Repository navigation
fix(mcp): send one $mcp_initialize per initialize request - #1103
Conversation
The Python MCP SDK answers initialize itself, so posthog.mcp sent the event on the first request of each session, once per process. A stateless fleet sent one event per pod. A client that sent only initialize sent no event. Now MCP SDK 2.x reports the event from Server.middleware, on every transport. MCP SDK 1.x over HTTP reports it from PostHogMcpStatelessSessionMiddleware, which takes a new optional server= argument. MCP SDK 1.x over stdio keeps the first-request fallback. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
posthog-python Compliance ReportDate: 2026-10-23T12:02:36.488961+00:00 ✅ All Tests Passed!121/121 tests passed Capture_V1 Tests✅ 95/95 tests passed View Details
Capture_Ai Tests✅ 5/5 tests passed View Details
Feature_Flags Tests✅ 17/17 tests passed View Details
Feature_Flags_Local_Evaluation Tests✅ 4/4 tests passed View Details
|
There was a problem hiding this comment.
PostHog Review · Standard · reviewed 57d8dc6: 3 Should fix.
This is the only automatic review while this pull request is a draft. Comment @posthog review to review new changes sooner. Otherwise, a review of the new changes runs when you mark it ready for review.
The mcp 1.x hook now keeps only the status and the Mcp-Session-Id header of the initialize response. It no longer parses the JSON or SSE body. The event uses the protocol version that the client asked for. record_initialize now reads the client name, version, and protocol from the initialize params and reply, so both hooks pass them through. The new tests share their request helpers and drop the SSE body case. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- SSE transport: the initialize event now lands in the session that the SSE calls use. On SDK 1.x the middleware leaves SSE requests to the first-request fallback. On SDK 2.x the hook uses the process session. - The bound middleware marks each request that it passes on. The fallback now stops only for marked requests, not for every HTTP request. - The hooks compute the handshake session without a write to the shared session that McpAnalytics.capture() reads. - A server= value that cannot be bound no longer breaks requests. - Remove the unused _mint_token_if_initialize. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Both handshake hooks run record_initialize in a tracked background task. It started the capture as a second task, after flush() took its snapshot of pending tasks. With a slow before_send, flush() returned early and shutdown dropped $mcp_initialize. The handshake task now awaits the capture itself. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On MCP SDK 2.x, a stateless client can send initialize with an existing Mcp-Session-Id and keep sending it. Its later calls resolve their session from that header, but the handshake hook read only the connection id and the minted token. The event landed in a generated session. The hook now falls back to the incoming header. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On MCP SDK 1.x, the middleware read the body only of a POST with no Mcp-Session-Id, because only those need a token. A client that sent initialize with an existing session id got no event: the middleware marked the request, so the first-request fallback did not run either. A middleware bound to a server now reads those bodies too, behind a cheap check for "initialize". It still mints only without a header. The event uses the header that the client keeps sending. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
PostHog Review · Standard · couldn't review
|
PostHog Review · Standard · couldn't review
|
When the client disconnected while it sent the body, the middleware stopped its read and replayed the partial body as a complete request. The app parsed half a request and never saw the disconnect. The middleware now replays the partial body with more_body set, then hands the app the disconnect. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A bound middleware reads the body of a POST that carries a session id, to catch an initialize that reuses one. That held every tool call in memory, up to 256 KB, before the app saw it. The middleware now stops after 4 KB when "initialize" is not in it, and streams the rest. JSON-RPC clients put "method" before "params", so a handshake shows up in that window. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The v2 handshake hook read the Mcp-Session-Id header and decoded the token itself. Every later request gets the same pair from _resolve_ctx. The hook now calls it, so the handshake and later requests follow one rule and cannot drift apart into two sessions. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
dustinbyrne
left a comment
There was a problem hiding this comment.
The handshake-count fixes are well covered and reproduce correctly against the base. One optional resource-safety follow-up is noted inline.
AI-assisted review.
| return await call_next(ctx) | ||
| started = datetime.now(timezone.utc) | ||
| result = await call_next(ctx) | ||
| fire_and_forget(_record_v2_initialize(data, ctx, result, started), data) |
There was a problem hiding this comment.
[P2] Optional follow-up: bound detached handshake recorder admission
Consider adding a finite, nonblocking per-server admission cap before creating handshake recorder tasks, including the equivalent v1 HTTP path in asgi.py:186–194.
This matters when a configured async identify or event_properties callback stays pending—for example, an identity lookup using httpx.AsyncClient(timeout=None) against a service that accepts the connection but never replies. Each successful handshake can then leave another analytics task waiting after the request finishes and the client disconnects.
With the same gated-callback test on base e17a8be and head bb21c6a, both MCP majors retained 0 tasks on base versus 16, 32, and 1,056 on head after that many completed handshakes. Head flush waited for callback release; releasing the gate drained everything to zero. The regression used an illustrative 1,024-task threshold, not a specification-prescribed number; unconditional scheduling in source establishes the missing bound.
The MCP observer-only contract explicitly calls for count-bounded pending state. Sensible caller-side timeouts and cached lookups substantially mitigate this, though, so I’m treating it as optional hardening rather than a merge requirement. This is not an ordinary-operation leak or a demonstrated production OOM.
A saturation regression should exceed the chosen cap, verify successful unchanged handshake responses and bounded work after disconnect, then verify recording resumes once callbacks finish. An unlimited semaphore wait queue would not bound retained tasks. An admission cap also would not, by itself, guarantee flush termination for a callback that never returns; callback-deadline policy can remain separate.
There was a problem hiding this comment.
kind of a stretch, fwiw, given this is only truly unbounded if the caller allows an infinite timeout period - i left this in considering the reference to sdk-specs, but it seems pretty benign to me overall
There was a problem hiding this comment.
Thanks, good catch. The detached recorder was the real problem, so I removed it instead of capping it.
20c1243 runs identify and event_properties inline in the handshake request on both hooks, the same as on a tool call. A hung callback now holds that one request, where the host sees it, and leaves no analytics task behind. The capture still goes out in the background afterwards.
test_a_hung_identify_leaves_no_task_behind runs your scenario on all three server types and both SDK majors. It sends 5 handshakes against an identify that never returns, then asserts 0 pending tasks and that flush() returns. After the callback recovers, the SDK records the next handshake. On bb21c6a the test fails on the pending recorder tasks.
The trade-off: on both SDK majors the handshake reply now waits for identify, as a tool call already does. Since 132eaef the v1 middleware records it when the response starts, inside the request context.
Both handshake hooks ran identify and event_properties in a detached background task. If a callback never returned, each handshake left one more task pending, with no bound, and flush() waited for all of them. The spec requires pending state to be bounded by count. The hooks now run the callbacks inline, the same as a tool call does. A hung callback holds that request, where the host sees it, and leaves no task behind. The capture still runs in the background after the callbacks, as for every other event. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
There was a problem hiding this comment.
PostHog Review · Standard · reviewed 20c1243: 2 Should fix.
This is review round 3 on this pull request. When findings keep coming back in the same code, the approach is usually the problem. Before the next fix, check whether a different design would remove the whole class of findings.
The session middleware sits outside FastMCP's AuthContextMiddleware. It ran identify after the app returned, when that middleware had already reset the authenticated user. An identify that calls get_access_token() got None, so $mcp_initialize stayed anonymous under OAuth. The middleware now records the handshake when the response starts, while the app still handles the request. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The 4 KB peek stopped when "initialize" was not in the first 4 KB. JSON key order is arbitrary, so an initialize with large params before its method got no event. The peek now stops only when the prefix shows a "method" and no "initialize". Without a method yet, it reads up to the full cap. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
already approved so wont approve again, left 2 new comments tho, address them if they make sense |
marandaneto
left a comment
There was a problem hiding this comment.
Two reproduced blocking findings from the review. The complete patch was revalidated before posting.
| if not peeked and total >= _PEEK_BODY: | ||
| peeked = True | ||
| prefix = b"".join(chunks) | ||
| if b'"method"' in prefix and b'"initialize"' not in prefix: |
There was a problem hiding this comment.
blocking: A nested method can still hide the actual initialize method. The latest cutoff handles a missing method in the prefix, but it also matches nested keys: an initialize with an existing session header and params first can contain capabilities.experimental.vendor = {"method": "custom", "padding": ...} before its top-level method. With over 4 KB of parameters, buffering stops at that nested key, so SDK 1.x successfully answers the handshake but emits no $mcp_initialize; the bound middleware also suppresses the fallback. Only the top-level RPC method can establish that the request is not initialize. Reproduction: reproduced — test_nested_method_before_top_level_initialize_is_counted received HTTP 200 with a successful result but zero initialize events on the reviewed head; disabling the premature cutoff made it pass.
There was a problem hiding this comment.
Good catch, thanks. Both of your findings came from the same byte checks, so 0773e32 removes them instead of patching them again.
On SDK 1.x the middleware no longer reads requests that carry an Mcp-Session-Id. Nothing guesses at the method from raw bytes now. The cost is that on SDK 1.x an initialize that reuses an existing session id gets no event. The README lists that limit. SDK 2.x still counts it, because Server.middleware gets the parsed method from the SDK.
Your case is now test_a_nested_method_before_the_top_level_initialize_is_counted. It runs on SDK 2.x for all three server types.
| """The JSON-RPC message in ``body`` if it is an ``initialize`` request, else | ||
| ``None`` (never raises).""" | ||
| # Cheap first: with a bound middleware this runs on every tool call too. | ||
| if not body or b'"initialize"' not in body: |
There was a problem hiding this comment.
blocking: Preserve JSON-escaped initialize methods. The valid JSON method string "\u0069nitialize" decodes to initialize, but this new raw-byte filter rejects it before JSON parsing. This regresses session-token minting even for unbound middleware, losing cross-pod session correlation, and prevents bound SDK 1.x middleware from observing the handshake. Reproduction: reproduced — test_escaped_initialize_still_mints_a_session returned HTTP 200 without Mcp-Session-Id on the reviewed head under both SDK majors, while the identical test passed on the merge base.
There was a problem hiding this comment.
Agreed, that one broke behavior that worked on main. Fixed in 0773e32: the middleware parses the body as JSON again before it checks the method, as main does, so "initialize" gets its token and its event.
Your case is now test_an_escaped_initialize_still_mints_a_session, on both SDK majors for all three server types. It fails on 23a0677.
The middleware guessed from raw bytes whether a request was initialize. A nested "method" key in params stopped the 4 KB peek too early, and a JSON-escaped "initialize" failed the quick byte check. That second case also stopped the token mint, which worked before this PR. The middleware now parses the body as JSON, as main does, and reads only requests with no Mcp-Session-Id. On MCP SDK 1.x, an initialize that reuses an existing session id is not captured. The README lists this limit. MCP SDK 2.x still captures it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai): keep streamed OpenAI tool calls that have no index (#1091)
* fix(ai): keep streamed OpenAI tool calls that have no index
accumulate_openai_tool_calls skipped every delta without an index, so
tool calls from OpenAI-compatible providers that omit it never reached
$ai_output. A delta with a new id now opens a call, and one without an
id continues the latest call.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* fix(ai): keep synthetic tool call keys apart from provider indexes
A call without an index took key max + 1, which a later call with that real index overwrote, merging two calls and dropping one. Index-less calls now get string keys of their own.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* fix(ai): widen the streamed tool call accumulator key type
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai): update streamed tool call API snapshot
---------
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit ffde3c57f26b9daf92f12fbb21edd4f359e4388b)
* chore: Release v7.75.7 [skip ci]
(cherry picked from commit 7f4c9be1c8aa66bf55cb2080cf0775ff4ec28cff)
* Update generated references
(cherry picked from commit b5eb2debabc7bc6e4e5d033b923d1eef6a6508a6)
* docs: require signed commits in contributor docs (#1111)
Contributors often open PRs with unsigned commits because signing isn't documented here.
(cherry picked from commit e65ed67b3a61122c6480c2198c019a493061845c)
* fix(flags): fall back for incompatible local regex evaluation (#1108)
* fix(flags): fall back for incompatible local regex evaluation
* fix(flags): defer nested regex quantifiers and fast-path ASCII values
* fix(flags): defer strict-end searches with final newline backtracking
* perf(flags): cache pure regex pattern metadata
(cherry picked from commit d58380e87f38b725ded6d38b870b734056a526e7)
* chore: Release v7.75.8 [skip ci]
(cherry picked from commit 72e013122e07345a827d108de74f079672220f1d)
* Update generated references
(cherry picked from commit a020e703fd89e4e35211419ad6f1ba3b656d798f)
* fix(examples): use gpt-image-2.5-flare in the OpenAI image generation example (#1109)
OpenAI shuts down gpt-image-1 on 2026-10-23 and lists gpt-image-2.5-sunburst or
gpt-image-2.5-flare as the replacement
(https://developers.openai.com/api/docs/deprecations).
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit efc866ec4b18115518597bfa9f6b82a6f17cc270)
* fix(mcp): send one $mcp_initialize per initialize request (#1103)
* fix(mcp): send one $mcp_initialize per initialize request
The Python MCP SDK answers initialize itself, so posthog.mcp sent the
event on the first request of each session, once per process. A
stateless fleet sent one event per pod. A client that sent only
initialize sent no event.
Now MCP SDK 2.x reports the event from Server.middleware, on every
transport. MCP SDK 1.x over HTTP reports it from
PostHogMcpStatelessSessionMiddleware, which takes a new optional
server= argument. MCP SDK 1.x over stdio keeps the first-request
fallback.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(mcp): read only the initialize response head on mcp 1.x
The mcp 1.x hook now keeps only the status and the Mcp-Session-Id header
of the initialize response. It no longer parses the JSON or SSE body.
The event uses the protocol version that the client asked for.
record_initialize now reads the client name, version, and protocol from
the initialize params and reply, so both hooks pass them through. The
new tests share their request helpers and drop the SSE body case.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): address review on the initialize hooks
- SSE transport: the initialize event now lands in the session that the
SSE calls use. On SDK 1.x the middleware leaves SSE requests to the
first-request fallback. On SDK 2.x the hook uses the process session.
- The bound middleware marks each request that it passes on. The fallback
now stops only for marked requests, not for every HTTP request.
- The hooks compute the handshake session without a write to the shared
session that McpAnalytics.capture() reads.
- A server= value that cannot be bound no longer breaks requests.
- Remove the unused _mint_token_if_initialize.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): wait for the initialize capture inside its handshake task
Both handshake hooks run record_initialize in a tracked background task.
It started the capture as a second task, after flush() took its snapshot
of pending tasks. With a slow before_send, flush() returned early and
shutdown dropped $mcp_initialize. The handshake task now awaits the
capture itself.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): resolve the v2 handshake session from an incoming header
On MCP SDK 2.x, a stateless client can send initialize with an existing
Mcp-Session-Id and keep sending it. Its later calls resolve their
session from that header, but the handshake hook read only the
connection id and the minted token. The event landed in a generated
session. The hook now falls back to the incoming header.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): capture a v1 initialize that carries a session header
On MCP SDK 1.x, the middleware read the body only of a POST with no
Mcp-Session-Id, because only those need a token. A client that sent
initialize with an existing session id got no event: the middleware
marked the request, so the first-request fallback did not run either.
A middleware bound to a server now reads those bodies too, behind a
cheap check for "initialize". It still mints only without a header. The
event uses the header that the client keeps sending.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): pass a disconnect mid-body through the session middleware
When the client disconnected while it sent the body, the middleware
stopped its read and replayed the partial body as a complete request.
The app parsed half a request and never saw the disconnect. The
middleware now replays the partial body with more_body set, then hands
the app the disconnect.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): stop buffering tool calls once they are not an initialize
A bound middleware reads the body of a POST that carries a session id,
to catch an initialize that reuses one. That held every tool call in
memory, up to 256 KB, before the app saw it. The middleware now stops
after 4 KB when "initialize" is not in it, and streams the rest.
JSON-RPC clients put "method" before "params", so a handshake shows up
in that window.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(mcp): read the v2 handshake header through _resolve_ctx
The v2 handshake hook read the Mcp-Session-Id header and decoded the
token itself. Every later request gets the same pair from _resolve_ctx.
The hook now calls it, so the handshake and later requests follow one
rule and cannot drift apart into two sessions.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): run the initialize callbacks inline in the handshake request
Both handshake hooks ran identify and event_properties in a detached
background task. If a callback never returned, each handshake left one
more task pending, with no bound, and flush() waited for all of them.
The spec requires pending state to be bounded by count.
The hooks now run the callbacks inline, the same as a tool call does. A
hung callback holds that request, where the host sees it, and leaves no
task behind. The capture still runs in the background after the
callbacks, as for every other event.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): record the v1 handshake inside the request's auth context
The session middleware sits outside FastMCP's AuthContextMiddleware. It
ran identify after the app returned, when that middleware had already
reset the authenticated user. An identify that calls get_access_token()
got None, so $mcp_initialize stayed anonymous under OAuth. The
middleware now records the handshake when the response starts, while
the app still handles the request.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): stop the body peek only on a method that is not initialize
The 4 KB peek stopped when "initialize" was not in the first 4 KB. JSON
key order is arbitrary, so an initialize with large params before its
method got no event. The peek now stops only when the prefix shows a
"method" and no "initialize". Without a method yet, it reads up to the
full cap.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): drop the body byte checks from the session middleware
The middleware guessed from raw bytes whether a request was initialize.
A nested "method" key in params stopped the 4 KB peek too early, and a
JSON-escaped "initialize" failed the quick byte check. That second
case also stopped the token mint, which worked before this PR.
The middleware now parses the body as JSON, as main does, and reads
only requests with no Mcp-Session-Id. On MCP SDK 1.x, an initialize
that reuses an existing session id is not captured. The README lists
this limit. MCP SDK 2.x still captures it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 8cd8eb5b6fdcdb19db4c4d07fe911c6eb3976d5a)
* fix(ai): take cumulative usage and web searches from the Claude Agent SDK message_delta (#1112)
The tracker only read output_tokens from a message_delta. Its usage is cumulative,
and with server tools (web search, ...) the input and cache counts exceed the
message_start values, so streamed generations under-reported them, and the
number of web searches was never recorded. Keep the larger input and cache
counts, as the Anthropic wrapper does, and set $ai_web_search_count from
server_tool_use.web_search_requests.
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit 48889b6cc8d0a9eec579684640cb74b393cdd56c)
* chore: Release v7.75.9 [skip ci]
(cherry picked from commit 5a2ea5f7e0c71d6b9dc70112ab9d5c29c6f99bb1)
* Update generated references
(cherry picked from commit e3fd9a49c6ca1beeb2d4f9b6a889ea7ee0774f57)
* fix(ai): record the HTTP status of google-genai errors (#1110)
* fix(ai): record the HTTP status of google-genai errors
The generation and embedding wrappers read the HTTP status of a failed call from
the exception's status_code, which OpenAI and Anthropic errors have. google-genai's
APIError (ClientError, ServerError) carries it as code, so every failed Gemini
call was captured with $ai_http_status 0. Read either attribute through a small
helper; a code outside the HTTP range still counts as no status.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* fix: remove unused import from HTTP status tests
---------
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit 25d2767a70378da02c321879f0fa3a2e52d071b7)
* chore: Release v7.75.10 [skip ci]
(cherry picked from commit 82f948b0871ecbbf5c6fd30714481dc5877adbf1)
* Update generated references
(cherry picked from commit b0a2783b53e7a8e5546f11674318225b26139ec4)
* fix(aio): keep content out of ai events in privacy mode (#1105)
* fix: ai privacy mode leaks
* fix: address privacy mode review findings
* fix: strip remaining otel content in privacy mode
* fix: redact mcp credentials in otel tool definitions
* fix: address otel privacy review findings
* fix: always redact mcp credentials in otel tool definitions
* fix: strip otel embedding vectors in privacy mode
* fix: drop only the otel span that fails redaction
* fix: keep vercel rerank scores in otel privacy mode
* fix: strip logfire payload attributes in otel privacy mode
(cherry picked from commit 04e6a4c1c4f15e4dd0d010dee5fa83244f9b6dd8)
* chore: Release v7.75.11 [skip ci]
(cherry picked from commit fb9b66bcc1d679180f5aee9c1fe4397636074c75)
* Update generated references
(cherry picked from commit 16d618b1636e47dfcd3a530231fddf16defa6b81)
* chore(deps): bump opentelemetry-api from 1.40.0 to 1.45.1 (#1117)
Bumps [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python) from 1.40.0 to 1.45.1.
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
---
updated-dependencies:
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit bc7b40331a4a9bf18456f6e9136147ab7118ca0f)
* chore(deps): bump djangorestframework from 3.18.1 to 3.18.2 (#1118)
Bumps [djangorestframework](https://github.com/encode/django-rest-framework) from 3.18.1 to 3.18.2.
- [Release notes](https://github.com/encode/django-rest-framework/releases)
- [Commits](https://github.com/encode/django-rest-framework/compare/3.18.1...3.18.2)
---
updated-dependencies:
- dependency-name: djangorestframework
dependency-version: 3.18.2
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 125b26654ea317ce72077b7f3eb83d11461cf9b2)
* chore(deps): bump the uv group across 31 directories with 1 update (#1119)
Bumps the uv group with 1 update in the /examples/example-ai-anthropic directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-autogen directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-aws-bedrock directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-azure-openai directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-cerebras directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-cloudflare-ai-gateway directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-cohere directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-crewai directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-dedalus directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-deepseek directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-fireworks-ai directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-gemini directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-groq directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-helicone directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-hugging-face directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-instructor directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-langchain directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-langgraph directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-llamaindex directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-mirascope directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-mistral directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-ollama directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-openai directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-openrouter directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-perplexity directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-portkey directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-semantic-kernel directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-smolagents directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-together-ai directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-vercel-ai-gateway directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Bumps the uv group with 1 update in the /examples/example-ai-xai directory: [opentelemetry-api](https://github.com/open-telemetry/opentelemetry-python).
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.34.1 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
Updates `opentelemetry-api` from 1.40.0 to 1.45.1
- [Release notes](https://github.com/open-telemetry/opentelemetry-python/releases)
- [Changelog](https://github.com/open-telemetry/opentelemetry-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/open-telemetry/opentelemetry-python/compare/v1.40.0...v1.45.1)
---
updated-dependencies:
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
- dependency-name: opentelemetry-api
dependency-version: 1.45.1
dependency-type: indirect
dependency-group: uv
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 3f6c80eb4df1ddffd9e5b9d1d8aae8facf9f83b2)
* feat(llma): support per-item offline evaluation models (#1130)
(cherry picked from commit 284340d6ba6df08f68c27eac750b13f3ec89ab19)
* chore: Release v7.76.0 [skip ci]
(cherry picked from commit 7d15127fd4e3aeac72bb1af59f49d96c1c81be7e)
* Update generated references
(cherry picked from commit 7833e95266da6130bf41028623f4a5e69a950d71)
* feat(ai): record the Anthropic web search count in the LangChain callback handler (#1097)
* feat(ai): record the Anthropic web search count in the LangChain callback handler
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* chore: update public API snapshot for ModelUsage.web_search_count
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: regenerate LangChain ModelUsage API snapshot
* fix(ai): read the LangChain web search count from llm_output usage and omit zero
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit b0a2b59dc09e96903cdf97ea3c8ab5298bdff7bb)
* chore: Release v7.76.1 [skip ci]
(cherry picked from commit a736b43290fc88fecc929916887a3c1c215984a7)
* Update generated references
(cherry picked from commit 3044d8ed5919b6b11b42642359651855c6f9ec38)
* feat(mcp): add a send_initialize_event option (#1115)
* feat(mcp): add a capture_initialize option
MCPAnalyticsOptions(capture_initialize=False) stops $mcp_initialize. The
option is on by default. Many clients reconnect before every few tool
calls, so the handshake event can outnumber $mcp_tool_call.
With the option off, record_initialize and the first-request fallback
return early. Nothing else changes: the middleware still mints the
session token, so tool calls keep their sessions and client names.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): keep the handshake identity with capture_initialize off
record_initialize returned before handle_identify when the option was
off. An identify callback that resolves the user only from the
initialize request then left the session anonymous, so later tool calls
lost the user. Identify now runs first, and the option stops only the
event.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(mcp): rename capture_initialize to send_initialize_event
PostHogMCP already has a capture_initialize() method that sends the
event by hand. An option with the same name next to that method makes
readers link the two. The new name says what the option controls.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs(mcp): name the PostHog screens that read $mcp_initialize
MCP onboarding and the users and sessions tiles of the default MCP
dashboard read $mcp_initialize. The README now says that they show no
data while send_initialize_event is off.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit d8a1b976d665d9f7b3249ac788ef253bb21eed50)
* chore: Release v7.77.0 [skip ci]
(cherry picked from commit 786db579d383a34fc6b4d21d1332743b5eec17b5)
* Update generated references
(cherry picked from commit 0894015a3730c8bbdf1cfc3276da12913bcdac27)
* feat(mcp): add a send_tools_list_event option (#1116)
MCPAnalyticsOptions(send_tools_list_event=False) stops $mcp_tools_list.
The option is on by default. Clients list tools on every reconnect, so
the listing event is about as common as $mcp_tool_call.
With the option off, record_tools_list returns early, which also drops a
failed listing's $exception. Nothing else changes: tools keep their
injected arguments, and the virtual tools stay listed.
The name says "event" to match send_initialize_event.
PostHogMCP.capture_tools_list() already captures the event by hand.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 351da59c252afb7bffed79d21c23aa7e2539a38e)
* chore: Release v7.78.0 [skip ci]
(cherry picked from commit 39110204fdf2aceb1e00f66f18bd5656f0783aff)
* Update generated references
(cherry picked from commit 75a17943805604a040ac2f204fd74e3fbeb501a3)
* chore(deps): bump the github-actions group with 3 updates (#1128)
Bumps the github-actions group with 3 updates: [github/codeql-action/init](https://github.com/github/codeql-action), [github/codeql-action/analyze](https://github.com/github/codeql-action) and [PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml](https://github.com/posthog/posthog-sdk-test-harness).
Updates `github/codeql-action/init` from 4.38.3 to 4.39.0
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](https://github.com/github/codeql-action/compare/24c54180a607b1449ed407dd24f251e4e9147c8d...6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee)
Updates `github/codeql-action/analyze` from 4.38.3 to 4.39.0
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](https://github.com/github/codeql-action/compare/24c54180a607b1449ed407dd24f251e4e9147c8d...6f2ac81f5cd81fe351a197ba0b00d91d03cd2aee)
Updates `PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml` from 1.15.0 to 1.17.0
- [Release notes](https://github.com/posthog/posthog-sdk-test-harness/releases)
- [Changelog](https://github.com/PostHog/posthog-sdk-test-harness/blob/main/CHANGELOG.md)
- [Commits](https://github.com/posthog/posthog-sdk-test-harness/compare/64ffa6ab19166541880c077d349abe18a7e42395...8ca75c478d8a1b7d5be3f9b82b1a744b8ee630c3)
---
updated-dependencies:
- dependency-name: github/codeql-action/init
dependency-version: 4.39.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
- dependency-name: github/codeql-action/analyze
dependency-version: 4.39.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
- dependency-name: PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml
dependency-version: 1.17.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 7083998df0c26079e748f9279f92ca764ceb19ea)
* feat: report unresolved local flags on evaluate_flags snapshots (#1133)
* feat: report unresolved local flags on evaluate_flags snapshots
Implements the "Snapshot unresolved flag reporting" and "Warning for flags local evaluation never resolves" requirements of the evaluate-flags spec (PostHog/sdk-specs#85).
- Add `FeatureFlagEvaluations.unresolved_flags`, with an `UnresolvedFlagReason` for each flag and the spec's fixed precedence.
- Report `local_evaluation_inconclusive` instead of `flag_missing` when a snapshot read hits an unresolved flag.
- Do not stop a condition at the first inconclusive filter, so a filter that does not match resolves the condition locally.
- Check `active` before experience continuity, also for dependencies.
- Log one warning per flag that local evaluation can never resolve, repeated only when its definition changes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: 39793b31-809e-4689-a5d8-b4359cbb22c1
* fix: address review findings for unresolved local flags
* test(flags): check flag warnings run outside the publication lock
* fix(flags): fall back to the server when a flag dependency needs server data
* fix(flags): keep server fallback when the definition reason lookup fails
(cherry picked from commit bb2b9d6bddd250f6dcf03be565af8ba94694e5db)
* chore: Release v7.79.0 [skip ci]
(cherry picked from commit 91d3188bb4dbf5ed8e59165f0dbd62836a05d384)
* Update generated references
(cherry picked from commit 130f5a1e8508a7a9005bf46658ff8d43b7457232)
* feat(metrics): metrics autocapture for HTTP, database and runtime metrics (#992)
* feat(metrics): add metrics autocapture for HTTP, database and runtime metrics
`metrics={"autocapture": True}` starts the installed OpenTelemetry instrumentors with private meter and tracer providers and exports to `/i/v1/metrics`. The packages come from the new `posthog[metrics]` extra.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: ef9b57c2-47ff-47e6-a509-8873ffe1fab4
* test: check concurrent LangChain traces without assuming order
Generated-By: PostHog Desktop
Task-Id: c0218209-575c-46f0-a201-d0c831e38096
* fix(metrics): address autocapture review findings
- Honour send=False in the autocapture export gate.
- Strip trailing slashes from the host before building the metrics endpoint.
- Set OTEL_SEMCONV_STABILITY_OPT_IN only while the instrumentors load, then
restore the process environment.
- Limit each synchronous instrument to 2000 attribute sets; send the rest to
an otel.metric.overflow series, so user-supplied hosts cannot grow the SDK cache.
- After fork, replace the module lock and point the runtime instrumentor at
the child process.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: 10838116-90e2-4d23-af38-8099d7887d07
* fix(metrics): keep app-owned instrumentors intact and hold ownership through shutdown
- Skip an instrumentor whose singleton the app already instrumented before creating it. Creating it ran __init__ again and reset the app's system metrics config.
- Uninstrument while the module lock is held, so a client that starts during shutdown cannot skip libraries that are about to be uninstrumented. The last export still runs outside the lock.
- Correct the module docstring: an app cannot instrument a library again with its own OpenTelemetry setup while autocapture instruments it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: a129c1a0-57e3-4370-a4df-6542e710ab75
* fix(metrics): use stable HTTP metric names when another instrumentor read the opt-in first
OpenTelemetry reads OTEL_SEMCONV_STABILITY_OPT_IN once per process. If any instrumentor ran before the client started, autocapture sent http.client.duration (ms) and not http.client.request.duration (s). When the app has not set an opt-in, autocapture now sets the HTTP mode to stable after initialisation, so the names do not depend on import order.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: a129c1a0-57e3-4370-a4df-6542e710ab75
* fix(metrics): address the second review round of metrics autocapture
- Do not send the app's OTEL_EXPORTER_OTLP_* settings (other vendors' headers, endpoint, TLS files) to PostHog: the private exporter is built without them.
- Give HTTP instrumentors a no-op tracer, so app requests no longer carry an unsampled traceparent that makes downstream services drop their traces.
- Record nothing while the client is disabled, and apply metrics.before_send to autocaptured measurements and runtime observations (value and attributes, or drop).
- Exclude the PostHog host in any case and with or without its default port, escape commas, keep OTEL_PYTHON_*_EXCLUDED_URLS, and apply the exclusion to httpx.
- Reset the reader's export lock in a forked child, export autocaptured metrics on Client.flush() and within the client's exit budget (no 10 s exit wait), roll back on a failed start, and uninstrument and reinstrument Flask apps across a restart.
- Start autocapture on a later module-level setup(), once per client.
- Validate flush_interval like client.metrics, use the same resource as client.metrics, keep the first word of db.operation.name, and raise the minimum OpenTelemetry versions to the first ones with the runtime metric names.
- Rename the module to posthog/_metrics_autocapture.py to keep internals out of the public API.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: a129c1a0-57e3-4370-a4df-6542e710ab75
* fix(metrics): keep app middleware on shutdown, stop context propagation, and fix fork and flush issues
- Flask: shutdown uninstruments an app only when its WSGI app is still the one the instrumentation set. uninstrument_app() would otherwise remove middleware the app added later, such as authentication. Instrumentation left in place records nothing after shutdown.
- Do not propagate context: the instrumentors that autocapture starts no longer inject trace context or baggage into outgoing requests, including a trace extracted from an incoming request.
- Keep the attributes that a database span starts with (asyncpg passes db.system then).
- Export the last window at exit in sync mode.
- Replace the metrics SDK collection and aggregation locks in a forked child, where a parent thread could hold them.
- Use one flush thread at a time, with one follow-up export for calls made during a flush.
- Run metrics.before_send as an SDK callback, so a flush() it calls is deferred and cannot deadlock the collection.
- Raise the minimum OpenTelemetry instrumentation version to 0.60b0, the first in which the httpx instrumentor excludes URLs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: a129c1a0-57e3-4370-a4df-6542e710ab75
* fix(metrics): do not let the Django instrumentor configure empty settings
Without configured settings, DjangoInstrumentor calls settings.configure() with empty settings, so an app that configures its settings in code after creating the client fails with "Settings already configured". Autocapture now starts the Django instrumentor only when the settings are configured, as in AppConfig.ready().
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: a129c1a0-57e3-4370-a4df-6542e710ab75
* fix(metrics): drop raw URL attributes, normalize hook attributes, and stop flush loops from hooks
- Never record raw URLs and paths (url.full, http.url, http.target, ...), client addresses, user agents or captured headers. Instrumentors such as Tornado put them on metrics, and they can hold tokens and emails. Routes stay.
- Keep only valid OpenTelemetry attribute values, with sequences as tuples, before and after metrics.before_send. SDK 1.39 raised TypeError for a list value inside the app's request. Recording errors no longer reach the instrumented call.
- A flush() called from a metrics before_send hook still flushes events and spans, but does not start another autocapture export, which ran the hook again without end.
- Each flush request waits only for the first export that starts after it, not for later exports.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: a129c1a0-57e3-4370-a4df-6542e710ab75
* fix(metrics): isolate exporter settings and autocapture lifecycle state
* fix(metrics): address remaining autocapture lifecycle feedback
---------
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit febb3ed2f1584e68c05c73625becbdd18fe5f944)
* chore: Release v7.80.0 [skip ci]
(cherry picked from commit ce03e476bb0256bed4f3b6745ebb50fc3dead745)
* Update generated references
(cherry picked from commit 175fac6d6e4fdbb179ead60869ed5a864ea1f6ff)
* fix(ai): handle None and NOT_GIVEN stream_options without mutating the caller's dict (#1144)
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit 1625f4fbc1809d7a19b34354ad2df2a0e016928f)
* chore: Release v7.80.1 [skip ci]
(cherry picked from commit 58d69e3127134967e317ee29e25ad70de3909b79)
* Update generated references
(cherry picked from commit e4f43a4bf81b7e8c6ec151f53086964c88e39854)
* fix(ai): capture an $ai_embedding event when an OpenAI embeddings call fails (#1143)
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit ad1b1cb1e2052621d979cfdccb4870d6b4b31613)
* chore: Release v7.80.2 [skip ci]
(cherry picked from commit 9a9d8067157f922c55503b53a68e9a220d568351)
* Update generated references
(cherry picked from commit ad79bd03c268eb02f4b17ab8fc21998a1e3bf2fe)
* fix(ai): report OpenAI Agents cached tokens (#1102)
* fix(ai): report OpenAI Agents cached and reasoning tokens
The Agents SDK nests cached input and reasoning tokens under the usage
details fields: input_tokens_details/output_tokens_details on generation
span usage and on the Responses usage object of response spans. The
processor read flat keys that the SDK never sets, so both were always
dropped. Read the nested fields, keeping the flat keys for custom models.
* fix(ai): declare inclusive cache reporting for nested Agents usage
OpenAI-shaped usage counts cached tokens inside input_tokens. Declare
$ai_cache_reporting_exclusive: False when the cache count comes from the
nested usage details, as the Node Agents processor does, so the cost backend
does not infer exclusive reporting from a Claude model name served through an
OpenAI-compatible endpoint. Flat custom-model keys keep their own convention,
and a caller-supplied value still takes precedence.
* fix(ai): don't forward inclusive Agents reasoning tokens
OpenAI-compatible providers such as OpenRouter count reasoning inside
completion_tokens, while the cost backend adds reasoning on top for Gemini
model names, so forwarding the nested count priced reasoning twice. Keep
the original flat reasoning_tokens key only; cached tokens are unchanged.
(cherry picked from commit 4d6e44766175f80fbbf538ab4369b1f3916f05f7)
* chore: Release v7.80.3 [skip ci]
(cherry picked from commit 2989cd2f36607406c6d607d7033507ca69936711)
* Update generated references
(cherry picked from commit c380dc8cc731c4d1474a2427afcd3e426bf68b88)
* chore(deps): bump setuptools from 83.0.0 to 84.1.0 in /examples/example-ai-autogen in the uv group across 1 directory (#1131)
chore(deps): bump setuptools
Bumps the uv group with 1 update in the /examples/example-ai-llamaindex directory: [setuptools](https://github.com/pypa/setuptools).
Updates `setuptools` from 83.0.0 to 84.1.0
- [Release notes](https://github.com/pypa/setuptools/releases)
- [Changelog](https://github.com/pypa/setuptools/blob/main/NEWS.rst)
- [Commits](https://github.com/pypa/setuptools/compare/v83.0.0...v84.1.0)
---
updated-dependencies:
- dependency-name: setuptools
dependency-version: 84.1.0
dependency-type: indirect
dependency-group: uv
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 6f765a3cb491de5b414e157e095c8155b59f18e2)
* chore(deps): bump authlib from 1.7.2 to 1.9.1 (#1140)
Bumps [authlib](https://github.com/authlib/authlib) from 1.7.2 to 1.9.1.
- [Release notes](https://github.com/authlib/authlib/releases)
- [Commits](https://github.com/authlib/authlib/compare/v1.7.2...v1.9.1)
---
updated-dependencies:
- dependency-name: authlib
dependency-version: 1.9.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 871ad9e526058b889efd88957f29d0d86ccce5d0)
* chore(deps): bump the ai-providers group across 1 directory with 7 updates (#1145)
Bumps the ai-providers group with 7 updates in the / directory:
| Package | From | To |
| --- | --- | --- |
| [langchain](https://github.com/langchain-ai/langchain) | `1.4.4` | `1.4.7` |
| [langgraph](https://github.com/langchain-ai/langgraph) | `1.2.14` | `1.2.16` |
| [langchain-core](https://github.com/langchain-ai/langchain) | `1.6.9` | `1.6.13` |
| [langchain-openai](https://github.com/langchain-ai/langchain) | `1.7.0` | `1.7.2` |
| [langchain-anthropic](https://github.com/langchain-ai/langchain) | `1.7.5` | `1.7.6` |
| [google-genai](https://github.com/googleapis/python-genai) | `2.29.0` | `2.32.0` |
| [langchain-protocol](https://github.com/langchain-ai/agent-protocol) | `0.0.19` | `0.0.20` |
Updates `langchain` from 1.4.4 to 1.4.7
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain==1.4.4...langchain==1.4.7)
Updates `langgraph` from 1.2.14 to 1.2.16
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/1.2.14...1.2.16)
Updates `langchain-core` from 1.6.9 to 1.6.13
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-core==1.6.9...langchain-core==1.6.13)
Updates `langchain-openai` from 1.7.0 to 1.7.2
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-openai==1.7.0...langchain-openai==1.7.2)
Updates `langchain-anthropic` from 1.7.5 to 1.7.6
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-anthropic==1.7.5...langchain-anthropic==1.7.6)
Updates `google-genai` from 2.29.0 to 2.32.0
- [Release notes](https://github.com/googleapis/python-genai/releases)
- [Changelog](https://github.com/googleapis/python-genai/blob/main/CHANGELOG.md)
- [Commits](https://github.com/googleapis/python-genai/compare/v2.29.0...v2.32.0)
Updates `langchain-protocol` from 0.0.19 to 0.0.20
- [Release notes](https://github.com/langchain-ai/agent-protocol/releases)
- [Commits](https://github.com/langchain-ai/agent-protocol/compare/langchain-protocol==0.0.19...langchain-protocol==0.0.20)
---
updated-dependencies:
- dependency-name: langchain
dependency-version: 1.4.7
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langgraph
dependency-version: 1.2.16
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-core
dependency-version: 1.6.13
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-openai
dependency-version: 1.7.2
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-anthropic
dependency-version: 1.7.6
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: google-genai
dependency-version: 2.32.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: ai-providers
- dependency-name: langchain-protocol
dependency-version: 0.0.20
dependency-type: indirect
update-type: version-update:semver-patch
dependency-group: ai-providers
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit c9105c5be181b3e81737c7481dc92f68f0cafcf7)
* ci: pin Python 3.11 by minor version for Ubuntu 26.04 runners (#1153)
(cherry picked from commit 50cf3573f2af46455c1a313e1649649f9d671180)
* feat: send transactional email from posthog templates (#1093)
* feat: send transactional email from posthog templates
Add posthog.emails.send() on Client and AsyncClient, plus standalone Emails and AsyncEmails in posthog.emails for processes that only send email. Sends go to the app host with a project secret API key and an Idempotency-Key, and retry network errors, rate limits, an in-flight key and 503 with the same key. Errors raise EmailError with PostHog's code and a Resend-style name.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: c62b30cd-eb2e-496c-a73d-2a6e7a52a62e
* fix: keep the email secret key off custom hosts and close email transports
client.emails only infers PostHog Cloud app hosts. A custom host raises app_host_required before any request, so an ingestion proxy never receives the project secret key. A kept emails reference now reads the client's disabled state on every send. Shutdown closes the email transport, a forked child drops the parent's email session, and the retry ceiling applies after jitter. Docs examples use client.emails.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: c62b30cd-eb2e-496c-a73d-2a6e7a52a62e
* fix: refuse email sends after shutdown and drain async sends first
client.emails now asks the parent client to admit each send. After shutdown, a kept or new client.emails raises EmailError with code client_closed and makes no request. On AsyncClient, an admitted send is an in-flight operation, so shutdown waits for it, retries included, before it closes the email transport.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: c62b30cd-eb2e-496c-a73d-2a6e7a52a62e
* feat: configure email sends on the client and document setup
Posthog and AsyncPosthog take app_host, email_request_timeout_seconds and email_request_max_retries, so client.emails works behind a custom host and a job runner can turn retries off. Emails takes a session and AsyncEmails an http_client, which gives tests a supported no-network path. The posthog.emails module docs now hold a setup quickstart: keys and scope, template ID, hosts, retries, errors to expect, cleanup and testing. The release note names client.emails.send().
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: c62b30cd-eb2e-496c-a73d-2a6e7a52a62e
* fix: match the email contract's missing_app_host and keep network causes
- A non-Cloud host without app_host now fails with missing_app_host, the code the cross-SDK contract in PostHog/posthog#120921 defines, matching posthog-node.
- A network_error keeps the requests or httpx exception as __cause__, so a failed send is easier to debug.
- Regenerate the public API snapshot after the rebase onto main.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* fix: keep the bearer token and send timeout on injected async clients
An httpx.AsyncClient passed as http_client can carry its own auth and timeout. Its auth replaced the email's Bearer header, and its timeout replaced the send timeout, so a client built with timeout=None left sends unbounded. Each async send now passes auth=None and timeout=self.timeout.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* fix: name 422 send checks validation_error
The template send route answers 422 for recipient_suppressed, sending_paused and sending_suspended as well as idempotency_key_reused. Only idempotency_key_reused is now invalid_idempotent_request; the send checks are validation_error, as the cross-SDK contract names them and posthog-node does.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* fix: raise client_disabled for email sends from a disabled client
A disabled client returned SendEmailResult(id=None), so a caller that treats a returned result as sent dropped the email silently. It now sends nothing and raises EmailError with code client_disabled (name application_error), as the cross-SDK contract in PostHog/posthog#120921 defines and posthog-node does. SendEmailResult.id is always the queued message ID, so its type is str.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* feat: send transactional email through the single send endpoint
`emails.send()` now posts to `/api/projects/@current/messaging/send/email/` with the template ID in the body as `template.id`, instead of the template-scoped route.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* feat: read a transactional email's status with emails.get
`emails.get(message_id)` on `Emails` and `AsyncEmails` reads `/api/projects/@current/messaging/emails/{id}/` and returns an `EmailStatus` with `status`, `created_at`, `status_at` and `reason`. It retries network errors, rate limits and an unavailable service like `send`, which now shares that attempt loop.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* docs: describe the email error name as a category
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
* feat: add a per-send max_retries to emails.send
`send(max_retries=...)` on `Emails` and `AsyncEmails` overrides the client's retry limit for one send, like posthog-node's `maxRetries`. A negative or non-integer value raises `ValueError` before any request.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Generated-By: PostHog Desktop
Task-Id: e72a2c10-f145-4f7c-8754-a4fcc06a18be
(cherry picked from commit 01e91db94185969f636d501a58a21eb9f2c3721e)
* chore: Release v7.81.0 [skip ci]
(cherry picked from commit 139161e95fc7328148a54e442f3792a3a6038da0)
* Update generated references
(cherry picked from commit af8e1aa3f000a89091fe43fe7b639449671e1529)
* fix(ai): keep the choices of an n>1 OpenAI chat stream apart (#1152)
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit be77b83462a690c8c303f5676a28207a9c17f68a)
* fix(ai): preserve Gemini tool call IDs in captured generations (#1150)
Gemini returns IDs on function calls and function responses, but the
captured $ai_output_choices and $ai_input dropped them, so tool results
could not be matched to their calls. Keep the call ID on output (streaming
and non-streaming) and on input history calls, and the result's ID as
tool_use_id, matching PostHog/posthog-js#5087.
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit a61e64d1a40be337af3e09925d53f56c78d0baba)
* chore: Release v7.81.1 [skip ci]
(cherry picked from commit f23efe9d3e0dfe68a7136f80a48e6420ada38e41)
* Update generated references
(cherry picked from commit dca22075ced7f4beaca798a8dd155169eec50b4d)
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: alexcastgonz <82875882+pcbeingused333@users.noreply.github.com>
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
Co-authored-by: releaser-posthog-python[bot] <262414804+releaser-posthog-python[bot]@users.noreply.github.com>
Co-authored-by: Anna Garcia <11654201+turnipdabeets@users.noreply.github.com>
Co-authored-by: Manoel Aranda Neto <5731772+marandaneto@users.noreply.github.com>
Co-authored-by: Georgis Andonis <6430745+gesh@users.noreply.github.com>
Co-authored-by: Carlos Marchal <carlos@posthog.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Radu Raicea <radu@raicea.com>
Co-authored-by: Gustavo H. Strassburger <gustavo@posthog.com>
Co-authored-by: Daniel Visca <daniel.v@posthog.com>
Co-authored-by: mosafariuk <mosafariuk@gmail.com>
Co-authored-by: Anders <754494+andehen@users.noreply.github.com>
Co-authored-by: Harley Alexander <43975092+mayteio@users.noreply.github.com>
Co-authored-by: Jae Bird <jaeminbird@gmail.com>
* chore: add major changeset for posthog 8.0 capture v1 release
* feat!: send capture through v1 by default; capture_ai to /i/v1/ai/events (#1017)
feat!: send capture through v1 by default; capture_ai posts to /i/v1/ai/events
Capture v1 is now the default capture mode. The AI lane always posts capture v1 to /i/v1/ai/events, uncompressed, regardless of the analytics capture_mode. Tests move to a shared capture v1 send seam (posthog/test/capture_helpers.py); v0-only tests are pinned to CaptureMode.V0 until v0 removal.
* feat!: remove capture v0 and legacy transport options (#1018)
Capture v1 is the only capture path. Remove CaptureMode, the capture_mode
kwarg and POSTHOG_CAPTURE_MODE, the gzip kwarg, request.batch_post and the
v0 endpoint constants, and the backoff dependency. Client and AsyncPosthog
constructors are keyword-only after host.
* refactor!: split capture_v1 into capture_event and capture_send (#1019)
Rename CaptureV1Error to CaptureError and export it from posthog. Event
shaping moves to posthog.capture_event and transport to
posthog.capture_send. No behavior change.
* feat!: report capture v1 results through CaptureError and on_error (#1020)
* feat!: report capture v1 results through CaptureError and on_error
* test: cover _uuid7 layout for the mutation gate
* fix: re-raise sync capture failures in debug mode after reporting them
Also document which events verdict_summary() counts.
* feat: AI lane config and size-aware batching (#1022)
* feat: AI lane config and size-aware batching
* chore: tighten AI lane comments
* fix: reject non-finite AI lane config values
* test(mcp): fix get_tool checks for fastmcp 4.0.11 (#1050)
test(mcp): drop get_tool checks that fastmcp 4.0.11 invalidated
fastmcp 4.0.11 resolves middleware-injected tools through the server's
tool lookup (PrefectHQ/fastmcp#5431), so get_tool() now returns them.
The two setup assertions that expected None fail on any fresh install.
The SDK behavior the tests check is unchanged and passes on 4.0.10 and
4.0.11.
(cherry picked from commit 897cd43d322156d9903d4950ee4caa06fcaa7d3f)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat!: add per-event capture options (#1023)
feat!: per-event capture options and legacy property hoisting
* feat!: add global and context option layers (#1024)
* feat!: super_options, context options and personless as the lowest option layer
* docs: state the option layer rules in capture docstrings
* feat!: fill context and super values after before_send
Context tags, context options, super_properties, super_options, the
derived personless option and the environment $release_id now fill only
keys an event leaves unset, after before_send runs. before_send sees
only the event's own values and SDK enrichment, and its changes beat
every default. A None option counts as unset and is filled. Legacy
properties still fill only unset options and are always removed.
* feat!: fill context and super values before before_send
Context tags, context options, super_properties, super_options, the
derived personless option and the environment $release_id now fill
before before_send runs, still only into keys the event leaves unset.
before_send sees every value and has the final say, including removing
a super property. $set, $set_once, $groups and $group_set fill one
level deep when both values are dicts. The set() and set_once() values
now win key by key over a $set or $set_once in properties, as ingestion
merges them. Hoisting still runs once, after the hook.
* feat!: SDK values are defaults that caller values override
$is_server, $geoip_disable and system context now fill last, only keys the
event, context tags and super_properties left unset, before before_send. A
super property $geoip_disable: False now wins over disable_geoip=True.
The groups argument merges into a $groups property key by key and wins,
in Client, AsyncClient and posthog.mcp events.
* fix: copy async default layers at admission; typed groups win on MCP exception events
AsyncPosthog filled defaults in the worker from references to the live
super_properties and options, so a change after capture could reach a queued
event. Each layer is now shallow-copied when the event is admitted, as 7.x
merged super_properties into a new dict at capture.
The MCP exception event now merges typed groups after custom properties, like
the primary event, so both events of a failing call get the same groups.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* feat!: AI and MCP send personless as an event option (#1025)
feat!: AI wrappers and MCP send personless as a per-event option
* chore(ci): run compliance harness 1.13.1 once per codec (#1026)
* chore(ci): run compliance harness 1.13.1 once per codec
The adapter now advertises capture_ai_v1 and event_options, passes options and uuids through unchanged, and takes its codec from COMPRESSION. The workflow runs the harness containers directly in a gzip/deflate/zstd matrix, so it no longer needs pull-requests: write.
* chore(ci): install zstd extra for adapter protocol tests
* chore: describe the single capture compliance job and harness 1.13.1
The standalone adapter-test setup installs the zstd extra, matching CI.
* feat!: AI wrappers always send through capture_ai (#1027)
enable_full_ai_capture now controls only truncation and media redaction. A client object without capture_ai still gets capture calls.
* feat: add an AI capture lane to AsyncPosthog (#1028)
* feat: AsyncPosthog AI capture lane
* fix: type capture v1 send timeouts as float
* feat: AsyncPosthog privacy_mode and enable_full_ai_capture
* fix: keep async capture_ai from raising on a non-string event name
* test: cover capture invariants on both lanes (#1029)
* test: capture invariant hardening
* test: assert exactly one capture loss line per failed batch
* docs: 8.0 migration guide and openfeature-provider pin (#1030)
* docs: 8.0 migration guide, README and openfeature-provider pin
* chore: let openfeature provider accept posthog 7 and 8
* docs: say options beat legacy properties at every layer
* docs: name the CaptureError import and the posthoganalytics mirror
* docs: note that sync_mode failures re-raise in debug mode
* docs: describe the late fill of context and super values
* docs: describe the fill of context and super values before before_send
* docs: SDK values are defaults that caller values override
* docs: use real quota tags; a billing limit is a 402
Capture never sends billing_limit_exceeded or billing as a per-event tag.
Product quotas drop single events in a 2xx with tags such as
llm_events_over_quota; a request over the billing limit gets a 402 with
no per-event results.
* docs: complete the 8.0 migration guide
* chore(examples): run the pinned AI examples against the local SDK
* feat!: MCP no longer relabels the client SDK identity (#1034)
* feat!: keep the posthog-python identity when instrumenting MCP
MCP instrumentation relabeled the whole client, so the app's own events and flag requests reported posthog-python-mcp. Capture v1 takes $lib from the per-request PostHog-Sdk-Info header, which is now always posthog-python.
* chore: remove the unused request identity plumbing and stale MCP client advice
* fix!: follow capture redirects only to the same origin (#1035)
fix!: follow capture redirects only to the configured origin
_post_v1 disables automatic redirects and resends the batch only on a 307 or 308 to the origin of host, at most 5 times. Any other redirect returns as a terminal failure. Covers the sync client and the async client, which lost its v0 same-origin guard when v1 became the only path.
* chore: sync main into v1 (7.65.0–7.67.0) (#1044)
* ci: reuse Python SDK upgrade PRs unless queued (#1021)
* ci: reuse Python SDK upgrade PRs unless queued
* ci: protect reused upgrade PRs from stale and queued writes
(cherry picked from commit 945bbbc96774eb95df9849ecd313e92a28a291a8)
* feat(error-tracking): standardize exception event metadata (#898)
* feat(error-tracking): standardize exception metadata
* fix(error-tracking): preserve explicit trace context
* fix(error-tracking): restrict exception group traversal
* fix(error-tracking): deprecate reserved property overrides
* fix(error-tracking): bound exception group traversal
(cherry picked from commit 6d6cc3dac989569f3c571308e4db9b9f6ecf7b36)
* chore: Release v7.65.0 [skip ci]
(cherry picked from commit c4e6bdd7a89b9b7fb71f530e6d8e392c8fe02909)
* Update generated references
(cherry picked from commit 50efa658f160766aa5296a699393a7aad80b8e40)
* feat(asgi): add error tracking middleware (#1037)
* feat(asgi): add error tracking middleware
* chore(asgi): type exception capture metadata
* fix(asgi): make tracing header trust explicit
* refactor(asgi): expose request properties terminology
(cherry picked from commit 1c6a47ae235c127329c38db02cb6837a7f1c6434)
* feat(mcp): resolve fresh low-level tool ownership (#1009)
* feat(mcp): resolve fresh low-level tool ownership
Add resolve_original_tool for raw MCP SDK 1.x and 2.x servers. Prefer ownership learned from a served listing and keep unknown ownership fail-open.
Generated-By: PostHog Desktop
Task-Id: db1a8a08-fe03-43b6-9e49-705e8b1f375e
* fix(mcp): preserve listed argument ownership
Generated-By: PostHog Desktop
Task-Id: db1a8a08-fe03-43b6-9e49-705e8b1f375e
* fix(mcp): preserve arguments for unknown schemas
Generated-By: PostHog Desktop
Task-Id: db1a8a08-fe03-43b6-9e49-705e8b1f375e
* fix(mcp): preserve low-level tool schemas
Generated-By: PostHog Desktop
Task-Id: db1a8a08-fe03-43b6-9e49-705e8b1f375e
(cherry picked from commit 127009dc394af6638a3ea8a88bdb0dcae46db0c3)
* feat(flask): add error tracking integration (#1038)
* feat(flask): add error tracking integration
* fix(flask): use canonical exception metadata
* chore(flask): type exception capture metadata
* refactor(flask): expose request properties terminology
* fix(flask): preserve exception privacy settings
(cherry picked from commit 292855d1f267ad50e9c3b8341c9fbc839b36cf5c)
* chore: Release v7.66.0 [skip ci]
(cherry picked from commit d23ef68b2e72daa3bb30cc4b324ee339f354b8df)
* Update generated references
(cherry picked from commit c0e05b1eba5ce1a3c109b9b0ab18c111cbc2d677)
* feat(drf): add automatic error tracking integration (#1036)
* feat(drf): add automatic error tracking integration
* fix(drf): align exception metadata with SDK spec
* chore(drf): type exception capture metadata
* fix(drf): honor Django request filtering
* test(drf): describe context data as properties
* feat(drf): support exception capture opt-out
* chore(drf): update public API snapshot
* fix(drf): align exception capture configuration
* test(drf): preserve omitted setting default
(cherry picked from commit 9baf8a5a84545568952490ff9397f599e0d6c9b4)
* chore: Release v7.67.0 [skip ci]
(cherry picked from commit a655c8ba25428c57a17cf38cc99bbf4987f142bf)
* Update generated references
(cherry picked from commit 509c8525fd51b52baa0ec959abe72c35aea20219)
---------
Co-authored-by: Dustin Byrne <dustin@posthog.com>
Co-authored-by: Hugues Pouillot <hpouillot@gmail.com>
Co-authored-by: releaser-posthog-python[bot] <262414804+releaser-posthog-python[bot]@users.noreply.github.com>
Co-authored-by: Georgis Andonis <6430745+gesh@users.noreply.github.com>
* feat!: exception level, keyword-only args, uuid and geoip (#1046)
* fix: make request.post and request.flags arguments keyword-only
* feat: add a level argument to capture_exception and ignore reserved exception properties
* feat: warn when a non-string session or window id is dropped
* docs: describe the exception level, keyword-only request args and session id warning
* fix: warn once without the value when replacing an invalid event uuid
An invalid caller uuid is still replaced with a generated UUIDv7, but the
SDK now logs one warning that names the rule instead of an error that
echoes the value. An empty string counts as unset and gets a generated
uuid without a log. Client and AsyncClient share one helper.
* fix: treat a per-call disable_geoip as a value of the event
A disable_geoip argument now fills $geoip_disable as the event's own
value: above context tags, super_properties and the client setting, and
below a $geoip_disable in the call's properties. disable_geoip=False now
sends $geoip_disable: false. Client and AsyncClient share the layer in
_build_event_defaults.
* fix(ai)!: AI integrations require a client with capture_ai (#1048)
* fix(ai): fail at setup when an AI integration's client lacks capture_ai
* fix(ai)!: log and disable AI capture for a client without capture_ai
Raising TypeError at construction could stop the host application over an
analytics problem. The integration now logs one error at setup and captures no
AI events; provider calls work and return normally.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* chore: sync main into v1 (7.67.1–7.68.0) (#1051)
* feat(mcp): set $mcp_interface on mcp analytics events (#1032)
feat(mcp): add interface property to server events
Generated-By: PostHog Desktop
Task-Id: 651bf7d9-01f4-4d75-8583-868e29fdd314
(cherry picked from commit a3bd254bb924322bbd48a2ee2c778fe761a7ee73)
* chore: Release v7.67.1 [skip ci]
(cherry picked from commit 4ae3d26abeaae89062428f662e2817f82d77b410)
* Update generated references
(cherry picked from commit 492d71b4b1415a6b0de41ab461374fbb8ff7d9a7)
* feat(integrations): align request middleware configuration (#1040)
* Align ASGI and Flask integration defaults
* feat(integrations): align request middleware configuration
(cherry picked from commit 2f0d67d55b074ce29b650931bb63ffe498da80a4)
* chore: Release v7.68.0 [skip ci]
(cherry picked from commit ad553debbff78a8713147e5a845928df1613aedc)
* Update generated references
(cherry picked from commit 90f8d6910a54fb9a009f78ecc760811885e32638)
* chore(deps): bump the uv group across 2 directories with 3 updates (#1042)
Bumps the uv group with 1 update in the /examples/example-ai-llamaindex directory: [banks](https://github.com/masci/banks).
Bumps the uv group with 2 updates in the /examples/example-ai-pydantic-ai directory: [pydantic-ai](https://github.com/pydantic/pydantic-ai) and [pydantic-ai-slim](https://github.com/pydantic/pydantic-ai).
Updates `banks` from 2.4.5 to 2.5.1
- [Release notes](https://github.com/masci/banks/releases)
- [Commits](https://github.com/masci/banks/compare/v2.4.5...v2.5.1)
Updates `pydantic-ai` from 1.102.0 to 1.107.7
- [Release notes](https://github.com/pydantic/pydantic-ai/releases)
- [Changelog](https://github.com/pydantic/pydantic-ai/blob/main/docs/changelog.md)
- [Commits](https://github.com/pydantic/pydantic-ai/compare/v1.102.0...v1.107.7)
Updates `pydantic-ai-slim` from 1.102.0 to 1.107.7
- [Release notes](https://github.com/pydantic/pydantic-ai/releases)
- [Changelog](https://github.com/pydantic/pydantic-ai/blob/main/docs/changelog.md)
- [Commits](https://github.com/pydantic/pydantic-ai/compare/v1.102.0...v1.107.7)
---
updated-dependencies:
- dependency-name: banks
dependency-version: 2.5.1
dependency-type: indirect
dependency-group: uv
- dependency-name: pydantic-ai
dependency-version: 1.107.7
dependency-type: direct:production
dependency-group: uv
- dependency-name: pydantic-ai-slim
dependency-version: 1.107.7
dependency-type: indirect
dependency-group: uv
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit ee686ffb0593fa1adfd1f2fa4bcc146270d4f07d)
* test(django): read the middleware context test's event after defaults fill
On v1, context properties are filled inside _enqueue, before before_send.
The test patched _enqueue itself, so it saw the event before the fill and
lost $request_path and role. It now records the event in before_send.
The assertions are unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: redirect origin and logging fixes from review; scope AI routing docs
- Compare redirect origins as requests sends them, so a Unicode host
matches its IDNA form.
- Log a refused or exhausted capture redirect at debug; failed-batch
reporting owns warnings.
- The migration guide says the OpenTelemetry integration still exports
to /i/v0/ai/otel.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Georgis Andonis <6430745+gesh@users.noreply.github.com>
Co-authored-by: releaser-posthog-python[bot] <262414804+releaser-posthog-python[bot]@users.noreply.github.com>
Co-authored-by: Hugues Pouillot <hpouillot@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix!: drop only the invalid event, not its whole batch (#1052)
* fix: drop only the invalid event, and size analytics by capture's limits
An event with a missing, empty or non-string name, or one that cannot be
serialized (for example with NaN), is dropped alone instead of failing the
whole batch at capture. A property key JSON cannot represent is dropped from
its event. The analytics per-event limit is capture's 10 MiB request limit,
since capture reports an event over its per-event limit in the response.
A personal API key disables the client like an empty key, and logs no longer
include event content or invalid timestamp values.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: cover the event name, warn-once and personal key helpers in test_utils
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep the module client disabled for a personal API key; narrow two guide claims
- setup() re-derived disabled from the key being non-empty, which
re-enabled a client given a phx_ key on every module call.
- The guide now says finite float keys are stringified (NaN keys drop
the event) and that only the SDK's own log lines drop event content.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: note the 200-byte event name limit in the 8.0 migration guide
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: drop an event whose before_send leaves a non-string distinct_id
before_send can set any value, and capture v1 rejects the whole request
for a non-string distinct_id. The SDK now drops that event locally with
one warning per reason, and never converts the value or makes up an ID.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix!: group_identify and alias never guess a distinct id (#1053)
* fix: take group and alias ids from the caller, and apply request context by one rule
group_identify uses the caller's distinct id, then the context id, then
$<group_type>_<group_key>, never a random id, and no longer adds the context
session id. alias() no longer takes its target from the context distinct id.
Context tags and options now reach alias and group_identify like capture.
An empty or whitespace-only distinct id counts as missing, and generated
personless distinct ids are UUIDv7.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: context reach for alias and group_identify; 200-byte distinct id limit
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: drop product_tour_id from the guide; name the legacy option properties
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: spread capture retry waits by up to 25% (#1058)
Clients that fail together now retry at slightly different times, so they
do not all hit capture at once while it recovers. Retry-After still sets a
minimum wait, and the 30 s cap still applies.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: read tracing headers by default in v1 integrations (port of #1061) (#1107)
* fix(integrations): align tracing-header capture across frameworks (#1061)
(cherry picked from commit 780cba9aeea0d990a65fafe88860905bb4941d81)
* fix: adapt the tracing header port to v1 and note it in the 8.0 guide
v1 turns person processing off for a generated distinct ID with an event
option, which beats the legacy property, so the ported test checks the
derived option. The 8.0 migration guide notes the default and the off
switch.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Dustin Byrne <dustin@posthog.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: report capture's dropped duplicate copies as drops (#1113)
* fix: report capture's dropped duplicate copies as drops
Capture now keeps the first event for each uuid in a request and returns
duplicates_dropped on that uuid's result. The SDK reports that many later
copies as drops with reason duplicate_event_uuid and never resends them,
and verdict_summary counts each drop by its own reason.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: note older capture's 400 for duplicate uuids
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* docs: mark the migration guide to link the public capture v1 guide (#1114)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* chore: sync main into v1 (7.69.0–7.75.6) (#1120)
* feat(metrics): attach trace exemplars to flushed metric series (#1057)
(cherry picked from commit 3cc2d6468d22306897db285bf5fa291a94287e71)
* chore: Release v7.69.0 [skip ci]
(cherry picked from commit 653ff87684d7453ee01dd3f2f19dbf709bcf6592)
* Update generated references
(cherry picked from commit 6f658988e5b843c03ec73287677cae0f83b391e3)
* feat(ai): add per-request context to span processor (#1060)
* feat: span processor request context
* fix: span processor review feedback
* fix: span processor review follow-ups
(cherry picked from commit 69164994c920bbaf445c3a2c20b9f558f6a5a473)
* chore: Release v7.70.0 [skip ci]
(cherry picked from commit a615eed8fb157f4dfa5e4d141a998c137c4b9ba3)
* Update generated references
(cherry picked from commit a49648e0a0f9842914df91c3d2790ad9e4edca71)
* fix(prompts): share one request between concurrent fetches of the same prompt (#1059)
(cherry picked from commit 10d094e384efce1422ae1853951b7d2eaa0885ef)
* chore: Release v7.70.1 [skip ci]
(cherry picked from commit ec71a24065b34fb326f5022a9c0225398f82ec75)
* Update generated references
(cherry picked from commit fc3c4347d3371dc84dc4ea0276d3355c353a2eb7)
* fix(ai): mark cancelled async LLM calls as errors (#1065)
* fix(ai): mark cancelled async LLM calls as errors
* test: fix Python 3.10 cancellation and FastMCP compatibility
(cherry picked from commit fec41f24cb497d37a8cd0dd53490b74c98554dfa)
* chore: Release v7.70.2 [skip ci]
(cherry picked from commit e3818080b5aa2f7f885b3b99643a7f34f9f9f3d8)
* Update generated references
(cherry picked from commit f33d55d0f1fd01698140cff73e21b9f65bd1f0d7)
* chore(deps): bump the ai-providers group with 8 updates (#1054)
Bumps the ai-providers group with 8 updates:
| Package | From | To |
| --- | --- | --- |
| [langchain](https://github.com/langchain-ai/langchain) | `1.4.2` | `1.4.3` |
| [anthropic](https://github.com/anthropics/anthropic-sdk-python) | `1.8.0` | `1.11.0` |
| [langgraph](https://github.com/langchain-ai/langgraph) | `1.2.12` | `1.2.13` |
| [langchain-core](https://github.com/langchain-ai/langchain) | `1.6.5` | `1.6.6` |
| [langchain-openai](https://github.com/langchain-ai/langchain) | `1.6.6` | `1.6.7` |
| [langchain-anthropic](https://github.com/langchain-ai/langchain) | `1.7.4` | `1.7.5` |
| [google-genai](https://github.com/googleapis/python-genai) | `2.25.0` | `2.28.0` |
| [langchain-text-splitters](https://github.com/langchain-ai/langchain) | `1.1.2` | `1.1.3` |
Updates `langchain` from 1.4.2 to 1.4.3
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain==1.4.2...langchain==1.4.3)
Updates `anthropic` from 1.8.0 to 1.11.0
- [Release notes](https://github.com/anthropics/anthropic-sdk-python/releases)
- [Changelog](https://github.com/anthropics/anthropic-sdk-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/anthropics/anthropic-sdk-python/compare/v1.8.0...v1.11.0)
Updates `langgraph` from 1.2.12 to 1.2.13
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/1.2.12...1.2.13)
Updates `langchain-core` from 1.6.5 to 1.6.6
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-core==1.6.5...langchain-core==1.6.6)
Updates `langchain-openai` from 1.6.6 to 1.6.7
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-openai==1.6.6...langchain-openai==1.6.7)
Updates `langchain-anthropic` from 1.7.4 to 1.7.5
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-anthropic==1.7.4...langchain-anthropic==1.7.5)
Updates `google-genai` from 2.25.0 to 2.28.0
- [Release notes](https://github.com/googleapis/python-genai/releases)
- [Changelog](https://github.com/googleapis/python-genai/blob/main/CHANGELOG.md)
- [Commits](https://github.com/googleapis/python-genai/compare/v2.25.0...v2.28.0)
Updates `langchain-text-splitters` from 1.1.2 to 1.1.3
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-text-splitters==1.1.2...langchain-text-splitters==1.1.3)
---
updated-dependencies:
- dependency-name: langchain
dependency-version: 1.4.3
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: anthropic
dependency-version: 1.11.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: ai-providers
- dependency-name: langgraph
dependency-version: 1.2.13
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-core
dependency-version: 1.6.6
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-openai
dependency-version: 1.6.7
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-anthropic
dependency-version: 1.7.5
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: google-genai
dependency-version: 2.28.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: ai-providers
- dependency-name: langchain-text-splitters
dependency-version: 1.1.3
dependency-type: indirect
update-type: version-update:semver-patch
dependency-group: ai-providers
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Dustin Byrne <dustin@posthog.com>
(cherry picked from commit f95e1f46ef4de0b6903750583f3d63843a6dd685)
* chore(deps): bump the github-actions group with 2 updates (#1055)
Bumps the github-actions group with 2 updates: [dtolnay/rust-toolchain](https://github.com/dtolnay/rust-toolchain) and [PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml](https://github.com/posthog/posthog-sdk-test-harness).
Updates `dtolnay/rust-toolchain` from 7e38f4b43b4db5c8dd498af069a4f6196df1d067 to e2a55d2ffb04f378e9626c28d38b36d230d1e12f
- [Release notes](https://github.com/dtolnay/rust-toolchain/releases)
- [Commits](https://github.com/dtolnay/rust-toolchain/compare/7e38f4b43b4db5c8dd498af069a4f6196df1d067...e2a55d2ffb04f378e9626c28d38b36d230d1e12f)
Updates `PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml` from 1.11.0 to 1.13.1
- [Release notes](https://github.com/posthog/posthog-sdk-test-harness/releases)
- [Changelog](https://github.com/PostHog/posthog-sdk-test-harness/blob/main/CHANGELOG.md)
- [Commits](https://github.com/posthog/posthog-sdk-test-harness/compare/4593de8b423f61fa222115da592e5c18dc82ad3c...e32f08bd30fab57ce543da5808a668d0fda697b0)
---
updated-dependencies:
- dependency-name: dtolnay/rust-toolchain
dependency-version: e2a55d2ffb04f378e9626c28d38b36d230d1e12f
dependency-type: direct:production
dependency-group: github-actions
- dependency-name: PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml
dependency-version: 1.13.1
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Dustin Byrne <dustin@posthog.com>
(cherry picked from commit 9b7e63290109c1c5ccdbe5c5225cb07c77e97f73)
* chore(deps): bump mcp from 1.28.1 to 1.30.0 (#1068)
Bumps [mcp](https://github.com/modelcontextprotocol/python-sdk) from 1.28.1 to 1.30.0.
- [Release notes](https://github.com/modelcontextprotocol/python-sdk/releases)
- [Changelog](https://github.com/modelcontextprotocol/python-sdk/blob/main/RELEASE.md)
- [Commits](https://github.com/modelcontextprotocol/python-sdk/compare/v1.28.1...v1.30.0)
---
updated-dependencies:
- dependency-name: mcp
dependency-version: 1.30.0
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 12e88a254e900e71824aa9fdc95987ec7082c312)
* docs: clarify reusable flush and terminal shutdown guidance (#1043)
* docs: clarify reusable flush and terminal shutdown guidance
* docs: preserve published 7.67.0 reference snapshot
(cherry picked from commit d0b6f7127f6d60a17d1c67724ad5eb50d12a7dd6)
* chore: Release v7.71.0 [skip ci]
(cherry picked from commit 20a574ec0d723a2228f51d3a1d63b44ecaf343d4)
* Update generated references
(cherry picked from commit 883eacaba876dfc7d50febbf44b791470df7cc51)
* chore(deps): bump the uv group across 4 directories with 2 updates (#1069)
Bumps the uv group with 1 update in the /examples/example-ai-llamaindex directory: [tinytag](https://github.com/tinytag/tinytag).
Bumps the uv group with 1 update in the /examples/example-ai-openai-agents directory: [mcp](https://github.com/modelcontextprotocol/python-sdk).
Bumps the uv group with 1 update in the /examples/example-ai-pydantic-ai directory: [mcp](https://github.com/modelcontextprotocol/python-sdk).
Bumps the uv group with 1 update in the /examples/example-ai-semantic-kernel directory: [mcp](https://github.com/modelcontextprotocol/python-sdk).
Updates `tinytag` from 2.2.1 to 2.3.0
- [Release notes](https://github.com/tinytag/tinytag/releases)
- [Commits](https://github.com/tinytag/tinytag/compare/2.2.1...2.3.0)
Updates `mcp` from 1.28.1 to 1.30.0
- [Release notes](https://github.com/modelcontextprotocol/python-sdk/releases)
- [Changelog](https://github.com/modelcontextprotocol/python-sdk/blob/main/RELEASE.md)
- [Commits](https://github.com/modelcontextprotocol/python-sdk/compare/v1.28.1...v1.30.0)
Updates `mcp` from 1.29.1 to 1.30.0
- [Release notes](https://github.com/modelcontextprotocol/python-sdk/releases)
- [Changelog](https://github.com/modelcontextprotocol/python-sdk/blob/main/RELEASE.md)
- [Commits](https://github.com/modelcontextprotocol/python-sdk/compare/v1.28.1...v1.30.0)
Updates `mcp` from 2.1.1 to 2.2.0
- [Release notes](https://github.com/modelcontextprotocol/python-sdk/releases)
- [Changelog](https://github.com/modelcontextprotocol/python-sdk/blob/main/RELEASE.md)
- [Commits](https://github.com/modelcontextprotocol/python-sdk/compare/v1.28.1...v1.30.0)
---
updated-dependencies:
- dependency-name: tinytag
dependency-version: 2.3.0
dependency-type: indirect
dependency-group: uv
- dependency-name: mcp
dependency-version: 1.30.0
dependency-type: indirect
dependency-group: uv
- dependency-name: mcp
dependency-version: 1.30.0
dependency-type: indirect
dependency-group: uv
- dependency-name: mcp
dependency-version: 2.2.0
dependency-type: indirect
dependency-group: uv
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit b1363dc5e20c46f6a2c7f33cbf586fd9c302d80b)
* chore(deps-dev): bump claude-agent-sdk from 0.1.50 to 0.2.121 (#1073)
Bumps [claude-agent-sdk](https://github.com/anthropics/claude-agent-sdk-python) from 0.1.50 to 0.2.121.
- [Release notes](https://github.com/anthropics/claude-agent-sdk-python/releases)
- [Changelog](https://github.com/anthropics/claude-agent-sdk-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/anthropics/claude-agent-sdk-python/compare/v0.1.50...v0.2.121)
---
updated-dependencies:
- dependency-name: claude-agent-sdk
dependency-version: 0.2.121
dependency-type: direct:development
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit a89acf807c35a780545c1327530c97c8c1b0a008)
* feat(mcp): stop sending standalone $identify events (#1067)
* feat(mcp): stop sending standalone $identify events
The identify callback still sets distinct_id, $set and $groups on every
event. The standalone event carried no $anon_distinct_id, so ingestion
merged no person, and stateless servers sent one per tool call.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore(mcp): assert no $identify over the wire and refresh docs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit facd617491a74d8c3c751f0a628661b3817b250d)
* chore: Release v7.72.0 [skip ci]
(cherry picked from commit 876b955942cf86579dfda7032ec03a42de06769f)
* Update generated references
(cherry picked from commit b8327de20f3ed1ba59863c1cbb7e086655cdce12)
* chore(deps): bump the github-actions group with 6 updates (#1083)
Bumps the github-actions group with 6 updates:
| Package | From | To |
| --- | --- | --- |
| [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) | `10.2.0` | `10.3.0` |
| [github/codeql-action/init](https://github.com/github/codeql-action) | `4.38.2` | `4.38.3` |
| [github/codeql-action/analyze](https://github.com/github/codeql-action) | `4.38.2` | `4.38.3` |
| [actions/create-github-app-token](https://github.com/actions/create-github-app-token) | `3.2.0` | `3.3.0` |
| [dtolnay/rust-toolchain](https://github.com/dtolnay/rust-toolchain) | `e2a55d2ffb04f378e9626c28d38b36d230d1e12f` | `683b588c487a69d01f6c6ddf40f036ff682cc2c8` |
| [PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml](https://github.com/posthog/posthog-sdk-test-harness) | `1.13.1` | `1.15.0` |
Updates `astral-sh/setup-uv` from 10.2.0 to 10.3.0
- [Release notes](https://github.com/astral-sh/setup-uv/releases)
- [Commits](https://github.com/astral-sh/setup-uv/compare/c18668ad3cf93ea998bef934396af7bb5c839dc7...1c37ad07a6a961277cf70c0d37d6f313000f5884)
Updates `github/codeql-action/init` from 4.38.2 to 4.38.3
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](https://github.com/github/codeql-action/compare/2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2...24c54180a607b1449ed407dd24f251e4e9147c8d)
Updates `github/codeql-action/analyze` from 4.38.2 to 4.38.3
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](https://github.com/github/codeql-action/compare/2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2...24c54180a607b1449ed407dd24f251e4e9147c8d)
Updates `actions/create-github-app-token` from 3.2.0 to 3.3.0
- [Release notes](https://github.com/actions/create-github-app-token/releases)
- [Changelog](https://github.com/actions/create-github-app-token/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/create-github-app-token/compare/bcd2ba49218906704ab6c1aa796996da409d3eb1...64ab729a6294000f5aa4a4bc0b73d1f32bc45510)
Updates `dtolnay/rust-toolchain` from e2a55d2ffb04f378e9626c28d38b36d230d1e12f to 683b588c487a69d01f6c6ddf40f036ff682cc2c8
- [Release notes](https://github.com/dtolnay/rust-toolchain/releases)
- [Commits](https://github.com/dtolnay/rust-toolchain/compare/e2a55d2ffb04f378e9626c28d38b36d230d1e12f...683b588c487a69d01f6c6ddf40f036ff682cc2c8)
Updates `PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml` from 1.13.1 to 1.15.0
- [Release notes](https://github.com/posthog/posthog-sdk-test-harness/releases)
- [Changelog](https://github.com/PostHog/posthog-sdk-test-harness/blob/main/CHANGELOG.md)
- [Commits](https://github.com/posthog/posthog-sdk-test-harness/compare/e32f08bd30fab57ce543da5808a668d0fda697b0...64ffa6ab19166541880c077d349abe18a7e42395)
---
updated-dependencies:
- dependency-name: astral-sh/setup-uv
dependency-version: 10.3.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
- dependency-name: github/codeql-action/init
dependency-version: 4.38.3
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: github-actions
- dependency-name: github/codeql-action/analyze
dependency-version: 4.38.3
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: github-actions
- dependency-name: actions/create-github-app-token
dependency-version: 3.3.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
- dependency-name: dtolnay/rust-toolchain
dependency-version: 683b588c487a69d01f6c6ddf40f036ff682cc2c8
dependency-type: direct:production
dependency-group: github-actions
- dependency-name: PostHog/posthog-sdk-test-harness/.github/workflows/test-sdk-action.yml
dependency-version: 1.15.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: github-actions
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 3822271b1f45d31e24e717b61ad5c2db1224503d)
* chore(deps): bump the ai-providers group with 6 updates (#1082)
Bumps the ai-providers group with 6 updates:
| Package | From | To |
| --- | --- | --- |
| [langchain](https://github.com/langchain-ai/langchain) | `1.4.3` | `1.4.4` |
| [anthropic](https://github.com/anthropics/anthropic-sdk-python) | `1.11.0` | `1.13.0` |
| [langgraph](https://github.com/langchain-ai/langgraph) | `1.2.13` | `1.2.14` |
| [langchain-core](https://github.com/langchain-ai/langchain) | `1.6.6` | `1.6.9` |
| [langchain-openai](https://github.com/langchain-ai/langchain) | `1.6.7` | `1.7.0` |
| [google-genai](https://github.com/googleapis/python-genai) | `2.28.0` | `2.29.0` |
Updates `langchain` from 1.4.3 to 1.4.4
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain==1.4.3...langchain==1.4.4)
Updates `anthropic` from 1.11.0 to 1.13.0
- [Release notes](https://github.com/anthropics/anthropic-sdk-python/releases)
- [Changelog](https://github.com/anthropics/anthropic-sdk-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/anthropics/anthropic-sdk-python/compare/v1.11.0...v1.13.0)
Updates `langgraph` from 1.2.13 to 1.2.14
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/1.2.13...1.2.14)
Updates `langchain-core` from 1.6.6 to 1.6.9
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-core==1.6.6...langchain-core==1.6.9)
Updates `langchain-openai` from 1.6.7 to 1.7.0
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain-openai==1.6.7...langchain-openai==1.7.0)
Updates `google-genai` from 2.28.0 to 2.29.0
- [Release notes](https://github.com/googleapis/python-genai/releases)
- [Changelog](https://github.com/googleapis/python-genai/blob/main/CHANGELOG.md)
- [Commits](https://github.com/googleapis/python-genai/compare/v2.28.0...v2.29.0)
---
updated-dependencies:
- dependency-name: langchain
dependency-version: 1.4.4
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: anthropic
dependency-version: 1.13.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: ai-providers
- dependency-name: langgraph
dependency-version: 1.2.14
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-core
dependency-version: 1.6.9
dependency-type: direct:production
update-type: version-update:semver-patch
dependency-group: ai-providers
- dependency-name: langchain-openai
dependency-version: 1.7.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: ai-providers
- dependency-name: google-genai
dependency-version: 2.29.0
dependency-type: direct:production
update-type: version-update:semver-minor
dependency-group: ai-providers
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 9b70476eeeea0f653212bf3f7fe7abba8508b329)
* feat(llma): support scorer and experiment tags (#1085)
(cherry picked from commit b086f65437c4904310279646da76321a80294056)
* chore: Release v7.73.0 [skip ci]
(cherry picked from commit 81931fa3048df82243d0d63e636a9ceecd1d0148)
* Update generated references
(cherry picked from commit 9e62e0f9c5a7d6a23a419f93c8f016d43faec2db)
* fix(flags): accept rediss:// URLs for flag_fallback_cache_url (#1080)
Signed-off-by: Sebastian Turner <sebastiant3484@gmail.com>
(cherry picked from commit 20dabaa258b810bae3696bcb67b9679c18ef8f25)
* chore: Release v7.73.1 [skip ci]
(cherry picked from commit 223b592a9666b8c28f6bd90883126ced513d4195)
* Update generated references
(cherry picked from commit e9e0830aece3d22871fca082b6143cc2f0265e5c)
* chore(deps): bump aiohttp from 3.14.3 to 3.14.4 (#1086)
---
updated-dependencies:
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 305dee3ab53afe20482295690dcf3d978a574b67)
* chore(deps): bump the uv group across 7 directories with 1 update (#1087)
---
updated-dependencies:
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
- dependency-name: aiohttp
dependency-version: 3.14.4
dependency-type: indirect
dependency-group: uv
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
(cherry picked from commit 1b865499fc0e51a44c8a6d32f5a953241444bb45)
* fix(flags): compare numeric string properties numerically (#1088)
(cherry picked from commit 63b5dcca4ebaf3d42fee4cf6c9639e516dc2df4a)
* chore: Release v7.73.2 [skip ci]
(cherry picked from commit cb7580e2b884ca99b0693913fc822d2da1559701)
* Update generated references
(cherry picked from commit 1222ac7f269b1acc189a5f9284fb74bafdc2f572)
* fix(ai): keep the openai.Stream API on sync OpenAI streams (#1062)
Sync chat completions and Responses streams returned a bare generator, so
`with`, `close()` and attributes such as `.response` were lost. Wrap them
with _StreamWrapper, as #804 did for Anthropic and #645 did for async.
Co-authored-by: Dustin Byrne <dustin@posthog.com>
(cherry picked from commit f70b3cc3f0c5054f35ffc974b50005431aea511d)
* fix(ai): take cumulative Anthropic stream usage from message_delta (#1074)
Anthropic's message_delta usage is cumulative. With server tools (web
search, web fetch, code execution) its input and cache counts exceed
message_start's, but the stream accumulator only recorded message_start's
input and cache counts, so streamed generations under-reported input
tokens and cache writes. Keep the larger of the two for each count.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 57d160712e8d01750031c953bea093065d217128)
* chore: Release v7.73.3 [skip ci]
(cherry picked from commit 24c6722fb3a6317ea41917400c148ca44f64cc43)
* Update generated references
(cherry picked from commit bf873523c700d9940c8ec86b677d2bd4904dfa55)
* feat(llma): add datasets to offline evaluations (#1090)
* feat(llma): add datasets to offline evaluations
* chore(llma): share evaluation request and response helpers
* fix(llma): address dataset sdk review feedback
(cherry picked from commit b8879a7550e1bc2728bb5d23d8ddb215ba3602a7)
* chore: Release v7.74.0 [skip ci]
(cherry picked from commit ac7fa9955ce1dc6f2f11b0d36017eb65727624a1)
* Update generated references
(cherry picked from commit b14dd9e3f00c06af510e524379a4dea34572f4c9)
* feat(django): add request context to OpenTelemetry spans (#1070)
* feat(django): add request context to OpenTelemetry spans
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* fix(tracing): preserve span attributes and active context values
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* chore: use current tracing header settings in span checks
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* fix(tracing): respect disabled context owners
Generated-By: PostHog Desktop
Task-Id: bfd18848-e498-4352-a58a-b9ba85de4198
(cherry picked from commit 5f01fe93b893944f9b04c9e0f0536df46810143f)
* fix: enrich Flask, ASGI, and Celery spans with context (#1075)
* fix(flask): add request context to active OpenTelemetry spans
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* fix(asgi): enrich active request spans
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* fix(celery): enrich active task spans with job context
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* chore: use current tracing header settings in framework checks
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* fix(celery): preserve caller span identity during eager tasks
Generated-By: PostHog Desktop
Task-Id: 5681be44-4986-48db-b140-1bda88f75f96
* chore(tests): use enabled clients in span tests
Generated-By: PostHog Desktop
Task-Id: bfd18848-e498-4352-a58a-b9ba85de4198
(cherry picked from commit 5ddb4464a634a1dddf9b585cb9cf804c671a2edf)
* chore: Release v7.75.0 [skip ci]
(cherry picked from commit 908c77bc34e73aab009d04248131ccdbfe5ade5a)
* Update generated references
(cherry picked from commit a5b93eed7125a1ef7a9c9a442ec75487027f1f59)
* fix(flags): match explicit null properties with string operators (#1092)
(cherry picked from commit e9056e3051911b72aa1c8f9d39eb08fa4b0b65c4)
* chore: Release v7.75.1 [skip ci]
(cherry picked from commit 361ca83dbf06c3f1674b4b2c5be05ffcc555191e)
* Update generated references
(cherry picked from commit 5e296d88138157ee730916a293044e0c25fc7aef)
* fix(ai): capture OpenAI chat custom tool calls instead of raising (#1098)
A custom tool call has `custom` instead of `function`, so formatting the
response raised AttributeError from the wrapped create(), after the provider
call had succeeded. Read the name and input from `custom`, matching
PostHog/posthog-js#5251.
(cherry picked from commit 4697e6fcc837d1de3508a8b53273f609b6d63415)
* chore: Release v7.75.2 [skip ci]
(cherry picked from commit e63a898f2689be0b7a1f77c643ae5e62c5d25d15)
* Update generated references
(cherry picked from commit e9710ec2817e5104e9f9a713acdd8734e9caf485)
* fix(ai): record mid-stream errors on streamed OpenAI, Anthropic and Gemini events (#1094)
* fix(ai): record mid-stream errors on streamed OpenAI, Anthropic and Gemini events
capture_streaming_event hard-coded $ai_http_status=200, and the stream
generators only had a finally block. When the provider stream raised after
the first chunk (overloaded, connection reset), the event was sent as a
success with no $ai_is_error/$ai_error, unlike the non-streaming path.
Catch the exception in each sync and async generator, pass it through
StreamingEventData, and re-raise unchanged. The event now carries
$ai_is_error, $ai_error and the error's status code (0 when it has none).
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* fix(ai): pass the stream error to StreamingEventData directly and update the API snapshot
mypy 1.16 rejected splatting {"error": error} into StreamingEventData(...)
(typeddict-item). The field accepts None and capture_streaming_event reads it
with .get(), so pass error=error. Regenerate the public API snapshot for the new
StreamingEventData.error field.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit dc2a2b4e33659e7909786fa48c625d37dc4da94d)
* fix(ai): keep the refusal of a non-streamed OpenAI chat completion in the captured output (#1095)
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit 42c8b7bc1ba1b1acca1b931830ded4818b26df33)
* fix(ai): record an integer $ai_http_status in the LangChain callback handler (#1096)
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit a6ddc2ed3227a1f8efa170f3eb7fce5b9aef36db)
* chore: Release v7.75.3 [skip ci]
(cherry picked from commit dc0126690696694809d3c5ff3785f142c509e4fb)
* Update generated references
(cherry picked from commit 9185524005c394e78a977092dcf9fcb7885160dc)
* fix(ai): keep latest cumulative output tokens across message_deltas (#1100)
* fix(ai): keep latest cumulative output tokens across message_deltas
Server tools such as web search can emit several message_delta events in
one Anthropic stream, and each delta's usage is cumulative. The stream
accumulator added every delta's output_tokens together, so a stream with
two deltas reporting 50 then 110 cumulative tokens captured 160. Keep
the latest cumulative value, matching how the input and cache counts are
already handled and how the Anthropic SDK accumulates usage.
* style(ai): format cumulative token async regression test
---------
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit 34ec4f828a45728c91e452e960aa0119a3052812)
* chore: Release v7.75.4 [skip ci]
(cherry picked from commit 84664b48304ff81c68ae5ed0a92e938a27d22a46)
* Update generated references
(cherry picked from commit e17a8bed922739c67bfbadd55d0c8ec9aab9ac2e)
* fix: serialize non-finite floats as null in JSON payloads (#1081)
* fix: serialize non-finite floats as null in JSON payloads
Added a helper function to replace non-finite floats with None in JSON serialization.
* test: cover non-finite float serialization in batch payloads
* chore: refresh public API snapshot for DatetimeSerializer.encode
(cherry picked from commit 18b39e895a45eed0e078c97848c03d0f066b3287)
* fix: annotate client timeouts as float (#1106)
`timeout` and `feature_flags_request_timeout_seconds` were typed (or
inferred) as `int`, so type checkers rejected fractional values even
though they go straight to requests/httpx, which accept floats.
Fixes #1089
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
(cherry picked from commit b3fcec639aa9c49514344ba97b24492f03e87b86)
* chore: Release v7.75.5 [skip ci]
(cherry picked from commit a7742232151193989e722907d9c025045bda2631)
* Update generated references
(cherry picked from commit 8c2d8f625f7c40cfc3b87f47dc65bc15c4721d7b)
* fix(flags): retain tracking metadata in local evaluation snapshots (#1041)
(cherry picked from commit a95331f171a33ca0674833a5aada371cc6446bc9)
* chore: Release v7.75.6 [skip ci]
(cherry picked from commit a5909dc4d507e36a7cb08b21a685ca8b06d7f7de)
* Update generated references
(cherry picked from commit 4b280fcace78f10af24ef47bac1fa7ff7d9b56c9)
* chore(deps): bump uv to 0.13.4 and certifi to 2026.10.19 (#1104)
Bump uv to 0.13.4 and certifi to 2026.10.19
Eight eMudhra intermediate CA private keys were broken, so anyone
holding them can impersonate TLS servers to clients that still trust
emSign ECC Root CA - G3. uv 0.13.4 and certifi 2026.10.19 are the first
releases whose bundled CA store drops that root, and the versions pinned
here still trust it. See the Python.org notice.
https://discuss.python.org/t/information-for-python-users-regarding-emudhra-emsign-ca-certificate-security-incident/109576
Claude-Session: https://claude.ai/code/session_01T4ck1tYoQv3mzBTXH17asD
Co-authored-by: Claude <noreply@anthropic.com>
(cherry picked from commit 7651b10da2d3594de0dbd808883c5a7f2e5398e8)
* test: send NaN and Infinity as null on the v1 path, as #1081 does on main
#1081 keeps an event whose properties hold a non-finite float and writes
the value as null. The v1 before_send test expected that event to be
dropped; a capture v1 body test now pins the null on the wire, and the
migration guide says so.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Sebastian Turner <sebastiant3484@gmail.com>
Co-authored-by: Daniel Visca <daniel.v@posthog.com>
Co-authored-by: releaser-posthog-python[bot] <262414804+releaser-posthog-python[bot]@users.noreply.github.com>
Co-authored-by: Carlos Marchal <carlos@posthog.com>
Co-authored-by: Juraj Majerik <juro.majerik@gmail.com>
Co-authored-by: Manoel Aranda Neto <5731772+marandaneto@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Dustin Byrne <dustin@posthog.com>
Co-authored-by: Georgis Andonis <6430745+gesh@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Radu Raicea <radu@raicea.com>
Co-authored-by: Sebastian Turner <sebastiant3484@gmail.com>
Co-authored-by: mosafariuk <mosafariuk@gmail.com>
Co-authored-by: alexcastgonz <82875882+pcbeingused333@users.noreply.github.com>
Co-authored-by: Paul D'Ambra <paul.dambra@gmail.com>
Co-authored-by: Harsh Kashyap <55448981+Harsh23Kashyap@users.noreply.github.com>
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
Co-authored-by: Anna Garcia <11654201+turnipdabeets@users.noreply.github.com>
Co-authored-by: Georges-Antoine Assi <3247106+gantoine@users.noreply.github.com>
* fix: fill feature flag properties below context tags and super properties (#1121)
Flag properties from flags or send_feature_flags are values the SDK
adds, so they now fill after the call's properties, context tags and
super_properties, like $is_server and system properties. 7.x already
let context tags and super_properties win over them.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: own capture connection retries and redact hook error logs (#1125)
* fix: own capture connection retries and redact hook error logs
Capture uses a session whose adapter never retries, so each connection
try is an SDK attempt with its own attempt number and request timestamp.
The hidden adapter retries reused a stale timestamp, which capture reads
as clock skew.
A raising before_send logs the event name and exception type, never the
exception message; the traceback goes to debug. A non-dict return logs
its type and drops the event. The migration guide lists all four legacy
option properties.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: cover the before_send log helpers in test_utils
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* perf: copy an event only when it holds a non-finite number
Encode strictly first and replace NaN and Infinity with null only after
that encode fails, so normal events skip the full copy.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: reverse proxy checklist for capture v1 in the migration guide
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: fill OpenTelemetry trace IDs below context tags and super properties (#1122)
fix: fill opentelemetry trace ids below context tags and super properties
The $trace_id and $span_id taken from the active OpenTelemetry span are
values the SDK adds, so they now fill after the call's properties,
context tags and super_properties, and before before_send. They fill as
a pair: when any layer sets either key, the SDK adds neither. This
covers capture, capture_ai and capture_exception on Client and
AsyncPosthog.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: add OpenTelemetry span IDs to async capture_exception (#1123)
fix: add opentelemetry span ids to async capture_exception
AsyncPosthog.capture_exception now adds the active span's $trace_id and
$span_id even with capture_trace_context off, like Client.capture_exception.
They follow the same SDK-value fill order and pair rule.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* fix: retry capture requests that get 404 or 429 (#1132)
* fix: retry capture requests that get 404 or 429
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: explain a lasting 404 in the 8.0 migration guide
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* test: an event JSON cannot serialize is dropped alone (#1138)
* test: an event JSON cannot serialize is dropped alone
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: cover an event that fails json after it is queued
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* chore: run the capture v1 compliance suites from harness 1.25.0 (#1137)
* chore: run the capture v1 compliance suites from harness 1.23.0
Declare the adapter capabilities harness 1.23.0 uses to gate tests:
event_uuid_override, bounded_retries, disable_geoip and historical_migration.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: support the harness reported_drops, log_capture, generated_payloads, property_layers and fail_open features
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: clear adapter diagnostics after the old client shuts down, size padding markers in bytes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* chore: run the capture v1 compliance suites from harness 1.25.0
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(adapter): name each duplicate uuid drop after its own copy
Also point adapter docs at harness 1.25.0.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(adapter): type the duplicate drop names for mypy
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* chore: run the capture v1 compliance suites from harness 1.26.0 (#1142)
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
* chore: sync main into v1 (7.75.7–7.81.1) (#1169)
* fix(ai): keep streamed OpenAI tool calls that have no index (#1091)
* fix(ai): keep streamed OpenAI tool calls that have no index
accumulate_openai_tool_calls skipped every delta without an index, so
tool calls from OpenAI-compatible providers that omit it never reached
$ai_output. A delta with a new id now opens a call, and one without an
id continues the latest call.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* fix(ai): keep synthetic tool call keys apart from provider indexes
A call without an index took key max + 1, which a later call with that real index overwrote, merging two calls and dropping one. Index-less calls now get string keys of their own.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
* fix(ai): widen the streamed tool call accumulator key type
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(ai): update streamed tool call API snapshot
---------
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: Manoel Aranda Neto <marandaneto@gmail.com>
(cherry picked from commit ffde3c57f26b9daf92f12fbb21edd4f359e4388b)
* chore: Release v7.75.7 [skip ci]
(cherry picked from commit 7f4c9be1c8aa66bf55cb2080cf0775ff4ec28cff)
* Update generated references
(cherry picked from commit b5eb2debabc7bc6e4e5d033b923d1eef6a6508a6)
* docs: require signed commits in contributor docs (#1111)
Contributors often open PRs with unsigned commits because signing isn't documented here.
(cherry picked from commit e65ed67b3a61122c6480c2198c019a493061845c)
* fix(flags): fall back for incompatible local regex evaluation (#1108)
* fix(flags): fall back for incompatible local regex evaluation
* fix(flags): defer nested regex quantifiers and fast-path ASCII values
* fix(flags): defer strict-end searches with final newline backtracking
* perf(flags): cache pure regex pattern metadata
(cherry picked from commit d58380e87f38b725ded6d38b870b734056a526e7)
* chore: Release v7.75.8 [skip ci]
(cherry picked from commit 72e013122e07345a827d108de74f079672220f1d)
* Update generated references
(cherry picked from commit a020e703fd89e4e35211419ad6f1ba3b656d798f)
* fix(examples): use gpt-image-2.5-flare in the OpenAI image generation example (#1109)
OpenAI shuts down gpt-image-1 on 2026-10-23 and lists gpt-image-2.5-sunburst or
gpt-image-2.5-flare as the replacement
(https://developers.openai.com/api/docs/deprecations).
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
(cherry picked from commit efc866ec4b18115518597bfa9f6b82a6f17cc270)
* fix(mcp): send one $mcp_initialize per initialize request (#1103)
* fix(mcp): send one $mcp_initialize per initialize request
The Python MCP SDK answers initialize itself, so posthog.mcp sent the
event on the first request of each session, once per process. A
stateless fleet sent one event per pod. A client that sent only
initialize sent no event.
Now MCP SDK 2.x reports the event from Server.middleware, on every
transport. MCP SDK 1.x over HTTP reports it from
PostHogMcpStatelessSessionMiddleware, which takes a new optional
server= argument. MCP SDK 1.x over stdio keeps the first-request
fallback.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* refactor(mcp): read only the initialize response head on mcp 1.x
The mcp 1.x hook now keeps only the status and the Mcp-Session-Id header
of the initialize response. It no longer parses the JSON or SSE body.
The event uses the protocol version that the client asked for.
record_initialize now reads the client name, version, and protocol from
the initialize params and reply, so both hooks pass them through. The
new tests share their request helpers and drop the SSE body case.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): address review on the initialize hooks
- SSE transport: the initialize event now lands in the session that the
SSE calls use. On SDK 1.x the middleware leaves SSE requests to the
first-request fallback. On SDK 2.x the hook uses the process session.
- The bound middleware marks each request that it passes on. The fallback
now stops only for marked requests, not for every HTTP request.
- The hooks compute the handshake session without a write to the shared
session that McpAnalytics.capture() reads.
- A server= value that cannot be bound no longer breaks requests.
- Remove the unused _mint_token_if_initialize.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix(mcp): wait for the initialize capture inside its handshake task
Both handshake hooks run record_initialize in a tracked background task.
It started the capture as a second task, a…
💡 Motivation and Context
initializeitself, soposthog.mcpcannot wrap it. Until now, it sent$mcp_initializeon the first request of each session, once per process.initialize.$mcp_initializeonly for aninitializethat the client sent.Changes
The SDK now sends one
$mcp_initializefor eachinitializerequest, in the session that the client's later requests use.Server.middleware. The SDK hands it the parsedinitialize.PostHogMcpStatelessSessionMiddleware. It parses each request with noMcp-Session-Idas JSON, as it already did to mint the token. It records the event when the response starts.instrument()binds the middleware on the apps that it autowires. If you mount the middleware by hand, pass the new optionalserver=argument. Without it, each pod still sends the event on its first request.identifyandevent_propertiesrun inline in the handshake request, the same as on a tool call. The capture runs in the background, andanalytics.flush()waits for it.$mcp_parameterswith the handshake request. On MCP SDK 2.x, it also has$mcp_responsewith the server reply.conversation_idanchors no longer gets its own$mcp_initialize.Check in review
ServerSession._connection. A guard handles it, and the stateful tests fail if the SDK renames it.Mcp-Session-Id. So the event has the protocol version that the client asked for, and aninitializethat fails with a JSON-RPC error still counts.extra["ctx"]for the handshake callbacks has only.request.get_request_headers(extra)works as before.$mcp_initializecount goes down for stateless Python fleets. The default MCP dashboard counts users and sessions from this event.Known limits
server=keeps the per-pod event.initializethat reuses an existingMcp-Session-Idgets no event. The middleware does not read requests that carry one, so tool calls stay unread.initializeand nothing else gets no event.conversation_idgets no event.💚 How did you test it?
test_initialize_handshake.pydrives real apps with raw JSON-RPC and counts the events. Two pods with round-robin requests stand in for a fleet.Serveron both majors. It also runs real stdio and SSE servers, and aPostHogMCPdispatcher.identify, a hungidentify,flush(), an escaped or nested method, and the 2026-07-28 spec.main, 23 of the new tests fail on SDK 1.x and 28 fail on SDK 2.x.mcp1.30.0 withfastmcp3.x, and SDK 2.x runsmcp2.3.0 withfastmcp4.1.0.0773e32with real uvicorn servers and a client that reconnects 3 times. The table shows the$mcp_initializecount. Themaincolumn is posthog 7.75.4 on SDK 1.x.tools/listtools/listtools/list, and 2 tool callsOn this PR, the counts are the same for stateful and stateless servers, on both SDK majors.
📝 Checklist
If releasing new changes
sampo addto generate a changeset file🤖 Agent context
Autonomy: Human-driven (agent-assisted)
claude-opus-5-5).initialize. SDK 1.x has no such hook, so the ASGI middleware observes the handshake over HTTP, and stdio keeps the first-request fallback.🤖 Generated with Claude Code