Sipflow

[cost: free (pure CPU, no network) | read-only, no persistence] Take two SIP messages (typically the same request observed at two adjacent hops - e.g. the INVITE leaving FreeSWITCH and the INVITE arriving at Kamailio) and surface a structured per-header diff: `added`, `removed`, `mutated` (with old/new value), `duplicated` (single header → many), `de-duplicated`, `whitespace-only-change`, `parameter-reorder` (Via params, From tag), and `body-changed`. SDP bodies on both sides are delegated to `compareSdp` for codec / DTLS / ICE diffs. Use FIRST when the user has two captures or two log lines that should be carrying the same message and wants to know what an intermediate proxy / SBC / B2BUA changed. Far more reliable than visual inspection. Pair with: `parse_sip_message` to inspect either side in isolation; `lint_sip_request` if the diff reveals the downstream side became malformed; `search_sip_docs(vendor=<intermediate>)` once you know which hop's behavior is the source of the change.

[cost: external_io (DNS via Cloudflare + Google; TLS handshake + a SIP OPTIONS keepalive to public targets when applicable) | read-only | rate-limited per IP: 10/min, 200/day] Walk DNS the same way a SIP UA does (RFC 3263 §4.1): NAPTR → SRV → A/AAAA. Given a SIP URI ("sip:example.com"), bare hostname ("example.com"), or "host:port" string, return the records that exist and the resolution ladder a UA would try. When the queried target uses TLS (`sips:` URI, `transport=tls/wss`, or any `_sips._tcp` SRV record), the tool also performs a TLS handshake against each resolved sips target and reports the negotiated TLS version + cipher, the leaf certificate's subject / issuer / SANs / validity, the chain length and whether it validates against Node's default trust store, plus two cert-domain checks: RFC 5922 §7.2 strict (cert must cover the original SIP domain) and a lenient SAN match against the SRV target hostname. SIP liveness: DNS resolving and a TLS handshake succeeding do NOT prove the endpoint actually speaks SIP - a load-balanced node can accept TCP/TLS yet black-hole SIP. So the tool ALSO sends a real SIP OPTIONS keepalive to each resolved public IP across the relevant transports (UDP/TCP on 5060, TLS on 5061 / SRV port) and reports per-IP answered / timeout / refused. Any SIP response (even 405/403/404) proves the stack is alive on that IP. When a name resolves to multiple IPs it is treated as a load-balancer fan-out and each IP is probed individually, with a warning about the known failure modes of fronting stateful SIP/RTP with a cloud L4 LB (AWS NLB/ALB etc.): cross-zone-off targets that black-hole, the ~120s UDP idle timeout, and per-5-tuple hashing splitting signaling from media. Egress safety: - Per-IP rate limited. - Hostnames that resolve only to RFC 1918 / loopback / link-local / documentation / multicast space are refused (SSRF guard). - Walk depth capped to prevent runaway NAPTR / CNAME chains. - TLS probes capped at 6 (host, port, ip) tuples per call, 5 s handshake timeout each, public-IP only (we connect to the resolved IP, not the hostname, so the system resolver cannot redirect us into private space). - SIP OPTIONS probes capped at 6 (ip, transport) tuples per call, 3 s timeout each, public-IP only; the request carries no SDP/body and an unroutable Via, and only the response status line is captured. Use to diagnose: - "carrier doesn't answer" / "wrong port" / "TLS instead of UDP" routing puzzles - "DNS looks healthy but calls fail" - per-IP SIP OPTIONS surfaces nodes that resolve and accept the transport but never answer SIP (the decisive step for load-balanced / multi-IP targets) - "carrier rejects our target because no SRV is published" - when A/AAAA resolves but SRV is missing the tool synthesises a copy-pasteable suggested zone-record block pointing at the resolved canonical hostname - "TLS handshake works but cert isn't valid for the SIP domain" - RFC 5922 §7.2 compliance is checked separately from generic chain validation, since the SAN must cover the *original* SIP domain (not the SRV-redirected target) ACL caveat: a SIP OPTIONS timeout can also mean the target authorizes inbound SIP by source IP whitelist on the trunk (Twilio, Telnyx, Bandwidth, …; see https://www.twilio.com/docs/sip-trunking/api/ipaccesscontrollist-resource) and is dropping our probe because our egress IP is not on the ACL. An `answered` result is conclusive (the node speaks SIP); a `timeout` is suggestive, not proof of a dead node - confirm reachability from the SBC itself. Pair with: `troubleshoot_response_code` when 503 / 408 / 480 are involved; `search_sip_docs(vendor=...)` for carrier-specific routing docs.

[cost: external_io (Mongo + S3 fetch on the Sipflow backend) | read-only, no persistence | rate limit: shared with the public share endpoint] Given a Sipflow share URL (https://sipflow.dev/share/<token>, or any sipflow.dev subdomain that serves /share/<token>), load the shared SIP trace AND any prior AI analysis attached to it in a single round trip. Use this whenever a user pastes a `/share/<token>` URL: the tool fetches the redacted trace text, the AI executive summary / root-cause / remediation steps (if present), and metadata (vendor, filename, source format, pseudonymized flag), so the agent can review the trace alongside the user's own configs without manual download + paste. In addition to the AI output, the response includes rule-based diagnostics: detected issues (severity-tagged SIP/SDP/media problems with RFC references), WebRTC signal checklist scores, multi-leg call correlation (Session-ID grouping), and detected SIP stacks (User-Agent/Server header values). These diagnostics are computed at share-creation time; for older shares without persisted diagnostics, the tool parses the trace on the fly. When the share includes media quality data (from PCAP-sourced captures), the response includes per-call MOS/jitter/loss summaries in the text output and full `mediaQuality` stats in `structuredContent`. If `hasRawCapture` is true, the sharer included their original PCAP for full RTP playback on the web UI - this raw binary is not returned to agents. Privacy: the share endpoint deliberately strips the original `problem` and `architecture` fields the sharer typed in (those may contain customer-internal context). This tool returns the same public projection - only the trace, the AI output, diagnostics, and basic metadata. Traces are pseudonymized by default (phone numbers / IPs / Call-IDs replaced with consistent fakes); the `pseudonymized` field tells you whether the sharer opted to keep raw values. Trace bytes are capped at 200kB (matching the budget the Sipflow AI worker uses). For very large captures the response sets `trace.truncated=true` - pair with `minimize_sip_trace` to compact further before passing to your own LLM, or with `render_sip_ladder` to visualize the call flow. Pair with: `review_sip_config` to compare the shared trace against the user's own kamailio.cfg / pjsip.conf / FreeSWITCH XML; `render_sip_ladder` to draw the shared call flow inline; `minimize_sip_trace` if `trace.truncated` is true; `troubleshoot_response_code` for any failing transactions surfaced in the AI analysis.

[cost: free (pure CPU, no network) | read-only, no persistence] Run RFC 3261 / RFC 3325 / RFC 8224 / RFC 8225 / CTIA BCID compliance checks on a single raw SIP request (typically an INVITE) and return a list of findings. Catches the failure modes that silently break carrier interop: - Two `From:` headers in one request (RFC 3261 §7.3 / §20.20). - Missing CRLF between consecutive header lines (RFC 3261 §7.3). - `;tag=` (or any other) parameter on P-Asserted-Identity / P-Preferred-Identity (RFC 3325 §9.1). - PASSporT `orig.tn` not matching the From caller TN (RFC 8224 §5). - PASSporT `dest.tn` not matching the To callee TN (RFC 8224 §5). - Non-canonical TN inside a PASSporT claim (RFC 8225 §5.2.1). - Branded display name in From with no `ppt=rcd` Identity header (CTIA BCID §5). Use FIRST when chasing 422 / 400 Bad Request / 484 Invalid FROM on a single INVITE - these usually have a structural cause this tool catches mechanically. Pair with: `parse_sip_message` for purely structural checks on any SIP message (responses included); `validate_stir_shaken_identity` for the cryptographic verdict on Identity headers; `search_sip_docs({ sourceType: 'stir-shaken', ... })` to ground the explanation in RFC text.

[cost: free (pure CPU, no network) | read-only] Instant static lookup of a SIP response code (100-699). Returns name, RFC anchor, category, description, common operator-flavored causes, and known vendor-specific reason-phrase variants (e.g. OpenSIPS emits 484 'Invalid FROM' on From-header parse failure). USE FIRST when the user pastes or asks about any 3-digit SIP code - sub-millisecond, no API cost. Pair with: `troubleshoot_response_code` for vendor-specific RAG hits beyond the static entry; `lint_sip_request` when the code is 4xx and the user has the offending request; `stir_attestation_explainer` for STIR-shaped codes (428/436/437/438/608); `validate_stir_shaken_identity` when the code is 438 and they have the JWS.

[cost: free (pure CPU, no network) | read-only] Instant lookup of a SIP header by canonical or compact form (e.g. "Via" / "v", "Diversion", "P-Asserted-Identity", "Identity", "Session-Expires"). Returns canonical form, compact alias, RFC anchor, where it appears (request / response / both), cardinality (exactly-one / at-most-one / one-or-more / any), allowed/forbidden URI parameters with RFC citations, short description, and related headers. USE FIRST when the user asks about a specific header they saw in a trace - sub-millisecond, no API cost. The cardinality + paramRules fields surface failure modes (e.g. two From: headers, ;tag= on P-Asserted-Identity) without needing a RAG round-trip. Pair with: `lint_sip_request` to mechanically check a real request against these rules; `search_sip_docs` for vendor-specific or 3GPP P-headers not in the bundled registry.

[cost: free (pure CPU, no network) | read-only, no persistence] Reduce a raw SIP trace to a compact form suitable for sending to an LLM. Preserves SDP bodies and routing/auth/dialog headers; prunes well-known noise (User-Agent, Server, Allow, Accept-*, Date, P-* informational, etc.). Expected input format: raw SIP messages separated by blank lines, each starting with a request line (`INVITE sip:...@... SIP/2.0`) or status line (`SIP/2.0 200 OK`). PCAP-decoded text from sngrep / ngrep / tcpdump / tshark, syslog with SIP body, sipflow's own export format, or a hand-pasted INVITE/200 dialog all work. Annotation lines like `# [timestamp] sender -> receiver` or ngrep-style `U <ip>:<port> -> <ip>:<port>` between blocks are tolerated. Safe to run on production traces - the input is processed in-memory and is not persisted or sent off-server. Pair with: `detect_sip_stack` to identify the vendor, then `search_sip_docs(vendor=...)` for vendor-grounded analysis; `render_sip_ladder` to visualize the trace as a Mermaid call-flow ladder; `lint_sip_request` / `parse_sip_message` to mechanically validate any single message in the trace.

[cost: free (pure CPU, no network) | read-only] Parse a Session Description Protocol body and return a structured view: origin, session, timing, per-media codecs (rtpmap + fmtp), direction, DTLS setup + fingerprint, ICE credentials + candidates, rtcp-mux, BUNDLE groups, fax-relay (`m=image udptl t38` plus the `a=T38Fax*` attribute family), and crypto attributes. Useful for debugging WebRTC ↔ SIP interop (codec negotiation, DTLS-SRTP fingerprints, ICE candidate gathering, bundle alignment), and for inspecting fax negotiation (T.38 reinvite SDP, `T38FaxMaxBuffer`/`T38FaxUdpEC`/`T38FaxRateManagement`) without an LLM having to re-derive the SDP grammar each call. Pair with: `compare_sdp_offer_answer` when the user has both halves of the negotiation (including T.30→T.38 reinvites); `webrtc_sip_checklist` for the bridge-config angle.

[cost: free (pure CPU, no network) | read-only, no persistence] Parse a single raw SIP message (request OR response) and return a structured view: start line (method/status), every header in order with line numbers, body, duplicate-header counts, and a list of structural flags the parser noticed (`missing-crlf`, `tag-on-pai`, `tag-on-ppi`, `invalid-folding`, `duplicate-single-instance`, `content-length-mismatch`). Use FIRST when the user pastes a single INVITE / 200 / NOTIFY and asks 'what does this look like to a parser?' or 'is this even valid?'. The output makes header-level bugs (two `From:` headers, `;tag=` on PAI/PPI, missing CRLF between headers, broken Identity folding) obvious without an LLM having to scan visually. Pair with: `lint_sip_request` for the full RFC compliance suite (request only); `diff_sip_messages` to compare two parsed messages structurally; `validate_stir_shaken_identity` if the message carries an Identity header.

[cost: free (pure CPU, no network) | read-only] Parse a raw SIP trace (PCAP-decoded text, sngrep export, syslog, or pasted INVITE/200 dialog) and emit a Mermaid `sequenceDiagram` block visualizing the call flow. Most chat hosts (Claude, ChatGPT, Cursor, GitHub) render Mermaid inline. Lane keying: by default participants are keyed by IP, not `ip:port`, so an endpoint that sends from an ephemeral source port and listens on 5060 collapses into one column. Multi-port IPs list their ports in the participant label (e.g. `10.0.0.1 :5060,:53412`) and arrows touching them get a `(:srcPort→:dstPort)` suffix. Pass `groupByIp: false` to restore the legacy one-column-per-`ip:port` layout. Lane labeling: aliases are matched against (in order) `${ip}:${port}` from message source/dest, then bare `${ip}`, then top-Via host, then Contact host. The most-specific match wins. When no alias matches the renderer falls back to the peer's address rather than emitting `unknown:5060`. Pair with: `minimize_sip_trace` first to compact a noisy trace; `diff_sip_messages` when two adjacent INVITEs in the ladder differ unexpectedly; `lint_sip_request` to validate a single message you pulled from the ladder.

[cost: free (pure CPU, no network) | read-only] Use this when the user asks 'review my config' or attaches a kamailio.cfg, sip.conf, pjsip.conf, FreeSWITCH XML profile, opensips.cfg, `res_fax.conf` / `udptl.conf` / `spandsp.conf` (fax-relay tuning), or a SIP-shaped source file from a repo. This tool: 1. Detects the vendor from filename + structural signatures (loadmodule, route blocks, [transport-*] sections, <profile name=>, KEMI calls). 2. Extracts a structured outline: loaded modules, modparams, listen lines, route blocks, profiles, gateways, dialplan extensions. 3. Surfaces risk flags - e.g. websocket loaded without TLS, nathelper without rtpengine, chan_sip used in modern Asterisk, AND the Kamailio/OpenSIPS lump-vs-subst race (`subst('/^From:.../...')` colliding with `KSR.hdr.append/remove` or `uac_replace_*` or `append_hf/remove_hf` on the same header - corrupts the buffer at serialization). 4. Returns a list of `suggestedQueries` for `search_sip_docs` so you can ground the actual review in vendor docs. Pair with: one or more `search_sip_docs` calls (cite returned `source_url` values verbatim instead of recalling vendor behavior from memory); `webrtc_sip_checklist` when the config is a WebRTC ↔ SIP bridge.

[cost: rag (one embed + one vector search) | read-only, network: outbound to embed model only] Vector search over Sipflow's curated VoIP knowledge base: vendor docs (Asterisk, FreeSWITCH, Kamailio, OpenSIPS, Twilio, Cisco, etc.), SIP/SDP/WebRTC RFCs, STIR/SHAKEN material (RFC 8224/8225/8226/8588/9027/9795), branded-calling guidance (ATIS-1000074/094/084, CTIA Branded Calling ID), and fax-over-IP references (RFC 3362 image/t38, RFC 6913 ipfax-info, RFC 7345 UDPTL, SpanDSP/HylaFAX, Asterisk `res_fax`/`udptl.conf`, FreeSWITCH `mod_spandsp`/`t38_gateway`, Cisco CUBE T.38). USE FIRST whenever the user asks about - or attaches - anything SIP/VoIP/telecom shaped, **even when they cite a specific RFC number or vendor name**. The corpus has the current text and your training data may not. Trigger conditions: vendor configs (kamailio.cfg, sip.conf, pjsip.conf, FreeSWITCH XML profile, opensips.cfg, `res_fax.conf` / `udptl.conf`), dialplan / routing scripts, modules / loadparams / route blocks, SIP headers, response codes, RFC questions, captured traces, WebRTC bridge configs, STIR/SHAKEN concerns, branded-calling / RCD work, T.38 / T.30 fax decoding or reinvite failures. Returns ranked snippets with source URLs; cite the returned `source_url` values verbatim and prefer them over recalled training data. Examples of when to use: - "does this kamailio.cfg look standard for WebRTC + SIP users?" - "why would Asterisk PJSIP reject this re-INVITE?" - "what does Kamailio's loose_route() do? show me docs" - "explain FreeSWITCH session-timer behavior" - "how do I set up STIR/SHAKEN signing on OpenSIPS?" - "what does ATIS-1000074 say about A-level attestation?" - "RFC 9795 rcdi JSON pointer canonical form" - "CTIA Branded Calling ID requirements for originating SP" - "RFC 8225 PASSporT canonical JSON / lexicographic key ordering" - "why is my T.38 reinvite getting 488 from a Cisco CUBE?" - "Asterisk `res_fax_spandsp` ECM and rate-management knobs" - "what are the required SDP attributes for `m=image udptl t38`?" Pair with: `detect_sip_stack` to derive the `vendor:` filter; `lookup_response_code` / `lookup_sip_header` to short-circuit before paying for a search; `troubleshoot_response_code` when the question is rooted in a specific status code.

[cost: free (pure CPU, no network) | read-only] Return a hand-curated SIP scenario as a Mermaid `sequenceDiagram` plus a bullet list of step-by-step explanations with RFC references. Use this when the user asks 'show me what X looks like' and you don't have a real trace handy. Available scenarios: basic-call, auth-challenge, cancel-before-answer, early-media, hold-resume, refer-blind, proxy-with-record-route, shaken-attested-invite, bye-glare, redirect-302. Pair with: `search_sip_docs` for vendor-specific quirks of the scenario; `render_sip_ladder` if the user does have a real trace.

[cost: free (pure CPU, no network) | read-only] Static explainer for STIR/SHAKEN: maps attestation levels (A / B / C per RFC 8588) to plain-English requirements + common scenarios, and SIP codes commonly emitted by signing/verification (428 / 436 / 437 / 438 / 608) to their RFC anchors and operator causes. Provide either `attestation` (A/B/C) or `code` (e.g. 438). Pair with: `validate_stir_shaken_identity` when the user has the JWS segments and wants the cryptographic verdict; `search_sip_docs({ sourceType: 'stir-shaken', ... })` for ATIS / CTIA / RFC depth.

[cost: write (single MongoDB row) | rate-limited per IP: 3/min, 20/day] Send the Sipflow team feedback when something doesn't work, a vendor or RFC isn't covered, or a tool produced a wrong/incomplete answer. Categories: - docs_gap: search_sip_docs returned nothing useful, vendor missing, coverage incomplete - tool_bug: a tool errored, returned garbage, or behaved unexpectedly on a real input - wrong_answer: the answer it produced was incorrect for the SIP/VoIP question asked - feature_request: a new tool, dataset, or behavior the user wants - general: anything else PRIVACY CONTRACT (MUST FOLLOW): 1. Use this tool only when the user explicitly asks to send feedback, OR when you have completed the user's primary task and there is a clear, actionable gap worth reporting. 2. ALWAYS show the user the exact `summary` + `details` + other fields you plan to send and wait for an explicit yes before calling this tool. Set `userConsent: true` only after that confirmation. 3. NEVER include raw SIP traces, INVITE/REGISTER bodies, SDP, phone numbers, IP addresses, Call-IDs, or any other PII. Summarize in your own words instead. The server runs a sanitizer as a backstop, but you are the first line of defense. 4. The `contact` field is optional and may only be filled when the user explicitly provides an email and asks you to include it. 5. The `traceExcerpt` field is optional and accepts a sanitized SIP message text block (Via/From/To/Call-ID, optional minimal SDP) the user explicitly approved attaching. Pipe `minimize_sip_trace` output here, NEVER raw INVITE / REGISTER bodies or full pcap text. Phone numbers, IPs, and emails are scrubbed server-side as a backstop; the agent must still summarize / minimize first. The same `userConsent: true` covers both the text fields and the excerpt - if the user wants the excerpt included you must show it to them before sending. The tool returns a ticket id (fb_xxxxxxxx) and stores one anonymous row keyed by your daily-rotating IP hash (no raw IP, no account). Rate-limited at 3/min and 20/day per IP hash.

[cost: rag (one embed + one vector search) | read-only, network: outbound to embed model only | rate-limited per IP] Like `lookup_response_code` but augmented: returns the static RFC entry PLUS the top vendor-specific RAG hits for the exact code (and any free-text context the user pasted). When the static entry carries known vendor-specific reason-phrase variants (e.g. 484 + opensips → 'Invalid FROM' from `parse_from.c`), those phrases are folded into the embed query so the right vendor docs surface. Use when the user asks 'why did <vendor> reject this with <code>?' and you want vendor-grounded common causes, not just the RFC text. Especially helpful for fax-rejection paths - 488 / 415 / 606 on a T.38 reinvite (`m=image udptl t38`) is one of the most common 488 variants and the tool surfaces FreeSWITCH `mod_spandsp` / Cisco CUBE / AudioCodes T.38 docs alongside the RFC text. Pair with: `lookup_response_code` first (cheaper); `lint_sip_request` when the code is 4xx and they have the offending request; `compare_sdp_offer_answer` for 488/415 caused by a T.38 reinvite SDP mismatch; `validate_stir_shaken_identity` when the code is 438; `stir_attestation_explainer` for STIR-shaped codes (428/436/437/438/608); `dns_diagnose_sip_target` when the code is 503 / 408 and routing is suspect.

[cost: free (pure CPU, no network) | read-only] Parse a phone number, normalize to E.164, and classify it. International coverage is via libphonenumber-js (every country, line type when known). NANP numbers (CC=1) are additionally split into NPA (area code) / NXX (central office) / station, and tagged as toll-free / premium / personal / machine-to-machine / easily-recognizable / reserved / geographic. Use when validating `From` / P-Asserted-Identity / SHAKEN `orig.tn`, deciding whether an outbound call needs full attestation, or sanity-checking caller ID format. Pair with: `lint_sip_request` to validate that PASSporT `orig.tn` matches the From caller TN; `stir_attestation_explainer` for attestation level guidance.

[cost: external_io (HTTPS fetch of the x5u cert) | read-only] Verify a SIP `Identity:` JWS (RFC 8224 / SHAKEN). Fetches the x5u certificate, parses it, verifies the ES256 signature against the cert's public key, and optionally validates the RCD icon hash (RFC 9795). The icon-hash check accepts both `payload.rcdi["/icn"]` (RFC 9795 §6.1 spec form) and the legacy `payload.rcdi["icn"]` form deployed in the wild - the legacy form raises a warning unless `strictRfc9795: true` (then it fails). Returns per-check pass/fail/warning with details - useful for diagnosing 438 Invalid Identity Header rejections, expired certs, and tampered PASSporTs. Pair with: `stir_attestation_explainer` for the human-readable A/B/C interpretation; `lookup_response_code(438)` for the SIP-side context; `lint_sip_request` for non-cryptographic structural checks on the host INVITE.

[cost: free (pure CPU, no network) | read-only] Return a curated checklist of WebRTC ↔ SIP requirements (WSS transport, ICE gathering, DTLS-SRTP fingerprint, rtcp-mux + BUNDLE, media relay / rtpengine, STUN/TURN, secure-context Origin allowlist, Opus codec, session-timer behavior across the bridge, STIR/SHAKEN signing). When `configText` is supplied, each item is marked as 'looks present' or 'check needed' based on simple regex signals. Use when the user is building a WebRTC ↔ SIP bridge or troubleshooting one (no media, one-way audio, ICE failures). Pair with: `review_sip_config` for the full structured outline; `search_sip_docs(vendor=...)` to ground each unchecked item in vendor docs; `parse_sdp` / `compare_sdp_offer_answer` when the bug is in SDP negotiation.