Skip to content

feat(mcp): tell directory reviews what the virtual tools record - #1204

Merged
lucasheriques merged 1 commit into
mainfrom
lucas/mcp-directory-listing
Nov 6, 2026
Merged

lucasheriques merged 1 commit into
mainfrom
lucas/mcp-directory-listing

Conversation

@lucasheriques

@lucasheriques lucasheriques commented Nov 6, 2026 •

Copy link
Copy Markdown
Contributor

Problem

ChatGPT's and Claude's plugin directory reviews flag servers instrumented with posthog.mcp. get_more_tools and send_feedback claim to be read-only, idempotent and open-world, though each call records an event in the server owner's PostHog project, and the injected context description asks for more text than review allows. The MCP analytics spec (sdk-specs, "Virtual tool annotations" and "Arguments the SDK injects") now requires them.

Changes

  • get_more_tools and send_feedback annotations: readOnlyHint, destructiveHint, idempotentHint and openWorldHint are all false (VIRTUAL_TOOL_HINTS), with no title.
  • The injected context description is the shared text every PostHog MCP SDK sends: a few words of purpose, people by role, no quoting the user.
  • llm_model is never required. The unused required plumbing behind it is removed. A model the client sends in _meta still wins.
  • Minor changeset. Published tool definitions change, so directory listings may re-review.

This is the listing-only part of posthog-python#1199, split out because it adds no public API. The unknown-tool event stays in #1199.

How I tested

  • pytest posthog/test/mcp:
    • mcp 1.30 with fastmcp 3.2: 670 passed.
    • mcp 2.3: 518 passed.
    • fastmcp 2.14: 665 passed. The one failure, test_jlowin_middleware_defaults_work_across_fresh_instances, fails on main too, and posthog-python#1203 fixes it.
  • ruff format --check ., ruff check ., and mypy through mypy-baseline filter are clean.
  • make public_api_check passes with the snapshot unchanged.

What: `get_more_tools` and `send_feedback` declare readOnlyHint,
destructiveHint, idempotentHint and openWorldHint as false with no title
(shared VIRTUAL_TOOL_HINTS). The injected `context` description is the short
cross-SDK text. `llm_model` is never added to a schema's `required` list.

Why: promised to OpenAI's plugin directory review. A call records an event in
the server owner's project, so the old read-only/idempotent hints were wrong.
Split from posthog-python#1199 so this has no public API change.

Tested with: pytest posthog/test/mcp on the 1.x, v2 and fastmcp-2 venvs (670,
518, 665 passed); ruff format/check, mypy-baseline filter and
`make public_api_check` clean (snapshot unchanged).

Reviewer note: on the fastmcp-2 venv
test_fastmcp_v2.py::test_jlowin_middleware_defaults_work_across_fresh_instances
fails identically on origin/main, unrelated to this change.
@lucasheriques
lucasheriques requested a review from a team as a code owner November 6, 2026 20:26
@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 published tool contracts enter risky territory, covered by the trusted current-head review with no findings. The changes match the disclosed scope, and no substantive concerns or other refusal grounds were found.

  • Author wrote 58% of the modified lines and has 5 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 ✓ 62L, 5F substantive, 170L/13F incl. docs/generated/snapshots — within ceiling
tier ✓ T1-agent / T1c-medium (170L, 13F, two-areas, feat)
stamphog 2.7.0 .stamphog/policy.yml @ f05a850 · reviewed head f05a850

@github-actions

github-actions Bot commented Nov 6, 2026 •

Copy link
Copy Markdown
Contributor

posthog-python Compliance Report

Date: 2026-11-06T20:31:11.315427+00:00
Duration: 259537ms

✅ 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 ✅ 513ms
Endpoint And Method.Does Not Use Legacy Endpoints ✅ 509ms
Required Headers.Has Authorization Bearer Header ✅ 508ms
Required Headers.Has Content Type Json ✅ 509ms
Required Headers.Has Posthog Sdk Info Format ✅ 508ms
Required Headers.Has Posthog Attempt Header ✅ 509ms
Required Headers.Has Posthog Request Id ✅ 508ms
Required Headers.Has Posthog Request Timestamp ✅ 508ms
Required Headers.Has User Agent ✅ 508ms
Body Format.Body Has Created At And Batch ✅ 508ms
Body Format.No Api Key In Body ✅ 509ms
Body Format.No Sent At In Body ✅ 508ms
Event Format.Event Has Required Root Fields ✅ 508ms
Event Format.Event Uuid Is Valid ✅ 509ms
Event Format.Event Timestamp Is Rfc3339 ✅ 508ms
Event Format.Non Utc Event Timestamp Is Converted To Utc ✅ 522ms
Event Format.Distinct Id Is String ✅ 509ms
Event Format.Distinct Id At Root Not Properties ✅ 508ms
Event Format.Custom Properties Preserved ✅ 508ms
Event Format.Set Properties Preserved ✅ 509ms
Event Format.Set Once Properties Preserved ✅ 508ms
Event Format.Groups Properties Preserved ✅ 508ms
Event Format.Sdk Generates Uuid If Not Provided ✅ 508ms
Event Format.Event Has Required Root Fields Batch ✅ 511ms
Event Format.Event Uuid Is Valid Batch ✅ 510ms
Event Format.Event Timestamp Is Rfc3339 Batch ✅ 511ms
Event Format.Distinct Id Is String Batch ✅ 511ms
Event Format.Distinct Id At Root Not Properties Batch ✅ 511ms
Event Format.Custom Properties Preserved Batch ✅ 511ms
Event Format.Set Properties Preserved Batch ✅ 511ms
Event Format.Set Once Properties Preserved Batch ✅ 511ms
Event Format.Groups Properties Preserved Batch ✅ 511ms
Event Format.Sdk Generates Uuid If Not Provided Batch ✅ 511ms
Batch Behavior.Multiple Events In Single Batch ✅ 514ms
Batch Behavior.Batch Envelope Smoke ✅ 512ms
Batch Behavior.Flush With No Events Sends Nothing ✅ 505ms
Batch Behavior.Flush At Triggers Batch ✅ 1009ms
Batch Behavior.Created At Reflects Batch Creation Time ✅ 509ms
Deduplication.Generates Unique Uuids ✅ 514ms
Deduplication.Different Events Same Content Different Uuids ✅ 510ms
Deduplication.Preserves Uuid On Retry ✅ 6517ms
Deduplication.Preserves Timestamp On Retry ✅ 6517ms
Deduplication.Preserves Uuid And Timestamp On Batch Retry ✅ 6518ms
Deduplication.No Duplicate Events In Batch ✅ 514ms
Header Behavior On Retry.Attempt Header Starts At One ✅ 508ms
Header Behavior On Retry.Attempt Header Increments On Retry ✅ 13525ms
Header Behavior On Retry.Request Id Preserved On Retry ✅ 6517ms
Header Behavior On Retry.Different Requests Have Different Request Ids ✅ 3017ms
Header Behavior On Retry.Request Timestamp Changes On Retry ✅ 6517ms
Response Format Validation.Success Response Has Uuid Keyed Results ✅ 508ms
Response Format Validation.Success Response Has Ok For Each Event ✅ 512ms
Response Format Validation.Success No Retry After When All Ok ✅ 510ms
Response Format Validation.Success Retry After Present When Retry Events ✅ 1513ms
Response Format Validation.Success No Retry After When Drop Only ✅ 510ms
Response Format Validation.Response Echoes Request Id ✅ 509ms
Retry Behavior.Retries On 408 ✅ 6516ms
Retry Behavior.Retries On 500 ✅ 6513ms
Retry Behavior.Retries On 503 ✅ 8517ms
Retry Behavior.Retries On 504 ✅ 6517ms
Retry Behavior.Retryable Errors Have Retry After ✅ 3514ms
Retry Behavior.Respects Retry After On Retryable Error ✅ 11519ms
Retry Behavior.Does Not Retry On 400 ✅ 2512ms
Retry Behavior.Does Not Retry On 401 ✅ 2512ms
Retry Behavior.Does Not Retry On 402 ✅ 2511ms
Retry Behavior.Does Not Retry On 413 ✅ 2512ms
Retry Behavior.Does Not Retry On 415 ✅ 2510ms
Retry Behavior.Non Retryable Errors Have No Retry After ✅ 2511ms
Retry Behavior.Implements Backoff ✅ 22533ms
Retry Behavior.Max Retries Respected ✅ 22533ms
Partial Batch Handling.Handles 200 Full Success ✅ 2510ms
Partial Batch Handling.Handles 200 With All Ok ✅ 3512ms
Partial Batch Handling.Does Not Retry Dropped Events ✅ 3511ms
Partial Batch Handling.Does Not Retry Limited Events ✅ 3513ms
Partial Batch Handling.Prunes Ok Events On Partial Retry ✅ 6516ms
Partial Batch Handling.Prunes Dropped Events On Partial Retry ✅ 6517ms
Partial Batch Handling.Retries Only Retry Events From Partial ✅ 6519ms
Partial Batch Handling.Partial Retry Preserves Uuids ✅ 6519ms
Partial Batch Handling.Partial Retry Attempt Header Increments ✅ 6518ms
Partial Batch Handling.Partial Retry Request Id Preserved ✅ 6519ms
Partial Batch Handling.Respects Retry After On Partial ✅ 8515ms
Partial Batch Handling.Unknown Result Treated As Terminal ✅ 3513ms
Partial Batch Handling.Mixed Ok Drop Limited No Retry ✅ 3517ms
Compression.Sends Gzip Content Encoding ✅ 509ms
Compression.No Content Encoding When Disabled ✅ 508ms
Compression.Compressed Body Is Decompressible ✅ 508ms
Error Handling.Does Not Retry On Unknown 4Xx ✅ 2511ms
Event Options.Cookieless Mode Override ✅ 509ms
Event Options.Disable Skew Correction Override ✅ 508ms
Event Options.Process Person Profile Override ✅ 508ms
Event Options.Product Tour Id Override ✅ 508ms
Event Options.Unset Options Omitted ✅ 508ms
Event Options.Options Override In Batch ✅ 511ms
Geoip And Historical Migration.Geoip Disable Injected Into Properties ✅ 508ms
Geoip And Historical Migration.Historical Migration Set In Body ✅ 509ms
Geoip And Historical Migration.Historical Migration Absent By Default ✅ 508ms

Capture_Ai Tests

✅ 5/5 tests passed

View Details
Test Status Duration
Routing.Capture Ai Posts To Ai Endpoint ✅ 508ms
Routing.Capture Does Not Reroute Ai Named Events ✅ 508ms
Identity.Capture Ai Event Has Uuid ✅ 509ms
Identity.Capture Ai Keeps Supplied Uuid ✅ 509ms
Timestamp Format.Non Utc Event Timestamp Is Converted To Utc ✅ 508ms

Feature_Flags Tests

✅ 17/17 tests passed

View Details
Test Status Duration
Request Payload.Request With Person Properties Device Id ✅ 9ms
Request Payload.Flags Request Uses V4 Query Param ✅ 7ms
Request Payload.Flags Request Hits Flags Path Not Decide ✅ 7ms
Request Payload.Flags Request Omits Authorization Header ✅ 7ms
Request Payload.Token In Flags Body Matches Init ✅ 7ms
Request Payload.Groups Round Trip ✅ 8ms
Request Payload.Groups Default To Empty Object ✅ 7ms
Request Payload.Disable Geoip False Propagates As Geoip Disable False ✅ 7ms
Request Payload.Disable Geoip Omitted Defaults To False ✅ 7ms
Request Payload.Flag Keys To Evaluate Contains Only Requested Key ✅ 7ms
Request Lifecycle.No Flags Request On Init Alone ✅ 3ms
Request Lifecycle.No Flags Request On Normal Capture ✅ 508ms
Request Lifecycle.Two Flag Calls Produce Two Remote Requests ✅ 11ms
Request Lifecycle.Mock Response Value Is Returned To Caller ✅ 7ms
Retry Behavior.Retries Flags On 502 ✅ 310ms
Retry Behavior.Retries Flags On 504 ✅ 311ms
Side Effect Events.Get Feature Flag Captures Feature Flag Called Event ✅ 509ms

Feature_Flags_Local_Evaluation Tests

✅ 4/4 tests passed

View Details
Test Status Duration
Versioned Boolean Matching.Matching Version Missing ✅ 53ms
Versioned Boolean Matching.Matching Version 1 ✅ 54ms
Versioned Boolean Matching.Matching Version 2 ✅ 51ms
Versioned Boolean Matching.Version Only Reload 1 2 1 2 Missing ✅ 27ms

@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% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Allocations per operation 1,096.59 count/op 1,096.6 count/op <0.1% more Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Time per operation 114.24 µs/op 112.28 µs/op 1.7% less time Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Idle process memory (RSS) 35.99 MiB 36.08 MiB 0.2% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Observed peak process memory (RSS) 37.74 MiB 37.82 MiB 0.2% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Process memory after settling (RSS) 37.74 MiB 37.82 MiB 0.2% more memory Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Process CPU time per operation 115.41 µs/op 112.94 µs/op 2.1% less time Not flagged
Capture and deliver events (32-byte payload, burst)
Shard: capture
Lifetime peak process memory (RSS) 39.86 MiB 39.86 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 1,089.64 count/op 1,089.55 count/op <0.1% fewer Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Time per operation 146.81 µs/op 156.26 µs/op 6.4% more time Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Idle process memory (RSS) 40.77 MiB 40.86 MiB 0.2% more memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Observed peak process memory (RSS) 45.87 MiB 45.96 MiB 0.2% more memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Process memory after settling (RSS) 45.87 MiB 45.96 MiB 0.2% more memory Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Process CPU time per operation 139.92 µs/op 149.08 µs/op 6.5% more time Not flagged
Capture and deliver events (4,096-byte payload, burst)
Shard: capture
Lifetime peak process memory (RSS) 50.7 MiB 50.74 MiB <0.1% more 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% more memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Allocations per operation 1,136.61 count/op 1,136.6 count/op <0.1% fewer Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Time per operation 130.84 µs/op 126.88 µs/op 3% less time Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Idle process memory (RSS) 35.93 MiB 35.91 MiB <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Observed peak process memory (RSS) 36.04 MiB 36.02 MiB <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Process memory after settling (RSS) 36.04 MiB 36.02 MiB <0.1% less memory Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Process CPU time per operation 130.38 µs/op 126.31 µs/op 3.1% less time Not flagged
Capture and deliver events (32-byte payload, steady)
Shard: capture
Lifetime peak process memory (RSS) 39.86 MiB 39.86 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% less memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Allocations per operation 1,129.48 count/op 1,129.46 count/op <0.1% fewer Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Time per operation 160.21 µs/op 149.42 µs/op 6.7% less time Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Idle process memory (RSS) 40.67 MiB 40.72 MiB 0.1% more memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Observed peak process memory (RSS) 40.68 MiB 40.73 MiB 0.1% more memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Process memory after settling (RSS) 40.68 MiB 40.73 MiB 0.1% more memory Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Process CPU time per operation 152.93 µs/op 142.32 µs/op 6.9% less time Not flagged
Capture and deliver events (4,096-byte payload, steady)
Shard: capture
Lifetime peak process memory (RSS) 41 MiB 41 MiB <0.1% less memory Not flagged
Queue an event (32-byte payload)
Shard: capture
Caller-thread CPU time per operation 81.73 µs/op 83.76 µs/op 2.5% more time Not flagged
Queue an event (32-byte payload)
Shard: capture
Time per operation 86.67 µs/op 91.34 µs/op 5.4% more time Not flagged
Queue an event (4,096-byte payload)
Shard: capture
Caller-thread CPU time per operation 81.69 µs/op 87.24 µs/op 6.8% more time Not flagged
Queue an event (4,096-byte payload)
Shard: capture
Time per operation 85.98 µs/op 89.79 µs/op 4.4% 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 60.09 µs/op 60.23 µs/op 0.2% more time Not flagged
Evaluate all 10 flags
Shard: flags-scaling
Process CPU time per operation 60.08 µs/op 60.23 µs/op 0.2% 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 581.18 µs/op 590.45 µs/op 1.6% more time Not flagged
Evaluate all 100 flags
Shard: flags-scaling
Process CPU time per operation 581.21 µs/op 590.52 µs/op 1.6% 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 6.51 ms/op 6.34 ms/op 2.6% less time Not flagged
Evaluate all 1,000 flags
Shard: flags-scaling
Process CPU time per operation 6.51 ms/op 6.34 ms/op 2.6% less time Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Idle process memory (RSS) 42.28 MiB 41.65 MiB 1.5% less memory Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Observed peak process memory (RSS) 42.6 MiB 41.97 MiB 1.5% less memory Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Process memory after settling (RSS) 42.6 MiB 41.97 MiB 1.5% less memory Not flagged
Evaluate 1,000 flags under concurrent load
Shard: flags-memory
Lifetime peak process memory (RSS) 42.47 MiB 42.48 MiB <0.1% more memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Idle process memory (RSS) 42.1 MiB 42.07 MiB <0.1% less memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Observed peak process memory (RSS) 42.18 MiB 42.12 MiB 0.1% less memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Process memory after settling (RSS) 41.51 MiB 42 MiB 1.2% more memory Not flagged
Refresh 1,000 flag definitions
Shard: flags-memory
Lifetime peak process memory (RSS) 42.54 MiB 42.56 MiB <0.1% more 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 12.57 µs/op 12.77 µs/op 1.6% more time Not flagged
Evaluate one boolean flag
Shard: flags-single
Process CPU time per operation 12.57 µs/op 12.77 µs/op 1.6% more 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 16.79 µs/op 16.61 µs/op 1.1% less time Not flagged
Evaluate a cohort-filtered flag
Shard: flags-single
Process CPU time per operation 16.79 µs/op 16.61 µs/op 1.1% 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 24.02 µs/op 23.93 µs/op 0.4% less time Not flagged
Evaluate a flag (early match)
Shard: flags-single
Process CPU time per operation 24.02 µs/op 23.93 µs/op 0.4% less 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 34.31 µs/op 34.06 µs/op 0.7% less time Not flagged
Evaluate a flag (late match)
Shard: flags-single
Process CPU time per operation 34.3 µs/op 34.05 µs/op 0.7% 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 32.63 µs/op 32.23 µs/op 1.2% less time Not flagged
Evaluate a flag (no match)
Shard: flags-single
Process CPU time per operation 32.63 µs/op 32.23 µs/op 1.2% 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 13.89 µs/op 13.82 µs/op 0.5% less time Not flagged
Evaluate a property-filtered flag
Shard: flags-single
Process CPU time per operation 13.89 µs/op 13.82 µs/op 0.5% 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 14.95 µs/op 14.87 µs/op 0.5% less time Not flagged
Evaluate a regex-filtered flag
Shard: flags-single
Process CPU time per operation 14.95 µs/op 14.87 µs/op 0.5% less 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 11.73 µs/op 11.66 µs/op 0.6% less time Not flagged
Evaluate a rollout flag
Shard: flags-single
Process CPU time per operation 11.73 µs/op 11.66 µs/op 0.6% 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 13.01 µs/op 12.98 µs/op 0.2% less time Not flagged
Evaluate a multivariate flag
Shard: flags-single
Process CPU time per operation 13.01 µs/op 12.98 µs/op 0.2% less 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 1402030092d31e8598e4853264be3fc341c8f8fc → f05a850d38901ba5b24aa231199ccb165a0703a0.

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 merged commit 778f386 into main Nov 6, 2026
51 checks passed
@lucasheriques
lucasheriques deleted the lucas/mcp-directory-listing branch November 6, 2026 20:36
lucasheriques added a commit that referenced this pull request Nov 6, 2026
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 added a commit that referenced this pull request Nov 6, 2026
* feat(mcp): align posthog.mcp with the sdk-specs MCP spec before v1

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).

* fix(mcp): close unknown-tool gaps found in review of the spec alignment

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.

* fix(mcp): bound the listing probe and give manual capture a session

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.

* fix(mcp): make the stalled-listing test stall on mcp 2.x

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.

* fix(mcp): stop treating a tools/list listing as proof a tool is unknown

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.

* fix(mcp): drop the manual unknown-tool API and shrink the spec alignment

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.

* fix(mcp): treat FastMCP 2.x mounts as unable to rule out a tool

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.
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