fix(agent): live chat turns persist incrementally, survive client disconnect

Fix A3 of plans/2026-07-11-nomos-agent-code-review.md. handleChat only ever
saved the assistant message ONCE, after a.chat(...) returned, using
ctx := r.Context() for that write — the same context that cancels the instant
the client disconnects (Stop button, tab close, network blip). A disconnect
mid-turn meant the final save ran with an already-cancelled context and its
error was never checked: the entire turn's tool-call history was silently
lost from the persisted transcript, even though real work (executions
launched, knowledge written) had already happened server-side.

Brought handleChat in line with resumeSession's existing pattern
(continue.go): insert a placeholder assistant row immediately, update the
SAME row after every tool call. The key fix is WHICH context the writes use —
a new pctx := context.Background() for every DB write in this handler
(session creation/touch, the user message, question auto-close, the
placeholder + incremental updates, the title update), while ctx/r.Context()
still gates the agent's own work (a.chat) and the SSE writes exactly as
before — a disconnect still correctly stops the agent from doing further
work, it just no longer also erases what it already did.

Verified live: sent a message requiring 6 tool calls (get_entity/
get_relations/get_blast_radius on two targets) and force-killed the client
connection mid-stream with curl -m 12 (confirmed via exit code 28). Before
this fix the persisted transcript would show 0 tool-call entries; after,
all 12 raw tool_use/tool_result entries (6 calls × 2) were present and
correctly attributed by tool name — proving both that progress survives an
abort and that the incremental writes aren't corrupting the data.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

cmd/nomos/main.go

@@ -17,6 +17,7 @@ import (
 	"time"
 
 	"github.com/dtoro/oikos/internal/safego"
+	"github.com/google/uuid"
 )
 
 func main() {
@@ -173,9 +174,21 @@ func handleChat(w http.ResponseWriter, r *http.Request, a *agent, st *store) {
 	ctx := r.Context()
 	sessionID := req.SessionID
 
+	// pctx (persistence context) is deliberately context.Background(), not
+	// ctx/r.Context(), for every DB write in this handler — ctx cancels the
+	// instant the client disconnects (Stop button, tab close, network blip),
+	// and a write made with an already-cancelled context fails. Before this
+	// fix, the assistant message was only ever saved ONCE, at the very end,
+	// using ctx — so a disconnect mid-turn silently lost the ENTIRE turn's
+	// tool-call history from the persisted transcript, even though real work
+	// (executions launched, knowledge written) had already happened
+	// server-side. The agent's own work (a.chat below) still correctly stops
+	// when ctx cancels — this only changes what happens to persistence.
+	pctx := context.Background()
+
 	if sessionID == "" {
 		title := truncate(req.Message, 80)
-		sess, err := st.createSession(ctx, title)
+		sess, err := st.createSession(pctx, title)
 		if err != nil {
 			slog.Error("nomos: create session", "error", err)
 			sessionID = "ephemeral"
@@ -183,20 +196,20 @@ func handleChat(w http.ResponseWriter, r *http.Request, a *agent, st *store) {
 			sessionID = sess.ID
 		}
 	} else {
-		st.touchSession(ctx, sessionID)
+		st.touchSession(pctx, sessionID)
 	}
 
 	slog.Info("nomos: chat", "session", sessionID, "message", truncate(req.Message, 100))
 
 	userMsg, _ := json.Marshal(map[string]any{"role": "user", "text": req.Message})
-	st.saveMessage(ctx, sessionID, "user", userMsg)
+	st.saveMessage(pctx, sessionID, "user", userMsg)
 
 	// If this task has a pending operator question, the incoming message IS the
 	// answer — close it so the panel clears. No separate resume needed: this
 	// chat turn is the resume, and the agent sees the question + answer in its
 	// replayed history.
-	if qid := st.openQuestionID(ctx, sessionID); qid != "" {
+	if qid := st.openQuestionID(pctx, sessionID); qid != "" {
-		st.answerQuestion(ctx, sessionID, qid, req.Message)
+		st.answerQuestion(pctx, sessionID, qid, req.Message)
 	}
 
 	sseEvent(w, flusher, agentEvent{Type: "session", Data: sessionID, SessionID: sessionID})
@@ -204,12 +217,34 @@ func handleChat(w http.ResponseWriter, r *http.Request, a *agent, st *store) {
 	toolCalls := []map[string]any{}
 	var finalText string
 
+	// Incremental persistence, mirroring resumeSession's existing
+	// placeholder+update pattern (continue.go): insert a placeholder now,
+	// update the SAME row after every tool call, so whatever happened before
+	// an abort is never lost — only what hadn't happened yet is.
+	placeholder, _ := json.Marshal(map[string]any{"role": "assistant", "text": ""})
+	msgID, err := st.insertMessageReturningID(pctx, sessionID, "assistant", placeholder)
+	if err != nil {
+		slog.Error("nomos: chat placeholder insert failed", "session", sessionID, "error", err)
+	}
+	persist := func() {
+		if msgID == uuid.Nil {
+			return
+		}
+		body, _ := json.Marshal(map[string]any{
+			"role":       "assistant",
+			"text":       finalText,
+			"tool_calls": toolCalls,
+		})
+		st.updateMessage(pctx, msgID, body)
+	}
+
 	a.chat(ctx, sessionID, req.Message, func(ev agentEvent) {
 		if ev.Type == "tool_use" || ev.Type == "tool_result" {
 			if m, ok := ev.Data.(map[string]any); ok {
 				m["type"] = ev.Type
 				toolCalls = append(toolCalls, m)
 			}
+			persist() // live: survives even if the client disconnects right after
 		}
 		if ev.Type == "text" {
 			finalText, _ = ev.Data.(string)
@@ -217,19 +252,14 @@ func handleChat(w http.ResponseWriter, r *http.Request, a *agent, st *store) {
 		sseEvent(w, flusher, ev)
 	})
 
-	assistantMsg, _ := json.Marshal(map[string]any{
+	persist() // final state — same row, updated one last time with the concluding text
-		"role":       "assistant",
-		"text":       finalText,
-		"tool_calls": toolCalls,
-	})
-	st.saveMessage(ctx, sessionID, "assistant", assistantMsg)
 
 	// Generate a meaningful title from the assistant's first answer
 	// instead of reusing the raw user message for every session.
 	if finalText != "" && sessionID != "ephemeral" {
 		title := truncate(finalText, 80)
 		if title != "" {
-			st.updateSessionTitle(ctx, sessionID, title)
+			st.updateSessionTitle(pctx, sessionID, title)
 		}
 	}
 }