Skip to content

feat(mcp): align posthog.mcp with the sdk-specs MCP spec - #1199

Merged
lucasheriques merged 7 commits into
mainfrom
lucas/mcp-v1-spec-align
Nov 6, 2026
Merged

lucasheriques merged 7 commits into
mainfrom
lucas/mcp-v1-spec-align

Conversation

@lucasheriques

@lucasheriques lucasheriques commented Nov 6, 2026 •

Copy link
Copy Markdown
Contributor

Problem

posthog.mcp is about to be declared stable, which promises that customers' insights keep working (sdk-specs#189). Before that promise, it has to count tool calls the way the spec and the other SDKs do:

  • Unregistered tools. A call to a tool the server never registered is recorded as a failed $mcp_tool_call plus an $exception. The spec says it is never a tool call.
  • Annotations and context wording. Plugin directory reviews read the virtual tools' annotations and the injected context description, and the spec now fixes both.

Changes

  • Unregistered tools send $mcp_unknown_tool with the requested name (redacted like intent), session and identity, and no $exception. The client gets the same error as before.
    • FastMCP, the low-level Server (mcp 1.x and 2.x) and PostHogMCP.capture_unknown_tool() are covered.
    • A call still counts as failed when the SDK can't prove the tool is missing: a raw low-level server with no tools/list handler, a name missing from a listing page that has more pages, or standalone FastMCP whose middleware overrides listing or dispatch. The spec allows all three.
    • One helper, ToolCallLifecycle.record_if_unknown_tool, makes the decision. Each adapter calls it once per raise path and once per error-result path.
  • get_more_tools and send_feedback annotations are all false with no title (VIRTUAL_TOOL_HINTS), matching the spec scenario and the other SDKs.
  • llm_model is never in required (sdk-specs#189).
  • context description is the shared text every SDK now sends.

Release note: .sampo/changesets/mcp-v1-spec-align.md (minor). It warns that published tool definitions change and directory listings may re-review.

For reviewers:

  • Failed-call analytics change for servers that receive calls to unknown tools: those calls leave $mcp_tool_call counts and error rates.
  • A failed call may run the host's tools/list handler once to check the name, but only when the registry can't answer.
  • Doesn't touch client conversation ids (posthog-python#1193).

TypeScript: posthog-js#5583. Go: posthog-go#418. Ruby: posthog-ruby#332. Rust: posthog-rs#333.

Behavior changes to note

  • Manual capture sessions and anonymous identity. A PostHogMCP manual capture called without a session_id used to send no $session_id and the shared distinct id "anonymous". Each such capture now gets a fresh ses_<uuidv7> $session_id, and anonymous captures use it as their distinct id, with $process_person_profile: false as before. The spec requires a non-empty $session_id on every event and uses it as an anonymous event's distinct id. Hosts that pass session_id or distinct_id see no change. posthog-js#5583 (merged) made the same change.
  • Unregistered tools. On servers whose registry the SDK can read and that dispatches the call, a call to a name the server never registered sends $mcp_unknown_tool instead of a failed $mcp_tool_call plus $exception. That changes failed-call counts and error rates for those calls. Raw low-level servers with their own dispatcher, and servers with mounts, proxies or custom providers, keep recording failed calls.
  • Truncation. Strings cut to a property limit now stop exactly at the limit, ... included, as the spec says. They used to come out 3 characters past it.
  • No public API change. The manual capture_unknown_tool() was dropped from this PR. It can come back in its own PR.

How I tested

  • pytest posthog/test/mcp: 678 passed, 10 skipped. New test_unknown_tool.py covers each server shape. The annotations test compares exact JSON, and it fails when a title is put back.
  • ruff format --check ., ruff check ., mypy through mypy-baseline filter, and make public_api_check are clean.
  • Full suite: 6142 passed. The 3 failures are the macOS-only fork tests in test_metrics_autocapture.py, unrelated to MCP.

Pre-PR gate: an Opus adversary ran every server shape on fastmcp 2.14, 3.2 and 4.1 and mcp 1.30 and 2.3. Its findings are fixed, each with a test that failed first:

  • Mounted servers. A disabled tool on a mounted FastMCP sub-server was recorded as unknown. A server with mounts or other providers now answers "can't tell".
  • Stock middleware. FastMCP's own logging, timing, error-handling and other stock middleware turned off unknown-tool detection. They're now trusted by exact type, and app middleware still isn't.
  • Nameless and long names. A call naming no tool now emits nothing. Truncated strings now stop exactly at their limit, marker included, as "Property reference" says. They used to come out 3 characters over.
  • Deprecation warning. A nextCursor deprecation warning no longer fires on mcp 2 with fastmcp 4.
  • Conversation handle. An unknown-tool isError result keeps the conversation handle origin/main appended, matching posthog-js.
  • Release note. It now names the one-time tools/list check, hidden or per-user tools counting as unknown, nameless calls and the 256-character cut.

Tests: 694 passed, 11 skipped on mcp 1.30 with fastmcp 3.2. test_unknown_tool.py also passes on fastmcp 2.14, mcp 2.3 and mcp 2.3 with fastmcp 4.1.

@lucasheriques
lucasheriques added this pull request to stack #1201 November 6, 2026 17:13
@github-actions

github-actions Bot commented Nov 6, 2026 •

Copy link
Copy Markdown
Contributor

posthog-python Compliance Report

Date: 2026-11-06T21:36:26.127359+00:00
Duration: 259854ms

✅ All Tests Passed!

121/121 tests passed


Capture_V1 Tests

✅ 95/95 tests passed

View Details
Test Status Duration
Endpoint And Method.Targets V1 Endpoint ✅ 516ms
Endpoint And Method.Does Not Use Legacy Endpoints ✅ 511ms
Required Headers.Has Authorization Bearer Header ✅ 510ms
Required Headers.Has Content Type Json ✅ 511ms
Required Headers.Has Posthog Sdk Info Format ✅ 510ms
Required Headers.Has Posthog Attempt Header ✅ 512ms
Required Headers.Has Posthog Request Id ✅ 511ms
Required Headers.Has Posthog Request Timestamp ✅ 510ms
Required Headers.Has User Agent ✅ 511ms
Body Format.Body Has Created At And Batch ✅ 511ms
Body Format.No Api Key In Body ✅ 510ms
Body Format.No Sent At In Body ✅ 511ms
Event Format.Event Has Required Root Fields ✅ 511ms
Event Format.Event Uuid Is Valid ✅ 510ms
Event Format.Event Timestamp Is Rfc3339 ✅ 511ms
Event Format.Non Utc Event Timestamp Is Converted To Utc ✅ 522ms
Event Format.Distinct Id Is String ✅ 511ms
Event Format.Distinct Id At Root Not Properties ✅ 510ms
Event Format.Custom Properties Preserved ✅ 511ms
Event Format.Set Properties Preserved ✅ 510ms
Event Format.Set Once Properties Preserved ✅ 511ms
Event Format.Groups Properties Preserved ✅ 510ms
Event Format.Sdk Generates Uuid If Not Provided ✅ 510ms
Event Format.Event Has Required Root Fields Batch ✅ 514ms
Event Format.Event Uuid Is Valid Batch ✅ 514ms
Event Format.Event Timestamp Is Rfc3339 Batch ✅ 513ms
Event Format.Distinct Id Is String Batch ✅ 513ms
Event Format.Distinct Id At Root Not Properties Batch ✅ 514ms
Event Format.Custom Properties Preserved Batch ✅ 514ms
Event Format.Set Properties Preserved Batch ✅ 514ms
Event Format.Set Once Properties Preserved Batch ✅ 513ms
Event Format.Groups Properties Preserved Batch ✅ 515ms
Event Format.Sdk Generates Uuid If Not Provided Batch ✅ 513ms
Batch Behavior.Multiple Events In Single Batch ✅ 517ms
Batch Behavior.Batch Envelope Smoke ✅ 516ms
Batch Behavior.Flush With No Events Sends Nothing ✅ 507ms
Batch Behavior.Flush At Triggers Batch ✅ 1013ms
Batch Behavior.Created At Reflects Batch Creation Time ✅ 511ms
Deduplication.Generates Unique Uuids ✅ 519ms
Deduplication.Different Events Same Content Different Uuids ✅ 512ms
Deduplication.Preserves Uuid On Retry ✅ 6519ms
Deduplication.Preserves Timestamp On Retry ✅ 6519ms
Deduplication.Preserves Uuid And Timestamp On Batch Retry ✅ 6520ms
Deduplication.No Duplicate Events In Batch ✅ 517ms
Header Behavior On Retry.Attempt Header Starts At One ✅ 511ms
Header Behavior On Retry.Attempt Header Increments On Retry ✅ 13521ms
Header Behavior On Retry.Request Id Preserved On Retry ✅ 6522ms
Header Behavior On Retry.Different Requests Have Different Request Ids ✅ 3020ms
Header Behavior On Retry.Request Timestamp Changes On Retry ✅ 6520ms
Response Format Validation.Success Response Has Uuid Keyed Results ✅ 512ms
Response Format Validation.Success Response Has Ok For Each Event ✅ 515ms
Response Format Validation.Success No Retry After When All Ok ✅ 513ms
Response Format Validation.Success Retry After Present When Retry Events ✅ 1517ms
Response Format Validation.Success No Retry After When Drop Only ✅ 513ms
Response Format Validation.Response Echoes Request Id ✅ 510ms
Retry Behavior.Retries On 408 ✅ 6520ms
Retry Behavior.Retries On 500 ✅ 6517ms
Retry Behavior.Retries On 503 ✅ 8520ms
Retry Behavior.Retries On 504 ✅ 6521ms
Retry Behavior.Retryable Errors Have Retry After ✅ 3518ms
Retry Behavior.Respects Retry After On Retryable Error ✅ 11522ms
Retry Behavior.Does Not Retry On 400 ✅ 2515ms
Retry Behavior.Does Not Retry On 401 ✅ 2514ms
Retry Behavior.Does Not Retry On 402 ✅ 2515ms
Retry Behavior.Does Not Retry On 413 ✅ 2514ms
Retry Behavior.Does Not Retry On 415 ✅ 2516ms
Retry Behavior.Non Retryable Errors Have No Retry After ✅ 2515ms
Retry Behavior.Implements Backoff ✅ 22537ms
Retry Behavior.Max Retries Respected ✅ 22537ms
Partial Batch Handling.Handles 200 Full Success ✅ 2513ms
Partial Batch Handling.Handles 200 With All Ok ✅ 3520ms
Partial Batch Handling.Does Not Retry Dropped Events ✅ 3518ms
Partial Batch Handling.Does Not Retry Limited Events ✅ 3519ms
Partial Batch Handling.Prunes Ok Events On Partial Retry ✅ 6524ms
Partial Batch Handling.Prunes Dropped Events On Partial Retry ✅ 6520ms
Partial Batch Handling.Retries Only Retry Events From Partial ✅ 6524ms
Partial Batch Handling.Partial Retry Preserves Uuids ✅ 6524ms
Partial Batch Handling.Partial Retry Attempt Header Increments ✅ 6520ms
Partial Batch Handling.Partial Retry Request Id Preserved ✅ 6522ms
Partial Batch Handling.Respects Retry After On Partial ✅ 8523ms
Partial Batch Handling.Unknown Result Treated As Terminal ✅ 3513ms
Partial Batch Handling.Mixed Ok Drop Limited No Retry ✅ 3521ms
Compression.Sends Gzip Content Encoding ✅ 513ms
Compression.No Content Encoding When Disabled ✅ 511ms
Compression.Compressed Body Is Decompressible ✅ 511ms
Error Handling.Does Not Retry On Unknown 4Xx ✅ 2514ms
Event Options.Cookieless Mode Override ✅ 512ms
Event Options.Disable Skew Correction Override ✅ 511ms
Event Options.Process Person Profile Override ✅ 511ms
Event Options.Product Tour Id Override ✅ 510ms
Event Options.Unset Options Omitted ✅ 510ms
Event Options.Options Override In Batch ✅ 514ms
Geoip And Historical Migration.Geoip Disable Injected Into Properties ✅ 511ms
Geoip And Historical Migration.Historical Migration Set In Body ✅ 511ms
Geoip And Historical Migration.Historical Migration Absent By Default ✅ 511ms

Capture_Ai Tests

✅ 5/5 tests passed

View Details
Test Status Duration
Routing.Capture Ai Posts To Ai Endpoint ✅ 511ms
Routing.Capture Does Not Reroute Ai Named Events ✅ 511ms
Identity.Capture Ai Event Has Uuid ✅ 511ms
Identity.Capture Ai Keeps Supplied Uuid ✅ 511ms
Timestamp Format.Non Utc Event Timestamp Is Converted To Utc ✅ 513ms

Feature_Flags Tests

✅ 17/17 tests passed

View Details
Test Status Duration
Request Payload.Request With Person Properties Device Id ✅ 13ms
Request Payload.Flags Request Uses V4 Query Param ✅ 10ms
Request Payload.Flags Request Hits Flags Path Not Decide ✅ 9ms
Request Payload.Flags Request Omits Authorization Header ✅ 8ms
Request Payload.Token In Flags Body Matches Init ✅ 9ms
Request Payload.Groups Round Trip ✅ 9ms
Request Payload.Groups Default To Empty Object ✅ 8ms
Request Payload.Disable Geoip False Propagates As Geoip Disable False ✅ 9ms
Request Payload.Disable Geoip Omitted Defaults To False ✅ 8ms
Request Payload.Flag Keys To Evaluate Contains Only Requested Key ✅ 9ms
Request Lifecycle.No Flags Request On Init Alone ✅ 2ms
Request Lifecycle.No Flags Request On Normal Capture ✅ 509ms
Request Lifecycle.Two Flag Calls Produce Two Remote Requests ✅ 17ms
Request Lifecycle.Mock Response Value Is Returned To Caller ✅ 9ms
Retry Behavior.Retries Flags On 502 ✅ 315ms
Retry Behavior.Retries Flags On 504 ✅ 316ms
Side Effect Events.Get Feature Flag Captures Feature Flag Called Event ✅ 512ms

Feature_Flags_Local_Evaluation Tests

✅ 4/4 tests passed

View Details
Test Status Duration
Versioned Boolean Matching.Matching Version Missing ✅ 66ms
Versioned Boolean Matching.Matching Version 1 ✅ 60ms
Versioned Boolean Matching.Matching Version 2 ✅ 61ms
Versioned Boolean Matching.Version Only Reload 1 2 1 2 Missing ✅ 32ms

@github-actions

github-actions Bot commented Nov 6, 2026 •

Copy link
Copy Markdown
Contributor

SDK performance: posthog-python

Benchmarks completed. No changes flagged for review.

Flags require at least a 5% change in the median and all six pairs agreeing on direction. This is a noise filter, not proof of a performance change or a CI gate.

View all results
Test Measurement Before PR With PR Change Assessment
Capture and deliver events (32-byte payload, burst)
Shard: capture
Managed heap after settling — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​; head:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Managed heap after settling — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​; head:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​
Capture and deliver events (32-byte payload, steady)
Shard: capture
Managed heap after settling — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​; head:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Managed heap after settling — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​; head:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​
Queue an event (32-byte payload)
Shard: capture
Allocated memory per operation — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​; head:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​
Queue an event (32-byte payload)
Shard: capture
Allocations per operation — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​; head:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​
Queue an event (4,096-byte payload)
Shard: capture
Allocated memory per operation — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​; head:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​
Queue an event (4,096-byte payload)
Shard: capture
Allocations per operation — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​; head:​ Background preparation has no public completion boundary before flush; see capture.​drain for full-pipeline allocations.​
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Managed heap after settling — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​; head:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​
Refresh 1,000 flag definitions
Shard: flags-memory
Managed heap after settling — — — unavailable; base:​ unsupported; head:​ unsupported; base:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​; head:​ CPython has no uninstrumented total managed-heap byte counter; tracing would distort this RSS pass.​
Capture and deliver events (32-byte payload, burst)
Shard: capture
Allocated memory per operation 113.54 KiB/op 113.54 KiB/op <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Allocations per operation 1,096.6 count/op 1,096.59 count/op <0.1% fewer Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Time per operation 53.27 µs/op 55.44 µs/op 4.1% more time Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Idle process memory (RSS) 35.99 MiB 36.04 MiB 0.1% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Observed peak process memory (RSS) 37.75 MiB 37.79 MiB <0.1% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Process memory after settling (RSS) 37.75 MiB 37.79 MiB <0.1% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Process CPU time per operation 54.28 µs/op 56.53 µs/op 4.1% more time Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Lifetime peak process memory (RSS) 40.45 MiB 40.45 MiB No observed change Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Allocated memory per operation 166.1 KiB/op 166.1 KiB/op <0.1% less memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Allocations per operation 1,089.59 count/op 1,089.59 count/op <0.1% fewer Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Time per operation 75.05 µs/op 76.49 µs/op 1.9% more time Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Idle process memory (RSS) 40.88 MiB 40.75 MiB 0.3% less memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Observed peak process memory (RSS) 45.98 MiB 45.85 MiB 0.3% less memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Process memory after settling (RSS) 45.98 MiB 45.85 MiB 0.3% less memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Process CPU time per operation 69.92 µs/op 72.4 µs/op 3.5% more time Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Lifetime peak process memory (RSS) 50.74 MiB 50.7 MiB <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Allocated memory per operation 117.68 KiB/op 117.68 KiB/op <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Allocations per operation 1,136.6 count/op 1,136.59 count/op <0.1% fewer Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Time per operation 64.4 µs/op 63.21 µs/op 1.8% less time Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Idle process memory (RSS) 35.96 MiB 35.96 MiB <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Observed peak process memory (RSS) 36.06 MiB 36.07 MiB <0.1% more memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Process memory after settling (RSS) 36.06 MiB 36.07 MiB <0.1% more memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Process CPU time per operation 63.67 µs/op 63.21 µs/op 0.7% less time Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Lifetime peak process memory (RSS) 40.45 MiB 40.45 MiB No observed change Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Allocated memory per operation 170.57 KiB/op 170.57 KiB/op <0.1% more memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Allocations per operation 1,129.46 count/op 1,129.49 count/op <0.1% more Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Time per operation 81.68 µs/op 77.51 µs/op 5.1% less time Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Idle process memory (RSS) 40.71 MiB 40.7 MiB <0.1% less memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Observed peak process memory (RSS) 40.71 MiB 40.71 MiB <0.1% more memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Process memory after settling (RSS) 40.71 MiB 40.71 MiB <0.1% more memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Process CPU time per operation 78.75 µs/op 74.26 µs/op 5.7% less time Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Lifetime peak process memory (RSS) 40.97 MiB 40.97 MiB <0.1% more memory Not flagged
Queue an event (32-byte payload)
Shard: capture
Caller-thread CPU time per operation 36.52 µs/op 35.77 µs/op 2.1% less time Not flagged
Queue an event (32-byte payload)
Shard: capture
Time per operation 36.52 µs/op 38.22 µs/op 4.6% more time Not flagged
Queue an event (4,096-byte payload)
Shard: capture
Caller-thread CPU time per operation 34.58 µs/op 34.98 µs/op 1.2% more time Not flagged
Queue an event (4,096-byte payload)
Shard: capture
Time per operation 34.57 µs/op 36.38 µs/op 5.2% more time Not flagged
Evaluate all 10 flags
Shard: flags-scaling
Allocated memory per operation 200.98 KiB/op 200.98 KiB/op No observed change Not flagged
Evaluate all 10 flags
Shard: flags-scaling
Allocations per operation 2,339.33 count/op 2,339.33 count/op No observed change Not flagged
Evaluate all 10 flags
Shard: flags-scaling
Time per operation 63.99 µs/op 65.19 µs/op 1.9% more time Not flagged
Evaluate all 10 flags
Shard: flags-scaling
Process CPU time per operation 63.99 µs/op 65.18 µs/op 1.9% more time Not flagged
Evaluate all 100 flags
Shard: flags-scaling
Allocated memory per operation 1.93 MiB/op 1.93 MiB/op No observed change Not flagged
Evaluate all 100 flags
Shard: flags-scaling
Allocations per operation 23,013.56 count/op 23,013.56 count/op No observed change Not flagged
Evaluate all 100 flags
Shard: flags-scaling
Time per operation 611.48 µs/op 620.14 µs/op 1.4% more time Not flagged
Evaluate all 100 flags
Shard: flags-scaling
Process CPU time per operation 611.51 µs/op 620.16 µs/op 1.4% more time Not flagged
Evaluate all 1,000 flags
Shard: flags-scaling
Allocated memory per operation 19.24 MiB/op 19.24 MiB/op No observed change Not flagged
Evaluate all 1,000 flags
Shard: flags-scaling
Allocations per operation 229,654.94 count/op 229,654.94 count/op No observed change Not flagged
Evaluate all 1,000 flags
Shard: flags-scaling
Time per operation 6.09 ms/op 6.1 ms/op 0.2% more time Not flagged
Evaluate all 1,000 flags
Shard: flags-scaling
Process CPU time per operation 6.09 ms/op 6.1 ms/op 0.2% more time Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Idle process memory (RSS) 42.35 MiB 41.68 MiB 1.6% less memory Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Observed peak process memory (RSS) 42.66 MiB 41.97 MiB 1.6% less memory Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Process memory after settling (RSS) 42.66 MiB 41.97 MiB 1.6% less memory Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Lifetime peak process memory (RSS) 42.55 MiB 42.58 MiB <0.1% more memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Idle process memory (RSS) 42.05 MiB 42.12 MiB 0.2% more memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Observed peak process memory (RSS) 42.11 MiB 42.18 MiB 0.2% more memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Process memory after settling (RSS) 41.45 MiB 41.52 MiB 0.2% more memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Lifetime peak process memory (RSS) 42.48 MiB 42.47 MiB <0.1% less memory Not flagged
Evaluate one boolean flag
Shard: flags-single
Allocated memory per operation 15.05 KiB/op 15.05 KiB/op No observed change Not flagged
Evaluate one boolean flag
Shard: flags-single
Allocations per operation 173.76 count/op 173.76 count/op No observed change Not flagged
Evaluate one boolean flag
Shard: flags-single
Time per operation 10.91 µs/op 10.85 µs/op 0.6% less time Not flagged
Evaluate one boolean flag
Shard: flags-single
Process CPU time per operation 10.92 µs/op 10.85 µs/op 0.6% less time Not flagged
Evaluate a cohort-filtered flag
Shard: flags-single
Allocated memory per operation 23.12 KiB/op 23.12 KiB/op No observed change Not flagged
Evaluate a cohort-filtered flag
Shard: flags-single
Allocations per operation 270.27 count/op 270.27 count/op No observed change Not flagged
Evaluate a cohort-filtered flag
Shard: flags-single
Time per operation 15.26 µs/op 15.02 µs/op 1.6% less time Not flagged
Evaluate a cohort-filtered flag
Shard: flags-single
Process CPU time per operation 15.26 µs/op 15.02 µs/op 1.6% less time Not flagged
Evaluate a flag (early match)
Shard: flags-single
Allocated memory per operation 35.71 KiB/op 35.71 KiB/op No observed change Not flagged
Evaluate a flag (early match)
Shard: flags-single
Allocations per operation 387.27 count/op 387.27 count/op No observed change Not flagged
Evaluate a flag (early match)
Shard: flags-single
Time per operation 21.43 µs/op 21.51 µs/op 0.3% more time Not flagged
Evaluate a flag (early match)
Shard: flags-single
Process CPU time per operation 21.43 µs/op 21.51 µs/op 0.3% more time Not flagged
Evaluate a flag (late match)
Shard: flags-single
Allocated memory per operation 53.59 KiB/op 53.59 KiB/op No observed change Not flagged
Evaluate a flag (late match)
Shard: flags-single
Allocations per operation 576.27 count/op 576.27 count/op No observed change Not flagged
Evaluate a flag (late match)
Shard: flags-single
Time per operation 30.55 µs/op 30.41 µs/op 0.5% less time Not flagged
Evaluate a flag (late match)
Shard: flags-single
Process CPU time per operation 30.55 µs/op 30.41 µs/op 0.5% less time Not flagged
Evaluate a flag (no match)
Shard: flags-single
Allocated memory per operation 52.14 KiB/op 52.14 KiB/op No observed change Not flagged
Evaluate a flag (no match)
Shard: flags-single
Allocations per operation 556.77 count/op 556.77 count/op No observed change Not flagged
Evaluate a flag (no match)
Shard: flags-single
Time per operation 28.94 µs/op 28.69 µs/op 0.9% less time Not flagged
Evaluate a flag (no match)
Shard: flags-single
Process CPU time per operation 28.94 µs/op 28.68 µs/op 0.9% less time Not flagged
Evaluate a property-filtered flag
Shard: flags-single
Allocated memory per operation 17.84 KiB/op 17.84 KiB/op No observed change Not flagged
Evaluate a property-filtered flag
Shard: flags-single
Allocations per operation 198.27 count/op 198.27 count/op No observed change Not flagged
Evaluate a property-filtered flag
Shard: flags-single
Time per operation 12.31 µs/op 12.27 µs/op 0.4% less time Not flagged
Evaluate a property-filtered flag
Shard: flags-single
Process CPU time per operation 12.31 µs/op 12.27 µs/op 0.4% less time Not flagged
Evaluate a regex-filtered flag
Shard: flags-single
Allocated memory per operation 19.23 KiB/op 19.23 KiB/op No observed change Not flagged
Evaluate a regex-filtered flag
Shard: flags-single
Allocations per operation 210.77 count/op 210.77 count/op No observed change Not flagged
Evaluate a regex-filtered flag
Shard: flags-single
Time per operation 12.89 µs/op 12.92 µs/op 0.3% more time Not flagged
Evaluate a regex-filtered flag
Shard: flags-single
Process CPU time per operation 12.89 µs/op 12.92 µs/op 0.3% more time Not flagged
Evaluate a rollout flag
Shard: flags-single
Allocated memory per operation 14.04 KiB/op 14.04 KiB/op No observed change Not flagged
Evaluate a rollout flag
Shard: flags-single
Allocations per operation 160.76 count/op 160.76 count/op No observed change Not flagged
Evaluate a rollout flag
Shard: flags-single
Time per operation 10.27 µs/op 10.09 µs/op 1.8% less time Not flagged
Evaluate a rollout flag
Shard: flags-single
Process CPU time per operation 10.27 µs/op 10.09 µs/op 1.8% less time Not flagged
Evaluate a multivariate flag
Shard: flags-single
Allocated memory per operation 15.21 KiB/op 15.21 KiB/op No observed change Not flagged
Evaluate a multivariate flag
Shard: flags-single
Allocations per operation 177.77 count/op 177.77 count/op No observed change Not flagged
Evaluate a multivariate flag
Shard: flags-single
Time per operation 11.25 µs/op 11.28 µs/op 0.3% more time Not flagged
Evaluate a multivariate flag
Shard: flags-single
Process CPU time per operation 11.25 µs/op 11.28 µs/op 0.3% more time Not flagged

Values are medians of paired measurements. Not flagged does not mean unchanged. Unavailable means a measurement could not be provided, not zero. Estimated allocation measurements retain their instrumentation uncertainty. RSS measures the whole process, not just SDK allocations; observed peaks are sampled checkpoints. Paired ranges in the diagnostics describe variability, not confidence intervals.

Each shard uses its own runner; compare Before PR against With PR within a row, not across shards.

Compared 778f386eaacd1ea9379852c3b032a9f19a6271ea → b4e012cca3333ad1bc19cfe6cc8e2689eedf43e0.

Full report and diagnostics

102 metric rows; 102 rows shown in all results. Omitted or shortened data remain in comparison.json, including per-runner environments, resource limits, measurement methods, samples and checkpoints.

@lucasheriques
lucasheriques force-pushed the lucas/mcp-v1-spec-align branch from af10d66 to 8b1c0a0 Compare November 6, 2026 17:47
@lucasheriques
lucasheriques marked this pull request as ready for review November 6, 2026 17:47
@lucasheriques
lucasheriques requested a review from a team as a code owner November 6, 2026 17:47

@posthog posthog Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PostHog Review · Standard · reviewed 8b1c0a0: 2 Should fix.

See this review and its findings in PostHog Review. Comment @posthog review --deep for a Deep review. A Deep review takes longer and looks deeper than a Standard review.

Comment thread posthog/mcp/_instrumentation.py Resolved
Comment thread posthog/mcp/posthog_mcp.py Resolved
@lucasheriques lucasheriques added the stamphog Request stamphog review label Nov 6, 2026

@stamphog stamphog Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not approved — this change needs a human reviewer.

Re-adding the stamphog label gives the same result unless the changed files change.

stamphog can't auto-approve this pull request because two gates refused it. The deny-list gate flagged a match on public_api, which fits the change to references/public_api_snapshot.txt and the new public PostHogMCP.capture_unknown_tool() in posthog/mcp/posthog_mcp.py. The tier gate classified it as T2-never: it is a cross-cutting feature touching 28 files and 1225 lines, across the adapters, shared instrumentation, and tool schemas.

The size gate passed, so splitting is not required, but it could make review easier. Ask a human reviewer to look at it, and consider separating the public API addition from the annotation and llm_model schema changes.

Gate mechanics and policy version
Gate Result
prerequisites ✓ all clear
deny-list ✗ matches: public_api
size ✓ 548L, 14F substantive, 1225L/28F incl. docs/generated/snapshots — within ceiling
tier ✗ classified as T2-never: T2-never (1225L, 28F, cross-cutting, feat)
stamphog 2.7.0 .stamphog/policy.yml @ unknown · reviewed head 665fe23

@stamphog stamphog Bot removed the stamphog Request stamphog review label Nov 6, 2026

@posthog posthog Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PostHog Review · Standard · reviewed 665fe23: no findings. This pull request is large, so the review ran in 4 parts with less depth than usual.

@lucasheriques
lucasheriques requested review from a team and removed request for a team November 6, 2026 20:51
What:
- get_more_tools and send_feedback annotate readOnlyHint, destructiveHint,
  idempotentHint and openWorldHint as false, with no title, so the spec's
  exact annotations JSON matches. Hosts cannot override them.
- The injected `context` argument uses the spec's shared description string.
- `llm_model` is never added to a schema's `required` list.
- A tools/call naming a tool the server never registered sends
  $mcp_unknown_tool (tool name, identity, session) instead of
  $mcp_tool_call and $exception. The client gets the same response.
  A disabled tool, invalid arguments, a raw server with no tools/list
  handler or a name missing from a paginated first page, and standalone
  FastMCP with dispatch-overriding middleware stay failed tool calls.
  PostHogMCP.capture_unknown_tool() covers custom dispatchers.
- Every adapter's raise path and isError-result path calls one
  ToolCallLifecycle.record_if_unknown_tool(). The standalone FastMCP
  registry lookup and its middleware check moved to _instrumentation.py,
  so _instrument_v2 no longer imports from _instrument_lowlevel.
- Minor sampo changeset.

Why: posthog.mcp is about to be declared stable. Customers' insights over
$mcp_* events must not shift after that, so every SDK matches the spec now.

Tested:
- pytest posthog/test/mcp: 678 passed, 10 skipped
- annotations test compares the exact JSON; fails 2/4 with a title present
- ruff format --check . and ruff check .: clean
- mypy --no-site-packages --config-file mypy.ini . | mypy-baseline filter: clean
- python -W error -c "import posthog": ok; make public_api_check: up to date
- full pytest without provider API keys: 6142 passed, 3 failed in
  test_metrics_autocapture.py fork tests (macOS objc fork-safety abort,
  unrelated to this change)

Reviewer notes: _standalone_tool_exists catches the cached fastmcp
not-found errors, which include DisabledError; get_tool raises only
NotFoundError in fastmcp 2.14 and 3.2, so a disabled tool still reads
as existing. Client conversation ids are untouched (posthog-python#1193).
What:
- A disabled tool on a mounted FastMCP 3+ server stays a failed
  $mcp_tool_call. A server serving other providers (mounts, proxies)
  can't prove a name absent, so existence answers "can't tell".
- FastMCP's stock middleware (logging, timing, error handling, retry,
  rate limiting, ping, auth, caching, response limiting) no longer hides
  the registry. Tool-injection middleware and app middleware still do.
- A call naming no tool emits nothing, automatic or manual.
- Truncated strings fit their limit with the "..." marker included, so
  $mcp_tool_name stops at 256 characters (the spec's Property reference).
- first_listing_page reads nextCursor only when next_cursor is absent,
  so fastmcp 4 on MCP 2 logs no deprecation warning.
- A raw server's unknown-tool error result carries the conversation
  handle again, and $mcp_unknown_tool carries it once delivered, as
  origin/main did and as posthog-js does.
- Unknown-tool tests skip only the FastMCP.disable cases on fastmcp 2.
- Changeset names the listing probe and hidden-tool upgrade differences.

Why: posthog.mcp must match the sdk-specs MCP spec before it is declared
stable, so customers' insights don't shift afterwards.

Tested:
- pytest posthog/test/mcp (mcp 1.30 + fastmcp 3.2): 694 passed, 11 skipped
- test_unknown_tool.py on mcp 1.30 + fastmcp 2.14.7: 21 passed, 4 skipped;
  mcp 2.3: 15 passed, 10 skipped; mcp 2.3 + fastmcp 4.1.6: 25 passed
- ruff format --check, ruff check, mypy | mypy-baseline filter,
  make public_api_check: clean

Reviewer notes: posthog-js truncates with the marker past the limit too
and needs the same fix. test_fastmcp_v2.py::
test_jlowin_middleware_defaults_work_across_fresh_instances fails on
fastmcp 2.14.7 on origin/main as well ($mcp_input_keys is
["[redacted]"]); not touched here.
What: raw_listing_owns_tool_name waits at most LISTING_PROBE_DEADLINE_SECONDS (1s)
for the host's tools/list and treats a timeout as None (can't tell), so a failed
call records a failed $mcp_tool_call and the client gets its error promptly.
PostHogMCP._base_event mints a fresh ses_<UUIDv7> when no session_id is passed,
so capture_unknown_tool (and capture_tool_call and the other manual captures)
no longer send no $session_id and an anonymous distinct_id.

Why: PostHog Review on #1199. A stalled tools/list handler held every failed
call forever; the spec's Session identity and Manual capture require a
non-empty $session_id, fresh per call when nothing groups it.

Tested: pytest posthog/test/mcp (697 passed, 11 skipped); ruff format/check,
mypy | mypy-baseline filter, make public_api_check all clean. New tests failed
first: stalled listing (timed out), manual capture without session (KeyError).

Reviewer: a manual capture passing conversation_id but no session_id still gets
a fresh session, not one derived from the handle.
What: `_raw(stall_listing=True)` now stalls every tools/list on mcp 2.x; on 1.x it
still spares the server's own cache refresh.

Why: the v2 adapter probes the host listing as `original(ctx, None)`, and the
helper stalled only when a request was present, so the probe was answered at once,
the call was recorded as `$mcp_unknown_tool`, and the test found no
`$mcp_tool_call` (CI: MCP SDK v2 and v2-bare, Python 3.10). The product code was
right: the deadline path falls back to a failed call on mcp 2.

Tested: `pytest posthog/test/mcp` on mcp 1.30 + fastmcp 3.2 (697 passed), mcp 2.3
(536), mcp 2.3 + fastmcp 4.1.6 (579), and Python 3.10 with mcp 2.x bare (536) and
with fastmcp 4 (579). Raising the deadline to 999s makes the test fail on mcp 2.
ruff format/check and mypy baseline clean.
A call is now unknown only on authoritative evidence: jlowin FastMCP's
registry when nothing overrides dispatch, or the official high-level
server's registry. A raw low-level server's own dispatcher decides which
names exist and its listing may hide tools it serves, so there the SDK
answers "can't tell" and records a failed $mcp_tool_call (spec, "Tool
call event"). This removes the failure-path listing probe, its one-second
deadline, the pagination flag and FirstListingPage.

The deadline also sat in the check that decides whether get_more_tools
and send_feedback are virtual-tool calls, so a tools/list slower than one
second sent those calls to the application. That check is back to
origin/main's.

Tested with:
- new tests failed on the previous head: a slow tools/list still answers
  get_more_tools and send_feedback; a raw low-level server records a
  failed $mcp_tool_call for an unknown name and for a hidden tool
- pytest posthog/test/mcp: .venv (mcp 1.30, fastmcp 3.2) 696 passed;
  v2 (mcp 2.3) 533 passed; v2f4 (mcp 2.3, fastmcp 4.1) 577 passed;
  f2 (mcp 1.30, fastmcp 2.14) 688 passed, 1 failed
- ruff format --check, ruff check, mypy | mypy-baseline filter,
  make public_api_check: clean

Reviewer notes: the f2 failure,
test_jlowin_middleware_defaults_work_across_fresh_instances, also fails
on origin/main in that venv. The unknown-tool handle-delivery test now
covers the error-result branch through standalone FastMCP, since a raw
low-level server no longer records unknown tools.
What: removed the public PostHogMCP.capture_unknown_tool() and the public
PostHogMCPAnalyticsEvent.UNKNOWN_TOOL constant; the event name now lives in the
private event-name map. The registry helpers stay in _instrument_lowlevel next
to _dispatch_can_differ instead of moving to _instrumentation. Dropped the
slow-listing and hidden-tool test cases (they guarded a listing probe this
branch no longer has and pass on main), the lowlevel test fixture edits, and
README text that documented #1204's annotations. The manual-session test moved
to test_posthog_mcp.py.

Why: stamphog refused #1199 for a public API change and its size. The spec
makes manual capture methods optional, so capture_unknown_tool can return in
its own PR.

Tested with: pytest posthog/test/mcp on .venv, v2, f2, v2f4 (689, 526, 681,
570 passed; f2's one failure is
test_jlowin_middleware_defaults_work_across_fresh_instances, failing on main
until #1203). ruff format/check, mypy-baseline filter clean. make
public_api_check: snapshot up to date, identical to origin/main.
@lucasheriques
lucasheriques force-pushed the lucas/mcp-v1-spec-align branch from cb8b2fd to 5799773 Compare November 6, 2026 21:05
@lucasheriques lucasheriques added the stamphog Request stamphog review label Nov 6, 2026

@posthog posthog Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

PostHog Review · Standard · reviewed 5799773: 1 Should fix.

Comment thread posthog/mcp/_instrument_lowlevel.py Resolved

@stamphog stamphog Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not approved — this change needs a human reviewer.

Re-add the stamphog label to request another review once you have addressed this.

The current-head review has an unresolved substantive concern, and there is no qualifying independent assurance for the risky changes. Address @PostHog's mounted-server finding and request review from Georgis Andonis or another teammate, explicitly covering the manual-capture identity change.

  • Author wrote 65% of the modified lines and has 6 merged PRs in these paths (familiarity MODERATE).
  • PostHog Review (Standard) reviewed the current head: 1 finding, posted on the PR.
  • posthog[bot] reviewed the current head.
  • @PostHog on posthog/mcp/_instrument_lowlevel.py: the mounted-server concern remains unaddressed. registered_tool_exists() converts lookup-not-found errors into a negative result, while _serves_other_providers() checks only the newer providers collection and has no FastMCP 2.x mount check. An unavailable mounted tool can therefore be classified as unknown, suppressing failure and exception analytics. Preserve an indeterminate result for FastMCP 2.x mounts and add an outage regression test before re-requesting.
  • Undisclosed risky behavior: posthog/mcp/posthog_mcp.py changes session and distinct-identity defaults for manual capture without a session. The release note acknowledges this, but the title and PR description do not disclose it. Update the description to explain the identity and analytics consequences and request human review before re-requesting.
Gate mechanics and policy version
Gate Result
prerequisites ✓ all clear
deny-list ✓ no deny categories matched
size ✓ 223L, 10F substantive, 631L/17F incl. docs/generated/snapshots — within ceiling
tier ✓ T1-agent / T1d-complex (631L, 17F, two-areas, feat)
stamphog 2.7.0 .stamphog/policy.yml @ 5799773 · reviewed head 5799773

@stamphog stamphog Bot removed the stamphog Request stamphog review label Nov 6, 2026
Review: _serves_other_providers only checked FastMCP 3.x providers, so on 2.x
a mounted server (or one whose mount failed to load) made a missing name look
unregistered and emitted $mcp_unknown_tool instead of a failed tool call. It
now also checks 2.x's _mounted_servers.

Tested: new server-with-mounted-server case fails on fastmcp 2.14.7 before the
fix and passes after; pytest posthog/test/mcp on fastmcp 3.2 (690 passed),
2.14.7 and mcp 2.3+fastmcp 4.1 (only failures are the stdio handshake tests,
which fail locally without this change, and the 2.x input-keys test that
posthog-python#1203 fixes); ruff clean.
@lucasheriques lucasheriques added the stamphog Request stamphog review label Nov 6, 2026

@stamphog stamphog Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approved.

The analytics contract and capture changes enter risky territory, covered by the trusted current-head review with no findings. No concrete unresolved review concern or production/security showstopper is established by the supplied context and code.

  • Author wrote 65% of the modified lines and has 6 merged PRs in these paths (familiarity MODERATE).
  • PostHog Review (Standard) reviewed the current head: no findings.
Gate mechanics and policy version
Gate Result
prerequisites ✓ all clear
deny-list ✓ no deny categories matched
size ✓ 226L, 10F substantive, 660L/17F incl. docs/generated/snapshots — within ceiling
tier ✓ T1-agent / T1d-complex (660L, 17F, two-areas, feat)
stamphog 2.7.0 .stamphog/policy.yml @ b4e012c · reviewed head b4e012c

@lucasheriques
lucasheriques merged commit 0aa5df1 into main Nov 6, 2026
51 checks passed
@lucasheriques
lucasheriques deleted the lucas/mcp-v1-spec-align branch November 6, 2026 21:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

stamphog Request stamphog review

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant