME (default "Me") as the single source for the message
sender label and the first-person persona across daily summaries, SMS
context, insight generation, and chat. Eliminates the "Me:" transcript /
"what I did" ambiguity that confused smaller models, and unhardcodes
"Cameron" from prompt text + the knowledge-graph owner entity. Set
USER_NAME=Cameron in .env to preserve the existing owner entity row
(keyed on UNIQUE(name, entity_type)) — otherwise the next run creates
a fresh owner entity and orphans the existing facts/photo-links.

Also:
- search_messages redirect: when the model calls it with date/contact
  but no query, return a hint pointing at get_sms_messages instead of
  a bare missing-parameter error (prevents same-turn retry loops)
- sharpen search_messages vs get_sms_messages tool descriptions so
  content-vs-time-based intent is unambiguous
- extract build_daily_summary_prompt (+ DAILY_SUMMARY_MESSAGE_LIMIT,
  DAILY_SUMMARY_SYSTEM_PROMPT) shared by daily_summary_job and
  test_daily_summary binary — prompt tweaks now land in both
- EMBEDDING_MODEL const; fixes both insert sites that stored
  "mxbai-embed-large:335m" while generate_embeddings actually runs
  "nomic-embed-text:v1.5"
- test_daily_summary: add --num-ctx / --temperature / --top-p /
  --top-k / --min-p flags wired into OllamaClient setters, and print
  the configured knobs at the top of each run
- OllamaClient::generate now logs prompt/gen token counts and tok/s
  via log_chat_metrics (symmetric with chat_with_tools)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/ai/daily_summary_job.rs

@@ -6,12 +6,84 @@ use std::collections::HashMap;
 use std::sync::{Arc, Mutex};
 use tokio::time::sleep;
 
-use crate::ai::{OllamaClient, SmsApiClient, SmsMessage};
+use crate::ai::{EMBEDDING_MODEL, OllamaClient, SmsApiClient, SmsMessage, user_display_name};
 use crate::database::{DailySummaryDao, InsertDailySummary};
 use crate::otel::global_tracer;
 
 /// Strip boilerplate prefixes and common phrases from summaries before embedding.
 /// This improves embedding diversity by removing structural similarity.
+/// Maximum number of messages passed to the summarizer for a single day.
+/// Tuned to avoid token overflow on typical chat models; shared between
+/// the production job and the test binary so they can't drift.
+pub const DAILY_SUMMARY_MESSAGE_LIMIT: usize = 300;
+
+/// System prompt used when generating daily conversation summaries.
+pub const DAILY_SUMMARY_SYSTEM_PROMPT: &str =
+    "You are a conversation summarizer. Create clear, factual summaries with \
+     precise subject attribution AND extract distinctive keywords. Focus on \
+     specific, unique terms that differentiate this conversation from others.";
+
+/// Build the prompt for a single day's conversation summary. Shared by the
+/// production job and the test binary so prompt tweaks land in both places.
+/// Returns `(prompt, system_prompt)`.
+pub fn build_daily_summary_prompt(
+    contact: &str,
+    date: &NaiveDate,
+    messages: &[SmsMessage],
+) -> (String, &'static str) {
+    let user_name = user_display_name();
+    let messages_text: String = messages
+        .iter()
+        .take(DAILY_SUMMARY_MESSAGE_LIMIT)
+        .map(|m| {
+            if m.is_sent {
+                format!("{}: {}", user_name, m.body)
+            } else {
+                format!("{}: {}", m.contact, m.body)
+            }
+        })
+        .collect::<Vec<_>>()
+        .join("\n");
+
+    let prompt = format!(
+        r#"Summarize this day's conversation between {user_name} and {contact}.
+
+CRITICAL FORMAT RULES:
+- Do NOT start with "Based on the conversation..." or "Here is a summary..." or similar preambles
+- Do NOT repeat the date at the beginning
+- Start DIRECTLY with the content - begin with a person's name or action
+- Write in past tense, as if recording what happened
+
+NARRATIVE (4-8 sentences):
+- What specific topics, activities, or events were discussed?
+- What places, people, or organizations were mentioned?
+- What plans were made or decisions discussed?
+- Clearly distinguish between what {user_name} did versus what {contact} did
+
+KEYWORDS (comma-separated):
+5-10 specific keywords that capture this conversation's unique content:
+- Proper nouns (people, places, brands)
+- Specific activities ("drum corps audition" not just "music")
+- Distinctive terms that make this day unique
+
+Date: {month_day_year} ({weekday})
+Messages:
+{messages_text}
+
+YOUR RESPONSE (follow this format EXACTLY):
+Summary: [Start directly with content, NO preamble]
+
+Keywords: [specific, unique terms]"#,
+        user_name = user_name,
+        contact = contact,
+        month_day_year = date.format("%B %d, %Y"),
+        weekday = date.format("%A"),
+        messages_text = messages_text,
+    );
+
+    (prompt, DAILY_SUMMARY_SYSTEM_PROMPT)
+}
+
 pub fn strip_summary_boilerplate(summary: &str) -> String {
     let mut text = summary.trim().to_string();
 
@@ -290,65 +362,10 @@ async fn generate_and_store_daily_summary(
     span.set_attribute(KeyValue::new("contact", contact.to_string()));
     span.set_attribute(KeyValue::new("message_count", messages.len() as i64));
 
-    // Format messages for LLM
-    let messages_text: String = messages
-        .iter()
-        .take(200) // Limit to 200 messages per day to avoid token overflow
-        .map(|m| {
-            if m.is_sent {
-                format!("Me: {}", m.body)
-            } else {
-                format!("{}: {}", m.contact, m.body)
-            }
-        })
-        .collect::<Vec<_>>()
-        .join("\n");
-
-    let weekday = date.format("%A");
-
-    let prompt = format!(
-        r#"Summarize this day's conversation between me and {}.
-
-CRITICAL FORMAT RULES:
-- Do NOT start with "Based on the conversation..." or "Here is a summary..." or similar preambles
-- Do NOT repeat the date at the beginning
-- Start DIRECTLY with the content - begin with a person's name or action
-- Write in past tense, as if recording what happened
-
-NARRATIVE (3-5 sentences):
-- What specific topics, activities, or events were discussed?
-- What places, people, or organizations were mentioned?
-- What plans were made or decisions discussed?
-- Clearly distinguish between what "I" did versus what {} did
-
-KEYWORDS (comma-separated):
-5-10 specific keywords that capture this conversation's unique content:
-- Proper nouns (people, places, brands)
-- Specific activities ("drum corps audition" not just "music")
-- Distinctive terms that make this day unique
-
-Date: {} ({})
-Messages:
-{}
-
-YOUR RESPONSE (follow this format EXACTLY):
-Summary: [Start directly with content, NO preamble]
-
-Keywords: [specific, unique terms]"#,
-        contact,
-        contact,
-        date.format("%B %d, %Y"),
-        weekday,
-        messages_text
-    );
+    let (prompt, system_prompt) = build_daily_summary_prompt(contact, date, messages);
 
     // Generate summary with LLM
-    let summary = ollama
-        .generate(
-            &prompt,
-            Some("You are a conversation summarizer. Create clear, factual summaries with precise subject attribution AND extract distinctive keywords. Focus on specific, unique terms that differentiate this conversation from others."),
-        )
-        .await?;
+    let summary = ollama.generate(&prompt, Some(system_prompt)).await?;
 
     log::debug!(
         "Generated summary for {}: {}",
@@ -381,8 +398,7 @@ Keywords: [specific, unique terms]"#,
         message_count: messages.len() as i32,
         embedding,
         created_at: Utc::now().timestamp(),
-        // model_version: "nomic-embed-text:v1.5".to_string(),
-        model_version: "mxbai-embed-large:335m".to_string(),
+        model_version: EMBEDDING_MODEL.to_string(),
     };
 
     // Create context from current span for DB operation