mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-19 05:32:19 +03:00
* feat(responses): virtualize previous_response_id continuation regardless of upstream support OmniRoute now exposes OpenAI-compatible previous_response_id/store continuation to clients unconditionally, even when the selected upstream provider has no native Responses-API state support. Reconstruction happens server-side in handleChatImplementation, before any downstream validation or provider translation: OmniRoute resolves the response id back to the full input/output it previously produced, prepends it to the client's delta, and forwards the full reconstructed history upstream exactly as it does today. Client<->OmniRoute traffic shrinks to the new delta only; OmniRoute<->provider traffic is unchanged. Storage reuses the existing call-log pipeline artifact (already gated by call_log_pipeline_enabled, already retained/cleaned up by the existing call-log lifecycle) instead of duplicating conversation content into a second store -- only a lightweight call_logs.response_id index is new. Every lookup is scoped by api_key_id so one client can never resolve another client's stored conversation, and any unresolvable/missing/ size-limit-omitted state fails closed with OpenAI's own previous_response_not_found contract. Stacked on feat/openai-responses-store-toggle (#10121). * feat(dashboard): agentic conversation tracking with live transcript view Every agentic chat request now gets a conversation id (X-ConversationId response header). OmniRoute detects when a follow-up request continues the same conversation via fingerprint + bounded prefix-hash matching, with a strict-growth invariant to prevent false merges between independent single-shot requests that happen to share identical opening content. Continuation detection excludes the system message from the identity anchor, since real coding-agent CLIs commonly regenerate it every request with live context (timestamp, cwd, git status) — without this, that volatility alone broke every continuation check against real traffic. - `/dashboard/logs`: new toggleable Conversation column. - `/dashboard/logs/timeline`: requests sharing a conversation id share a timeline lane, connected by an arrow, with a configurable lane-reuse window. - Request detail panel: new Full Conversation transcript above the raw SSE event stream — Markdown rendering, per-turn timestamps, turn-relative view, click-any-turn navigation, live auto-refresh building the transcript in real time from the in-flight SSE chunk buffer while a request is still streaming, auto-scroll-to-bottom as the live turn grows. - New `/dashboard/conversations` page listing conversations with 2+ turns, no-forking model (an edited/duplicated mid-history turn mints its own independent conversation instead of merging), pagination, duplicate- anchor fix. - Configurable auto-refresh intervals on both the timeline and conversations list pages. - Responses API tool-call gap fix: turnsFromOpenAiMessages only handled role-based Chat Completions messages, so bare {type:"function_call"} / {type:"function_call_output"} / {type:"reasoning"} items (real Responses API traffic) silently vanished from the Conversation Context panel. - truncateForLog now counts input[] (Responses API), not just messages[] (Chat Completions), so a truncated /v1/responses request still shows a placeholder instead of nothing. - RequestTimeline.tsx now reads the same debugEnabled/emailsVisible settings RequestLoggerV2.tsx already used, instead of hardcoding both false — the timeline view never showed SSE/stream-chunk events or respected email-masking, regardless of the actual setting. Migrations 147/148 (agentic_conversations, conversation_turn_nodes) — 135 and 136 are now taken upstream; 143-145 are documented KNOWN_GAPS, so this uses the next free slot past upstream's current highest. Test plan: - npm run typecheck:core — clean - npm run lint — clean - node --import tsx/esm scripts/check/check-migration-numbering.mjs — OK, 0 collisions - 109 unit tests across the conversation-tracking, migration-renumber, and dashboard-wiring surface — 0 failures * refactor(dashboard): reuse call-log artifacts for conversation transcript content conversation_turn_nodes no longer stores turn text/tool-call content (text_preview/block_kind/tool_name) -- it's identity-only now (id/parent/ content_hash), matching agentic_conversations' existing lightweight-index shape. Every node's originating request is already fully captured by the call-log pipeline artifact its last_correlation_id points at, so the /dashboard/conversations tree view resolves each node's actual display content on demand from there (open-sse/services/conversationTurnContent.ts), re-running the same extractCanonicalTurns/hashTurnContent the write path used and matching by content_hash, instead of duplicating conversation content into a second store under a separate retention/gating policy. This also drops the old 8000-char text_preview truncation entirely -- resolved content is always full and untruncated. The frontend contract is unchanged (tree API still returns {textPreview, blockKind, toolName} per node), so the dashboard UI itself (page.tsx, RequestLoggerDetail/RequestTimeline, sidebar, i18n) needed no changes. Renumbered the cherry-picked 147/148 migrations to 153/154 -- 147 now collides with 147_api_keys_model_access_mode.sql, which landed on release/v3.8.50 after this work was originally built. Also includes a standalone, unrelated fix carried along from this rebase: close isProviderModelHidden's missing function-body brace in modelSelectModalHelpers.ts (separately landed as #10206). Stacked on feat/responses-previous-response-id-virtualization (#3), which is itself stacked on feat/openai-responses-store-toggle (#10121). * fix(dashboard): resync conversation list on open so the live-text poll starts immediately openConversation() seeded activeConversation (and therefore activeCallLogId, which gates the live-partial-text poll effect) from whatever row snapshot the list's own fixed-interval poll last produced. A conversation opened right after a reply started streaming -- after that tick, before the next -- had activeCallLogId still null, so the live-text poll never started; only a subsequent background list-poll resync (already existed) picked it up, which is why closing and reopening the same conversation "just worked". loadConversations() is now a shared callback so openConversation can force one immediately on open instead of waiting on pollSeconds. Live-verified against omniroute-dev: opening a conversation mid-stream now shows live reasoning on the first open. * style: prettier formatting for conversationTurnContent.test.ts * fix(db): close migration numbering gap left by decoupling from #3/#10262 153/154 (originally 154/155) were chosen back when this branch stacked on top of the previous_response_id migration (153_call_logs_response_id.sql). Decoupling removed that migration from this branch's history, leaving an unused 153 slot that check-migration-numbering.test.ts correctly flags as a gap. * refactor(dashboard): split RequestTimeline/RequestLoggerDetail under the 1000-line file-size cap Both files exceeded check-file-size's new-file cap after this PR's own additions (RequestTimeline 1048, RequestLoggerDetail 1163). Extracted pure non-component logic (types, constants, allocateLanes and its helpers) out of RequestTimeline.tsx into RequestTimeline.utils.ts, and the two self-contained presentational sub-components (PayloadSection, ConversationContextSection + its private helper) out of RequestLoggerDetail.tsx into RequestLoggerDetail.sections.tsx. No behavior change; existing external imports (default exports, allocateLanes, TimelineLog, CONVERSATION_LANE_REUSE_STORAGE_KEY) still resolve from the original file paths. * fix(db): renumber agentic-conversation migrations to clear 153 collision + sync migration-count docs The refresh-merge of release/v3.8.50 exposed that the feature's three migrations collided at slot 153 with the base's radar_local_model_state (153) and its own call_logs_response_id. Migration runner enforces unique numeric prefixes -> every DB init threw, red-ing Vitest, all Unit shards and the DB-backed quality gates. Renumber the feature's pair to 155_agentic_conversations / 156_conversation_turn_nodes and move call_logs_response_id to 154 (keeps 153_radar base-owned, preserves agentic-before-turn_nodes ordering). Update SQL headers and the 154/156 references in feature code + tests. Migration count is now 151 (was 148 stale in README/AGENTS/llm.txt) — sync the doc counts to clear the docs-accuracy gate. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(ui): drop unused CONVERSATION_LANE_REUSE_STORAGE_KEY re-export from RequestTimeline Knip 6.32 (baseline 415) flags the public re-export of CONVERSATION_LANE_REUSE_STORAGE_KEY from RequestTimeline.tsx as dead: no external consumer imports it through that re-export (it is imported and used directly from RequestTimeline.utils.ts inside the component). Removed the unused re-export; the internal import stays. DEAD_TOTAL 416 -> 415, back to the frozen baseline. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(agentic-conversations): guard resolveConversationId, drop dead whole-chain export - Wrap resolveConversationId() in try/catch in chat.ts, matching the defensive pattern used by every other best-effort side call nearby, so a DB hiccup in conversation tracking can't turn a working chat request into a hard failure. - Remove getConversationTurnTree: knip's project scope excludes tests/**, so an export used only by tests can never register as used there. Swap its 8 test call sites to the paginated getConversationTurnPage (already the dashboard's canonical query) with a generous limit, collapsing to one query path instead of keeping a second whole-chain export alive solely for test convenience. - Regenerate i18n llm.txt mirrors from root (pre-existing drift on this branch, unrelated to the above, caught by the docs-sync pre-commit gate). Addresses PR review feedback. * fix(i18n): close requestLogger conversation-column gap, fix domain-modules count drift - fr.json, vi.json were missing requestLogger.columns.conversation (added in the conversation-tracking feature), failing i18n-vi-completeness.test.ts. - docs/i18n/*/llm.txt mirrors still said 117 domain-specific files after an earlier rebase fixed the migration count but missed this companion number, failing check-docs-sync.mjs across all 42 locales. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> * fix(docs): restore PROXY_LOG_INCLUDE_IPS env/doc entries (env-doc-sync red) .env.example and docs/reference/ENVIRONMENT.md were both missing the PROXY_LOG_INCLUDE_IPS entry that src/lib/proxyLogger.ts already reads (confirmed present at this branch's merge-base too, so this predates the conversation-tracking work and is unrelated to it) -- the entry was added on release/v3.8.50 after this branch's last sync and this branch never picked it up. That gap red-lines tests/unit/check-env-doc-sync.test.ts and tests/unit/issue-7793-env-doc-sync-repro.test.ts (Unit Tests fast-path 2/4 in CI). Restore both entries verbatim from the current release/v3.8.50 tip -- no feature-code change. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: hartmark <hartmark@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
243 lines
8.8 KiB
TypeScript
243 lines
8.8 KiB
TypeScript
"use client";
|
|
|
|
import { useState, useEffect, useRef } from "react";
|
|
import { useTranslations } from "next-intl";
|
|
import { ChatBubble } from "@/app/(dashboard)/dashboard/tools/traffic-inspector/components/chat/ChatBubble";
|
|
import { buildRequestTurns, buildResponseTurns } from "@/mitm/inspector/conversationNormalizer";
|
|
import type { InterceptedRequest, NormalizedTurn } from "@/mitm/inspector/types";
|
|
|
|
// ─── Payload Code Block ─────────────────────────────────────────────────────
|
|
|
|
export function PayloadSection({ title, json, onCopy, collapsible = true, defaultOpen = true }) {
|
|
const t = useTranslations("requestLogger.detail");
|
|
const [copied, setCopied] = useState(false);
|
|
const [open, setOpen] = useState(defaultOpen);
|
|
|
|
const handleCopy = async () => {
|
|
const success = await onCopy();
|
|
if (success !== false) {
|
|
setCopied(true);
|
|
setTimeout(() => setCopied(false), 2000);
|
|
}
|
|
};
|
|
|
|
return (
|
|
<div>
|
|
<div className="flex items-center justify-between mb-2">
|
|
<div className="flex items-center gap-3">
|
|
<h3 className="text-[11px] text-text-muted uppercase tracking-wider font-bold">
|
|
{title}
|
|
</h3>
|
|
{collapsible && (
|
|
<button
|
|
onClick={() => setOpen((v) => !v)}
|
|
className="p-1 rounded hover:bg-bg-subtle text-text-muted hover:text-text-primary transition-colors"
|
|
aria-label={open ? t("collapse", { title }) : t("expand", { title })}
|
|
>
|
|
<span className="material-symbols-outlined text-[16px]">
|
|
{open ? "expand_less" : "expand_more"}
|
|
</span>
|
|
</button>
|
|
)}
|
|
</div>
|
|
<button
|
|
onClick={handleCopy}
|
|
className="flex items-center gap-1 px-2 py-1 text-xs text-text-muted hover:text-text-primary transition-colors"
|
|
aria-label={t("copyTitle", { title })}
|
|
>
|
|
<span className="material-symbols-outlined text-[14px]">
|
|
{copied ? "check" : "content_copy"}
|
|
</span>
|
|
{copied ? t("copied") : t("copy")}
|
|
</button>
|
|
</div>
|
|
{open && (
|
|
<pre className="p-4 rounded-xl bg-black/5 dark:bg-black/30 border border-border overflow-x-auto text-xs font-mono text-text-main max-h-150 overflow-y-auto leading-relaxed whitespace-pre-wrap break-words">
|
|
{json}
|
|
</pre>
|
|
)}
|
|
</div>
|
|
);
|
|
}
|
|
|
|
// ─── Conversation context section ───────────────────────────────────────────
|
|
// Renders THIS request's own context (its request body's messages/input, plus
|
|
// its response) — a plain single-request normalization, same shape as the
|
|
// traffic-inspector's ConversationTab, no cross-request reconstruction. While
|
|
// the request is still generating (detail.active === true) the response side
|
|
// shows the partial text captured so far, refreshed on a short poll scoped to
|
|
// just this section.
|
|
const CONVERSATION_ACTIVE_POLL_INTERVAL_MS = 1200;
|
|
|
|
function asInterceptedResponseBody(responseBody: unknown): InterceptedRequest {
|
|
return {
|
|
id: "",
|
|
source: "custom-host",
|
|
timestamp: "",
|
|
method: "POST",
|
|
host: "",
|
|
path: "",
|
|
requestHeaders: {},
|
|
requestBody: null,
|
|
requestSize: 0,
|
|
responseHeaders: {},
|
|
responseBody: responseBody != null ? JSON.stringify(responseBody) : null,
|
|
responseSize: 0,
|
|
status: 0,
|
|
detectedKind: "llm",
|
|
};
|
|
}
|
|
|
|
export function ConversationContextSection({ log, detail }) {
|
|
const [open, setOpen] = useState(true);
|
|
const [liveDetail, setLiveDetail] = useState(detail);
|
|
const [liveRefresh, setLiveRefresh] = useState(() => {
|
|
try {
|
|
const v = localStorage.getItem("pref:conversationContext:liveRefresh");
|
|
return v == null ? true : v === "1";
|
|
} catch {
|
|
return true;
|
|
}
|
|
});
|
|
const turnsBoxRef = useRef<HTMLDivElement>(null);
|
|
|
|
useEffect(() => {
|
|
setLiveDetail(detail);
|
|
}, [detail]);
|
|
|
|
// Same live-poll pattern as the SSE Events section (StreamSection below),
|
|
// but gated on liveRefresh too: an active request keeps generating either
|
|
// way, this toggle only controls whether THIS panel keeps fetching/
|
|
// redrawing while the user reads it.
|
|
useEffect(() => {
|
|
if (!liveDetail?.active || !liveRefresh) return;
|
|
let cancelled = false;
|
|
let timeoutId: ReturnType<typeof setTimeout> | undefined;
|
|
|
|
const tick = () => {
|
|
if (cancelled) return;
|
|
if (document.visibilityState !== "visible") {
|
|
timeoutId = setTimeout(tick, CONVERSATION_ACTIVE_POLL_INTERVAL_MS);
|
|
return;
|
|
}
|
|
fetch(`/api/logs/${log.id}`, { cache: "no-store" })
|
|
.then((res) => (res.ok ? res.json() : null))
|
|
.then((data) => {
|
|
if (cancelled || !data) return;
|
|
setLiveDetail(data);
|
|
if (data.active) timeoutId = setTimeout(tick, CONVERSATION_ACTIVE_POLL_INTERVAL_MS);
|
|
})
|
|
.catch(() => {
|
|
timeoutId = setTimeout(tick, CONVERSATION_ACTIVE_POLL_INTERVAL_MS);
|
|
});
|
|
};
|
|
|
|
timeoutId = setTimeout(tick, CONVERSATION_ACTIVE_POLL_INTERVAL_MS);
|
|
return () => {
|
|
cancelled = true;
|
|
if (timeoutId) clearTimeout(timeoutId);
|
|
};
|
|
}, [liveDetail?.active, liveRefresh, log.id]);
|
|
|
|
const toggleLiveRefresh = () => {
|
|
const next = !liveRefresh;
|
|
setLiveRefresh(next);
|
|
try {
|
|
localStorage.setItem("pref:conversationContext:liveRefresh", next ? "1" : "0");
|
|
} catch {}
|
|
};
|
|
|
|
const scrollToBottom = () => {
|
|
const el = turnsBoxRef.current;
|
|
if (!el) return;
|
|
requestAnimationFrame(() => {
|
|
try {
|
|
el.scrollTop = el.scrollHeight;
|
|
} catch {}
|
|
});
|
|
};
|
|
|
|
const requestBody =
|
|
liveDetail?.requestBody ?? liveDetail?.pipelinePayloads?.clientRequest ?? null;
|
|
const requestTurns = buildRequestTurns(requestBody) ?? [];
|
|
|
|
const responseBody = liveDetail?.responseBody ?? null;
|
|
const responseTurns: NormalizedTurn[] =
|
|
responseBody != null
|
|
? buildResponseTurns(asInterceptedResponseBody(responseBody))
|
|
: liveDetail?.partialAssistantText
|
|
? [
|
|
{
|
|
role: "assistant",
|
|
blocks: [{ type: "text", text: liveDetail.partialAssistantText }],
|
|
},
|
|
]
|
|
: [];
|
|
|
|
const allTurns: NormalizedTurn[] = [...requestTurns, ...responseTurns];
|
|
|
|
// Follow new content as it streams in — same idea as StreamSection's
|
|
// autoscroll effect, tied to the same liveRefresh toggle.
|
|
useEffect(() => {
|
|
if (!liveRefresh || !open) return;
|
|
scrollToBottom();
|
|
}, [allTurns.length, liveDetail?.partialAssistantText, liveRefresh, open]);
|
|
|
|
if (allTurns.length === 0) return null;
|
|
|
|
return (
|
|
<div>
|
|
<div className="flex items-center justify-between gap-3 mb-2">
|
|
<div className="flex items-center gap-3">
|
|
<h3 className="text-[11px] text-text-muted uppercase tracking-wider font-bold">
|
|
Conversation Context
|
|
</h3>
|
|
<button
|
|
onClick={() => setOpen((v) => !v)}
|
|
className="p-1 rounded hover:bg-bg-subtle text-text-muted hover:text-text-primary transition-colors"
|
|
aria-label={open ? "Collapse Conversation Context" : "Expand Conversation Context"}
|
|
>
|
|
<span className="material-symbols-outlined text-[16px]">
|
|
{open ? "expand_less" : "expand_more"}
|
|
</span>
|
|
</button>
|
|
</div>
|
|
{open && (
|
|
<div className="flex items-center gap-1">
|
|
{liveDetail?.active && (
|
|
<button
|
|
onClick={toggleLiveRefresh}
|
|
title={liveRefresh ? "Live refresh: on" : "Live refresh: off"}
|
|
className={`p-1 rounded hover:bg-bg-subtle text-text-muted hover:text-text-primary transition-colors ${liveRefresh ? "text-primary" : ""}`}
|
|
aria-pressed={liveRefresh}
|
|
>
|
|
<span className="material-symbols-outlined text-[18px]">
|
|
{liveRefresh ? "sync" : "sync_disabled"}
|
|
</span>
|
|
</button>
|
|
)}
|
|
<button
|
|
onClick={scrollToBottom}
|
|
title="Go to bottom"
|
|
className="p-1 rounded hover:bg-bg-subtle text-text-muted hover:text-text-primary transition-colors"
|
|
aria-label="Go to bottom"
|
|
>
|
|
<span className="material-symbols-outlined text-[18px]">vertical_align_bottom</span>
|
|
</button>
|
|
</div>
|
|
)}
|
|
</div>
|
|
{open && (
|
|
<div
|
|
ref={turnsBoxRef}
|
|
className="rounded-xl bg-black/5 dark:bg-black/30 border border-border max-h-150 overflow-y-auto p-3 space-y-2"
|
|
>
|
|
{allTurns.map((turn, i) => (
|
|
<ChatBubble key={i} turn={turn} />
|
|
))}
|
|
</div>
|
|
)}
|
|
</div>
|
|
);
|
|
}
|