Merge feature/soft-errors: classify error results returned as data

The showcase repo is private and fastmcp-feedback-showcase was never
published, so both the link and the uvx command failed for everyone else.
Tested the new clone-and-run instructions against the now-public repo.

.gitea/workflows/test.yml

@@ -0,0 +1,67 @@
+name: Tests
+
+# fastmcp-feedback declares fastmcp>=2.12.2,<5, so every version family in
+# that range gets the full suite. A user on PyPI gets the newest FastMCP the
+# range allows, not what uv.lock pins, which is how 2026.01.12.1 shipped with
+# composition broken on 2.14 and 4.x without anyone noticing.
+
+on:
+  push:
+  pull_request:
+  workflow_dispatch:
+  schedule:
+    # Weekly, so a new FastMCP release is caught even when nobody pushes
+    - cron: '17 9 * * 1'
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    strategy:
+      fail-fast: false
+      matrix:
+        fastmcp: ['==2.12.2', '==2.14.3', '>=3.3,<4', '>=4,<5']
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: astral-sh/setup-uv@v6
+        with:
+          python-version: '3.13'
+
+      - name: Install against fastmcp${{ matrix.fastmcp }}
+        run: |
+          uv venv
+          uv pip install -e ".[dev]" "fastmcp${{ matrix.fastmcp }}"
+          uv pip show fastmcp | grep -i '^version'
+
+      - name: Lint
+        run: uv run --no-sync ruff check src/ examples/ tests/_compat.py tests/unit/test_instrumentation.py
+
+      - name: Test
+        run: uv run --no-sync pytest -q --no-cov
+
+  # Newest FastMCP with no ceiling. Allowed to fail: it exists to say
+  # "a new major version is out and here is what breaks" before users do.
+  canary:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    continue-on-error: true
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: astral-sh/setup-uv@v6
+        with:
+          python-version: '3.13'
+
+      - name: Install newest FastMCP, ignoring our ceiling
+        run: |
+          uv venv
+          uv pip install fastmcp "sqlalchemy[asyncio]" aiosqlite pydantic \
+            pytest pytest-asyncio pytest-cov pytest-mock pytest-html
+          uv pip install --no-deps -e .
+          uv pip show fastmcp | grep -i '^version'
+
+      - name: Test
+        run: uv run --no-sync pytest -q --no-cov

CHANGELOG.md

@@ -5,6 +5,163 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Calendar Versioning](https://calver.org/) (YYYY.MM.DD).
 
+## [2026.09.27.4] - 2026-09-27
+
+Count errors that tools return as data instead of raising.
+
+### Added
+- Records have an `outcome`: `ok`, `soft_error` (the tool returned a result
+  flagged as a failure) or `error` (the tool raised). Soft errors get
+  `error_type="SoftError"` and an `error_message` built from the result, such
+  as `status=failed: disk full`, redacted and truncated to `max_error_chars`.
+- `soft_error_classifier(statuses=..., status_keys=..., flag_keys=...,
+  extra_statuses=...)` builds a classifier that flags dict results where `ok`
+  or `success` is `False`, where `status` or `state` is `error`, `failed` or
+  `failure`, or that the tool marked `isError` without raising.
+  `DEFAULT_RESULT_CLASSIFIER` is `soft_error_classifier()`.
+- `InstrumentationMiddleware(..., result_classifier=...)` takes any
+  `(tool, result) -> str | None`; `None` turns classification off. A
+  classifier that raises is logged and the call is recorded as `ok`.
+- `feedback_context()` rows include `outcome`.
+
+### Changed
+- `ok` is now `outcome == "ok"`, so it is also false for soft errors. Existing
+  `WHERE NOT ok` queries and error rates will rise; filter on
+  `outcome = 'error'` for exceptions only. `CallLink.ok` follows.
+- The package's own feedback tools answer `{"success": False, ...}` on failure,
+  so those calls are now recorded as soft errors.
+
+### Migration
+- New nullable, indexed `outcome` column (`String(16)`) on
+  `{prefix}tool_calls`. Hosts that manage the schema with Alembic need a
+  migration adding it. `create_tables=True` does not alter a table that
+  already exists, so add the column by hand there
+  (`ALTER TABLE ffb_tool_calls ADD COLUMN outcome VARCHAR(16)` plus an index).
+  Until the column exists, `DatabaseSink` writes fail and those records are
+  dropped (logged). Rows from earlier versions keep NULL.
+
+## [2026.09.27.3] - 2026-09-27
+
+Link a feedback item to the tool calls that preceded it.
+
+### Added
+- `InstrumentationMiddleware.capture_recent_calls(ctx, n=20)` returns the
+  calls that led up to now. It matches the same client session first
+  (`session` rule), then fills remaining slots with calls by the same
+  `user_sub` inside `window` (`user_window` rule, 15 minutes by default), and
+  each link records which rule matched.
+- Calls are kept in an in-memory buffer as they happen, so calls still
+  waiting in the sink queue count. With a `DatabaseSink` the lookup falls back
+  to the database, which covers calls from other workers and from before a
+  restart.
+- `link_feedback(ref, links)` stores links against a feedback id of any
+  format (`bug-7Q2X`, `42`) in a new `{prefix}feedback_call_links` table.
+  `build_metadata()` includes it; hosts that manage the schema with Alembic
+  need a new migration.
+- `feedback_context(ref)` returns the linked calls in order with tool,
+  outcome, error type and matching rule, filling in calls not yet written
+  from memory.
+- `add_feedback_tools(..., instrumentation=mw)`: `submit_feedback` links the
+  preceding calls automatically and returns `linked_calls` in its response.
+- `session_key(ctx)` gives a per-client key that stays stable across calls:
+  the HTTP `mcp-session-id` header when present, then one key per process for
+  stdio, then `ctx.session_id`.
+
+### Fixed
+- With `create_tables=True`, the background writer and `link_feedback` could
+  both run `create_all` at once and fail with "table already exists". Table
+  creation is now serialized by a lock.
+
+### Note
+- Clients on MCP protocol 2026-07-28 (Claude Code, FastMCP 4's `Client`)
+  open no HTTP sessions, so their calls link by user only. HTTP servers should
+  configure an `identity_resolver`. Stdio servers link by session with every
+  client.
+
+## [2026.09.27.2] - 2026-09-27
+
+### Fixed
+- `DatabaseSink` stored missing `args`/`result` (every `meta` mode row) as the
+  JSON literal `null`, so `WHERE args IS NULL` matched nothing. They are now
+  SQL `NULL`. No schema change; rows written by 2026.09.27.1 keep JSON `null`
+  and can be backfilled with
+  `UPDATE ffb_tool_calls SET args = NULL WHERE args = 'null'::jsonb` (same for
+  `result`). Reported from production by blender-mcp.
+
+## [2026.09.27.1] - 2026-09-27
+
+Per-call instrumentation for any FastMCP server.
+
+### Added
+- `fastmcp_feedback.instrumentation`: `InstrumentationMiddleware` and
+  `instrument(app)` record every tool call on the server (tool, timing,
+  outcome, original error type, session and request ids, argument and result
+  sizes). Modes `off`, `meta` (default) and `full`, set by argument or
+  `FEEDBACK_INSTRUMENTATION_MODE`; `meta_only_tools` keeps chosen tools at
+  `meta`.
+- Recording never slows or breaks a call: records reach sinks from a
+  background task through a bounded queue and are dropped (and counted) when it
+  is full. Sink and hook errors are logged, never raised; async hooks are cut
+  off after `hook_timeout`.
+- `Redactor`: secrets removed from arguments, results, error text and hook
+  output, by key at any depth and by value pattern (JWT, bearer, `sk-`,
+  GitHub, Slack, AWS, PyPI and `bmcp_` tokens, `password=...` in text).
+- Sinks: `JsonLinesSink` (stderr), `CallbackSink`, `MemorySink`, and
+  `DatabaseSink` on async SQLAlchemy. `DatabaseSink` accepts the host's
+  `AsyncEngine`, writes to a prefixed `ffb_tool_calls` table, never creates
+  tables unless asked, and `build_metadata()` plugs the table into a host's
+  Alembic `env.py`.
+- `identity_resolver` and `enricher` hooks fill `user_sub`, `caller_kind`,
+  `client_id`, `server_version` and free-form `identity`/`extra` fields.
+- `instrumentation` extra: `sqlalchemy[asyncio]` and `aiosqlite`.
+- CI covers FastMCP 3.x as well as 2.12, 2.14 and 4.x.
+
+## [2026.09.27] - 2026-09-27
+
+FastMCP 4 support, and a composition bug that affected every earlier release.
+
+### Fixed
+- `compose_feedback_services()` composed nothing on FastMCP 2.14. It called
+  `import_server()`, which became async in 2.14, without awaiting it, then
+  logged success anyway. On FastMCP 4, where `import_server()` no longer
+  exists, it raised `AttributeError`. It now uses `mount()`, which is
+  synchronous and available on every supported version.
+- The test suite could not start (a pytest-html hook with pytest-html not
+  installed), so it had not run since the package was split out. It runs
+  again: 407 tests.
+
+### Changed
+- Dependency is now `fastmcp>=2.12.2,<5`. Earlier releases had no ceiling,
+  so a fresh install picked up FastMCP 4 untested.
+- `examples/` moved into this repository and ships in the sdist.
+  `create_demo_server()` accepts an optional `database_url`. Examples list
+  and call tools through `fastmcp.Client`, which works on 2.x and 4.x.
+
+### Added
+- CI (Gitea Actions) runs the suite against FastMCP 2.12.2, 2.14.3 and 4.x
+  on every push and weekly, plus a non-blocking job against the newest
+  FastMCP with no ceiling.
+- A composition test using real servers instead of mocks.
+
+### Documentation
+- README rewritten against the code and every Python example executed.
+  Previous docs described things that do not exist: four tools (there are
+  five, including `delete_feedback`), `get_feedback_stats` (it is
+  `get_feedback_statistics`), `InsightsMixin`, an `enable_insights`
+  parameter, feedback types `bug_report`/`feature_request`/`general` (they
+  are `bug`/`feature`/`improvement`/`question`), and a
+  `new -> reviewing -> planned` workflow (it is
+  `open -> in_progress -> resolved -> closed`).
+- The default database is in-memory SQLite (`sqlite:///:memory:`), not
+  `sqlite:///feedback.db` as previously documented. Pass `database_url` to
+  keep feedback across restarts.
+
+## [2026.01.12.1] - 2026-01-12
+
+### Fixed
+- `ImportError` on install: `mixins/base.py` did not re-export the names
+  the other mixin modules import from it.
+
 ## [2026.01.12] - 2026-01-12
 
 ### Added

README.md

@@ -1,17 +1,19 @@
 # FastMCP Feedback
 
-Production-ready feedback collection system for [FastMCP](https://gofastmcp.com) servers.
+Instrumentation and QA feedback for [FastMCP](https://gofastmcp.com) servers.
 
-Add structured feedback collection (bug reports, feature requests, general feedback) to any FastMCP server with a single line of code.
+Record every tool call your server handles, and let people and models report problems with it, each with a line or two of code.
 
 ## Features
 
+- **Per-Call Instrumentation** - Middleware records every tool call (timing, outcome, identity, payload sizes) without slowing or breaking it
+- **Secret Redaction** - Tokens and passwords removed from recorded arguments, results and errors by default
 - **One-Line Integration** - Add feedback tools to any FastMCP server instantly
 - **Modular Mixins** - Selective tool registration for fine-grained control
 - **Multi-Database Support** - SQLite (dev), PostgreSQL, MySQL (production)
 - **Privacy-Compliant Analytics** - Optional usage insights without sensitive data
 - **Type-Safe** - Full Pydantic validation and type hints
-- **Well-Tested** - 97%+ test coverage
+- **Well-Tested** - 98% coverage, run against FastMCP 2.12, 2.14, 3.x and 4.x
 
 ## Installation
 
@@ -67,59 +69,304 @@ from fastmcp import FastMCP
 from fastmcp_feedback import add_feedback_tools
 
 app = FastMCP("My Server")
-add_feedback_tools(app)  # Adds 4 feedback tools instantly!
+add_feedback_tools(app, database_url="sqlite:///feedback.db")
 
-# That's it! Your server now has:
-# - submit_feedback: Collect bug reports, feature requests, general feedback
-# - list_feedback: Retrieve and filter feedback items
-# - get_feedback_stats: Aggregate statistics
-# - update_feedback_status: Workflow management (new → reviewing → resolved)
+# Your server now has five tools:
+# - submit_feedback: bug reports, feature requests, improvements, questions
+# - list_feedback: page through feedback, filtered by type or status
+# - get_feedback_statistics: counts by type and status, plus the last 7 days
+# - update_feedback_status: move an item through open -> in_progress -> resolved -> closed
+# - delete_feedback: remove an item
 ```
 
-### With Custom Database
+Pass a `database_url`. Without one the tools use an in-memory SQLite
+database, which is handy for tests but loses everything when the process exits.
+
+### PostgreSQL
 
 ```python
-# SQLite with custom path
-add_feedback_tools(app, database_url="sqlite:///./data/feedback.db")
-
-# PostgreSQL for production
-add_feedback_tools(app, database_url="postgresql://user:pass@localhost/mydb")
+add_feedback_tools(app, database_url="postgresql://user:pass@db.example.com/feedback")
 ```
 
-### With Analytics Enabled
+Install the driver with `uv add "fastmcp-feedback[postgresql]"`.
+
+### Prefixed Tool Names
 
 ```python
-add_feedback_tools(app, enable_insights=True)
-# Enables privacy-compliant usage tracking
+add_feedback_tools(app, database_url="sqlite:///feedback.db", prefix="support")
+# support_submit_feedback, support_list_feedback, ...
 ```
 
+The prefix and tool name are joined with `separator` (default `_`), so leave
+the trailing underscore off the prefix.
+
+### Usage Analytics
+
+```python
+from fastmcp_feedback import FeedbackInsights
+
+add_feedback_tools(
+    app,
+    database_url="sqlite:///feedback.db",
+    insights=FeedbackInsights(enabled=True),
+)
+```
+
+Analytics are off unless you pass `FeedbackInsights(enabled=True)` or set
+`FEEDBACK_INSIGHTS_ENABLED=true`. When enabled they record tool usage and
+submission metadata (type, lengths, timing), never feedback text or contact details.
+
+## Instrumentation
+
+Record every tool call on your server:
+
+```python
+from fastmcp import FastMCP
+from fastmcp_feedback.instrumentation import instrument
+
+app = FastMCP("My Server")
+instrument(app)  # one JSON line per tool call on stderr
+```
+
+Each record has the tool name, start time, duration, outcome and error type,
+session and request ids, argument and result sizes, and whatever your hooks
+add. The recording happens in middleware, so it covers every tool on the server,
+not just the feedback ones.
+
+It never slows or breaks a tool call. Records go to the sinks from a background
+task through a bounded queue, and when the queue is full they are dropped and
+counted instead of waited on. Errors in a sink or a hook are logged and swallowed.
+
+### Modes
+
+| Mode | Records |
+|------|---------|
+| `off` | Nothing |
+| `meta` (default) | Tool, timing, outcome, identity, payload sizes |
+| `full` | Also the arguments and result, redacted |
+
+Set it with `mode=` or the `FEEDBACK_INSTRUMENTATION_MODE` environment variable.
+`meta_only_tools={"run_code", "create_token"}` keeps chosen tools at `meta`
+even in `full` mode.
+
+### Redaction
+
+Secrets are removed from arguments, results, error messages and hook output
+before anything reaches a sink. It matches keys at any depth (`password`,
+`token`, `authorization`, `client_secret`, `*_api_key`, ...) and secret-shaped
+values anywhere in text (JWTs, `Bearer ...`, `sk-...`, GitHub, Slack, AWS and
+PyPI tokens, `password=...` in error text). Add your own:
+
+```python
+from fastmcp_feedback.instrumentation import Redactor, instrument
+
+instrument(
+    app,
+    mode="full",
+    redactor=Redactor(extra_keys=["license"], extra_patterns=[r"acme_[A-Za-z0-9]{32}"]),
+)
+```
+
+### Sinks
+
+```python
+from fastmcp_feedback.instrumentation import CallbackSink, DatabaseSink, JsonLinesSink, instrument
+
+instrument(app, [
+    JsonLinesSink(),                                   # stderr
+    DatabaseSink("sqlite+aiosqlite:///calls.db", create_tables=True),
+    CallbackSink(lambda records: print(len(records))),  # sync or async
+])
+```
+
+`DatabaseSink` needs the `instrumentation` extra
+(`uv add "fastmcp-feedback[instrumentation]"`), plus `asyncpg` for Postgres.
+
+### Using your own database and migrations
+
+Pass the `AsyncEngine` you already have. Records go to a `ffb_tool_calls`
+table (the prefix is configurable), and nothing is created at startup unless you
+ask. To manage the table with Alembic, add it to your `env.py`:
+
+```python
+from fastmcp_feedback.instrumentation import build_metadata
+
+target_metadata = [Base.metadata, build_metadata(prefix="ffb_")]
+```
+
+```python
+from fastmcp_feedback.instrumentation import DatabaseSink, instrument
+
+sink = DatabaseSink(engine, prefix="ffb_")  # your engine is never disposed
+instrument(app, [sink])
+```
+
+### Errors returned as data
+
+Many tools report failure in their result instead of raising, for example
+`{"status": "failed", "error": "disk full"}` or `{"success": False, ...}`. A
+result classifier catches these, so error rates count them. Each record has an
+`outcome`:
+
+| `outcome` | `ok` | Meaning |
+|-----------|------|---------|
+| `ok` | true | The call succeeded |
+| `soft_error` | false | The tool returned a result the classifier flagged |
+| `error` | false | The tool raised |
+
+Soft errors get `error_type="SoftError"` and an `error_message` such as
+`status=failed: disk full`, redacted and truncated like exception text.
+
+The default classifier flags a dict result when `ok` or `success` is exactly
+`False`, when `status` or `state` is `error`, `failed` or `failure` (any case),
+or when the tool marked the result as an MCP error (`isError`) without raising.
+The message comes from the first of `error`, `message`, `detail` and `reason`.
+Add your own status values, or pass any `(tool, result) -> str | None`:
+
+```python
+from fastmcp_feedback.instrumentation import instrument, soft_error_classifier
+
+# blender-mcp answers {"status": "unknown_target", ...} for a missing object
+instrument(app, result_classifier=soft_error_classifier(extra_statuses=("unknown_target",)))
+```
+
+```python
+from fastmcp_feedback.instrumentation import instrument
+
+def classify(tool, result):
+    """None means ok; a string marks a soft error and is its message."""
+    if tool == "search" and isinstance(result, dict) and result.get("hits") == []:
+        return "no hits"
+    return None
+
+instrument(app, result_classifier=classify)
+```
+
+`result_classifier=None` turns classification off. The classifier only sees
+calls that did not raise, gets the same payload the record stores (structured
+content when present), and if it raises, the error is logged and the call is
+recorded as `ok`. It never changes what the client receives.
+
+**Upgrading:** soft errors set `ok` to false, so existing `WHERE NOT ok` counts
+include them from this release on. Filter on `outcome = 'error'` for exceptions
+only. The `outcome` column is new in 2026.09.27.4; it is nullable, and rows
+written by earlier versions have NULL there. Hosts that manage the schema with
+Alembic need a migration adding it (with its index) to `ffb_tool_calls`, and a
+table made earlier by `create_tables=True` needs
+`ALTER TABLE ffb_tool_calls ADD COLUMN outcome VARCHAR(16)`, since existing
+tables are not altered. Until the column exists, database writes fail and
+those records are dropped (logged).
+
+### Identity and enrichment hooks
+
+```python
+from fastmcp_feedback.instrumentation import instrument
+
+def who(context):
+    """Who made this call. May be async."""
+    user = context.fastmcp_context  # read your auth state from here
+    return {"user_sub": "user-123", "caller_kind": "pat:7", "client_id": "cli"}
+
+async def enrich(tool, args, result, context):
+    """Extra indexed fields. May be async."""
+    return {"job_id": (result or {}).get("job_id"), "server_version": "1.4.0"}
+
+instrument(app, identity_resolver=who, enricher=enrich)
+```
+
+`user_sub`, `caller_kind` and `client_id` become columns; other identity keys
+go in `identity`. Enricher output goes in `extra`, except `server_version`,
+which has its own column. Async hooks that take longer than `hook_timeout`
+(0.25 s by default) are skipped for that call.
+
+### Linking feedback to the calls behind it
+
+When a model reports "the render tool hung", the report is far more useful with
+the calls that led up to it attached. Pass the middleware to
+`add_feedback_tools` and every `submit_feedback` does this for you:
+
+```python
+from fastmcp_feedback import add_feedback_tools
+from fastmcp_feedback.instrumentation import DatabaseSink, instrument
+
+mw = instrument(app, [DatabaseSink("sqlite+aiosqlite:///calls.db", create_tables=True)])
+add_feedback_tools(app, database_url="sqlite:///feedback.db", instrumentation=mw)
+# submit_feedback now answers {"feedback_id": ..., "linked_calls": 3, ...}
+```
+
+Read the linked calls back, in order, with their outcomes:
+
+```python
+for call in await mw.feedback_context(feedback_id):
+    print(call["position"], call["tool"], call["outcome"], call["error_type"], call["rule"])
+```
+
+If you have your own feedback tools, use the same pieces directly. Feedback ids
+can be anything (`bug-7Q2X`, `42`):
+
+```python
+from fastmcp import Context
+
+@app.tool
+async def report_problem(summary: str, ctx: Context) -> dict:
+    ref = save_my_feedback(summary)                 # your storage, your id
+    links = await mw.capture_recent_calls(ctx, n=20)
+    await mw.link_feedback(ref, links)
+    return {"id": ref, "linked_calls": len(links)}
+```
+
+Calls are matched in two ways, and each link records which one (`rule`):
+
+- `session`: the same MCP client session. Over HTTP this is the
+  `mcp-session-id`; over stdio it is the server process, which serves one client.
+- `user_window`: the same `user_sub` within the last 15 minutes (`window=`),
+  for clients that open a new session per call (personal access tokens, CI).
+  This needs an `identity_resolver`.
+
+Session matches come first, and user matches fill any remaining slots. Calls
+still waiting in the queue are included, and with a `DatabaseSink`, so are
+calls from other workers or from before a restart.
+
+Links live in a `ffb_feedback_call_links` table next to `ffb_tool_calls`.
+`build_metadata()` includes it, so hosts that manage the schema with Alembic
+need one new migration before calling `link_feedback`.
+
+**Stateless clients:** clients on MCP protocol 2026-07-28, including Claude
+Code and FastMCP 4's own `Client`, do not open sessions over HTTP. Their calls
+link by user only, so configure an `identity_resolver` for HTTP servers. Stdio
+servers link by session with every client.
+
+### Middleware order and shutdown
+
+FastMCP runs the first middleware added as the outermost. Call `instrument()`
+before adding other middleware to include their time and record calls they
+reject; call it last to time only the tool. On shutdown, `await mw.aclose()`
+flushes queued records and closes the sinks.
+
 ## Advanced Usage
 
 ### Mixin Architecture
 
-For fine-grained control over which tools are exposed:
+Pick only the tool groups you want to expose:
 
 ```python
 from fastmcp_feedback import (
-    SubmissionMixin,
-    RetrievalMixin,
     ManagementMixin,
+    RetrievalMixin,
+    SubmissionMixin,
     get_database_session,
 )
 
-db_session = get_database_session("sqlite:///feedback.db")
+db = get_database_session("sqlite:///feedback.db")
 
-# Only expose submission (public-facing)
-submission = SubmissionMixin(db_session)
-submission.register_tools(app)
+# Public server: submission only
+SubmissionMixin(db).register_tools(app)
 
-# Add retrieval with custom prefix
-retrieval = RetrievalMixin(db_session)
-retrieval.register_tools(app, prefix="analytics_")
+# Reporting tools under a prefix: analytics_list_feedback, ...
+RetrievalMixin(db).register_tools(app, prefix="analytics")
 
-# Admin-only management tools
-management = ManagementMixin(db_session)
-management.register_tools(admin_app, prefix="admin_")
+# Admin server gets the workflow tools
+ManagementMixin(db).register_tools(admin_app, prefix="admin")
 ```
 
 ### Available Mixins
@@ -127,18 +374,16 @@ management.register_tools(admin_app, prefix="admin_")
 | Mixin | Tools | Use Case |
 |-------|-------|----------|
 | `SubmissionMixin` | `submit_feedback` | Public feedback collection |
-| `RetrievalMixin` | `list_feedback`, `get_feedback_stats` | Dashboards, reporting |
-| `ManagementMixin` | `update_feedback_status` | Admin workflow |
-| `InsightsMixin` | `record_insight`, `get_insights_summary` | Analytics |
+| `RetrievalMixin` | `list_feedback`, `get_feedback_statistics` | Dashboards, reporting |
+| `ManagementMixin` | `update_feedback_status`, `delete_feedback` | Admin workflow |
 
 ### Multi-Tenant Pattern
 
 ```python
-# Each tenant gets isolated database
-def get_tenant_tools(tenant_id: str):
-    session = get_database_session(f"sqlite:///data/{tenant_id}.db")
-    submission = SubmissionMixin(session)
-    submission.register_tools(app, prefix=f"tenant_{tenant_id}_")
+# Each tenant gets its own database
+def add_tenant_tools(tenant_id: str):
+    db = get_database_session(f"sqlite:///data/{tenant_id}.db")
+    SubmissionMixin(db).register_tools(app, prefix=f"tenant_{tenant_id}")
 ```
 
 ### Server Composition
@@ -146,49 +391,72 @@ def get_tenant_tools(tenant_id: str):
 ```python
 from fastmcp_feedback import create_feedback_server
 
-# Create dedicated feedback server
-feedback_server = create_feedback_server("Feedback API")
+feedback_server = create_feedback_server(
+    "Feedback API", database_url="sqlite:///feedback.db"
+)
 
-# Compose into main application
-main_app.import_server(feedback_server, prefix="feedback_")
+# Tools appear on main_app as feedback_submit_feedback, feedback_list_feedback, ...
+main_app.mount(feedback_server, "feedback")
 ```
 
+`mount()` works on every supported FastMCP version. `import_server()` was
+removed in FastMCP 4.
+
+## Compatibility
+
+Tested against FastMCP 2.12, 2.14, 3.x and 4.x on every commit. The dependency is
+declared as `fastmcp>=2.12.2,<5`, and the ceiling moves up once a new major
+version passes the suite.
+
 ## API Reference
 
-### `add_feedback_tools(app, database_url=None, enable_insights=False)`
+### `add_feedback_tools(mcp, database_url=None, insights=None, prefix="", separator="_", instrumentation=None)`
 
-Add all feedback tools to a FastMCP server.
+Add all five feedback tools to a FastMCP server.
 
 **Parameters:**
-- `app`: FastMCP server instance
-- `database_url`: Database connection string (default: `sqlite:///feedback.db`)
-- `enable_insights`: Enable privacy-compliant analytics (default: `False`)
+- `mcp`: FastMCP server instance
+- `database_url`: SQLAlchemy URL. Defaults to in-memory SQLite (`sqlite:///:memory:`)
+- `insights`: a `FeedbackInsights` instance. Defaults to one with analytics disabled
+- `prefix`: prepended to every tool name
+- `separator`: placed between `prefix` and the tool name
+- `instrumentation`: the middleware returned by `instrument()`. When given,
+  `submit_feedback` links the calls that preceded it to the new item and
+  returns `linked_calls` (see [Linking feedback to the calls behind it](#linking-feedback-to-the-calls-behind-it))
 
 ### Feedback Types
 
-- `bug_report` - Bug reports with severity levels
-- `feature_request` - Feature suggestions with priority
-- `general` - General feedback and comments
+- `bug` - something is broken
+- `feature` - a new capability
+- `improvement` - make an existing capability better
+- `question` - unclear behavior or usage
 
 ### Status Workflow
 
-`new` → `reviewing` → `planned` → `in_progress` → `resolved` / `wont_fix`
+`open` → `in_progress` → `resolved` → `closed`
 
 ## Documentation
 
 Full documentation: https://fastmcp-feedback.l.supported.systems
 
-- [Quick Start Guide](https://fastmcp-feedback.l.supported.systems/guides/quickstart/)
-- [Architecture Overview](https://fastmcp-feedback.l.supported.systems/reference/architecture/)
+- [Quick Start Tutorial](https://fastmcp-feedback.l.supported.systems/tutorials/quickstart/)
+- [Architecture](https://fastmcp-feedback.l.supported.systems/explanation/architecture/)
 - [API Reference](https://fastmcp-feedback.l.supported.systems/reference/api/)
-- [Examples](https://fastmcp-feedback.l.supported.systems/examples/)
+- [Integration Patterns](https://fastmcp-feedback.l.supported.systems/how-to/integration-patterns/)
 
 ## Examples
 
-See the [fastmcp-feedback-showcase](https://git.supported.systems/fastmcp-feedback/fastmcp-example) repository for comprehensive examples demonstrating all capabilities:
+The [`examples/`](https://git.supported.systems/fastmcp-feedback/fastmcp-feedback/src/branch/main/examples)
+directory has runnable servers, each with a walkthrough:
+
+- `simple_integration.py`: the one-line integration
+- `mcp_server.py`: a production-style server configured from environment variables
+- `demo_server.py`: every feature, including server composition and sample data
 
 ```bash
-uvx fastmcp-feedback-showcase  # Run full demo
+git clone https://git.supported.systems/fastmcp-feedback/fastmcp-feedback.git
+cd fastmcp-feedback
+uv run python examples/simple_integration.py
 ```
 
 ## Contributing
@@ -236,5 +504,4 @@ MIT License - see [LICENSE](LICENSE) for details.
 - **Documentation**: https://fastmcp-feedback.l.supported.systems
 - **Repository**: https://git.supported.systems/fastmcp-feedback/fastmcp-feedback
 - **Issues**: https://git.supported.systems/fastmcp-feedback/fastmcp-feedback/issues
-- **Showcase**: https://git.supported.systems/fastmcp-feedback/fastmcp-example
 - **FastMCP**: https://gofastmcp.com

examples/README.md

@@ -0,0 +1,318 @@
+# FastMCP Feedback Examples
+
+This directory contains comprehensive examples demonstrating all features of the FastMCP Feedback system.
+
+## 🚀 Demo Server
+
+### `demo_server.py`
+**Complete demonstration server showcasing all features**
+
+**Features Demonstrated:**
+- ✅ Complete feedback collection workflow
+- ✅ Privacy-compliant analytics (GDPR-ready) 
+- ✅ Multi-database support (SQLite, PostgreSQL, MySQL)
+- ✅ Thread-safe operations with 97% test coverage
+- ✅ Server composition patterns
+- ✅ Performance monitoring and health checks
+- ✅ Sample data for testing
+
+**Available Tools:**
+- `submit_feedback` - Submit bug reports, feature requests, improvements, questions
+- `list_feedback` - Query and filter feedback with pagination
+- `get_feedback_statistics` - Analytics and aggregate metrics
+- `update_feedback_status` - Change status (open → in_progress → resolved)
+- `delete_feedback` - Remove feedback items
+- `get_system_info` - Version and dependency information
+- `setup_sample_data` - Populate with realistic demo data
+
+**Usage:**
+
+```bash
+# Run the demo server
+python examples/demo_server.py
+
+# Or with uv
+uv run examples/demo_server.py
+```
+
+**Claude Desktop MCP Configuration:**
+```json
+{
+  "mcpServers": {
+    "fastmcp-feedback-demo": {
+      "command": "uv",
+      "args": ["run", "examples/demo_server.py"],
+      "env": {
+        "LOG_LEVEL": "INFO"
+      }
+    }
+  }
+}
+```
+
+## 🏗️ Architecture Examples
+
+### `simple_integration.py`
+**Minimal integration example - 3 lines of code**
+
+```python
+from fastmcp import FastMCP
+from fastmcp_feedback import add_feedback_tools
+
+app = FastMCP("My App")
+add_feedback_tools(app, database_url="sqlite:///feedback.db")
+```
+
+### `advanced_configuration.py` 
+**Production-ready configuration with all features**
+
+```python
+from fastmcp_feedback import (
+    add_feedback_tools,
+    FeedbackInsights,
+    FeedbackDatabase
+)
+
+# Configure privacy-compliant analytics
+insights = FeedbackInsights(
+    enabled=True,
+    retention_days=90,
+    privacy_compliant=True
+)
+
+# Setup database with connection pooling
+database = FeedbackDatabase(
+    "postgresql://user:pass@localhost/feedback",
+    pool_size=20,
+    max_overflow=10
+)
+
+# Add tools with custom prefix
+add_feedback_tools(
+    app,
+    database=database,
+    insights=insights,
+    prefix="support_"
+)
+```
+
+### `server_composition.py`
+**Multi-server composition patterns**
+
+```python
+from fastmcp_feedback.feedback import (
+    create_submission_server,
+    create_management_server,
+    create_analytics_server
+)
+
+# Create specialized servers
+public_server = create_submission_server("Public Portal")
+admin_server = create_management_server("Admin Panel") 
+analytics = create_analytics_server("Dashboard")
+
+# Compose into main application
+main_app = FastMCP("Main Application")
+await main_app.import_server(public_server, prefix="public")
+await main_app.import_server(admin_server, prefix="admin")
+await main_app.import_server(analytics, prefix="stats")
+```
+
+## 🎯 Usage Patterns
+
+### Basic Feedback Workflow
+
+1. **Submit Feedback:**
+   ```python
+   # Submit a bug report
+   result = await submit_feedback({
+       "request": {
+           "type": "bug",
+           "title": "Login page not responsive on mobile",
+           "description": "The login form overflows on screens < 768px width",
+           "submitter": "user_123",
+           "contact_info": "user@example.com"
+       }
+   })
+   ```
+
+2. **List and Filter:**
+   ```python
+   # Get all open bug reports
+   bugs = await list_feedback({
+       "type_filter": "bug",
+       "status_filter": "open", 
+       "limit": 20
+   })
+   ```
+
+3. **Update Status:**
+   ```python
+   # Mark as in progress
+   await update_feedback_status({
+       "feedback_id": "123",
+       "new_status": "in_progress",
+       "note": "Engineering team investigating"
+   })
+   ```
+
+4. **Get Analytics:**
+   ```python
+   # View statistics
+   stats = await get_feedback_statistics()
+   # Returns: {"total_count": 45, "by_type": {"BUG": 12, "FEATURE": 20}, ...}
+   ```
+
+## 🔒 Privacy & Security Examples
+
+### Privacy-Compliant Configuration
+```python
+insights = FeedbackInsights(
+    enabled=True,                    # Enable analytics
+    retention_days=90,               # Auto-cleanup after 90 days
+    privacy_compliant=True,          # Enforce GDPR compliance
+    anonymize_identifiers=True,      # Hash user identifiers
+    exclude_contact_info=True        # Don't store in metrics
+)
+```
+
+### Security Features
+```python
+# Input validation with Pydantic
+from fastmcp_feedback.models import SubmitFeedbackRequest
+
+# SQL injection prevention via SQLAlchemy ORM
+# Rate limiting support (extend mixins)
+# Authentication ready (add middleware)
+```
+
+## 📊 Performance Examples
+
+### Connection Pooling
+```python
+database = FeedbackDatabase(
+    "postgresql://localhost/feedback",
+    pool_size=20,           # Base connections
+    max_overflow=10,        # Burst capacity
+    pool_timeout=30,        # Connection timeout
+    pool_recycle=3600       # Refresh every hour
+)
+```
+
+### Bulk Operations
+```python
+# Bulk status updates
+result = await bulk_update_status(
+    feedback_ids=["1", "2", "3", "4", "5"],
+    new_status="resolved"
+)
+```
+
+### Performance Monitoring
+```python
+# Built-in health checks
+health = await database.health_check()
+if not health:
+    # Trigger alerts
+    pass
+
+# Performance metrics
+stats = await get_database_stats()
+# Returns connection pool status, query times, etc.
+```
+
+## 🧪 Testing Examples
+
+### Unit Testing with FastMCP Feedback
+```python
+import pytest
+from fastmcp_feedback import FeedbackDatabase
+
+@pytest.mark.asyncio
+async def test_feedback_submission():
+    # Use in-memory database for testing
+    db = FeedbackDatabase("sqlite:///:memory:")
+    await db.initialize()
+    
+    # Test feedback submission
+    # ... test code here
+    
+    await db.close()
+```
+
+### Integration Testing
+```python
+# Test complete workflows
+async def test_complete_feedback_lifecycle():
+    # Submit → List → Update → Verify → Analytics
+    pass
+```
+
+## 🚀 Production Deployment Examples
+
+### Docker Configuration
+```dockerfile
+FROM python:3.11-slim
+
+WORKDIR /app
+COPY pyproject.toml .
+RUN pip install -e .
+
+COPY src/ src/
+COPY examples/ examples/
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s \
+  CMD python -c "import asyncio; from examples.health_check import check; asyncio.run(check())"
+
+CMD ["python", "examples/demo_server.py"]
+```
+
+### Environment Configuration
+```bash
+# Database
+DATABASE_URL=postgresql://user:pass@db:5432/feedback
+
+# Analytics
+INSIGHTS_ENABLED=true
+INSIGHTS_RETENTION_DAYS=90
+
+# Performance
+CONNECTION_POOL_SIZE=20
+MAX_OVERFLOW=10
+
+# Security
+RATE_LIMIT_REQUESTS=100
+RATE_LIMIT_WINDOW=3600
+```
+
+## 📚 Documentation
+
+Each example includes:
+- **Comprehensive comments** explaining every feature
+- **Error handling** patterns
+- **Performance considerations**
+- **Security best practices**  
+- **Testing approaches**
+- **Production deployment guidance**
+
+## 🎯 Getting Started
+
+1. **Start with the demo server** - `python examples/demo_server.py`
+2. **Connect to Claude Desktop** using the MCP configuration above
+3. **Try the tools** - submit feedback, query results, update status
+4. **Explore the code** - see how each feature is implemented
+5. **Customize for your needs** - adapt patterns to your use case
+
+## 🤝 Contributing Examples
+
+We welcome additional examples! Please:
+- Include comprehensive comments
+- Add error handling
+- Provide usage instructions  
+- Update this README
+- Add tests if applicable
+
+---
+
+**These examples demonstrate production-ready FastMCP Feedback integration with 97% test coverage and enterprise-grade reliability.**

examples/demo_server.md

@@ -0,0 +1,247 @@
+# FastMCP Feedback Demo Server
+
+**File:** `demo_server.py`  
+**Purpose:** Comprehensive demonstration of all FastMCP Feedback features  
+**Lines:** 396 lines of production-ready code  
+**Test Coverage:** Validated through 396+ comprehensive tests  
+
+## 🎯 Overview
+
+The demo server is a complete, production-ready FastMCP server that showcases every feature of the FastMCP Feedback system. It's designed to demonstrate real-world usage patterns and serve as a reference implementation for developers.
+
+## ✨ Features Demonstrated
+
+### Core Feedback System
+- **Complete CRUD Operations** - Submit, retrieve, update, delete feedback
+- **Type Support** - Bug reports, feature requests, improvements, questions
+- **Status Management** - Open → In Progress → Resolved → Closed workflow
+- **Rich Metadata** - Timestamps, submitter info, contact details
+
+### Advanced Capabilities
+- **Privacy-Compliant Analytics** - GDPR-ready insights collection
+- **Multi-Database Support** - SQLite for development, PostgreSQL for production
+- **Thread-Safe Operations** - Concurrent request handling
+- **Performance Monitoring** - Health checks and dependency validation
+- **Server Composition** - Multiple specialized server types
+
+### Data Integrity
+- **Input Validation** - Pydantic models with comprehensive validation
+- **Unicode Support** - Emojis, special characters, international text
+- **Timezone Handling** - UTC-aware timestamp management
+- **Whitespace Normalization** - Consistent data cleaning
+
+## 🛠️ Available Tools (7 Total)
+
+| Tool | Description | Use Case |
+|------|-------------|----------|
+| `submit_feedback` | Submit new feedback items | Users reporting bugs/requesting features |
+| `list_feedback` | Query and filter feedback | Viewing feedback with pagination/filtering |
+| `get_feedback_statistics` | Analytics and metrics | Dashboard data and reporting |
+| `update_feedback_status` | Change feedback status | Admin workflow management |
+| `delete_feedback` | Remove feedback items | Content moderation |
+| `get_system_info` | Version/dependency info | System diagnostics |
+| `setup_sample_data` | Populate demo data | Testing and demonstration |
+
+## 📊 Sample Data
+
+The demo server includes realistic sample data:
+
+```python
+sample_feedback = [
+    {
+        "type": "bug",
+        "title": "Memory leak in analytics processing",
+        "description": "Analytics worker consumes increasing memory over time...",
+        "submitter": "alice@example.com",
+        "contact_info": "alice@engineering.example.com"
+    },
+    {
+        "type": "feature", 
+        "title": "Add export functionality for feedback data",
+        "description": "Users need ability to export feedback data as CSV or JSON...",
+        "submitter": "product_manager",
+        "contact_info": "pm@example.com"
+    }
+    # ... 3 more realistic examples
+]
+```
+
+## 🚀 Usage
+
+### Direct Execution
+```bash
+# Run with Python
+python examples/demo_server.py
+
+# Run with uv (recommended)
+uv run examples/demo_server.py
+```
+
+### Claude Desktop Integration
+```json
+{
+  "mcpServers": {
+    "fastmcp-feedback-demo": {
+      "command": "uv",
+      "args": ["run", "examples/demo_server.py"],
+      "env": {
+        "DATABASE_URL": "sqlite:///feedback_demo.db",
+        "LOG_LEVEL": "INFO"
+      }
+    }
+  }
+}
+```
+
+### Docker Deployment
+```dockerfile
+FROM python:3.11-slim
+COPY . /app
+WORKDIR /app
+RUN pip install uv && uv sync
+CMD ["uv", "run", "examples/demo_server.py"]
+```
+
+## 🔧 Configuration Options
+
+### Environment Variables
+- `DATABASE_URL` - Database connection string (default: temporary SQLite)
+- `LOG_LEVEL` - Logging verbosity (DEBUG, INFO, WARNING, ERROR)
+- `INSIGHTS_ENABLED` - Enable/disable analytics collection
+- `RETENTION_DAYS` - Analytics data retention period
+
+### Database Support
+- **SQLite** - `sqlite:///path/to/database.db` (development)
+- **PostgreSQL** - `postgresql://user:pass@host:port/db` (production)
+- **In-Memory** - `sqlite:///:memory:` (testing)
+
+## 📈 Performance Characteristics
+
+### Throughput
+- **Concurrent Requests** - Handles 100+ concurrent submissions
+- **Database Performance** - Optimized queries with indexing
+- **Memory Usage** - Efficient async/await patterns
+
+### Scalability
+- **Horizontal Scaling** - Stateless design supports load balancing
+- **Database Scaling** - Connection pooling and query optimization
+- **Analytics Scaling** - Configurable retention and aggregation
+
+## 🧪 Testing Integration
+
+The demo server is thoroughly tested through:
+
+### Unit Tests
+- Tool registration and configuration
+- Sample data generation
+- Error handling scenarios
+
+### Integration Tests
+- End-to-end workflow validation
+- Database operations
+- Server composition patterns
+
+### Performance Tests
+- High-volume operations
+- Concurrent request handling
+- Memory usage monitoring
+
+## 🎓 Learning Examples
+
+### Basic Feedback Submission
+```python
+# Submit a bug report
+result = await submit_feedback({
+    "type": "bug",
+    "title": "Application crashes on startup",
+    "description": "Detailed error description...",
+    "submitter": "developer@company.com"
+})
+```
+
+### Advanced Filtering
+```python
+# Get all open bug reports from last week
+feedback = await list_feedback({
+    "type_filter": "bug",
+    "status_filter": "open", 
+    "limit": 50
+})
+```
+
+### Analytics Query
+```python
+# Get comprehensive statistics
+stats = await get_feedback_statistics()
+# Returns: total_count, by_type, by_status, recent_count
+```
+
+## 🔍 Architecture Insights
+
+### Server Composition Pattern
+```python
+# The demo server demonstrates server composition:
+main_server = FastMCP("Demo Server")
+feedback_server = create_feedback_server("Feedback Service")
+main_server.import_server(feedback_server, prefix="feedback_")
+```
+
+### Database Abstraction
+```python
+# Flexible database backend:
+database = FeedbackDatabase(database_url)
+await database.initialize()  # Auto-creates tables
+```
+
+### Analytics Integration
+```python
+# Privacy-compliant analytics:
+insights = FeedbackInsights(enabled=True, retention_days=90)
+insights.record_metric("feedback_submitted", metadata)
+```
+
+## 📚 Related Documentation
+
+- **[Simple Integration](simple_integration.md)** - Minimal 3-line integration
+- **[Production Server](mcp_server.md)** - Environment-configured deployment
+- **[Testing Guide](../tests/README.md)** - Comprehensive test documentation
+- **[Architecture Overview](../docs/architecture.md)** - System design details
+
+## 🤝 Contributing
+
+When modifying the demo server:
+
+1. **Maintain Compatibility** - Ensure all existing tools continue working
+2. **Update Documentation** - Keep this file synchronized with code changes
+3. **Add Tests** - Include test coverage for new features
+4. **Version Compatibility** - Support multiple FastMCP versions where possible
+
+## 🐛 Troubleshooting
+
+### Common Issues
+
+**Database Errors**
+```bash
+# Check database permissions
+ls -la feedback_demo.db
+# Reset database
+rm feedback_demo.db && python examples/demo_server.py
+```
+
+**Import Errors**
+```bash
+# Ensure development installation
+uv sync
+# Check Python path
+python -c "import fastmcp_feedback; print('OK')"
+```
+
+**Performance Issues**
+```bash
+# Enable debug logging
+LOG_LEVEL=DEBUG python examples/demo_server.py
+# Monitor memory usage
+ps aux | grep demo_server
+```
+
+This demo server represents the gold standard for FastMCP Feedback integration, demonstrating every feature with production-ready code patterns and comprehensive error handling.

examples/demo_server.py

@@ -0,0 +1,402 @@
+#!/usr/bin/env python3
+"""
+FastMCP Feedback Demo Server
+
+A comprehensive demonstration server that showcases all features of the
+FastMCP Feedback system including:
+- Complete feedback collection workflow
+- Privacy-compliant analytics
+- Multi-database support
+- Performance monitoring
+- Server composition patterns
+
+Usage:
+    # Run the demo server
+    python examples/demo_server.py
+
+    # Or use uv
+    uv run examples/demo_server.py
+
+    # Connect from Claude Desktop with this MCP server configuration:
+    # {
+    #   "feedback-demo": {
+    #     "command": "uv",
+    #     "args": ["run", "examples/demo_server.py"]
+    #   }
+    # }
+"""
+
+import asyncio
+import logging
+import sys
+import tempfile
+from datetime import UTC, datetime
+from pathlib import Path
+
+# Add the src directory to the path for development
+sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
+
+from fastmcp import Client, FastMCP
+
+from fastmcp_feedback import (
+    FeedbackDatabase,
+    FeedbackInsights,
+    add_feedback_tools,
+    check_dependencies,
+    get_version_info,
+)
+from fastmcp_feedback.feedback import (
+    create_analytics_server,
+    create_management_server,
+    create_submission_server,
+)
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    handlers=[logging.StreamHandler(), logging.FileHandler("feedback_demo.log")],
+)
+
+logger = logging.getLogger(__name__)
+
+
+def create_temp_database() -> str:
+    """Create a temporary SQLite database for the demo."""
+    temp_dir = tempfile.mkdtemp(prefix="fastmcp_feedback_demo_")
+    db_path = Path(temp_dir) / "demo_feedback.db"
+    return f"sqlite:///{db_path}"
+
+
+async def setup_demo_data(database: FeedbackDatabase) -> None:
+    """Populate the database with sample feedback for demonstration."""
+    logger.info("Setting up demo data...")
+
+    sample_feedback = [
+        {
+            "type": "bug",
+            "title": "Memory leak in analytics processing",
+            "description": "Analytics worker consumes increasing memory over time, eventually causing OOM errors.",
+            "submitter": "alice@example.com",
+            "contact_info": "alice@engineering.example.com",
+        },
+        {
+            "type": "feature",
+            "title": "Add export functionality for feedback data",
+            "description": "Users need ability to export feedback data as CSV or JSON for external analysis.",
+            "submitter": "product_manager",
+            "contact_info": "pm@example.com",
+        },
+        {
+            "type": "improvement",
+            "title": "Optimize database query performance",
+            "description": "List feedback queries are slow with large datasets. Need pagination and indexing improvements.",
+            "submitter": "performance_team",
+        },
+        {
+            "type": "question",
+            "title": "Best practices for rate limiting?",
+            "description": "What are recommended rate limits for feedback submission to prevent abuse?",
+            "submitter": "security_team",
+            "contact_info": "security@example.com",
+        },
+        {
+            "type": "bug",
+            "title": "Unicode handling in feedback titles",
+            "description": "Emojis and special characters cause encoding errors in feedback titles. 🐛",
+            "submitter": "qa_engineer",
+        },
+    ]
+
+    try:
+        await database.initialize()
+
+        # Import the model here to avoid circular imports
+        from fastmcp_feedback.models import Feedback, FeedbackStatus, FeedbackType
+
+        async with database.session() as session:
+            for item in sample_feedback:
+                feedback = Feedback(
+                    type=FeedbackType(item["type"]),
+                    status=FeedbackStatus.OPEN,
+                    title=item["title"],
+                    description=item["description"],
+                    submitter=item["submitter"],
+                    contact_info=item.get("contact_info"),
+                    created_at=datetime.now(UTC),
+                    updated_at=datetime.now(UTC),
+                )
+                session.add(feedback)
+
+            session.commit()
+            logger.info(f"Added {len(sample_feedback)} sample feedback items")
+
+    except Exception as e:
+        logger.error(f"Failed to setup demo data: {e}")
+        raise
+
+
+def create_demo_server(database_url: str | None = None) -> FastMCP:
+    """Create the main demo server with all feedback tools.
+
+    Uses a fresh temporary SQLite database unless database_url is given.
+    """
+    logger.info("🚀 Creating FastMCP Feedback Demo Server")
+
+    # Create the main server
+    server = FastMCP("FastMCP Feedback Demo")
+    server.description = (
+        "Comprehensive demonstration of FastMCP Feedback system featuring "
+        "complete feedback lifecycle, analytics, and multi-database support."
+    )
+
+    # Create temporary database for demo
+    database_url = database_url or create_temp_database()
+    logger.info(f"Using demo database: {database_url}")
+
+    # Configure insights for demo (privacy-compliant by design)
+    insights = FeedbackInsights(
+        enabled=True,
+        retention_days=30,  # Short retention for demo
+    )
+
+    # Add all feedback tools to the main server
+    add_feedback_tools(
+        server,
+        database_url=database_url,
+        insights=insights,
+        prefix="",  # No prefix for main tools
+    )
+
+    # Add version info tool
+    @server.tool(description="Get FastMCP Feedback version and dependency information")
+    def get_system_info() -> dict:
+        """Get comprehensive system information."""
+        version_info = get_version_info()
+        dependency_status = check_dependencies()
+
+        return {
+            "system": "FastMCP Feedback Demo Server",
+            "status": "running",
+            "started_at": datetime.now(UTC).isoformat(),
+            "versions": version_info,
+            "dependencies": dependency_status,
+            "demo_features": [
+                "Complete feedback lifecycle",
+                "Privacy-compliant analytics",
+                "Multi-database support",
+                "Performance monitoring",
+                "Sample data included",
+            ],
+        }
+
+    # Add demo data setup tool
+    @server.tool(description="Populate database with sample feedback data")
+    async def setup_sample_data() -> dict:
+        """Setup sample feedback data for demonstration."""
+        try:
+            database = FeedbackDatabase(database_url)
+            await setup_demo_data(database)
+            await database.close()
+
+            return {
+                "success": True,
+                "message": "Sample data created successfully",
+                "items_added": 5,
+                "data_includes": [
+                    "Bug reports with technical details",
+                    "Feature requests from product team",
+                    "Performance improvement suggestions",
+                    "Security questions",
+                    "Unicode handling issues",
+                ],
+            }
+        except Exception as e:
+            logger.error(f"Failed to setup sample data: {e}")
+            return {"success": False, "error": str(e)}
+
+    return server
+
+
+async def create_composed_demo_server() -> FastMCP:
+    """Create a demo server using server composition patterns."""
+    logger.info("🏗️  Creating Composed Demo Server")
+
+    # Create main application server
+    main_server = FastMCP("Composed Feedback System")
+    main_server.description = "Demonstration of FastMCP server composition patterns"
+
+    # Create temporary databases for different services
+    public_db = create_temp_database()
+    admin_db = create_temp_database()
+    analytics_db = create_temp_database()
+
+    # Create specialized servers
+    public_server = create_submission_server(
+        "Public Feedback Portal",
+        database_url=public_db,
+        insights=FeedbackInsights(enabled=True, retention_days=90),
+    )
+
+    admin_server = create_management_server(
+        "Admin Management Panel",
+        database_url=admin_db,
+        insights=FeedbackInsights(enabled=True, retention_days=365),
+    )
+
+    analytics_server = create_analytics_server(
+        "Analytics Dashboard",
+        database_url=analytics_db,
+        insights=FeedbackInsights(enabled=True, retention_days=30),
+    )
+
+    # Compose servers with prefixes
+    main_server.mount(public_server, "public")
+    main_server.mount(admin_server, "admin")
+    main_server.mount(analytics_server, "analytics")
+
+    # Add composition info tool
+    @main_server.tool(description="Get information about server composition")
+    def get_composition_info() -> dict:
+        """Get information about the composed server architecture."""
+        return {
+            "architecture": "Multi-server composition",
+            "servers": {
+                "public": {
+                    "purpose": "Feedback submission for end users",
+                    "tools": ["submit_feedback"],
+                    "database": "isolated",
+                },
+                "admin": {
+                    "purpose": "Management and moderation",
+                    "tools": [
+                        "update_feedback_status",
+                        "delete_feedback",
+                        "bulk_operations",
+                    ],
+                    "database": "isolated",
+                },
+                "analytics": {
+                    "purpose": "Reporting and insights",
+                    "tools": ["generate_reports", "export_data", "usage_statistics"],
+                    "database": "isolated",
+                },
+            },
+            "benefits": [
+                "Separation of concerns",
+                "Independent scaling",
+                "Role-based access control",
+                "Database isolation",
+                "Service modularity",
+            ],
+        }
+
+    return main_server
+
+
+async def run_demo_tests(server: FastMCP) -> dict:
+    """Run basic functionality tests on the demo server."""
+    logger.info("🧪 Running demo functionality tests...")
+
+    try:
+        # Go through a client so this works the same on every FastMCP version
+        async with Client(server) as client:
+            tool_names = [tool.name for tool in await client.list_tools()]
+
+            system_info = None
+            if "get_system_info" in tool_names:
+                result = await client.call_tool("get_system_info", {})
+                system_info = result.structured_content
+
+            setup_result = None
+            if "setup_sample_data" in tool_names:
+                result = await client.call_tool("setup_sample_data", {})
+                setup_result = result.structured_content
+
+        return {
+            "test_status": "passed",
+            "tools_available": len(tool_names),
+            "tool_names": tool_names,
+            "system_info": system_info,
+            "sample_data_setup": setup_result,
+            "test_timestamp": datetime.now(UTC).isoformat(),
+        }
+
+    except Exception as e:
+        logger.error(f"Demo tests failed: {e}")
+        return {
+            "test_status": "failed",
+            "error": str(e),
+            "test_timestamp": datetime.now(UTC).isoformat(),
+        }
+
+
+def print_demo_banner():
+    """Print an informative banner for the demo server."""
+    banner = """
+╔══════════════════════════════════════════════════════════════════╗
+║                    🚀 FastMCP Feedback Demo Server               ║
+║                                                                  ║
+║  Features Demonstrated:                                          ║
+║  • Complete feedback collection system                          ║
+║  • Privacy-compliant analytics (GDPR-ready)                     ║
+║  • Multi-database support (SQLite, PostgreSQL)                  ║
+║  • Thread-safe operations with 97% test coverage                ║
+║  • Server composition patterns                                  ║
+║  • Performance monitoring and health checks                     ║
+║                                                                  ║
+║  Available Tools:                                                ║
+║  📝 submit_feedback        - Submit bug reports & feature requests║
+║  📋 list_feedback          - Query and filter feedback          ║
+║  📊 get_feedback_statistics - Analytics and metrics             ║
+║  🔧 update_feedback_status - Change status (admin)              ║
+║  🗑️  delete_feedback       - Remove feedback items              ║
+║  ℹ️  get_system_info       - Version and dependency info        ║
+║  🎯 setup_sample_data      - Populate with demo data            ║
+║                                                                  ║
+║  Usage: Connect this as an MCP server in Claude Desktop         ║
+║  Configuration: See comments in this file                       ║
+╚══════════════════════════════════════════════════════════════════╝
+"""
+    print(banner)
+
+
+async def main():
+    """Main entry point for the demo server."""
+    print_demo_banner()
+
+    try:
+        # Check dependencies first
+        deps = check_dependencies()
+        if not deps["all_available"]:
+            logger.error("Missing required dependencies!")
+            for dep, info in deps["details"].items():
+                if not info["available"]:
+                    logger.error(f"  Missing: {dep} {info['required']}")
+            sys.exit(1)
+
+        logger.info("All dependencies satisfied ✅")
+
+        # Create the main demo server
+        server = create_demo_server()
+
+        # Run functionality tests
+        test_results = await run_demo_tests(server)
+        logger.info(f"Demo tests: {test_results['test_status']}")
+
+        if test_results["test_status"] == "passed":
+            logger.info(f"Server ready with {test_results['tools_available']} tools")
+
+        # Start the FastMCP server
+        logger.info("🎬 Starting FastMCP Feedback Demo Server...")
+        await server.run()
+
+    except KeyboardInterrupt:
+        logger.info("Demo server stopped by user")
+    except Exception as e:
+        logger.error(f"Demo server failed: {e}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/mcp_server.md

@@ -0,0 +1,396 @@
+# FastMCP Feedback Production Server
+
+**File:** `mcp_server.py`  
+**Purpose:** Production-ready MCP server with environment configuration  
+**Lines:** 89 lines of deployment-focused code  
+**Target:** Production and staging environments  
+
+## 🎯 Overview
+
+This is a production-ready MCP server launcher designed for real-world deployments. It demonstrates environment-based configuration, proper logging, and integration patterns suitable for staging and production environments.
+
+## ✨ Production Features
+
+### Environment Configuration
+- **Database URL** - Configurable via `DATABASE_URL` environment variable
+- **Insights Control** - Enable/disable analytics via `INSIGHTS_ENABLED`
+- **Logging Levels** - Configurable via `LOG_LEVEL` (DEBUG, INFO, WARNING, ERROR)
+- **Graceful Defaults** - Sensible fallbacks for missing configuration
+
+### Security Considerations
+- **No Hardcoded Secrets** - All sensitive data via environment variables
+- **Input Validation** - Comprehensive Pydantic validation
+- **Error Handling** - Graceful failure without exposing internals
+- **Audit Logging** - Configurable logging for compliance
+
+### Deployment Ready
+- **Docker Compatible** - Environment variable based configuration
+- **Kubernetes Ready** - ConfigMap and Secret integration
+- **Load Balancer Friendly** - Stateless design
+- **Health Checks** - Built-in system info endpoint
+
+## 🚀 Usage
+
+### Local Development
+```bash
+# Run with default settings
+python examples/mcp_server.py
+
+# Run with uv (recommended)
+uv run examples/mcp_server.py
+
+# Run with custom database
+DATABASE_URL="postgresql://localhost/feedback" uv run examples/mcp_server.py
+```
+
+### Environment Variables
+```bash
+# Required/Optional Configuration
+export DATABASE_URL="postgresql://user:pass@host:5432/feedback_prod"
+export INSIGHTS_ENABLED="true"
+export LOG_LEVEL="INFO"
+export RETENTION_DAYS="90"
+
+# Run the server
+uv run examples/mcp_server.py
+```
+
+## 🔧 Configuration Options
+
+### Database Configuration
+```bash
+# SQLite (development/testing)
+DATABASE_URL="sqlite:///feedback.db"
+
+# PostgreSQL (production)
+DATABASE_URL="postgresql://user:password@host:5432/database"
+
+# PostgreSQL with SSL (production)
+DATABASE_URL="postgresql://user:pass@host:5432/db?sslmode=require"
+
+# Environment-specific databases
+DATABASE_URL_DEV="sqlite:///feedback_dev.db"
+DATABASE_URL_STAGING="postgresql://staging_user:pass@staging.db/feedback"
+DATABASE_URL_PROD="postgresql://prod_user:pass@prod.db/feedback"
+```
+
+### Analytics Configuration
+```bash
+# Enable analytics with retention
+INSIGHTS_ENABLED="true"
+RETENTION_DAYS="90"
+
+# Disable analytics (GDPR compliance)
+INSIGHTS_ENABLED="false"
+
+# Different retention by environment
+RETENTION_DAYS_DEV="7"
+RETENTION_DAYS_STAGING="30" 
+RETENTION_DAYS_PROD="365"
+```
+
+### Logging Configuration
+```bash
+# Production logging
+LOG_LEVEL="INFO"
+LOG_FORMAT="json"  # For log aggregation
+
+# Development logging  
+LOG_LEVEL="DEBUG"
+LOG_FORMAT="standard"
+
+# Disable logging (not recommended)
+LOG_LEVEL="CRITICAL"
+```
+
+## 🐳 Docker Deployment
+
+### Dockerfile
+```dockerfile
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install uv for faster dependency management
+RUN pip install uv
+
+# Copy dependency files
+COPY pyproject.toml uv.lock ./
+
+# Install dependencies
+RUN uv sync --frozen
+
+# Copy application code
+COPY . .
+
+# Set environment variables
+ENV DATABASE_URL="postgresql://postgres:password@db:5432/feedback"
+ENV INSIGHTS_ENABLED="true"
+ENV LOG_LEVEL="INFO"
+
+# Expose port (if needed)
+EXPOSE 8000
+
+# Run the MCP server
+CMD ["uv", "run", "examples/mcp_server.py"]
+```
+
+### Docker Compose
+```yaml
+version: '3.8'
+
+services:
+  feedback-server:
+    build: .
+    environment:
+      - DATABASE_URL=postgresql://postgres:password@db:5432/feedback
+      - INSIGHTS_ENABLED=true
+      - LOG_LEVEL=INFO
+      - RETENTION_DAYS=90
+    depends_on:
+      - db
+    restart: unless-stopped
+
+  db:
+    image: postgres:15
+    environment:
+      - POSTGRES_DB=feedback
+      - POSTGRES_USER=postgres
+      - POSTGRES_PASSWORD=password
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+    restart: unless-stopped
+
+volumes:
+  postgres_data:
+```
+
+## ☸️ Kubernetes Deployment
+
+### ConfigMap
+```yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: feedback-config
+data:
+  LOG_LEVEL: "INFO"
+  INSIGHTS_ENABLED: "true"
+  RETENTION_DAYS: "90"
+```
+
+### Secret
+```yaml
+apiVersion: v1
+kind: Secret
+metadata:
+  name: feedback-secrets
+type: Opaque
+stringData:
+  DATABASE_URL: "postgresql://user:password@postgres-service:5432/feedback"
+```
+
+### Deployment
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: feedback-server
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: feedback-server
+  template:
+    metadata:
+      labels:
+        app: feedback-server
+    spec:
+      containers:
+      - name: feedback-server
+        image: fastmcp-feedback:latest
+        ports:
+        - containerPort: 8000
+        envFrom:
+        - configMapRef:
+            name: feedback-config
+        - secretRef:
+            name: feedback-secrets
+        resources:
+          requests:
+            memory: "256Mi"
+            cpu: "250m"
+          limits:
+            memory: "512Mi"
+            cpu: "500m"
+```
+
+## 🎛️ Claude Desktop Configuration
+
+### Development
+```json
+{
+  "mcpServers": {
+    "fastmcp-feedback-dev": {
+      "command": "uv",
+      "args": ["run", "examples/mcp_server.py"],
+      "env": {
+        "DATABASE_URL": "sqlite:///feedback_dev.db",
+        "INSIGHTS_ENABLED": "true",
+        "LOG_LEVEL": "DEBUG"
+      }
+    }
+  }
+}
+```
+
+### Production
+```json
+{
+  "mcpServers": {
+    "fastmcp-feedback-prod": {
+      "command": "uv",
+      "args": ["run", "examples/mcp_server.py"],
+      "env": {
+        "DATABASE_URL": "postgresql://user:pass@prod.db/feedback",
+        "INSIGHTS_ENABLED": "true",
+        "LOG_LEVEL": "INFO",
+        "RETENTION_DAYS": "365"
+      }
+    }
+  }
+}
+```
+
+## 📊 Monitoring & Observability
+
+### Health Checks
+```python
+# Built-in health check endpoint
+await get_system_info()
+# Returns: version, dependencies, database_status, insights_status
+```
+
+### Logging Format
+```json
+{
+  "timestamp": "2024-01-15T10:30:00Z",
+  "level": "INFO",
+  "logger": "fastmcp_feedback.tools",
+  "message": "Feedback submitted successfully",
+  "feedback_id": "123",
+  "submitter_hash": "a1b2c3",
+  "type": "bug"
+}
+```
+
+### Metrics Collection
+- **Request Counts** - Total submissions, retrievals, updates
+- **Error Rates** - Failed operations and reasons  
+- **Performance** - Response times and database query duration
+- **Usage Patterns** - Popular feedback types, status distributions
+
+## 🔍 Troubleshooting
+
+### Common Issues
+
+**Database Connection Errors**
+```bash
+# Check database connectivity
+DATABASE_URL="postgresql://..." python -c "
+import asyncio
+from fastmcp_feedback import FeedbackDatabase
+async def test():
+    db = FeedbackDatabase('$DATABASE_URL')
+    await db.initialize()
+    print('✅ Database connection successful')
+asyncio.run(test())
+"
+```
+
+**Environment Variable Issues**
+```bash
+# Verify environment variables
+env | grep -E "(DATABASE_URL|INSIGHTS_ENABLED|LOG_LEVEL)"
+
+# Test with explicit variables
+DATABASE_URL="sqlite:///test.db" \
+INSIGHTS_ENABLED="false" \
+LOG_LEVEL="DEBUG" \
+python examples/mcp_server.py
+```
+
+**Permission Issues**
+```bash
+# Check file permissions
+ls -la feedback.db
+
+# Check directory permissions
+ls -ld $(dirname $(readlink -f feedback.db))
+
+# Fix permissions
+chmod 644 feedback.db
+chmod 755 $(dirname $(readlink -f feedback.db))
+```
+
+### Performance Tuning
+
+**Database Optimization**
+```bash
+# PostgreSQL connection pooling
+DATABASE_URL="postgresql://user:pass@host/db?pool_size=20&max_overflow=30"
+
+# SQLite optimization
+DATABASE_URL="sqlite:///feedback.db?journal_mode=WAL&synchronous=NORMAL"
+```
+
+**Memory Optimization**
+```bash
+# Limit analytics retention
+RETENTION_DAYS="30"
+
+# Disable insights in memory-constrained environments
+INSIGHTS_ENABLED="false"
+```
+
+## 🚀 Scaling Considerations
+
+### Horizontal Scaling
+- **Stateless Design** - No server-side session storage
+- **Database Sharing** - Multiple instances can share database
+- **Load Balancer Compatible** - Standard HTTP/JSON interfaces
+
+### Database Scaling
+- **Read Replicas** - Use read-only database URLs for list operations
+- **Connection Pooling** - Configure appropriate pool sizes
+- **Query Optimization** - Built-in indexing and pagination
+
+### Caching Strategy
+```python
+# Redis caching for statistics (optional)
+REDIS_URL="redis://localhost:6379/0"
+CACHE_TTL="300"  # 5 minutes
+
+# Memcached alternative
+MEMCACHED_SERVERS="localhost:11211"
+```
+
+## 📚 Related Documentation
+
+- **[Demo Server](demo_server.md)** - Complete feature showcase
+- **[Simple Integration](simple_integration.md)** - Minimal integration
+- **[Architecture Guide](../docs/architecture.md)** - System design
+- **[Security Guide](../docs/security.md)** - Security best practices
+
+## 🤝 Contributing
+
+When modifying the production server:
+
+1. **Maintain Backward Compatibility** - Don't break existing environment variables
+2. **Add Configuration Validation** - Validate new environment variables
+3. **Update Documentation** - Keep this file synchronized with changes
+4. **Test in Multiple Environments** - Docker, Kubernetes, bare metal
+5. **Consider Security Implications** - Audit any configuration changes
+
+This production server demonstrates enterprise-ready deployment patterns while maintaining the simplicity and power of the FastMCP Feedback system.

examples/mcp_server.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python3
+"""
+FastMCP Feedback - MCP Server Launcher
+
+This script provides a clean MCP server launcher that can be easily
+configured in Claude Desktop or other MCP clients.
+
+Usage:
+    # Direct execution
+    python examples/mcp_server.py
+
+    # With uv
+    uv run examples/mcp_server.py
+
+    # Claude Desktop configuration:
+    {
+      "mcpServers": {
+        "fastmcp-feedback": {
+          "command": "uv",
+          "args": ["run", "examples/mcp_server.py"],
+          "env": {
+            "DATABASE_URL": "sqlite:///feedback.db",
+            "INSIGHTS_ENABLED": "true",
+            "LOG_LEVEL": "INFO"
+          }
+        }
+      }
+    }
+"""
+
+import asyncio
+import logging
+import os
+import sys
+from pathlib import Path
+
+# Add the src directory to the path for development
+sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
+
+from fastmcp import Client, FastMCP
+
+from fastmcp_feedback import FeedbackInsights, add_feedback_tools
+
+# Configure logging based on environment
+log_level = os.getenv("LOG_LEVEL", "INFO").upper()
+logging.basicConfig(
+    level=getattr(logging, log_level),
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+)
+
+logger = logging.getLogger(__name__)
+
+
+def create_production_server() -> FastMCP:
+    """Create a production-ready FastMCP Feedback server."""
+    # Server configuration
+    server_name = os.getenv("SERVER_NAME", "FastMCP Feedback Server")
+    database_url = os.getenv("DATABASE_URL", "sqlite:///feedback.db")
+
+    # Create server
+    server = FastMCP(server_name)
+    server.description = "Production FastMCP Feedback collection system"
+
+    # Configure insights
+    insights_enabled = os.getenv("INSIGHTS_ENABLED", "true").lower() == "true"
+    retention_days = int(os.getenv("INSIGHTS_RETENTION_DAYS", "90"))
+
+    insights = FeedbackInsights(enabled=insights_enabled, retention_days=retention_days)
+
+    # Add feedback tools
+    tool_prefix = os.getenv("TOOL_PREFIX", "")
+    add_feedback_tools(
+        server, database_url=database_url, insights=insights, prefix=tool_prefix
+    )
+
+    logger.info(f"Server '{server_name}' configured")
+    logger.info(f"Database: {database_url}")
+    logger.info(f"Insights: {'enabled' if insights_enabled else 'disabled'}")
+    logger.info(f"Tool prefix: '{tool_prefix}' (empty = no prefix)")
+
+    return server
+
+
+async def main():
+    """Main entry point for the MCP server."""
+    try:
+        logger.info("🚀 Starting FastMCP Feedback Server")
+
+        # Create and start server
+        server = create_production_server()
+
+        # Show available tools
+        async with Client(server) as client:
+            tools = await client.list_tools()
+        logger.info(f"Server ready with {len(tools)} tools:")
+        for tool in tools:
+            logger.info(f"  • {tool.name}")
+
+        # Start the server
+        await server.run()
+
+    except KeyboardInterrupt:
+        logger.info("Server stopped by user")
+    except Exception as e:
+        logger.error(f"Server failed: {e}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/simple_integration.md

@@ -0,0 +1,274 @@
+# Simple FastMCP Feedback Integration
+
+**File:** `simple_integration.py`  
+**Purpose:** Minimal 3-line integration example  
+**Lines:** 48 lines of clean, documented code  
+**Complexity:** Beginner-friendly  
+
+## 🎯 Overview
+
+This example demonstrates the absolute minimal integration of FastMCP Feedback into any FastMCP server. With just 3 lines of code, you get a complete, production-ready feedback system.
+
+## ✨ Key Features
+
+### Minimal Code
+```python
+# This is all you need - 3 lines of code!
+app = FastMCP("Simple Feedback App")
+add_feedback_tools(app, database_url="sqlite:///simple_feedback.db")
+```
+
+### Automatic Tool Registration
+The integration automatically adds 5 production-ready tools:
+- ✅ `submit_feedback` - Submit bug reports & feature requests
+- ✅ `list_feedback` - Query and filter feedback
+- ✅ `get_feedback_statistics` - Analytics and metrics
+- ✅ `delete_feedback` - Remove feedback items  
+- ✅ `update_feedback_status` - Change status (admin)
+
+### Zero Configuration
+- **Database** - Automatically creates SQLite database
+- **Schema** - Auto-generates tables on first run
+- **Validation** - Built-in Pydantic input validation
+- **Error Handling** - Graceful failure scenarios
+
+## 🚀 Usage
+
+### Direct Execution
+```bash
+# Run the example
+python examples/simple_integration.py
+
+# With uv (recommended)
+uv run examples/simple_integration.py
+```
+
+### Expected Output
+```
+🚀 Simple FastMCP Feedback Integration
+==================================================
+✅ Feedback system added!
+📊 Available tools:
+  • submit_feedback - Submit feedback to the system
+  • get_feedback_statistics - Get feedback statistics and analytics
+  • list_feedback - List feedback items with optional filtering
+  • delete_feedback - Delete feedback item
+  • update_feedback_status - Update feedback status
+
+🎯 Total tools: 5
+
+🎬 Starting server...
+   Connect this as an MCP server in Claude Desktop
+```
+
+## 📋 Integration Steps
+
+### Step 1: Install Dependencies
+```bash
+# Using uv (recommended)
+uv add fastmcp-feedback
+
+# Using pip
+pip install fastmcp-feedback
+```
+
+### Step 2: Add to Your Server
+```python
+from fastmcp import FastMCP
+from fastmcp_feedback import add_feedback_tools
+
+# Your existing FastMCP server
+app = FastMCP("My Awesome App")
+
+# Add your existing tools here...
+# app.add_tool(my_custom_tool)
+
+# Add complete feedback system in one line
+add_feedback_tools(app, database_url="sqlite:///feedback.db")
+```
+
+### Step 3: Configure Claude Desktop
+```json
+{
+  "mcpServers": {
+    "my-app-with-feedback": {
+      "command": "python",
+      "args": ["my_server.py"]
+    }
+  }
+}
+```
+
+## 🔧 Customization Options
+
+### Database Configuration
+```python
+# SQLite (development)
+add_feedback_tools(app, database_url="sqlite:///feedback.db")
+
+# PostgreSQL (production) 
+add_feedback_tools(app, database_url="postgresql://user:pass@host/db")
+
+# In-memory (testing)
+add_feedback_tools(app, database_url="sqlite:///:memory:")
+```
+
+### Analytics Configuration
+```python
+from fastmcp_feedback import add_feedback_tools, FeedbackInsights
+
+# Enable analytics with custom retention
+insights = FeedbackInsights(enabled=True, retention_days=30)
+add_feedback_tools(app, insights=insights)
+```
+
+### Tool Prefixing
+```python
+# Add with prefix to avoid naming conflicts
+add_feedback_tools(app, prefix="support_")
+# Creates: support_submit_feedback, support_list_feedback, etc.
+```
+
+## 📊 What You Get
+
+### Complete CRUD Operations
+```python
+# Users can submit feedback
+await submit_feedback({
+    "type": "bug",
+    "title": "App crashes on login", 
+    "description": "Detailed error description",
+    "submitter": "user@example.com"
+})
+
+# Admins can manage feedback
+await update_feedback_status({
+    "feedback_id": "123",
+    "new_status": "resolved"
+})
+
+# Analytics for insights
+stats = await get_feedback_statistics()
+# Returns: total_count, by_type, by_status, recent_count
+```
+
+### Input Validation
+- **Type Validation** - Must be: bug, feature, improvement, question
+- **Required Fields** - title, description, submitter cannot be empty
+- **Length Limits** - title ≤ 255 chars, description ≤ 10,000 chars
+- **Format Validation** - email validation for contact_info (optional)
+
+### Database Schema
+Automatically creates:
+```sql
+CREATE TABLE feedback (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    type VARCHAR(50) NOT NULL,
+    title VARCHAR(255) NOT NULL,
+    description TEXT NOT NULL,
+    submitter VARCHAR(255) NOT NULL,
+    contact_info VARCHAR(255),
+    status VARCHAR(50) NOT NULL DEFAULT 'open',
+    created_at DATETIME NOT NULL,
+    updated_at DATETIME NOT NULL
+);
+```
+
+## 🎓 Learning Examples
+
+### Basic Usage Pattern
+```python
+#!/usr/bin/env python3
+from fastmcp import FastMCP
+from fastmcp_feedback import add_feedback_tools
+
+app = FastMCP("My App")
+
+# Your custom tools
+@app.tool()
+def my_custom_feature():
+    return "Custom functionality"
+
+# Add feedback system
+add_feedback_tools(app)
+
+# Run server
+app.run()
+```
+
+### Error Handling
+```python
+try:
+    add_feedback_tools(app, database_url="invalid://url")
+except Exception as e:
+    print(f"Failed to add feedback tools: {e}")
+    # Graceful fallback or alternative configuration
+```
+
+## 🔍 Under the Hood
+
+### What `add_feedback_tools()` Does
+1. **Creates Database Instance** - Initializes FeedbackDatabase with provided URL
+2. **Sets Up Insights** - Configures optional analytics collection
+3. **Registers Tools** - Adds 5 tools to your FastMCP server
+4. **Validates Configuration** - Ensures database connectivity
+5. **Logs Success** - Confirms successful integration
+
+### Tool Implementation Pattern
+```python
+# Each tool is implemented as an async function
+@app.tool(description="Submit feedback to the system")
+async def submit_feedback(request: dict) -> dict:
+    # Validate input with Pydantic
+    validated_request = SubmitFeedbackRequest(**request)
+    
+    # Store in database
+    feedback = await database.create_feedback(validated_request)
+    
+    # Record analytics (if enabled)
+    insights.record_metric("feedback_submitted", metadata)
+    
+    return {"success": True, "feedback_id": feedback.id}
+```
+
+## 🚀 Next Steps
+
+### For More Features
+If you need advanced capabilities, see:
+- **[Demo Server](demo_server.md)** - Complete feature showcase
+- **[Production Server](mcp_server.md)** - Environment configuration
+- **[Architecture Guide](../docs/architecture.md)** - System design
+
+### For Customization
+```python
+# Use individual mixins for fine-grained control
+from fastmcp_feedback.mixins import SubmissionMixin, RetrievalMixin
+
+submission = SubmissionMixin(database, insights)
+submission.register_tools(app, prefix="feedback_")
+```
+
+### For Testing
+```python
+# Test your integration
+import pytest
+from fastmcp_feedback import add_feedback_tools
+
+@pytest.mark.asyncio
+async def test_feedback_integration():
+    app = FastMCP("Test App")
+    add_feedback_tools(app, database_url="sqlite:///:memory:")
+    
+    tools = await app.get_tools()
+    assert "submit_feedback" in tools
+```
+
+## 🤝 Contributing
+
+When modifying this example:
+1. **Keep It Simple** - This is the "Hello World" of FastMCP Feedback
+2. **Document Changes** - Update this file with any modifications
+3. **Test Integration** - Ensure the 3-line pattern still works
+4. **Preserve Clarity** - Maintain beginner-friendly explanations
+
+This simple integration example proves that adding a complete, production-ready feedback system to any FastMCP server requires just 3 lines of code while providing enterprise-grade functionality.

examples/simple_integration.py

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""
+Simple FastMCP Feedback Integration Example
+
+This demonstrates the absolute minimal integration - just 3 lines of code
+to add a complete feedback system to any FastMCP server.
+
+Usage:
+    python examples/simple_integration.py
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+# Add the src directory to the path for development
+sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
+
+from fastmcp import Client, FastMCP
+
+from fastmcp_feedback import add_feedback_tools
+
+
+async def main():
+    """Minimal FastMCP Feedback integration example."""
+
+    print("🚀 Simple FastMCP Feedback Integration")
+    print("=" * 50)
+
+    # This is all you need - 3 lines of code!
+    app = FastMCP("Simple Feedback App")
+    add_feedback_tools(app, database_url="sqlite:///simple_feedback.db")
+
+    print("✅ Feedback system added!")
+    print("📊 Available tools:")
+
+    # Show what tools were added
+    async with Client(app) as client:
+        tools = await client.list_tools()
+    for tool in tools:
+        print(f"  • {tool.name} - {tool.description}")
+
+    print(f"\n🎯 Total tools: {len(tools)}")
+    print("\n🎬 Starting server...")
+    print("   Connect this as an MCP server in Claude Desktop")
+
+    # Start the server
+    await app.run()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/test_demo.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+Test script to verify demo server functionality without running the full MCP server.
+"""
+
+import asyncio
+import sys
+from pathlib import Path
+
+# Add the src directory to the path for development
+sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
+
+sys.path.insert(0, str(Path(__file__).parent))
+from demo_server import create_demo_server
+from fastmcp import Client
+
+
+async def test_demo_functionality():
+    """Test the demo server tools without running the MCP server."""
+    print("🧪 Testing FastMCP Feedback Demo Functionality")
+    print("=" * 55)
+
+    try:
+        # Create the demo server
+        server = create_demo_server()
+
+        async with Client(server) as client:
+            # Get available tools
+            tools = {tool.name: tool for tool in await client.list_tools()}
+            print(f"✅ Server created with {len(tools)} tools")
+
+            # List available tools
+            print("\n📋 Available Tools:")
+            for name, tool in tools.items():
+                print(f"  • {name}: {tool.description}")
+
+            # Test system info tool
+            if "get_system_info" in tools:
+                print("\n🔍 Testing system info...")
+                result = await client.call_tool("get_system_info", {})
+                info = result.structured_content
+                print(f"  Version: {info['versions']['fastmcp_feedback']}")
+                print(f"  Python: {info['versions']['python']}")
+                print(f"  Features: {len(info['demo_features'])}")
+
+            # Test sample data setup
+            if "setup_sample_data" in tools:
+                print("\n📊 Testing sample data setup...")
+                result = await client.call_tool("setup_sample_data", {})
+                data_result = result.structured_content
+                if data_result["success"]:
+                    print(f"  ✅ Added {data_result['items_added']} sample items")
+                else:
+                    print(f"  ❌ Failed: {data_result['error']}")
+
+            # Test feedback listing
+            if "list_feedback" in tools:
+                print("\n📝 Testing feedback listing...")
+                result = await client.call_tool("list_feedback", {})
+                feedback_data = result.structured_content
+                print(f"  Found {len(feedback_data['feedback'])} feedback items")
+
+                # Show first item details
+                if feedback_data["feedback"]:
+                    first = feedback_data["feedback"][0]
+                    print(f"  First item: {first['type']} - {first['title']}")
+
+            # Test statistics
+            if "get_feedback_statistics" in tools:
+                print("\n📈 Testing statistics...")
+                result = await client.call_tool("get_feedback_statistics", {})
+                stats = result.structured_content
+                print(f"  Total items: {stats['total_count']}")
+                print(f"  By type: {stats['by_type']}")
+                print(f"  By status: {stats['by_status']}")
+
+            print("\n🎉 All tests passed! Demo server is working correctly.")
+        return True
+
+    except Exception as e:
+        print(f"\n❌ Test failed: {e}")
+        import traceback
+
+        traceback.print_exc()
+        return False
+
+
+if __name__ == "__main__":
+    success = asyncio.run(test_demo_functionality())
+    sys.exit(0 if success else 1)

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "fastmcp-feedback"
-version = "2026.01.12.1"  # YYYYMMDD.patch versioning - update for each release
+version = "2026.09.27.4"  # YYYYMMDD.patch versioning - update for each release
 description = "Production-ready feedback collection system for FastMCP servers"
 readme = "README.md"
 license = "MIT"
@@ -43,27 +43,35 @@ classifiers = [
 ]
 requires-python = ">=3.11"
 dependencies = [
-    "fastmcp>=2.12.2",
+    "fastmcp>=2.12.2,<5",  # CI tests 2.12, 2.14 and 4.0; raise the ceiling once 5.x passes
     "sqlalchemy>=2.0.43",
     "pydantic>=2.11.7"
 ]
 
 [project.optional-dependencies]
 postgresql = ["psycopg2-binary>=2.9.0"]
+# Async database sink for per-call instrumentation. Postgres hosts add asyncpg.
+instrumentation = ["sqlalchemy[asyncio]>=2.0.43", "aiosqlite>=0.22.1"]
 mysql = ["pymysql>=1.1.0"]
 dev = [
+    "sqlalchemy[asyncio]>=2.0.43",
+    "aiosqlite>=0.22.1",
     "pytest>=8.2.0",
     "pytest-asyncio>=0.23.0",
     "pytest-cov>=5.0.0",
     "pytest-mock>=3.12.0",
+    "pytest-html>=4.2.0",
     "ruff>=0.1.0",
     "mypy>=1.7.0",
 ]
 test = [
+    "sqlalchemy[asyncio]>=2.0.43",
+    "aiosqlite>=0.22.1",
     "pytest>=8.2.0",
     "pytest-asyncio>=0.23.0",
     "pytest-cov>=5.0.0",
     "pytest-mock>=3.12.0",
+    "pytest-html>=4.2.0",
 ]
 all = ["fastmcp-feedback[postgresql,mysql,dev]"]
 
@@ -81,6 +89,7 @@ packages = ["src/fastmcp_feedback"]
 include = [
     "/src",
     "/tests",
+    "/examples",
     "README.md",
     "LICENSE",
     "CHANGELOG.md",
@@ -142,7 +151,13 @@ src = ["src", "tests"]
 
 [tool.ruff.lint]
 select = ["E", "W", "F", "UP", "B", "SIM", "I", "N", "C4"]
-ignore = ["E501", "B008"]
+ignore = [
+    "E501",
+    "B008",
+    # StrEnum changes str()/format() output of FeedbackType/FeedbackStatus,
+    # which reach the database and API responses. Worth doing, not silently.
+    "UP042",
+]
 
 [tool.ruff.lint.per-file-ignores]
 "tests/**/*.py" = ["ARG", "PLR2004"]

src/fastmcp_feedback/__init__.py

@@ -44,7 +44,7 @@ Quick Start:
 import logging
 
 # Version information - CalVer YYYY.MM.DD
-__version__ = "2026.01.12.1"
+__version__ = "2026.09.27.4"
 __author__ = "Ryan Malloy"
 __email__ = "ryan@supported.systems"
 
@@ -259,8 +259,8 @@ from fastmcp_feedback import create_feedback_server
 main_app = FastMCP("Main Application")
 feedback_service = create_feedback_server("Feedback Service")
 
-# Import feedback service with prefix
-main_app.import_server(feedback_service, prefix="feedback")
+# Mount feedback service; its tools become feedback_<name>
+main_app.mount(feedback_service, "feedback")
 """,
     "multi_tenant": """
 from fastmcp import FastMCP

src/fastmcp_feedback/feedback.py

@@ -260,8 +260,10 @@ def compose_feedback_services(
                     f"{service_name} Service", database_url, shared_insights
                 )
 
-            # Import service with prefix
-            main_server.import_server(service_server, prefix=service_name)
+            # mount() is sync on every supported FastMCP; the second positional
+            # arg is `prefix` on 2.x and `namespace` on 4.x. import_server() is
+            # gone in 4.x and was async (so silently never ran here) on 2.14.
+            main_server.mount(service_server, service_name)
 
         logger.info(f"Composed {len(services)} feedback services into main server")
 

src/fastmcp_feedback/instrumentation/__init__.py

@@ -0,0 +1,48 @@
+"""Per-call instrumentation for any FastMCP server.
+
+from fastmcp_feedback.instrumentation import instrument, DatabaseSink
+
+mw = instrument(app)  # every tool call as JSON lines on stderr
+mw = instrument(app, [DatabaseSink(engine)], identity_resolver=who)
+mw = instrument(app, result_classifier=soft_error_classifier(extra_statuses=("unknown_target",)))
+"""
+
+from .classify import (
+    DEFAULT_RESULT_CLASSIFIER,
+    ResultClassifier,
+    soft_error_classifier,
+)
+from .dispatch import RecordDispatcher
+from .middleware import MODE_ENV_VAR, MODES, InstrumentationMiddleware, instrument
+from .record import ToolCallRecord
+from .redaction import (
+    DEFAULT_SECRET_KEYS,
+    DEFAULT_SECRET_PATTERNS,
+    REDACTED,
+    Redactor,
+)
+from .sinks import CallbackSink, JsonLinesSink, MemorySink, Sink
+from .storage import DEFAULT_TABLE_PREFIX, DatabaseSink, build_metadata
+
+__all__ = [
+    "CallbackSink",
+    "DatabaseSink",
+    "DEFAULT_RESULT_CLASSIFIER",
+    "DEFAULT_SECRET_KEYS",
+    "DEFAULT_SECRET_PATTERNS",
+    "DEFAULT_TABLE_PREFIX",
+    "InstrumentationMiddleware",
+    "JsonLinesSink",
+    "MemorySink",
+    "MODE_ENV_VAR",
+    "MODES",
+    "RecordDispatcher",
+    "REDACTED",
+    "Redactor",
+    "ResultClassifier",
+    "Sink",
+    "ToolCallRecord",
+    "build_metadata",
+    "instrument",
+    "soft_error_classifier",
+]

src/fastmcp_feedback/instrumentation/classify.py

@@ -0,0 +1,97 @@
+"""Spotting tools that report failure as data instead of raising.
+
+A result classifier is ``(tool, result) -> str | None``. ``result`` is the
+recorded payload: the structured content when there is one, otherwise the
+content items. None means the call succeeded; a string marks it as a soft
+error and becomes the record's ``error_message`` (after redaction).
+
+A result the tool marked as an MCP error (``isError``) without raising reaches
+the classifier as a dict with ``"isError": True``, alongside the payload's own
+keys or with the payload under ``"content"``.
+"""
+
+from collections.abc import Callable, Iterable
+from typing import Any
+
+ResultClassifier = Callable[[str, Any], str | None]
+
+MESSAGE_KEYS = ("error", "message", "detail", "reason")
+ERROR_FLAG_KEYS = ("isError", "is_error")
+
+
+def _message(result: dict, depth: int = 0) -> str | None:
+    for key in MESSAGE_KEYS:
+        value = result.get(key)
+        if value is None or value == "":
+            continue
+        if isinstance(value, dict):
+            # {"error": {"code": 404, "message": "..."}}
+            if depth == 0 and (inner := _message(value, 1)):
+                return inner
+            continue
+        if isinstance(value, list | tuple):
+            continue
+        return str(value)
+    return None
+
+
+def _content_text(content: Any) -> str | None:
+    if isinstance(content, str):
+        return content
+    if not isinstance(content, list | tuple):
+        return None
+    texts = [
+        item if isinstance(item, str) else item.get("text")
+        for item in content
+        if isinstance(item, str | dict)
+    ]
+    return " ".join(t for t in texts if t) or None
+
+
+def _describe(label: str, detail: str | None) -> str:
+    return f"{label}: {detail}" if detail else label
+
+
+def soft_error_classifier(
+    *,
+    statuses: Iterable[str] = ("error", "failed", "failure"),
+    status_keys: Iterable[str] = ("status", "state"),
+    flag_keys: Iterable[str] = ("ok", "success"),
+    extra_statuses: Iterable[str] = (),
+) -> ResultClassifier:
+    """Build a classifier for dict results that describe their own failure.
+
+    A dict result is a soft error when any of ``flag_keys`` is exactly False,
+    when any of ``status_keys`` holds one of ``statuses`` or
+    ``extra_statuses`` (case-insensitive), or when the tool marked it
+    ``isError``. The message is the first of ``error``, ``message``,
+    ``detail`` and ``reason`` present, e.g. ``status=failed: disk full``.
+
+    >>> classify = soft_error_classifier(extra_statuses=("unknown_target",))
+    >>> classify("render", {"status": "unknown_target", "error": "no such object"})
+    'status=unknown_target: no such object'
+    """
+    bad = frozenset(s.lower() for s in (*statuses, *extra_statuses))
+    status_keys = tuple(status_keys)
+    flag_keys = tuple(flag_keys)
+
+    def classify(tool: str, result: Any) -> str | None:
+        if not isinstance(result, dict):
+            return None
+        for key in status_keys:
+            value = result.get(key)
+            if isinstance(value, str) and value.lower() in bad:
+                return _describe(f"{key}={value}", _message(result))
+        for key in flag_keys:
+            if key in result and result[key] is False:
+                return _describe(f"{key}=False", _message(result))
+        for key in ERROR_FLAG_KEYS:
+            if result.get(key) is True:
+                detail = _message(result) or _content_text(result.get("content"))
+                return _describe("isError", detail)
+        return None
+
+    return classify
+
+
+DEFAULT_RESULT_CLASSIFIER = soft_error_classifier()

src/fastmcp_feedback/instrumentation/correlation.py

@@ -0,0 +1,106 @@
+"""Linking feedback to the tool calls that came before it."""
+
+from collections.abc import Iterable
+from dataclasses import asdict, dataclass
+from datetime import UTC, datetime
+from typing import Any
+
+RULE_SESSION = "session"
+RULE_USER_WINDOW = "user_window"
+
+
+@dataclass
+class CallLink:
+    """A tool call linked to a piece of feedback, and why it matched."""
+
+    call_id: str
+    rule: str
+    tool: str
+    started_at: datetime
+    ok: bool
+    position: int = 0
+
+    def to_dict(self) -> dict[str, Any]:
+        data = asdict(self)
+        data["started_at"] = self.started_at.isoformat()
+        return data
+
+
+@dataclass
+class Candidate:
+    """The fields correlation needs, from a buffered record or a database row."""
+
+    id: str
+    tool: str
+    started_at: datetime
+    ok: bool
+    session_id: str | None
+    user_sub: str | None
+
+
+class ResolverContext:
+    """What an identity resolver receives when called during correlation.
+
+    Outside a tool call there is no MiddlewareContext, so this carries only the
+    ``fastmcp_context`` attribute, which is what resolvers normally read.
+    """
+
+    def __init__(self, fastmcp_context: Any):
+        self.fastmcp_context = fastmcp_context
+        self.message = None
+
+
+def as_utc(value: datetime) -> datetime:
+    # SQLite drops the timezone from DateTime(timezone=True) columns.
+    return value.replace(tzinfo=UTC) if value.tzinfo is None else value
+
+
+def select_calls(
+    candidates: Iterable[Candidate],
+    *,
+    session_id: str | None,
+    user_sub: str | None,
+    since: datetime,
+    limit: int,
+) -> list[CallLink]:
+    """Pick up to ``limit`` recent calls for a feedback item.
+
+    Calls from the same MCP session come first. If there are fewer than
+    ``limit``, the rest are filled with the same user's calls since ``since``,
+    which covers clients that open a new session per call (PATs, CI). The
+    result is in chronological order, numbered from 0.
+    """
+    unique: dict[str, Candidate] = {}
+    for c in candidates:
+        unique.setdefault(c.id, c)
+    newest_first = sorted(
+        unique.values(), key=lambda c: as_utc(c.started_at), reverse=True
+    )
+
+    chosen: list[tuple[Candidate, str]] = []
+    if session_id:
+        chosen += [
+            (c, RULE_SESSION) for c in newest_first if c.session_id == session_id
+        ][:limit]
+    if user_sub and len(chosen) < limit:
+        taken = {c.id for c, _ in chosen}
+        chosen += [
+            (c, RULE_USER_WINDOW)
+            for c in newest_first
+            if c.id not in taken
+            and c.user_sub == user_sub
+            and as_utc(c.started_at) >= since
+        ][: limit - len(chosen)]
+
+    chosen.sort(key=lambda pair: as_utc(pair[0].started_at))
+    return [
+        CallLink(
+            call_id=c.id,
+            rule=rule,
+            tool=c.tool,
+            started_at=as_utc(c.started_at),
+            ok=c.ok,
+            position=i,
+        )
+        for i, (c, rule) in enumerate(chosen)
+    ]

src/fastmcp_feedback/instrumentation/dispatch.py

@@ -0,0 +1,117 @@
+"""Background delivery of records to sinks, off the tool-call path."""
+
+import asyncio
+import contextlib
+import logging
+from collections.abc import Sequence
+
+from .record import ToolCallRecord
+from .sinks import Sink
+
+logger = logging.getLogger(__name__)
+
+
+class RecordDispatcher:
+    """Queue records and hand them to sinks from a background task.
+
+    ``submit`` never blocks and never raises: when the queue is full the record
+    is dropped and counted, so a slow or broken sink cannot slow down or fail
+    a tool call. Sink errors are logged and counted, never propagated.
+    """
+
+    def __init__(
+        self,
+        sinks: Sequence[Sink],
+        *,
+        max_queue: int = 1000,
+        batch_size: int = 100,
+        sink_timeout: float = 10.0,
+    ):
+        self.sinks = list(sinks)
+        self.max_queue = max_queue
+        self.batch_size = batch_size
+        self.sink_timeout = sink_timeout
+        self.dropped = 0
+        self.sink_errors = 0
+        self._queue: asyncio.Queue[ToolCallRecord] | None = None
+        self._task: asyncio.Task | None = None
+        self._loop: asyncio.AbstractEventLoop | None = None
+
+    def submit(self, record: ToolCallRecord) -> bool:
+        """Queue a record for delivery. Returns False if it was dropped."""
+        try:
+            loop = asyncio.get_running_loop()
+        except RuntimeError:
+            self._drop("no running event loop")
+            return False
+
+        # A queue belongs to one loop; tests and some hosts run several.
+        if self._queue is None or self._loop is not loop:
+            self._loop = loop
+            self._queue = asyncio.Queue(maxsize=self.max_queue)
+            self._task = loop.create_task(self._run(self._queue))
+
+        try:
+            self._queue.put_nowait(record)
+        except asyncio.QueueFull:
+            self._drop("queue full")
+            return False
+        return True
+
+    def _drop(self, reason: str) -> None:
+        self.dropped += 1
+        if self.dropped == 1 or self.dropped % 1000 == 0:
+            logger.warning(
+                "Dropped tool-call record (%s); %d dropped so far", reason, self.dropped
+            )
+
+    async def _run(self, queue: asyncio.Queue) -> None:
+        while True:
+            batch = [await queue.get()]
+            while len(batch) < self.batch_size:
+                try:
+                    batch.append(queue.get_nowait())
+                except asyncio.QueueEmpty:
+                    break
+            try:
+                await self._deliver(batch)
+            finally:
+                for _ in batch:
+                    queue.task_done()
+
+    async def _deliver(self, batch: list[ToolCallRecord]) -> None:
+        for sink in self.sinks:
+            try:
+                await asyncio.wait_for(sink.write(batch), self.sink_timeout)
+            except Exception:
+                self.sink_errors += 1
+                logger.warning(
+                    "Sink %s failed to write %d records",
+                    type(sink).__name__,
+                    len(batch),
+                    exc_info=True,
+                )
+
+    async def flush(self) -> None:
+        """Wait until every queued record has been handed to the sinks."""
+        if self._queue is not None and self._loop is asyncio.get_running_loop():
+            await self._queue.join()
+
+    async def aclose(self) -> None:
+        """Flush, stop the background task and close the sinks."""
+        await self.flush()
+        if self._task is not None:
+            self._task.cancel()
+            with contextlib.suppress(asyncio.CancelledError, RuntimeError):
+                await self._task
+            self._task = None
+            self._queue = None
+        for sink in self.sinks:
+            close = getattr(sink, "aclose", None)
+            if close is not None:
+                try:
+                    await close()
+                except Exception:
+                    logger.warning(
+                        "Sink %s failed to close", type(sink).__name__, exc_info=True
+                    )

src/fastmcp_feedback/instrumentation/middleware.py

@@ -0,0 +1,463 @@
+"""FastMCP middleware that records every tool call."""
+
+import asyncio
+import inspect
+import json
+import logging
+import os
+import time
+import uuid
+from collections import deque
+from collections.abc import Awaitable, Callable, Iterable, Sequence
+from datetime import UTC, datetime, timedelta
+from typing import Any
+
+from fastmcp import FastMCP
+from fastmcp.server.middleware import Middleware, MiddlewareContext
+
+from .classify import DEFAULT_RESULT_CLASSIFIER, ResultClassifier
+from .correlation import (
+    CallLink,
+    Candidate,
+    ResolverContext,
+    as_utc,
+    select_calls,
+)
+from .dispatch import RecordDispatcher
+from .record import ToolCallRecord
+from .redaction import Redactor
+from .sinks import JsonLinesSink, Sink
+from .storage import DatabaseSink
+
+logger = logging.getLogger(__name__)
+
+MODES = ("off", "meta", "full")
+MODE_ENV_VAR = "FEEDBACK_INSTRUMENTATION_MODE"
+
+IdentityResolver = Callable[
+    [MiddlewareContext], dict[str, Any] | Awaitable[dict[str, Any]] | None
+]
+Enricher = Callable[
+    [str, Any, Any, MiddlewareContext],
+    dict[str, Any] | Awaitable[dict[str, Any]] | None,
+]
+
+# Keys an identity resolver can return that get their own columns.
+_IDENTITY_COLUMNS = ("user_sub", "caller_kind", "client_id")
+
+
+def _attr(obj: Any, name: str) -> Any:
+    try:
+        value = getattr(obj, name, None)
+    except Exception:
+        return None
+    return str(value) if value is not None else None
+
+
+# stdio serves exactly one client per process, so the process is the session.
+_STDIO_SESSION = f"stdio:{os.getpid()}:{uuid.uuid4().hex[:8]}"
+
+
+def session_key(ctx: Any) -> str | None:
+    """A per-client key that stays the same across that client's calls.
+
+    Clients on MCP protocol 2026-07-28 (Claude Code, FastMCP 4's Client) do
+    not open sessions, and FastMCP then generates a new ``ctx.session_id`` for
+    every request. So stable signals come first: the HTTP ``mcp-session-id``
+    header (older protocol clients), then one key per process for stdio, then
+    ``ctx.session_id``. With a stateless HTTP client there is no session, and
+    correlation relies on the same-user rule.
+    """
+    if ctx is None:
+        return None
+    try:
+        from fastmcp.server.dependencies import get_http_headers
+
+        header = (get_http_headers(include_all=True) or {}).get("mcp-session-id")
+        if header:
+            return header
+    except Exception:
+        pass
+    if _attr(ctx, "transport") == "stdio":
+        return _STDIO_SESSION
+    return _attr(ctx, "session_id")
+
+
+def _result_payload(result: Any) -> Any:
+    structured = getattr(result, "structured_content", None)
+    if structured is not None:
+        return structured
+    content = getattr(result, "content", None)
+    if content is not None:
+        return [
+            getattr(item, "text", None) or {"type": getattr(item, "type", None)}
+            for item in content
+        ]
+    return result
+
+
+def _json_size(value: Any) -> int | None:
+    try:
+        return len(json.dumps(value, default=str).encode())
+    except Exception:
+        return None
+
+
+class InstrumentationMiddleware(Middleware):
+    """Record every tool call without ever slowing or breaking it.
+
+    Modes:
+        ``off``: pass calls straight through.
+        ``meta`` (default): tool, timing, outcome, identity and payload sizes.
+        ``full``: also the arguments and result, redacted.
+
+    The mode defaults to the ``FEEDBACK_INSTRUMENTATION_MODE`` environment
+    variable, then ``meta``. Records go to the sinks from a background task
+    through a bounded queue; when it fills, records are dropped, not waited on.
+
+    Args:
+        sinks: where records go. Defaults to JSON lines on stderr.
+        mode: see above.
+        redactor: secret redaction for args, results, error text and extras.
+        meta_only_tools: tools that are never recorded above ``meta``.
+        identity_resolver: ``(context) -> dict`` returning ``user_sub``,
+            ``caller_kind`` and ``client_id`` (stored as columns) plus any
+            other keys (stored in ``identity``). May be async.
+        enricher: ``(tool, args, result, context) -> dict`` of extra fields,
+            stored in ``extra``. A ``server_version`` key fills that column.
+            May be async.
+        server_version: default for the ``server_version`` column.
+        hook_timeout: seconds an async hook may take before it is skipped.
+        recent_calls: how many recent records to keep in memory for
+            correlation, including ones still waiting to reach the sinks.
+        correlation_timeout: seconds a database lookup during correlation may
+            take before it is skipped.
+        result_classifier: ``(tool, result) -> str | None`` run on results
+            of calls that did not raise. A string marks the call as a soft
+            error (``outcome="soft_error"``, ``ok=False``) and becomes the
+            error message. Defaults to ``DEFAULT_RESULT_CLASSIFIER``; None
+            turns it off. If it raises, the call is recorded as ok.
+    """
+
+    def __init__(
+        self,
+        sinks: Sequence[Sink] | None = None,
+        *,
+        mode: str | None = None,
+        redactor: Redactor | None = None,
+        meta_only_tools: Iterable[str] = (),
+        identity_resolver: IdentityResolver | None = None,
+        enricher: Enricher | None = None,
+        server_version: str | None = None,
+        hook_timeout: float = 0.25,
+        max_queue: int = 1000,
+        batch_size: int = 100,
+        sink_timeout: float = 10.0,
+        max_error_chars: int = 500,
+        recent_calls: int = 2000,
+        correlation_timeout: float = 1.0,
+        result_classifier: ResultClassifier | None = DEFAULT_RESULT_CLASSIFIER,
+    ):
+        mode = (mode or os.getenv(MODE_ENV_VAR) or "meta").lower()
+        if mode not in MODES:
+            raise ValueError(f"mode must be one of {MODES}, got {mode!r}")
+        self.mode = mode
+        self.redactor = redactor or Redactor()
+        self.meta_only_tools = frozenset(meta_only_tools)
+        self.identity_resolver = identity_resolver
+        self.enricher = enricher
+        self.server_version = server_version
+        self.hook_timeout = hook_timeout
+        self.max_error_chars = max_error_chars
+        self.correlation_timeout = correlation_timeout
+        self.result_classifier = result_classifier
+        self.recent: deque[ToolCallRecord] = deque(maxlen=recent_calls)
+        self.dispatcher = RecordDispatcher(
+            sinks if sinks is not None else [JsonLinesSink()],
+            max_queue=max_queue,
+            batch_size=batch_size,
+            sink_timeout=sink_timeout,
+        )
+
+    async def on_call_tool(self, context: MiddlewareContext, call_next):
+        if self.mode == "off":
+            return await call_next(context)
+
+        started_at = datetime.now(UTC)
+        start = time.perf_counter()
+        result = None
+        error: BaseException | None = None
+        try:
+            result = await call_next(context)
+            return result
+        except BaseException as exc:
+            error = exc
+            raise
+        finally:
+            duration_ms = (time.perf_counter() - start) * 1000
+            try:
+                record = await self._build_record(
+                    context, started_at, duration_ms, result, error
+                )
+                self.recent.append(record)
+                self.dispatcher.submit(record)
+            except Exception:
+                logger.warning("Failed to record tool call", exc_info=True)
+
+    async def _call_hook(self, hook: Callable | None, *args: Any) -> dict[str, Any]:
+        if hook is None:
+            return {}
+        try:
+            out = hook(*args)
+            if inspect.isawaitable(out):
+                out = await asyncio.wait_for(out, self.hook_timeout)
+            return dict(out) if out else {}
+        except Exception:
+            logger.warning("Instrumentation hook %r failed", hook, exc_info=True)
+            return {}
+
+    def _classify(self, tool: str, result: Any, payload: Any) -> str | None:
+        if getattr(result, "is_error", False) is True:
+            # FastMCP 3.4+ keeps isError on the ToolResult, not in the payload.
+            if isinstance(payload, dict):
+                payload = {**payload, "isError": True}
+            else:
+                payload = {"isError": True, "content": payload}
+        try:
+            message = self.result_classifier(tool, payload)
+        except Exception:
+            logger.warning(
+                "Result classifier %r failed", self.result_classifier, exc_info=True
+            )
+            return None
+        return None if message is None else str(message)
+
+    async def _build_record(
+        self,
+        context: MiddlewareContext,
+        started_at: datetime,
+        duration_ms: float,
+        result: Any,
+        error: BaseException | None,
+    ) -> ToolCallRecord:
+        message = context.message
+        tool = getattr(message, "name", None) or "unknown"
+        args = getattr(message, "arguments", None) or {}
+        ctx = context.fastmcp_context
+        payload = _result_payload(result) if result is not None else None
+
+        identity = await self._call_hook(self.identity_resolver, context)
+        extra = await self._call_hook(self.enricher, tool, args, payload, context)
+        identity = self.redactor.redact(identity)
+        extra = self.redactor.redact(extra)
+        columns = {k: identity.pop(k) for k in _IDENTITY_COLUMNS if k in identity}
+        server_version = extra.pop("server_version", None) or self.server_version
+
+        mode = "meta" if tool in self.meta_only_tools else self.mode
+        full = mode == "full"
+
+        outcome = "ok"
+        error_type = error_message = None
+        if error is not None:
+            # FastMCP wraps tool exceptions in ToolError; report the original.
+            cause = error.__cause__ or error
+            outcome = "error"
+            error_type = type(cause).__name__
+            error_message = self.redactor.redact_text(str(cause))[
+                : self.max_error_chars
+            ]
+        elif self.result_classifier is not None and payload is not None:
+            soft = self._classify(tool, result, payload)
+            if soft is not None:
+                outcome = "soft_error"
+                error_type = "SoftError"
+                error_message = (
+                    self.redactor.redact_text(soft)[: self.max_error_chars] or None
+                )
+
+        return ToolCallRecord(
+            tool=tool,
+            started_at=started_at,
+            duration_ms=duration_ms,
+            ok=outcome == "ok",
+            outcome=outcome,
+            mode=mode,
+            error_type=error_type,
+            error_message=error_message,
+            session_id=session_key(ctx),
+            request_id=_attr(ctx, "request_id"),
+            client_id=columns.get("client_id") or _attr(ctx, "client_id"),
+            user_sub=columns.get("user_sub"),
+            caller_kind=columns.get("caller_kind"),
+            identity=identity,
+            server_version=server_version,
+            args_size=_json_size(args),
+            result_size=_json_size(payload) if payload is not None else None,
+            args=self.redactor.redact(args) if full else None,
+            result=self.redactor.redact(payload)
+            if full and payload is not None
+            else None,
+            extra=extra,
+        )
+
+    @property
+    def database_sink(self) -> DatabaseSink | None:
+        """The first DatabaseSink among the sinks, if any."""
+        return next(
+            (s for s in self.dispatcher.sinks if isinstance(s, DatabaseSink)), None
+        )
+
+    async def capture_recent_calls(
+        self,
+        ctx: Any = None,
+        n: int = 20,
+        *,
+        user_sub: str | None = None,
+        window: timedelta = timedelta(minutes=15),
+    ) -> list[CallLink]:
+        """The calls that led up to now, for attaching to a feedback item.
+
+        Call from inside a tool. Returns up to ``n`` calls in chronological
+        order: first from the current MCP session, then, if that yields fewer
+        than ``n``, the same user's calls within ``window``. Each link says
+        which rule matched. Never raises; returns [] on any failure.
+
+        Args:
+            ctx: the FastMCP Context. Looked up automatically when omitted.
+            n: maximum number of calls.
+            user_sub: the caller's user id. When omitted, the identity
+                resolver is asked, given an object whose ``fastmcp_context``
+                is ``ctx``.
+            window: how far back the same-user fallback reaches.
+        """
+        try:
+            if ctx is None:
+                ctx = _current_context()
+            session_id = session_key(ctx)
+            if user_sub is None and self.identity_resolver is not None:
+                identity = await self._call_hook(
+                    self.identity_resolver, ResolverContext(ctx)
+                )
+                user_sub = identity.get("user_sub")
+            since = datetime.now(UTC) - window
+
+            candidates = [
+                Candidate(r.id, r.tool, r.started_at, r.ok, r.session_id, r.user_sub)
+                for r in self.recent
+            ]
+            links = select_calls(
+                candidates,
+                session_id=session_id,
+                user_sub=user_sub,
+                since=since,
+                limit=n,
+            )
+            sink = self.database_sink
+            if sink is not None and len(links) < n:
+                # Other workers, or calls from before a restart.
+                rows = await asyncio.wait_for(
+                    sink.recent_calls(
+                        session_id=session_id, user_sub=user_sub, since=since, limit=n
+                    ),
+                    self.correlation_timeout,
+                )
+                candidates += [
+                    Candidate(
+                        r["id"],
+                        r["tool"],
+                        as_utc(r["started_at"]),
+                        r["ok"],
+                        r["session_id"],
+                        r["user_sub"],
+                    )
+                    for r in rows
+                ]
+                links = select_calls(
+                    candidates,
+                    session_id=session_id,
+                    user_sub=user_sub,
+                    since=since,
+                    limit=n,
+                )
+            return links
+        except Exception:
+            logger.warning("Failed to capture recent calls", exc_info=True)
+            return []
+
+    async def link_feedback(self, feedback_ref: str, links: Sequence[CallLink]) -> bool:
+        """Store ``links`` against a feedback id of any format (``bug-XXXX``, 42).
+
+        Needs a DatabaseSink. Replaces earlier links for the same id. Returns
+        False, without raising, if they could not be stored.
+        """
+        sink = self.database_sink
+        if sink is None:
+            logger.warning("link_feedback needs a DatabaseSink; links not stored")
+            return False
+        linked_at = datetime.now(UTC)
+        try:
+            await sink.replace_links(
+                str(feedback_ref),
+                [
+                    {
+                        "feedback_ref": str(feedback_ref),
+                        "call_id": link.call_id,
+                        "position": link.position,
+                        "rule": link.rule,
+                        "linked_at": linked_at,
+                    }
+                    for link in links
+                ],
+            )
+            return True
+        except Exception:
+            logger.warning("Failed to link feedback %s", feedback_ref, exc_info=True)
+            return False
+
+    async def feedback_context(self, feedback_ref: str) -> list[dict[str, Any]]:
+        """The calls linked to a feedback id, in order, with their details.
+
+        Calls not yet written to the database are filled in from memory.
+        """
+        sink = self.database_sink
+        if sink is None:
+            return []
+        rows = await sink.linked_calls(str(feedback_ref))
+        in_memory = {r.id: r for r in self.recent}
+        for row in rows:
+            if row["tool"] is None and row["call_id"] in in_memory:
+                record = in_memory[row["call_id"]]
+                for key in row:
+                    if key not in ("call_id", "position", "rule"):
+                        row[key] = getattr(record, key, None)
+            if row["started_at"] is not None:
+                row["started_at"] = as_utc(row["started_at"])
+        return rows
+
+    async def flush(self) -> None:
+        """Wait until queued records have reached the sinks."""
+        await self.dispatcher.flush()
+
+    async def aclose(self) -> None:
+        """Flush and close the sinks. Call on server shutdown."""
+        await self.dispatcher.aclose()
+
+
+def _current_context() -> Any:
+    try:
+        from fastmcp.server.dependencies import get_context
+
+        return get_context()
+    except Exception:
+        return None
+
+
+def instrument(app: FastMCP, sinks: Sequence[Sink] | None = None, **kwargs: Any):
+    """Add an InstrumentationMiddleware to ``app`` and return it.
+
+    >>> mw = instrument(app)                      # JSON lines to stderr
+    >>> mw = instrument(app, [DatabaseSink(engine)], mode="full")
+    """
+    middleware = InstrumentationMiddleware(sinks, **kwargs)
+    app.add_middleware(middleware)
+    return middleware

src/fastmcp_feedback/instrumentation/record.py

@@ -0,0 +1,55 @@
+"""The per-call record produced by InstrumentationMiddleware."""
+
+import uuid
+from dataclasses import asdict, dataclass, field
+from datetime import datetime
+from typing import Any
+
+
+@dataclass
+class ToolCallRecord:
+    """One MCP tool call, as seen by the instrumentation middleware.
+
+    ``args`` and ``result`` are only populated in ``full`` mode, and are
+    already redacted when they are. Sizes are measured before redaction.
+
+    ``outcome`` is ``ok``, ``error`` (the tool raised) or ``soft_error`` (it
+    returned a result the classifier flagged). ``ok`` is ``outcome == "ok"``;
+    when ``outcome`` is not given it is derived from ``ok``.
+    """
+
+    tool: str
+    started_at: datetime
+    duration_ms: float
+    ok: bool
+    mode: str
+    outcome: str | None = None
+    id: str = field(default_factory=lambda: str(uuid.uuid4()))
+    error_type: str | None = None
+    error_message: str | None = None
+    session_id: str | None = None
+    request_id: str | None = None
+    client_id: str | None = None
+    user_sub: str | None = None
+    caller_kind: str | None = None
+    identity: dict[str, Any] = field(default_factory=dict)
+    server_version: str | None = None
+    args_size: int | None = None
+    result_size: int | None = None
+    args: Any = None
+    result: Any = None
+    extra: dict[str, Any] = field(default_factory=dict)
+
+    def __post_init__(self) -> None:
+        if self.outcome is None:
+            self.outcome = "ok" if self.ok else "error"
+
+    def to_row(self) -> dict[str, Any]:
+        """Column values for the tool_calls table."""
+        return asdict(self)
+
+    def to_dict(self) -> dict[str, Any]:
+        """JSON-friendly form, with the timestamp as ISO 8601."""
+        data = asdict(self)
+        data["started_at"] = self.started_at.isoformat()
+        return data

src/fastmcp_feedback/instrumentation/redaction.py

@@ -0,0 +1,125 @@
+"""Secret redaction for recorded tool arguments, results and error text."""
+
+import re
+from collections.abc import Iterable
+from typing import Any
+
+REDACTED = "[REDACTED]"
+TRUNCATED = "[TRUNCATED]"
+
+# Matched after lowercasing and turning "-" into "_", so "Authorization",
+# "X-Api-Key" style variants are covered too.
+DEFAULT_SECRET_KEYS = frozenset(
+    {
+        "token",
+        "access_token",
+        "refresh_token",
+        "id_token",
+        "auth_token",
+        "session_token",
+        "csrf_token",
+        "bearer",
+        "authorization",
+        "proxy_authorization",
+        "cookie",
+        "set_cookie",
+        "password",
+        "passwd",
+        "passphrase",
+        "secret",
+        "client_secret",
+        "api_key",
+        "apikey",
+        "x_api_key",
+        "private_key",
+    }
+)
+
+# github_token, db_password, stripe_api_key, ...
+DEFAULT_SECRET_SUFFIXES = (
+    "_token",
+    "_secret",
+    "_password",
+    "_api_key",
+    "_apikey",
+    "_private_key",
+)
+
+# Values that are secrets wherever they appear, including inside free text.
+DEFAULT_SECRET_PATTERNS = (
+    r"\bbmcp_[A-Za-z0-9_-]{8,}",  # blender-mcp personal access tokens
+    r"\beyJ[A-Za-z0-9_-]{5,}\.[A-Za-z0-9_-]{5,}\.[A-Za-z0-9_-]{5,}",  # JWT
+    r"(?i)\bbearer\s+[A-Za-z0-9._~+/=-]{8,}",
+    r"\bsk-[A-Za-z0-9_-]{16,}",  # OpenAI/Anthropic-style API keys
+    r"\bgh[pousr]_[A-Za-z0-9]{20,}",  # GitHub tokens
+    r"\bgithub_pat_[A-Za-z0-9_]{20,}",
+    r"\bxox[abposr]-[A-Za-z0-9-]{10,}",  # Slack
+    r"\bAKIA[0-9A-Z]{16}\b",  # AWS access key id
+    r"\bpypi-[A-Za-z0-9_-]{16,}",
+)
+
+# "password=hunter2", "api_key: abc" in error messages and logs. The key is
+# kept so the text still says what was removed.
+_KEY_VALUE_TEXT = re.compile(
+    r"(?i)\b(password|passwd|secret|token|api[_-]?key|authorization)(\s*[=:]\s*)[^\s,;&'\"]+"
+)
+
+
+def _normalize_key(key: Any) -> str:
+    return str(key).lower().replace("-", "_")
+
+
+class Redactor:
+    """Replace secrets in nested JSON-like data with a placeholder.
+
+    Dict values are redacted when their key looks like a secret, at any depth.
+    String values anywhere are scanned for secret-shaped substrings. The input
+    is never modified; a redacted copy is returned.
+    """
+
+    def __init__(
+        self,
+        keys: Iterable[str] = DEFAULT_SECRET_KEYS,
+        patterns: Iterable[str] = DEFAULT_SECRET_PATTERNS,
+        *,
+        extra_keys: Iterable[str] = (),
+        extra_patterns: Iterable[str] = (),
+        suffixes: Iterable[str] = DEFAULT_SECRET_SUFFIXES,
+        replacement: str = REDACTED,
+        max_depth: int = 32,
+    ):
+        self.keys = frozenset(_normalize_key(k) for k in (*keys, *extra_keys))
+        self.suffixes = tuple(_normalize_key(s) for s in suffixes)
+        self.patterns = tuple(re.compile(p) for p in (*patterns, *extra_patterns))
+        self.replacement = replacement
+        self.max_depth = max_depth
+
+    def is_secret_key(self, key: Any) -> bool:
+        normalized = _normalize_key(key)
+        return normalized in self.keys or normalized.endswith(self.suffixes)
+
+    def redact_text(self, text: str) -> str:
+        for pattern in self.patterns:
+            text = pattern.sub(self.replacement, text)
+        return _KEY_VALUE_TEXT.sub(
+            lambda m: f"{m.group(1)}{m.group(2)}{self.replacement}", text
+        )
+
+    def redact(self, value: Any) -> Any:
+        return self._redact(value, 0)
+
+    def _redact(self, value: Any, depth: int) -> Any:
+        if depth > self.max_depth:
+            return TRUNCATED
+        if isinstance(value, str):
+            return self.redact_text(value)
+        if isinstance(value, dict):
+            return {
+                k: self.replacement
+                if self.is_secret_key(k) and v is not None
+                else self._redact(v, depth + 1)
+                for k, v in value.items()
+            }
+        if isinstance(value, list | tuple | set | frozenset):
+            return [self._redact(v, depth + 1) for v in value]
+        return value

src/fastmcp_feedback/instrumentation/sinks.py

@@ -0,0 +1,55 @@
+"""Destinations for tool-call records."""
+
+import inspect
+import json
+import sys
+from collections.abc import Callable, Sequence
+from typing import IO, Any, Protocol, runtime_checkable
+
+from .record import ToolCallRecord
+
+
+@runtime_checkable
+class Sink(Protocol):
+    """Anything with ``async write(records)``. ``async aclose()`` is optional."""
+
+    async def write(self, records: Sequence[ToolCallRecord]) -> None: ...
+
+
+class JsonLinesSink:
+    """One JSON object per record, to stderr by default."""
+
+    def __init__(self, stream: IO[str] | None = None):
+        self._stream = stream
+
+    async def write(self, records: Sequence[ToolCallRecord]) -> None:
+        # Resolved per write so a stderr swapped by the host or a test is honored.
+        stream = self._stream or sys.stderr
+        for record in records:
+            stream.write(json.dumps(record.to_dict(), default=str) + "\n")
+        stream.flush()
+
+
+class CallbackSink:
+    """Pass each batch to a function, sync or async.
+
+    A sync callback runs on the event loop, so keep it quick.
+    """
+
+    def __init__(self, callback: Callable[[Sequence[ToolCallRecord]], Any]):
+        self.callback = callback
+
+    async def write(self, records: Sequence[ToolCallRecord]) -> None:
+        result = self.callback(records)
+        if inspect.isawaitable(result):
+            await result
+
+
+class MemorySink:
+    """Keep records in a list. Meant for tests."""
+
+    def __init__(self):
+        self.records: list[ToolCallRecord] = []
+
+    async def write(self, records: Sequence[ToolCallRecord]) -> None:
+        self.records.extend(records)

src/fastmcp_feedback/instrumentation/storage.py

@@ -0,0 +1,217 @@
+"""Async SQLAlchemy storage for tool-call records and feedback links.
+
+Hosts that manage their own schema include ``build_metadata(prefix)`` in their
+Alembic ``env.py`` (``target_metadata``) and pass their existing AsyncEngine to
+``DatabaseSink``. Nothing is created unless ``create_tables=True``.
+"""
+
+import asyncio
+from collections.abc import Sequence
+from datetime import datetime
+from typing import Any
+
+from sqlalchemy import (
+    JSON,
+    Boolean,
+    Column,
+    DateTime,
+    Float,
+    Integer,
+    MetaData,
+    String,
+    Table,
+    Text,
+    and_,
+    delete,
+    or_,
+    select,
+)
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.ext.asyncio import AsyncEngine, create_async_engine
+
+from .record import ToolCallRecord
+
+DEFAULT_TABLE_PREFIX = "ffb_"
+
+# none_as_null: a missing payload is SQL NULL, so "WHERE args IS NULL" works.
+_JSON = JSON(none_as_null=True).with_variant(JSONB(none_as_null=True), "postgresql")
+
+
+def build_metadata(
+    prefix: str = DEFAULT_TABLE_PREFIX, metadata: MetaData | None = None
+) -> MetaData:
+    """Return MetaData holding ``{prefix}tool_calls`` and ``{prefix}feedback_call_links``.
+
+    Pass an existing MetaData to add the tables to it instead.
+    """
+    metadata = metadata if metadata is not None else MetaData()
+    calls = f"{prefix}tool_calls"
+    links = f"{prefix}feedback_call_links"
+    if calls not in metadata.tables:
+        Table(
+            calls,
+            metadata,
+            Column("id", String(36), primary_key=True),
+            Column("started_at", DateTime(timezone=True), nullable=False, index=True),
+            Column("duration_ms", Float, nullable=False),
+            Column("tool", String(255), nullable=False, index=True),
+            Column("mode", String(8), nullable=False),
+            Column("ok", Boolean, nullable=False, index=True),
+            # ok, soft_error or error. NULL on rows from before 2026.09.27.4.
+            Column("outcome", String(16), index=True),
+            Column("error_type", String(255)),
+            Column("error_message", Text),
+            Column("session_id", String(255), index=True),
+            Column("request_id", String(255)),
+            Column("client_id", String(255)),
+            Column("user_sub", String(255), index=True),
+            Column("caller_kind", String(64)),
+            Column("identity", _JSON),
+            Column("server_version", String(64), index=True),
+            Column("args_size", Integer),
+            Column("result_size", Integer),
+            Column("args", _JSON),
+            Column("result", _JSON),
+            Column("extra", _JSON),
+        )
+    if links not in metadata.tables:
+        # No foreign key to tool_calls: a link can be written before its call
+        # record has left the queue, and hosts may keep calls elsewhere.
+        Table(
+            links,
+            metadata,
+            Column("feedback_ref", String(255), primary_key=True),
+            Column("call_id", String(36), primary_key=True, index=True),
+            Column("position", Integer, nullable=False),
+            Column("rule", String(32), nullable=False),
+            Column("linked_at", DateTime(timezone=True), nullable=False),
+        )
+    return metadata
+
+
+class DatabaseSink:
+    """Write records to ``{prefix}tool_calls`` through an async engine.
+
+    Args:
+        engine: an AsyncEngine the host already owns, or a URL such as
+            ``sqlite+aiosqlite:///calls.db`` or ``postgresql+asyncpg://...``.
+            An engine built from a URL is disposed on ``aclose()``; a passed-in
+            engine is left alone.
+        prefix: table name prefix, so the tables cannot collide with the host's.
+        create_tables: create the tables on first use. Off by default; hosts
+            with Alembic should generate a migration from ``build_metadata``.
+    """
+
+    def __init__(
+        self,
+        engine: AsyncEngine | str,
+        *,
+        prefix: str = DEFAULT_TABLE_PREFIX,
+        create_tables: bool = False,
+    ):
+        self._owns_engine = isinstance(engine, str)
+        self.engine = create_async_engine(engine) if isinstance(engine, str) else engine
+        self.metadata = build_metadata(prefix)
+        self.table = self.metadata.tables[f"{prefix}tool_calls"]
+        self.links = self.metadata.tables[f"{prefix}feedback_call_links"]
+        self.create_tables = create_tables
+        self._tables_ready = False
+        # The background writer and link_feedback can both reach _ready() at
+        # once; without the lock both run create_all and one fails.
+        self._tables_lock = asyncio.Lock()
+
+    async def ensure_tables(self) -> None:
+        """Create the tables if missing. Only called when create_tables=True."""
+        async with self.engine.begin() as conn:
+            await conn.run_sync(self.metadata.create_all)
+        self._tables_ready = True
+
+    async def _ready(self) -> None:
+        if self.create_tables and not self._tables_ready:
+            async with self._tables_lock:
+                if not self._tables_ready:
+                    await self.ensure_tables()
+
+    async def write(self, records: Sequence[ToolCallRecord]) -> None:
+        if not records:
+            return
+        await self._ready()
+        async with self.engine.begin() as conn:
+            await conn.execute(self.table.insert(), [r.to_row() for r in records])
+
+    async def recent_calls(
+        self,
+        *,
+        session_id: str | None,
+        user_sub: str | None,
+        since: datetime,
+        limit: int,
+    ) -> list[dict[str, Any]]:
+        """Calls from this session, or from this user since ``since``, newest first."""
+        t = self.table
+        conditions = []
+        if session_id:
+            conditions.append(t.c.session_id == session_id)
+        if user_sub:
+            conditions.append(and_(t.c.user_sub == user_sub, t.c.started_at >= since))
+        if not conditions:
+            return []
+        await self._ready()
+        query = (
+            select(
+                t.c.id, t.c.tool, t.c.started_at, t.c.ok, t.c.session_id, t.c.user_sub
+            )
+            .where(or_(*conditions))
+            .order_by(t.c.started_at.desc())
+            .limit(limit)
+        )
+        async with self.engine.connect() as conn:
+            return [dict(row) for row in (await conn.execute(query)).mappings()]
+
+    async def replace_links(
+        self, feedback_ref: str, links: Sequence[dict[str, Any]]
+    ) -> None:
+        """Set the calls linked to ``feedback_ref``, replacing any earlier set."""
+        await self._ready()
+        async with self.engine.begin() as conn:
+            await conn.execute(
+                delete(self.links).where(self.links.c.feedback_ref == feedback_ref)
+            )
+            if links:
+                await conn.execute(self.links.insert(), list(links))
+
+    async def linked_calls(self, feedback_ref: str) -> list[dict[str, Any]]:
+        """Links for ``feedback_ref`` in order, joined to their call records.
+
+        Call columns are None for calls not (yet) in this database.
+        """
+        await self._ready()
+        link, call = self.links, self.table
+        query = (
+            select(
+                link.c.call_id,
+                link.c.position,
+                link.c.rule,
+                call.c.tool,
+                call.c.started_at,
+                call.c.duration_ms,
+                call.c.ok,
+                call.c.outcome,
+                call.c.error_type,
+                call.c.error_message,
+                call.c.session_id,
+                call.c.user_sub,
+                call.c.caller_kind,
+                call.c.server_version,
+                call.c.extra,
+            )
+            .select_from(link.outerjoin(call, link.c.call_id == call.c.id))
+            .where(link.c.feedback_ref == feedback_ref)
+            .order_by(link.c.position)
+        )
+        async with self.engine.connect() as conn:
+            return [dict(row) for row in (await conn.execute(query)).mappings()]
+
+    async def aclose(self) -> None:
+        if self._owns_engine:
+            await self.engine.dispose()

src/fastmcp_feedback/mixins/submission.py

@@ -1,15 +1,37 @@
 """Submission mixin for feedback collection."""
 
 from datetime import UTC, datetime
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 from ..insights import record_feedback_submission
 from ..models import SubmitFeedbackRequest, create_feedback_from_request
-from .base import BaseFeedbackMixin, logger, mcp_tool
+from .base import (
+    BaseFeedbackMixin,
+    FeedbackDatabase,
+    FeedbackInsights,
+    logger,
+    mcp_tool,
+)
+
+if TYPE_CHECKING:
+    from ..instrumentation import InstrumentationMiddleware
 
 
 class SubmissionMixin(BaseFeedbackMixin):
-    """Mixin for feedback submission functionality."""
+    """Mixin for feedback submission functionality.
+
+    Pass an InstrumentationMiddleware to link each submission to the tool
+    calls that led up to it.
+    """
+
+    def __init__(
+        self,
+        database: FeedbackDatabase,
+        insights: FeedbackInsights | None = None,
+        instrumentation: "InstrumentationMiddleware | None" = None,
+    ):
+        super().__init__(database, insights)
+        self.instrumentation = instrumentation
 
     @mcp_tool(
         description="Submit feedback about your MCP experience - Use this tool when you encounter issues, have suggestions for improvement, or want to report positive experiences. AI models should proactively use this to help improve future MCP sessions. PRIVACY: Only include information you've already shared via previous MCP calls. Ask human permission before including any new sensitive data."
@@ -62,14 +84,23 @@ class SubmissionMixin(BaseFeedbackMixin):
                     source="mcp_tool",
                 )
 
+            linked_calls = 0
+            if self.instrumentation is not None:
+                links = await self.instrumentation.capture_recent_calls()
+                if await self.instrumentation.link_feedback(feedback_id, links):
+                    linked_calls = len(links)
+
             self._record_tool_usage("submit_feedback", start_time, True)
             logger.info(f"Feedback submitted successfully: {feedback_id}")
 
-            return {
+            response = {
                 "success": True,
                 "feedback_id": feedback_id,
                 "message": "Feedback submitted successfully",
             }
+            if self.instrumentation is not None:
+                response["linked_calls"] = linked_calls
+            return response
 
         except Exception as e:
             logger.error(f"Failed to submit feedback: {e}")

src/fastmcp_feedback/tools.py

@@ -17,6 +17,7 @@ def add_feedback_tools(
     insights: FeedbackInsights | None = None,
     prefix: str = "",
     separator: str = "_",
+    instrumentation=None,
 ) -> None:
     """Add all feedback tools to a FastMCP server.
 
@@ -29,6 +30,9 @@ def add_feedback_tools(
         insights: Optional insights instance. Creates default if not provided.
         prefix: Optional prefix for tool names.
         separator: Separator between prefix and tool name.
+        instrumentation: an InstrumentationMiddleware (see ``instrument``).
+            When given, each submission is linked to the tool calls that led
+            up to it, and the response reports ``linked_calls``.
     """
     try:
         # Initialize database
@@ -39,7 +43,7 @@ def add_feedback_tools(
             insights = FeedbackInsights()
 
         # Create mixin instances
-        submission_mixin = SubmissionMixin(database, insights)
+        submission_mixin = SubmissionMixin(database, insights, instrumentation)
         retrieval_mixin = RetrievalMixin(database, insights)
         management_mixin = ManagementMixin(database, insights)
 

tests/_compat.py

@@ -0,0 +1,10 @@
+"""Helpers that paper over FastMCP API differences between 2.x and 4.x."""
+
+from fastmcp import FastMCP
+
+
+async def tool_map(server: FastMCP) -> dict:
+    """Return {name: Tool}. 2.x has get_tools() -> dict, 4.x has list_tools() -> list."""
+    if hasattr(server, "get_tools"):
+        return await server.get_tools()
+    return {tool.name: tool for tool in await server.list_tools()}

tests/fixtures/stdio_correlation_server.py

@@ -0,0 +1,22 @@
+"""A stdio MCP server used by test_correlation to check session linking end to end."""
+
+from fastmcp import Context, FastMCP
+
+from fastmcp_feedback.instrumentation import MemorySink, instrument
+
+app = FastMCP("stdio-correlation")
+mw = instrument(app, [MemorySink()])
+
+
+@app.tool
+def echo(text: str) -> str:
+    return text
+
+
+@app.tool
+async def report(ctx: Context) -> list:
+    return [[link.tool, link.rule] for link in await mw.capture_recent_calls(ctx)]
+
+
+if __name__ == "__main__":
+    app.run(show_banner=False)

tests/integration/test_demo_servers.py

@@ -11,11 +11,14 @@ import sys
 from pathlib import Path
 from unittest.mock import patch
 
+from sqlalchemy import text
+
 # Add the examples directory to the path for imports
 sys.path.insert(0, str(Path(__file__).parent.parent.parent / "examples"))
 
 from fastmcp import FastMCP
 from fastmcp_feedback import FeedbackDatabase, FeedbackInsights
+from tests._compat import tool_map
 
 
 @pytest.mark.asyncio
@@ -35,7 +38,7 @@ class TestDemoServerIntegration:
         assert "demonstration" in server.description.lower()
         
         # Get all tools
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         
         # Verify all expected tools are present
         expected_tools = {
@@ -72,12 +75,12 @@ class TestDemoServerIntegration:
             from fastmcp_feedback.models import Feedback
             async with database.session() as session:
                 # Count feedback items
-                result = session.execute("SELECT COUNT(*) FROM feedback")
+                result = session.execute(text("SELECT COUNT(*) FROM feedback"))
                 count = result.scalar()
                 assert count >= 5, f"Expected at least 5 sample items, got {count}"
                 
                 # Verify types are present
-                result = session.execute("SELECT DISTINCT type FROM feedback")
+                result = session.execute(text("SELECT DISTINCT type FROM feedback"))
                 types = [row[0] for row in result.fetchall()]
                 expected_types = {"BUG", "FEATURE", "IMPROVEMENT", "QUESTION"}
                 assert expected_types.issubset(set(types)), f"Missing feedback types: {expected_types - set(types)}"
@@ -89,21 +92,19 @@ class TestDemoServerIntegration:
         """Test actual execution of demo server tools."""
         from demo_server import create_demo_server, create_temp_database, setup_demo_data
         
-        # Create server with temporary database
-        server = create_demo_server()
-        
-        # Override database URL for testing
+        # Seed a temporary database, then point the server at it
         db_url = create_temp_database()
         database = FeedbackDatabase(db_url)
         await setup_demo_data(database)
+        server = create_demo_server(database_url=db_url)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         
         # Test system info tool
         system_info_tool = tools["get_system_info"]
         info_result = await system_info_tool.run({})
-        assert info_result.structured_content["success"] is True
-        assert "version" in info_result.structured_content
+        assert info_result.structured_content["status"] == "running"
+        assert "versions" in info_result.structured_content
         assert "dependencies" in info_result.structured_content
         
         # Test statistics tool (should work with sample data)
@@ -126,7 +127,7 @@ class TestDemoServerIntegration:
         add_feedback_tools(app, database_url="sqlite:///:memory:")
         
         # Verify tools were added
-        tools = await app.get_tools()
+        tools = await tool_map(app)
         expected_tools = {
             "submit_feedback",
             "list_feedback",
@@ -176,7 +177,7 @@ class TestDemoServerIntegration:
         from demo_server import create_demo_server
         
         server = create_demo_server()
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         
         # Test submit_feedback with invalid data
         submit_tool = tools["submit_feedback"]
@@ -199,7 +200,7 @@ class TestDemoServerIntegration:
         from demo_server import create_demo_server, create_temp_database
         
         server = create_demo_server()
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         
         # Submit feedback
         submit_tool = tools["submit_feedback"]
@@ -225,7 +226,7 @@ class TestDemoServerIntegration:
         assert our_feedback is not None, "Submitted feedback not found in list"
         assert our_feedback["title"] == test_feedback["title"]
         assert our_feedback["type"] == test_feedback["type"]
-        assert our_feedback["status"] == "OPEN"
+        assert our_feedback["status"] == "open"
         
         # Update feedback status
         update_tool = tools["update_feedback_status"]
@@ -239,7 +240,7 @@ class TestDemoServerIntegration:
         list_result = await list_tool.run({})
         feedback_list = list_result.structured_content["feedback"]
         updated_feedback = next((f for f in feedback_list if f["id"] == feedback_id), None)
-        assert updated_feedback["status"] == "IN_PROGRESS"
+        assert updated_feedback["status"] == "in_progress"
         
         # Get statistics (should include our feedback)
         stats_tool = tools["get_feedback_statistics"]
@@ -272,7 +273,7 @@ class TestDemoServerDocumentation:
         from demo_server import create_demo_server
         
         server = create_demo_server()
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         
         # According to demo_server.md, should have exactly 7 tools
         assert len(tools) == 7, f"Expected 7 tools as documented, got {len(tools)}"
@@ -296,7 +297,7 @@ class TestDemoServerDocumentation:
         app = FastMCP("Test App")
         add_feedback_tools(app, database_url="sqlite:///:memory:")
         
-        tools = await app.get_tools()
+        tools = await tool_map(app)
         assert len(tools) == 5, f"Expected 5 tools as documented, got {len(tools)}"
         
         # Verify documented tool names
@@ -318,7 +319,7 @@ class TestDemoServerPerformance:
         from demo_server import create_demo_server
         
         server = create_demo_server()
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         
         # Submit multiple feedback items concurrently

tests/integration/test_full_workflow.py

@@ -10,6 +10,7 @@ from fastmcp_feedback.feedback import create_feedback_server
 from fastmcp_feedback.models import SubmitFeedbackRequest, FeedbackStatus
 from fastmcp_feedback.database import FeedbackDatabase
 from fastmcp_feedback.insights import FeedbackInsights
+from tests._compat import tool_map
 
 
 @pytest.mark.integration
@@ -25,7 +26,7 @@ class TestCompleteWorkflow:
         add_feedback_tools(server, database_url=memory_db_url, insights=insights)
         
         # Get tools
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         update_tool = tools["update_feedback_status"]
@@ -106,7 +107,7 @@ class TestCompleteWorkflow:
         server = FastMCP("Multi-Type Test Server")
         add_feedback_tools(server, database_url=memory_db_url)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         
@@ -179,7 +180,7 @@ class TestCompleteWorkflow:
         server = FastMCP("Error Test Server")
         add_feedback_tools(server, database_url=memory_db_url)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         update_tool = tools["update_feedback_status"]
         delete_tool = tools["delete_feedback"]
@@ -233,7 +234,7 @@ class TestCompleteWorkflow:
         insights = FeedbackInsights(enabled=True)
         add_feedback_tools(server, database_url=memory_db_url, insights=insights)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         
@@ -285,7 +286,7 @@ class TestCompleteWorkflow:
         server = FastMCP("Bulk Test Server")
         add_feedback_tools(server, database_url=memory_db_url)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         update_tool = tools["update_feedback_status"]
@@ -355,7 +356,7 @@ class TestServerCompositionWorkflow:
         )
         
         # Get tools from dedicated server
-        tools = await feedback_server.get_tools()
+        tools = await tool_map(feedback_server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         
@@ -384,11 +385,11 @@ class TestServerCompositionWorkflow:
         admin_feedback = create_feedback_server("Admin Feedback", database_url="sqlite:///:memory:")
         
         # Import servers with different prefixes
-        await main_server.import_server(user_feedback, prefix="user")
-        await main_server.import_server(admin_feedback, prefix="admin")
+        main_server.mount(user_feedback, "user")
+        main_server.mount(admin_feedback, "admin")
         
         # Get tools
-        tools = await main_server.get_tools()
+        tools = await tool_map(main_server)
         
         user_submit = tools["user_submit_feedback"]
         admin_submit = tools["admin_submit_feedback"]
@@ -439,7 +440,7 @@ class TestServerCompositionWorkflow:
         add_feedback_tools(server, database_url=memory_db_url, prefix="public")
         add_feedback_tools(server, database_url=memory_db_url, prefix="internal")
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         
         public_submit = tools["public_submit_feedback"]
         internal_submit = tools["internal_submit_feedback"]
@@ -490,7 +491,7 @@ class TestPerformanceWorkflow:
         insights = FeedbackInsights(enabled=True)
         add_feedback_tools(server, database_url=memory_db_url, insights=insights)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         stats_tool = tools["get_feedback_statistics"]
@@ -537,7 +538,7 @@ class TestPerformanceWorkflow:
         server = FastMCP("Filter Performance Server")
         add_feedback_tools(server, database_url=memory_db_url)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         update_tool = tools["update_feedback_status"]
@@ -611,7 +612,7 @@ class TestPerformanceWorkflow:
         server = FastMCP("Concurrent Mixed Server")
         add_feedback_tools(server, database_url=memory_db_url)
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         submit_tool = tools["submit_feedback"]
         list_tool = tools["list_feedback"]
         update_tool = tools["update_feedback_status"]

tests/unit/test_correlation.py

@@ -0,0 +1,416 @@
+"""Tests for linking feedback to the tool calls that preceded it."""
+
+import asyncio
+import contextlib
+import json
+import sys
+from datetime import UTC, datetime, timedelta
+from pathlib import Path
+
+import fastmcp
+import pytest
+from fastmcp import Client, Context, FastMCP
+from fastmcp.client.transports import PythonStdioTransport
+from fastmcp.exceptions import ToolError
+
+from fastmcp_feedback import add_feedback_tools
+from fastmcp_feedback.instrumentation import (
+    DatabaseSink,
+    MemorySink,
+    instrument,
+)
+from fastmcp_feedback.instrumentation import middleware as mw_module
+from fastmcp_feedback.instrumentation.correlation import (
+    RULE_SESSION,
+    RULE_USER_WINDOW,
+    Candidate,
+    select_calls,
+)
+
+NOW = datetime(2026, 9, 27, 12, 0, tzinfo=UTC)
+
+# FastMCP 4's Client speaks MCP 2026-07-28, which has no sessions, so each
+# in-memory call gets a new ctx.session_id and there is no header or stdio
+# signal to fall back on. Calls from one test client link by user instead.
+FASTMCP_4 = int(fastmcp.__version__.split(".")[0]) >= 4
+SAME_CLIENT_RULE = RULE_USER_WINDOW if FASTMCP_4 else RULE_SESSION
+
+
+@pytest.fixture
+async def db(tmp_path):
+    """Make DatabaseSinks whose engines are always disposed, even on failure.
+
+    An undisposed aiosqlite engine keeps a worker thread alive and the test
+    process never exits.
+    """
+    made = []
+
+    def factory(name="calls", cls=DatabaseSink):
+        sink = cls(f"sqlite+aiosqlite:///{tmp_path}/{name}.db", create_tables=True)
+        made.append(sink)
+        return sink
+
+    yield factory
+    for sink in made:
+        await sink.engine.dispose()
+
+
+def cand(id, minutes_ago, session="s1", user="u1", tool="t", ok=True):
+    return Candidate(id, tool, NOW - timedelta(minutes=minutes_ago), ok, session, user)
+
+
+class TestSelectCalls:
+    def test_session_first_then_user_window_chronological(self):
+        links = select_calls(
+            [cand("a", 1), cand("b", 3, session="s2"), cand("c", 2)],
+            session_id="s1",
+            user_sub="u1",
+            since=NOW - timedelta(minutes=15),
+            limit=10,
+        )
+        assert [(link.call_id, link.rule, link.position) for link in links] == [
+            ("b", RULE_USER_WINDOW, 0),
+            ("c", RULE_SESSION, 1),
+            ("a", RULE_SESSION, 2),
+        ]
+
+    def test_session_matches_take_priority_over_newer_user_calls(self):
+        links = select_calls(
+            [cand("old", 10), cand("new", 1, session="s2")],
+            session_id="s1",
+            user_sub="u1",
+            since=NOW - timedelta(minutes=15),
+            limit=1,
+        )
+        assert [(link.call_id, link.rule) for link in links] == [("old", RULE_SESSION)]
+
+    def test_user_window_excludes_old_calls_and_other_users(self):
+        links = select_calls(
+            [
+                cand("recent", 5, session="s2"),
+                cand("stale", 30, session="s2"),
+                cand("other", 1, session="s3", user="u2"),
+            ],
+            session_id="s9",
+            user_sub="u1",
+            since=NOW - timedelta(minutes=15),
+            limit=10,
+        )
+        assert [link.call_id for link in links] == ["recent"]
+
+    def test_limit_keeps_the_most_recent(self):
+        links = select_calls(
+            [cand(str(i), i) for i in range(10)],
+            session_id="s1",
+            user_sub=None,
+            since=NOW,
+            limit=3,
+        )
+        assert [link.call_id for link in links] == ["2", "1", "0"]
+
+    def test_duplicates_counted_once_and_naive_times_treated_as_utc(self):
+        naive = Candidate(
+            "a",
+            "t",
+            (NOW - timedelta(minutes=1)).replace(tzinfo=None),
+            True,
+            "s1",
+            "u1",
+        )
+        links = select_calls(
+            [naive, cand("a", 1)], session_id="s1", user_sub=None, since=NOW, limit=5
+        )
+        assert len(links) == 1 and links[0].started_at.tzinfo is not None
+
+    def test_no_session_or_user_means_no_links(self):
+        assert (
+            select_calls(
+                [cand("a", 1)], session_id=None, user_sub=None, since=NOW, limit=5
+            )
+            == []
+        )
+
+
+def build(sinks=None, user="u1", **kwargs):
+    app = FastMCP("correlated")
+
+    @app.tool
+    def echo(text: str) -> str:
+        return text
+
+    @app.tool
+    def render(scene: str) -> str:
+        raise RuntimeError(f"render of {scene} hung")
+
+    captured = {}
+
+    @app.tool
+    async def report(ctx: Context) -> list:
+        links = await mw.capture_recent_calls(ctx)
+        captured["links"] = links
+        return [link.call_id for link in links]
+
+    identity = {"user": user}
+    mw = instrument(
+        app,
+        sinks if sinks is not None else [MemorySink()],
+        identity_resolver=lambda c: {"user_sub": identity["user"]},
+        **kwargs,
+    )
+    return app, mw, captured, identity
+
+
+class TestCaptureRecentCalls:
+    async def test_same_session_calls_including_failures(self):
+        app, mw, captured, _ = build()
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "a"})
+            with contextlib.suppress(ToolError):
+                await client.call_tool("render", {"scene": "castle"})
+            await client.call_tool("report", {})
+
+        links = captured["links"]
+        assert [(link.tool, link.ok, link.rule) for link in links] == [
+            ("echo", True, SAME_CLIENT_RULE),
+            ("render", False, SAME_CLIENT_RULE),
+        ]
+
+    async def test_new_session_per_call_falls_back_to_user_window(self):
+        """PAT/CI clients open a new MCP session for every call."""
+        app, mw, captured, _ = build()
+        for text in ("one", "two"):
+            async with Client(app) as client:
+                await client.call_tool("echo", {"text": text})
+        async with Client(app) as client:
+            await client.call_tool("report", {})
+
+        assert [link.rule for link in captured["links"]] == [RULE_USER_WINDOW] * 2
+
+    async def test_other_users_calls_are_not_linked(self):
+        app, mw, captured, identity = build()
+        identity["user"] = "someone-else"
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "not mine"})
+        identity["user"] = "u1"
+        async with Client(app) as client:
+            await client.call_tool("report", {})
+        assert captured["links"] == []
+
+    async def test_calls_still_queued_are_found(self):
+        release = asyncio.Event()
+
+        class Stalled:
+            async def write(self, records):
+                await release.wait()
+
+        app, mw, captured, _ = build(sinks=[Stalled()])
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "queued"})
+            await client.call_tool("report", {})
+        release.set()
+        assert [link.tool for link in captured["links"]] == ["echo"]
+
+    async def test_database_fallback_after_restart(self, db):
+        app1, mw1, _, _ = build(sinks=[db("restart")])
+        async with Client(app1) as client:
+            await client.call_tool("echo", {"text": "before restart"})
+        await mw1.aclose()
+
+        # A new process: empty in-memory buffer, same database.
+        app2, mw2, captured, _ = build(sinks=[db("restart")])
+        async with Client(app2) as client:
+            await client.call_tool("report", {})
+        await mw2.aclose()
+
+        [link] = captured["links"]
+        assert link.tool == "echo" and link.rule == RULE_USER_WINDOW
+
+    @pytest.mark.skipif(
+        FASTMCP_4, reason="FastMCP 4 Client is sessionless (MCP 2026-07-28)"
+    )
+    async def test_failing_resolver_still_links_by_session(self):
+        app, mw, captured, _ = build()
+        mw.identity_resolver = lambda c: 1 / 0
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "a"})
+            await client.call_tool("report", {})
+        assert [link.rule for link in captured["links"]] == [RULE_SESSION]
+
+    async def test_slow_database_is_skipped(self, db):
+        class SlowDb(DatabaseSink):
+            async def recent_calls(self, **kwargs):
+                await asyncio.sleep(5)
+                return []
+
+        sink = db("slow", SlowDb)
+        app, mw, captured, _ = build(sinks=[sink], correlation_timeout=0.05)
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "a"})
+            await client.call_tool("report", {})
+        await mw.aclose()
+        # The lookup timed out, so capture returned [] rather than hanging.
+        assert captured["links"] == []
+
+    async def test_outside_a_tool_call_returns_empty(self):
+        _, mw, _, _ = build()
+        mw.identity_resolver = None
+        assert await mw.capture_recent_calls() == []
+
+
+class TestLinksAndContext:
+    async def test_link_and_read_back_with_external_ids(self, db):
+        sink = db("links")
+        app, mw, captured, _ = build(sinks=[sink])
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "a"})
+            with contextlib.suppress(ToolError):
+                await client.call_tool("render", {"scene": "castle"})
+            await client.call_tool("report", {})
+
+        assert await mw.link_feedback("bug-7Q2X", captured["links"])
+        await mw.flush()
+        context = await mw.feedback_context("bug-7Q2X")
+        await mw.aclose()
+
+        assert [(c["position"], c["tool"], c["ok"], c["rule"]) for c in context] == [
+            (0, "echo", True, SAME_CLIENT_RULE),
+            (1, "render", False, SAME_CLIENT_RULE),
+        ]
+        assert context[1]["error_type"] == "RuntimeError"
+
+    async def test_relinking_replaces_links(self, db):
+        sink = db("relink")
+        app, mw, captured, _ = build(sinks=[sink])
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "a"})
+            await client.call_tool("report", {})
+        links = captured["links"]
+        await mw.link_feedback("fb-1", links)
+        await mw.link_feedback("fb-1", links)
+        assert len(await mw.feedback_context("fb-1")) == 1
+        await mw.aclose()
+
+    async def test_context_fills_unflushed_calls_from_memory(self, db):
+        release = asyncio.Event()
+
+        class StalledDb(DatabaseSink):
+            async def write(self, records):
+                await release.wait()
+
+        sink = db("unflushed", StalledDb)
+        app, mw, captured, _ = build(sinks=[sink])
+        async with Client(app) as client:
+            await client.call_tool("echo", {"text": "a"})
+            await client.call_tool("report", {})
+        await mw.link_feedback("fb-2", captured["links"])
+
+        [row] = await mw.feedback_context("fb-2")
+        release.set()
+        await mw.aclose()
+        assert row["tool"] == "echo" and row["ok"] is True
+
+    async def test_link_without_database_sink_is_false(self):
+        _, mw, _, _ = build()
+        assert await mw.link_feedback("x", []) is False
+        assert await mw.feedback_context("x") == []
+
+
+class TestSubmitFeedbackAutoLinks:
+    async def test_submission_links_preceding_calls(self, db):
+        app = FastMCP("app")
+
+        @app.tool
+        def render(scene: str) -> str:
+            raise RuntimeError("hung")
+
+        sink = db("submit")
+        mw = instrument(app, [sink], identity_resolver=lambda c: {"user_sub": "u1"})
+        add_feedback_tools(app, database_url="sqlite:///:memory:", instrumentation=mw)
+
+        async with Client(app) as client:
+            with contextlib.suppress(ToolError):
+                await client.call_tool("render", {"scene": "castle"})
+            result = await client.call_tool(
+                "submit_feedback",
+                {
+                    "request": {
+                        "type": "bug",
+                        "title": "render hangs",
+                        "description": "the render tool hung",
+                        "submitter": "model",
+                    }
+                },
+            )
+
+        assert result.data["linked_calls"] == 1
+        await mw.flush()
+        [row] = await mw.feedback_context(result.data["feedback_id"])
+        await mw.aclose()
+        assert (row["tool"], row["ok"], row["error_type"]) == (
+            "render",
+            False,
+            "RuntimeError",
+        )
+
+    async def test_without_instrumentation_response_unchanged(self):
+        app = FastMCP("plain")
+        add_feedback_tools(app, database_url="sqlite:///:memory:")
+        async with Client(app) as client:
+            result = await client.call_tool(
+                "submit_feedback",
+                {
+                    "request": {
+                        "type": "bug",
+                        "title": "t",
+                        "description": "no instrumentation",
+                        "submitter": "m",
+                    }
+                },
+            )
+        assert "linked_calls" not in result.data
+
+
+class FakeContext:
+    def __init__(self, transport=None, session_id="ctx-session"):
+        self.transport = transport
+        self.session_id = session_id
+
+
+class TestSessionKey:
+    def test_http_session_header_wins(self, monkeypatch):
+        import fastmcp.server.dependencies as deps
+
+        monkeypatch.setattr(
+            deps,
+            "get_http_headers",
+            lambda include_all=False: {"mcp-session-id": "hdr-1"},
+        )
+        assert (
+            mw_module.session_key(FakeContext(transport="streamable-http")) == "hdr-1"
+        )
+
+    def test_stdio_uses_one_key_per_process(self):
+        a = mw_module.session_key(FakeContext(transport="stdio", session_id="x"))
+        b = mw_module.session_key(FakeContext(transport="stdio", session_id="y"))
+        assert a == b and a.startswith("stdio:")
+
+    def test_falls_back_to_ctx_session_id(self):
+        assert mw_module.session_key(FakeContext()) == "ctx-session"
+
+    def test_no_context(self):
+        assert mw_module.session_key(None) is None
+
+
+class TestStdioEndToEnd:
+    async def test_same_stdio_client_links_by_session(self):
+        """On a real stdio transport, one client's calls link by session on every FastMCP version."""
+        server = (
+            Path(__file__).parent.parent / "fixtures" / "stdio_correlation_server.py"
+        )
+        transport = PythonStdioTransport(str(server), python_cmd=sys.executable)
+        async with Client(transport) as client:
+            await client.call_tool("echo", {"text": "a"})
+            await client.call_tool("echo", {"text": "b"})
+            result = await client.call_tool("report", {})
+        pairs = json.loads(result.content[0].text)
+        assert pairs == [["echo", RULE_SESSION], ["echo", RULE_SESSION]]

tests/unit/test_feedback_servers.py

@@ -345,7 +345,7 @@ class TestServerComposition:
     async def test_compose_feedback_services_success(self):
         """Test successful service composition."""
         main_server = Mock()
-        main_server.import_server = Mock()
+        main_server.mount = Mock()
 
         services = {
             "service1": {
@@ -376,13 +376,38 @@ class TestServerComposition:
             mock_submission.assert_called_once()
             mock_management.assert_called_once()
             mock_feedback.assert_called_once()
-            assert main_server.import_server.call_count == 3
+            assert main_server.mount.call_count == 3
+
+    @pytest.mark.asyncio
+    async def test_compose_feedback_services_real_servers(self, tmp_path):
+        """Composed tools must actually appear under their prefix.
+
+        The mocked tests above can't catch a missing await: a sync Mock
+        records the call either way. This one uses real FastMCP servers.
+        """
+        from fastmcp import FastMCP
+
+        from tests._compat import tool_map
+
+        main_server = FastMCP("Main")
+        compose_feedback_services(
+            main_server,
+            {
+                "public": {"database_url": f"sqlite:///{tmp_path}/p.db", "type": "submission"},
+                "admin": {"database_url": f"sqlite:///{tmp_path}/a.db", "type": "full"},
+            },
+        )
+
+        names = set(await tool_map(main_server))
+        assert "public_submit_feedback" in names
+        assert "admin_list_feedback" in names
+        assert "admin_update_feedback_status" in names
 
     @pytest.mark.asyncio
     async def test_compose_feedback_services_with_shared_insights(self):
         """Test service composition with shared insights."""
         main_server = Mock()
-        main_server.import_server = Mock()
+        main_server.mount = Mock()
         shared_insights = Mock()
 
         services = {

tests/unit/test_instrumentation.py

@@ -0,0 +1,484 @@
+"""Tests for per-call instrumentation: redaction, middleware, dispatch, sinks.
+
+These run against real FastMCP servers through fastmcp.Client, so they
+exercise the same middleware path on every supported FastMCP version.
+"""
+
+import asyncio
+import io
+import json
+import time
+
+import pytest
+from fastmcp import Client, FastMCP
+from fastmcp.exceptions import ToolError
+from sqlalchemy import MetaData, inspect, select
+from sqlalchemy.ext.asyncio import create_async_engine
+
+from fastmcp_feedback import add_feedback_tools
+from fastmcp_feedback.instrumentation import (
+    REDACTED,
+    CallbackSink,
+    DatabaseSink,
+    InstrumentationMiddleware,
+    JsonLinesSink,
+    MemorySink,
+    RecordDispatcher,
+    Redactor,
+    ToolCallRecord,
+    build_metadata,
+    instrument,
+)
+
+BMCP_TOKEN = "bmcp_" + "A1b2C3d4E5f6G7h8I9j0"
+JWT = "eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxMjM0NTYifQ.c2lnbmF0dXJlLXZhbHVl"
+
+
+def make_app(sinks=None, **kwargs):
+    sink = MemorySink()
+    app = FastMCP("instrumented")
+
+    @app.tool
+    def echo(text: str) -> dict:
+        return {"echo": text}
+
+    @app.tool
+    def create_token(label: str) -> dict:
+        return {"label": label, "access_token": BMCP_TOKEN, "note": f"use {BMCP_TOKEN}"}
+
+    @app.tool
+    def login(user: str, password: str) -> str:
+        return f"welcome {user}"
+
+    @app.tool
+    def fail(secret: str) -> str:
+        raise ValueError(f"bad input secret={secret}")
+
+    mw = instrument(app, sinks if sinks is not None else [sink], **kwargs)
+    return app, sink, mw
+
+
+async def call(app, tool, args=None):
+    async with Client(app) as client:
+        return await client.call_tool(tool, args or {})
+
+
+class TestRedactor:
+    def test_secret_keys_at_any_depth(self):
+        data = {"a": {"b": [{"password": "hunter2", "keep": 1}]}, "Authorization": "x"}
+        out = Redactor().redact(data)
+        assert out["a"]["b"][0] == {"password": REDACTED, "keep": 1}
+        assert out["Authorization"] == REDACTED
+
+    def test_suffix_and_dash_variants(self):
+        out = Redactor().redact(
+            {
+                "github_token": "t",
+                "DB-Password": "p",
+                "X-Api-Key": "k",
+                "stripe_api_key": "s",
+            }
+        )
+        assert set(out.values()) == {REDACTED}
+
+    def test_non_secret_keys_untouched(self):
+        data = {"max_tokens": 100, "token_count": 3, "tool": "echo", "tokens": [1, 2]}
+        assert Redactor().redact(data) == data
+
+    def test_secret_values_inside_text(self):
+        text = f"pat {BMCP_TOKEN}, jwt {JWT}, header Bearer abcdefghijklmnop, key sk-{'x' * 20}"
+        out = Redactor().redact_text(text)
+        for secret in (BMCP_TOKEN, JWT, "abcdefghijklmnop", "sk-"):
+            assert secret not in out
+        assert out.count(REDACTED) == 4
+
+    def test_key_value_text_keeps_the_key(self):
+        out = Redactor().redact_text("failed: password=hunter2 api_key: abc123, ok")
+        assert out == f"failed: password={REDACTED} api_key: {REDACTED}, ok"
+
+    def test_input_not_mutated(self):
+        data = {"password": "hunter2", "nested": {"token": "t"}}
+        Redactor().redact(data)
+        assert data == {"password": "hunter2", "nested": {"token": "t"}}
+
+    def test_none_secret_value_left_as_none(self):
+        assert Redactor().redact({"password": None}) == {"password": None}
+
+    def test_extra_keys_and_patterns(self):
+        r = Redactor(extra_keys=["license"], extra_patterns=[r"ACME-\d{6}"])
+        assert r.redact({"license": "L", "msg": "code ACME-123456"}) == {
+            "license": REDACTED,
+            "msg": f"code {REDACTED}",
+        }
+
+    def test_depth_limit(self):
+        deep = current = {}
+        for _ in range(50):
+            current["n"] = {}
+            current = current["n"]
+        assert "[TRUNCATED]" in json.dumps(Redactor(max_depth=5).redact(deep))
+
+
+class TestMiddlewareRecording:
+    async def test_success_in_meta_mode(self):
+        app, sink, mw = make_app()
+        await call(app, "echo", {"text": "hello"})
+        await mw.flush()
+
+        [rec] = sink.records
+        assert rec.tool == "echo" and rec.ok and rec.mode == "meta"
+        assert rec.duration_ms > 0
+        assert rec.args_size == len(json.dumps({"text": "hello"}))
+        assert rec.result_size and rec.result_size > 0
+        assert rec.args is None and rec.result is None
+        assert rec.session_id and rec.request_id
+
+    async def test_full_mode_redacts_args_and_results(self):
+        app, sink, mw = make_app(mode="full")
+        await call(app, "create_token", {"label": "ci"})
+        await call(app, "login", {"user": "ryan", "password": "hunter2"})
+        await mw.flush()
+
+        token_rec, login_rec = sink.records
+        dumped = json.dumps([token_rec.to_dict(), login_rec.to_dict()])
+        assert BMCP_TOKEN not in dumped and "hunter2" not in dumped
+        assert token_rec.result["access_token"] == REDACTED
+        assert token_rec.result["note"] == f"use {REDACTED}"
+        assert token_rec.result["label"] == "ci"
+        assert login_rec.args == {"user": "ryan", "password": REDACTED}
+
+    async def test_failed_call_recorded_and_error_unchanged(self):
+        app, sink, mw = make_app()
+        with pytest.raises(ToolError, match="bad input"):
+            await call(app, "fail", {"secret": "hunter2"})
+        await mw.flush()
+
+        [rec] = sink.records
+        assert not rec.ok
+        assert rec.error_type == "ValueError"
+        assert "hunter2" not in rec.error_message
+        assert f"secret={REDACTED}" in rec.error_message
+
+    async def test_meta_only_tools_override_full_mode(self):
+        app, sink, mw = make_app(mode="full", meta_only_tools={"create_token"})
+        await call(app, "create_token", {"label": "ci"})
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        token_rec, echo_rec = sink.records
+        assert token_rec.mode == "meta" and token_rec.result is None
+        assert token_rec.result_size > 0
+        assert echo_rec.mode == "full" and echo_rec.result == {"echo": "hi"}
+
+    async def test_off_mode_records_nothing(self):
+        app, sink, mw = make_app(mode="off")
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+        assert sink.records == []
+
+    async def test_mode_from_environment(self, monkeypatch):
+        monkeypatch.setenv("FEEDBACK_INSTRUMENTATION_MODE", "full")
+        assert InstrumentationMiddleware([]).mode == "full"
+
+    def test_invalid_mode_rejected(self):
+        with pytest.raises(ValueError, match="mode must be one of"):
+            InstrumentationMiddleware([], mode="everything")
+
+
+class TestHooks:
+    async def test_identity_resolver_fills_columns(self):
+        def who(context):
+            assert context.fastmcp_context is not None
+            return {
+                "user_sub": "user-1",
+                "caller_kind": "pat:7",
+                "client_id": "blender-addon",
+                "org": "acme",
+                "token": BMCP_TOKEN,
+            }
+
+        app, sink, mw = make_app(identity_resolver=who)
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        [rec] = sink.records
+        assert (rec.user_sub, rec.caller_kind, rec.client_id) == (
+            "user-1",
+            "pat:7",
+            "blender-addon",
+        )
+        assert rec.identity == {"org": "acme", "token": REDACTED}
+
+    async def test_async_enricher_gets_result_and_sets_extra(self):
+        seen = {}
+
+        async def enrich(tool, args, result, context):
+            seen.update(tool=tool, args=args, result=result)
+            return {"job_id": "job-42", "server_version": "2026.9.27", "api_key": "k"}
+
+        app, sink, mw = make_app(enricher=enrich, server_version="default")
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        [rec] = sink.records
+        assert seen == {
+            "tool": "echo",
+            "args": {"text": "hi"},
+            "result": {"echo": "hi"},
+        }
+        assert rec.extra == {"job_id": "job-42", "api_key": REDACTED}
+        assert rec.server_version == "2026.9.27"
+
+    async def test_server_version_default(self):
+        app, sink, mw = make_app(server_version="1.0")
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+        assert sink.records[0].server_version == "1.0"
+
+    async def test_hook_exceptions_do_not_break_calls(self):
+        def boom(*args):
+            raise RuntimeError("hook bug")
+
+        app, sink, mw = make_app(identity_resolver=boom, enricher=boom)
+        result = await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        assert result.data == {"echo": "hi"}
+        [rec] = sink.records
+        assert rec.ok and rec.identity == {} and rec.extra == {}
+
+    async def test_slow_async_hook_is_cut_off(self):
+        async def slow(*args):
+            await asyncio.sleep(5)
+            return {"never": True}
+
+        app, sink, mw = make_app(enricher=slow, hook_timeout=0.05)
+        start = time.perf_counter()
+        await call(app, "echo", {"text": "hi"})
+        assert time.perf_counter() - start < 2
+        await mw.flush()
+        assert sink.records[0].extra == {}
+
+
+class TestNeverBlocksOrBreaks:
+    async def test_failing_sink_does_not_break_calls_or_other_sinks(self):
+        class Broken:
+            async def write(self, records):
+                raise ConnectionError("database down")
+
+        good = MemorySink()
+        app, _, mw = make_app(sinks=[Broken(), good])
+        result = await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        assert result.data == {"echo": "hi"}
+        assert mw.dispatcher.sink_errors == 1
+        assert len(good.records) == 1
+
+    async def test_stalled_sink_drops_records_instead_of_waiting(self):
+        release = asyncio.Event()
+
+        class Stalled:
+            def __init__(self):
+                self.records = []
+
+            async def write(self, records):
+                await release.wait()
+                self.records.extend(records)
+
+        stalled = Stalled()
+        app, _, mw = make_app(sinks=[stalled], max_queue=2, batch_size=1)
+
+        start = time.perf_counter()
+        async with Client(app) as client:
+            for i in range(6):
+                await client.call_tool("echo", {"text": str(i)})
+        assert time.perf_counter() - start < 3
+
+        # One record is in the stalled write, two fit the queue, the rest drop.
+        assert mw.dispatcher.dropped == 3
+        release.set()
+        await mw.flush()
+        assert len(stalled.records) == 3
+
+    async def test_record_building_failure_does_not_break_calls(self, monkeypatch):
+        app, sink, mw = make_app()
+
+        async def explode(*args, **kwargs):
+            raise RuntimeError("bug in record building")
+
+        monkeypatch.setattr(mw, "_build_record", explode)
+        result = await call(app, "echo", {"text": "hi"})
+        assert result.data == {"echo": "hi"}
+
+    async def test_tool_error_passes_through_even_if_recording_fails(self, monkeypatch):
+        app, sink, mw = make_app()
+
+        async def explode(*args, **kwargs):
+            raise RuntimeError("bug in record building")
+
+        monkeypatch.setattr(mw, "_build_record", explode)
+        with pytest.raises(ToolError, match="bad input"):
+            await call(app, "fail", {"secret": "x"})
+
+    def test_submit_without_event_loop_drops(self):
+        dispatcher = RecordDispatcher([MemorySink()])
+        record = ToolCallRecord(
+            tool="t",
+            started_at=__import__("datetime").datetime.now(),
+            duration_ms=1,
+            ok=True,
+            mode="meta",
+        )
+        assert dispatcher.submit(record) is False
+        assert dispatcher.dropped == 1
+
+
+class TestSinks:
+    async def test_json_lines_sink(self):
+        stream = io.StringIO()
+        app, _, mw = make_app(sinks=[JsonLinesSink(stream)])
+        await call(app, "echo", {"text": "hi"})
+        await call(app, "echo", {"text": "again"})
+        await mw.flush()
+
+        lines = [json.loads(line) for line in stream.getvalue().splitlines()]
+        assert [line["tool"] for line in lines] == ["echo", "echo"]
+        assert lines[0]["started_at"].endswith("+00:00")
+
+    async def test_callback_sink_sync_and_async(self):
+        got_sync, got_async = [], []
+
+        async def async_cb(records):
+            got_async.extend(records)
+
+        app, _, mw = make_app(
+            sinks=[CallbackSink(got_sync.extend), CallbackSink(async_cb)]
+        )
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+        assert len(got_sync) == len(got_async) == 1
+
+    async def test_aclose_closes_sinks(self):
+        closed = []
+
+        class Closable(MemorySink):
+            async def aclose(self):
+                closed.append(True)
+
+        app, _, mw = make_app(sinks=[Closable()])
+        await call(app, "echo", {"text": "hi"})
+        await mw.aclose()
+        assert closed == [True]
+
+
+class TestDatabaseSink:
+    async def test_end_to_end_with_created_tables(self, tmp_path):
+        url = f"sqlite+aiosqlite:///{tmp_path}/calls.db"
+        db = DatabaseSink(url, create_tables=True)
+        app, _, mw = make_app(sinks=[db], mode="full", server_version="9.9")
+        await call(app, "create_token", {"label": "ci"})
+        with pytest.raises(ToolError):
+            await call(app, "fail", {"secret": "hunter2"})
+        await mw.flush()
+
+        async with db.engine.connect() as conn:
+            rows = (
+                (await conn.execute(select(db.table).order_by(db.table.c.started_at)))
+                .mappings()
+                .all()
+            )
+        await mw.aclose()
+
+        assert [r["tool"] for r in rows] == ["create_token", "fail"]
+        assert rows[0]["ok"] is True and rows[1]["ok"] is False
+        assert rows[0]["result"]["access_token"] == REDACTED
+        assert rows[1]["error_type"] == "ValueError"
+        assert rows[0]["server_version"] == "9.9"
+        assert "hunter2" not in json.dumps([dict(r) for r in rows], default=str)
+
+    async def test_prefix_and_host_owned_engine(self, tmp_path):
+        engine = create_async_engine(f"sqlite+aiosqlite:///{tmp_path}/host.db")
+        db = DatabaseSink(engine, prefix="qa_", create_tables=True)
+        app, _, mw = make_app(sinks=[db])
+        await call(app, "echo", {"text": "hi"})
+        await mw.aclose()
+
+        # The host's engine is still usable: the sink did not dispose it.
+        async with engine.connect() as conn:
+            tables = await conn.run_sync(lambda c: inspect(c).get_table_names())
+        await engine.dispose()
+        assert sorted(tables) == ["qa_feedback_call_links", "qa_tool_calls"]
+
+    async def test_no_tables_created_by_default(self, tmp_path):
+        engine = create_async_engine(f"sqlite+aiosqlite:///{tmp_path}/host.db")
+        app, _, mw = make_app(sinks=[DatabaseSink(engine)])
+        result = await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        async with engine.connect() as conn:
+            tables = await conn.run_sync(lambda c: inspect(c).get_table_names())
+        await engine.dispose()
+
+        # The insert fails (no table), is counted, and the call still worked.
+        assert result.data == {"echo": "hi"}
+        assert tables == []
+        assert mw.dispatcher.sink_errors == 1
+
+    async def test_absent_payloads_are_sql_null(self, tmp_path):
+        """Meta mode stores no payloads; they must be SQL NULL, not JSON null."""
+        db = DatabaseSink(f"sqlite+aiosqlite:///{tmp_path}/n.db", create_tables=True)
+        app, _, mw = make_app(sinks=[db])
+        await call(app, "echo", {"text": "hi"})
+        await mw.flush()
+
+        t = db.table
+        async with db.engine.connect() as conn:
+            nulls = (
+                await conn.execute(select(t.c.args.is_(None), t.c.result.is_(None)))
+            ).one()
+        await mw.aclose()
+        assert tuple(nulls) == (True, True)
+
+    def test_build_metadata_joins_host_metadata(self):
+        host = MetaData()
+        assert build_metadata("ffb_", host) is host
+        build_metadata("ffb_", host)
+        assert sorted(host.tables) == ["ffb_feedback_call_links", "ffb_tool_calls"]
+
+
+class TestIntegration:
+    async def test_records_mounted_server_tools_by_prefixed_name(self):
+        main = FastMCP("main")
+        sub = FastMCP("sub")
+
+        @sub.tool
+        def ping() -> str:
+            return "pong"
+
+        main.mount(sub, "svc")
+        sink = MemorySink()
+        mw = instrument(main, [sink])
+        await call(main, "svc_ping")
+        await mw.flush()
+        assert [r.tool for r in sink.records] == ["svc_ping"]
+
+    async def test_records_feedback_tools(self):
+        app = FastMCP("with-feedback")
+        add_feedback_tools(app, database_url="sqlite:///:memory:")
+        sink = MemorySink()
+        mw = instrument(app, [sink])
+        await call(
+            app,
+            "submit_feedback",
+            {
+                "request": {
+                    "type": "bug",
+                    "title": "t",
+                    "description": "instrumented",
+                    "submitter": "me",
+                }
+            },
+        )
+        await mw.flush()
+        assert [r.tool for r in sink.records] == ["submit_feedback"]

tests/unit/test_mixins.py

@@ -7,6 +7,7 @@ from fastmcp import FastMCP
 from fastmcp_feedback.mixins import SubmissionMixin, RetrievalMixin, ManagementMixin
 from fastmcp_feedback.models import SubmitFeedbackRequest, FeedbackStatus
 from fastmcp_feedback.database import FeedbackDatabase
+from tests._compat import tool_map
 
 
 @pytest.mark.unit
@@ -95,7 +96,7 @@ class TestSubmissionMixin:
         mixin.register_tools(mock_fastmcp_server)
         
         # Verify tool was registered
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         assert "submit_feedback" in tool_names
     
@@ -107,7 +108,7 @@ class TestSubmissionMixin:
         mixin.register_tools(mock_fastmcp_server, prefix="support", separator="_")
         
         # Verify tool was registered with prefix
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         assert "support_submit_feedback" in tool_names
     
@@ -267,7 +268,7 @@ class TestRetrievalMixin:
         
         mixin.register_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         expected_tools = ["list_feedback", "get_feedback_statistics"]
@@ -437,7 +438,7 @@ class TestManagementMixin:
         
         mixin.register_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         expected_tools = ["update_feedback_status", "delete_feedback"]
@@ -532,7 +533,7 @@ class TestMixinIntegration:
         management.register_tools(mock_fastmcp_server)
         
         # Verify all tools are registered
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         expected_tools = [
@@ -555,7 +556,7 @@ class TestMixinIntegration:
         submission.register_tools(mock_fastmcp_server, prefix="admin")
         retrieval.register_tools(mock_fastmcp_server, prefix="public")
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "admin_submit_feedback" in tool_names
@@ -663,7 +664,7 @@ class TestMixinConfiguration:
         # Register with dash separator
         submission.register_tools(mock_fastmcp_server, prefix="api", separator="-")
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "api-submit_feedback" in tool_names
@@ -676,7 +677,7 @@ class TestMixinConfiguration:
         # Test the standard registration instead
         submission.register_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # SubmissionMixin should only register its tools

tests/unit/test_soft_errors.py

@@ -0,0 +1,397 @@
+"""Tests for classifying error results that tools return instead of raising.
+
+Real FastMCP servers through fastmcp.Client, as in test_instrumentation.py.
+"""
+
+import contextlib
+import logging
+
+import pytest
+from fastmcp import Client, FastMCP
+from fastmcp.exceptions import ToolError
+from mcp.types import CallToolResult, TextContent
+from sqlalchemy import select
+
+from fastmcp_feedback import add_feedback_tools
+from fastmcp_feedback.instrumentation import (
+    DEFAULT_RESULT_CLASSIFIER,
+    REDACTED,
+    DatabaseSink,
+    MemorySink,
+    ToolCallRecord,
+    instrument,
+    soft_error_classifier,
+)
+from fastmcp_feedback.mixins import submission
+
+BMCP_TOKEN = "bmcp_" + "A1b2C3d4E5f6G7h8I9j0"
+
+try:
+    from fastmcp.tools.tool import ToolResult
+except ImportError:  # FastMCP 4
+    from fastmcp.tools import ToolResult
+
+try:
+    ToolResult(content=[TextContent(type="text", text="x")], is_error=True)
+    TOOL_RESULT_IS_ERROR = True
+except TypeError:  # added in FastMCP 3.4
+    TOOL_RESULT_IS_ERROR = False
+
+
+@pytest.fixture
+async def db(tmp_path):
+    """DatabaseSinks whose engines are always disposed, or the process hangs."""
+    made = []
+
+    def factory(name="calls"):
+        sink = DatabaseSink(
+            f"sqlite+aiosqlite:///{tmp_path}/{name}.db", create_tables=True
+        )
+        made.append(sink)
+        return sink
+
+    yield factory
+    for sink in made:
+        await sink.engine.dispose()
+
+
+def make_app(sinks=None, **kwargs):
+    sink = MemorySink()
+    app = FastMCP("soft")
+
+    @app.tool
+    def render(status: str) -> dict:
+        return {"status": status, "error": f"render said {status}"}
+
+    @app.tool
+    def respond(payload: dict) -> dict:
+        return payload
+
+    @app.tool
+    def text(value: str) -> str:
+        return value
+
+    @app.tool
+    def items() -> list:
+        return [{"status": "failed"}]
+
+    @app.tool
+    def crash() -> dict:
+        raise RuntimeError("exploded")
+
+    @app.tool
+    def mcp_error() -> CallToolResult:
+        return CallToolResult(
+            content=[TextContent(type="text", text="target missing")], isError=True
+        )
+
+    mw = instrument(app, sinks if sinks is not None else [sink], **kwargs)
+    return app, sink, mw
+
+
+async def run(app, mw, tool, args=None):
+    async with Client(app) as client:
+        with contextlib.suppress(ToolError):
+            await client.call_tool(tool, args or {})
+    await mw.flush()
+
+
+async def record_for(tool, args=None, **kwargs) -> ToolCallRecord:
+    app, sink, mw = make_app(**kwargs)
+    await run(app, mw, tool, args)
+    [record] = sink.records
+    return record
+
+
+class TestClassifier:
+    @pytest.mark.parametrize(
+        "result, expected",
+        [
+            ({"status": "failed", "error": "disk full"}, "status=failed: disk full"),
+            ({"state": "ERROR"}, "state=ERROR"),
+            ({"ok": False, "message": "no scene"}, "ok=False: no scene"),
+            ({"success": False, "error": "nope"}, "success=False: nope"),
+            ({"success": False, "detail": "d", "reason": "r"}, "success=False: d"),
+            (
+                {"status": "failure", "error": {"code": 7, "message": "inner"}},
+                "status=failure: inner",
+            ),
+            ({"isError": True, "content": ["boom"]}, "isError: boom"),
+            (
+                {"is_error": True, "content": [{"type": "text", "text": "a"}]},
+                "isError: a",
+            ),
+        ],
+    )
+    def test_flagged(self, result, expected):
+        assert DEFAULT_RESULT_CLASSIFIER("t", result) == expected
+
+    @pytest.mark.parametrize(
+        "result",
+        [
+            {"status": "done"},
+            {"status": "unknown_target"},
+            {"ok": True},
+            {"ok": 0},
+            {"success": None},
+            {"result": False},
+            {"state": 3},
+            {"isError": False},
+            [{"status": "failed"}],
+            "failed",
+            None,
+        ],
+    )
+    def test_not_flagged(self, result):
+        assert DEFAULT_RESULT_CLASSIFIER("t", result) is None
+
+    def test_extra_statuses(self):
+        classify = soft_error_classifier(extra_statuses=("unknown_target",))
+        assert (
+            classify("t", {"status": "unknown_target", "error": "no cube"})
+            == "status=unknown_target: no cube"
+        )
+        assert classify("t", {"status": "failed"}) == "status=failed"
+
+    def test_custom_keys_replace_defaults(self):
+        classify = soft_error_classifier(
+            statuses=("bad",), status_keys=("phase",), flag_keys=("passed",)
+        )
+        assert classify("t", {"phase": "bad"}) == "phase=bad"
+        assert classify("t", {"passed": False}) == "passed=False"
+        assert classify("t", {"status": "failed", "ok": False}) is None
+
+
+class TestMiddleware:
+    async def test_status_failed_is_soft_error(self):
+        record = await record_for("render", {"status": "failed"})
+        assert (record.outcome, record.ok, record.error_type) == (
+            "soft_error",
+            False,
+            "SoftError",
+        )
+        assert record.error_message == "status=failed: render said failed"
+
+    @pytest.mark.parametrize("key", ["ok", "success"])
+    async def test_false_flags_are_soft_errors(self, key):
+        record = await record_for("respond", {"payload": {key: False, "error": "x"}})
+        assert (record.outcome, record.ok) == ("soft_error", False)
+        assert record.error_message == f"{key}=False: x"
+
+    async def test_message_is_redacted_and_truncated(self):
+        record = await record_for(
+            "respond",
+            {"payload": {"status": "error", "error": f"bad key {BMCP_TOKEN} " * 50}},
+            max_error_chars=60,
+        )
+        assert BMCP_TOKEN not in record.error_message
+        assert REDACTED in record.error_message
+        assert len(record.error_message) == 60
+
+    async def test_extra_statuses(self):
+        record = await record_for(
+            "render",
+            {"status": "unknown_target"},
+            result_classifier=soft_error_classifier(extra_statuses=("unknown_target",)),
+        )
+        assert record.outcome == "soft_error"
+        assert (
+            record.error_message == "status=unknown_target: render said unknown_target"
+        )
+
+    async def test_unknown_status_is_ok_by_default(self):
+        record = await record_for("render", {"status": "unknown_target"})
+        assert (record.outcome, record.ok, record.error_type) == ("ok", True, None)
+
+    @pytest.mark.parametrize(
+        "tool, args",
+        [
+            ("text", {"value": "failed"}),
+            ("items", {}),
+            ("respond", {"payload": {"status": "done", "count": 3}}),
+        ],
+    )
+    async def test_normal_results_stay_ok(self, tool, args):
+        record = await record_for(tool, args)
+        assert (record.outcome, record.ok, record.error_message) == ("ok", True, None)
+
+    async def test_none_disables(self):
+        record = await record_for(
+            "render", {"status": "failed"}, result_classifier=None
+        )
+        assert (record.outcome, record.ok, record.error_type) == ("ok", True, None)
+
+    async def test_custom_classifier(self):
+        seen = []
+
+        def classify(tool, result):
+            seen.append((tool, result))
+            return "empty" if result.get("count") == 0 else None
+
+        record = await record_for(
+            "respond", {"payload": {"count": 0}}, result_classifier=classify
+        )
+        assert seen == [("respond", {"count": 0})]
+        assert (record.outcome, record.error_message) == ("soft_error", "empty")
+
+    async def test_raising_classifier_records_ok(self, caplog):
+        def classify(tool, result):
+            raise KeyError("classifier bug")
+
+        app, sink, mw = make_app(result_classifier=classify)
+        with caplog.at_level(logging.WARNING):
+            async with Client(app) as client:
+                result = await client.call_tool("render", {"status": "failed"})
+            await mw.flush()
+        assert result.data["status"] == "failed"
+        [record] = sink.records
+        assert (record.outcome, record.ok, record.error_type) == ("ok", True, None)
+        assert "Result classifier" in caplog.text
+
+    async def test_classifier_not_run_on_exceptions(self):
+        calls = []
+        record = await record_for(
+            "crash", result_classifier=lambda t, r: calls.append(t) or "x"
+        )
+        assert calls == []
+        assert (record.outcome, record.ok, record.error_type) == (
+            "error",
+            False,
+            "RuntimeError",
+        )
+        assert record.error_message == "exploded"
+
+    async def test_mcp_error_result_without_raising(self):
+        """A CallToolResult with isError, on every FastMCP version."""
+        record = await record_for("mcp_error")
+        assert (record.outcome, record.ok) == ("soft_error", False)
+        assert record.error_message == "isError: target missing"
+
+    @pytest.mark.skipif(not TOOL_RESULT_IS_ERROR, reason="ToolResult.is_error is 3.4+")
+    async def test_tool_result_is_error(self):
+        app = FastMCP("is_error")
+
+        @app.tool
+        def lookup():
+            return ToolResult(
+                content=[TextContent(type="text", text="not found")], is_error=True
+            )
+
+        sink = MemorySink()
+        mw = instrument(app, [sink])
+        async with Client(app) as client:
+            await client.call_tool("lookup", {}, raise_on_error=False)
+        await mw.flush()
+        [record] = sink.records
+        assert (record.outcome, record.error_message) == (
+            "soft_error",
+            "isError: not found",
+        )
+
+    def test_record_outcome_defaults_from_ok(self):
+        from datetime import UTC, datetime
+
+        now = datetime.now(UTC)
+        assert ToolCallRecord("t", now, 1.0, True, "meta").outcome == "ok"
+        assert ToolCallRecord("t", now, 1.0, False, "meta").outcome == "error"
+
+
+class TestStorageAndCorrelation:
+    async def test_database_sink_writes_outcome(self, db):
+        sink = db()
+        app, _, mw = make_app(sinks=[sink])
+        async with Client(app) as client:
+            await client.call_tool("render", {"status": "done"})
+            await client.call_tool("render", {"status": "failed"})
+            with contextlib.suppress(ToolError):
+                await client.call_tool("crash", {})
+        await mw.flush()
+
+        t = sink.table
+        async with sink.engine.connect() as conn:
+            rows = (
+                await conn.execute(
+                    select(t.c.outcome, t.c.ok, t.c.error_type).order_by(t.c.started_at)
+                )
+            ).all()
+        assert [tuple(r) for r in rows] == [
+            ("ok", True, None),
+            ("soft_error", False, "SoftError"),
+            ("error", False, "RuntimeError"),
+        ]
+        async with sink.engine.connect() as conn:
+            [(failing,)] = (
+                await conn.execute(
+                    select(t.c.tool).where(~t.c.ok, t.c.outcome != "error")
+                )
+            ).all()
+        assert failing == "render"
+
+    async def test_links_and_feedback_context_show_soft_errors(self, db):
+        app, _, mw = make_app(
+            sinks=[db()], identity_resolver=lambda c: {"user_sub": "u1"}
+        )
+        captured = {}
+
+        @app.tool
+        async def report() -> int:
+            captured["links"] = await mw.capture_recent_calls()
+            await mw.link_feedback("bug-1", captured["links"])
+            return len(captured["links"])
+
+        async with Client(app) as client:
+            await client.call_tool("render", {"status": "failed"})
+            await client.call_tool("report", {})
+
+        links = captured["links"]
+        assert [(link.tool, link.ok) for link in links] == [("render", False)]
+        # Filled from memory or read from the database, depending on timing.
+        [row] = await mw.feedback_context("bug-1")
+        assert (row["outcome"], row["ok"], row["error_type"]) == (
+            "soft_error",
+            False,
+            "SoftError",
+        )
+        await mw.flush()
+        [row] = await mw.feedback_context("bug-1")
+        assert (row["tool"], row["outcome"], row["ok"]) == (
+            "render",
+            "soft_error",
+            False,
+        )
+        await mw.aclose()
+
+    async def test_submit_feedback_failure_is_soft_error(self, monkeypatch):
+        def broken(request):
+            raise RuntimeError("database down, password=hunter2")
+
+        monkeypatch.setattr(submission, "create_feedback_from_request", broken)
+        app = FastMCP("fb")
+        sink = MemorySink()
+        mw = instrument(app, [sink])
+        add_feedback_tools(app, database_url="sqlite:///:memory:", instrumentation=mw)
+
+        async with Client(app) as client:
+            result = await client.call_tool(
+                "submit_feedback",
+                {
+                    "request": {
+                        "type": "bug",
+                        "title": "t",
+                        "description": "d",
+                        "submitter": "m",
+                    }
+                },
+            )
+        await mw.flush()
+        assert result.data["success"] is False
+        [record] = sink.records
+        assert (record.tool, record.outcome, record.ok, record.error_type) == (
+            "submit_feedback",
+            "soft_error",
+            False,
+            "SoftError",
+        )
+        assert record.error_message == (
+            f"success=False: database down, password={REDACTED}"
+        )

tests/unit/test_tools.py

@@ -7,6 +7,7 @@ from fastmcp import FastMCP
 from fastmcp_feedback.tools import add_feedback_tools
 from fastmcp_feedback.feedback import create_feedback_server
 from fastmcp_feedback.models import SubmitFeedbackRequest
+from tests._compat import tool_map
 
 
 @pytest.mark.unit
@@ -18,7 +19,7 @@ class TestAddFeedbackTools:
         """Test adding feedback tools with basic configuration."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         expected_tools = [
@@ -40,7 +41,7 @@ class TestAddFeedbackTools:
             prefix="support"
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         expected_tools = [
@@ -62,7 +63,7 @@ class TestAddFeedbackTools:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         
         # Should have all standard tools - check tool names in the keys
         assert len([name for name in tools.keys() if "feedback" in name]) >= 5
@@ -76,7 +77,7 @@ class TestAddFeedbackTools:
         # Should use default SQLite database
         add_feedback_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "submit_feedback" in tool_names
@@ -91,7 +92,7 @@ class TestAddFeedbackTools:
             separator="-"
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "api-submit_feedback" in tool_names
@@ -105,7 +106,7 @@ class TestAddFeedbackTools:
         # Second call with different prefix
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url, prefix="user")
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have tools with both prefixes
@@ -128,7 +129,7 @@ class TestCreateFeedbackServer:
         assert isinstance(server, FastMCP)
         assert server.name == "Test Feedback Server"
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         tool_names = list(tools.keys())
         
         expected_tools = [
@@ -150,7 +151,7 @@ class TestCreateFeedbackServer:
         )
         
         assert server.name == "Custom DB Server"
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         assert len(tools) >= 5
     
     async def test_create_feedback_server_with_insights(self, test_insights):
@@ -162,7 +163,7 @@ class TestCreateFeedbackServer:
         
         assert server.name == "Analytics Server"
         # Verify insights are integrated
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         assert len(tools) >= 5
     
     async def test_create_feedback_server_with_description(self):
@@ -184,8 +185,8 @@ class TestCreateFeedbackServer:
         assert server1.name != server2.name
         
         # Each should have independent tool sets
-        tools1 = await server1.get_tools()
-        tools2 = await server2.get_tools()
+        tools1 = await tool_map(server1)
+        tools2 = await tool_map(server2)
         
         assert len(tools1) >= 5
         assert len(tools2) >= 5
@@ -201,7 +202,7 @@ class TestToolIntegration:
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
         # Get the submit_feedback tool
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         submit_tool = tools["submit_feedback"]
         
         assert submit_tool is not None
@@ -218,7 +219,7 @@ class TestToolIntegration:
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
         # Get the list_feedback tool
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         list_tool = tools["list_feedback"]
         
         assert list_tool is not None
@@ -234,7 +235,7 @@ class TestToolIntegration:
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
         # Get the statistics tool
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         stats_tool = tools["get_feedback_statistics"]
         
         assert stats_tool is not None
@@ -250,7 +251,7 @@ class TestToolIntegration:
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
         # Get the update status tool
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         update_tool = tools["update_feedback_status"]
         
         assert update_tool is not None
@@ -269,7 +270,7 @@ class TestToolIntegration:
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
         # Get the delete tool
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         delete_tool = tools["delete_feedback"]
         
         assert delete_tool is not None
@@ -290,7 +291,7 @@ class TestToolValidation:
         """Test submit_feedback tool parameter validation."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         submit_tool = tools["submit_feedback"]
         
         # Test with invalid parameters
@@ -301,7 +302,7 @@ class TestToolValidation:
         """Test list_feedback tool parameter validation."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         list_tool = tools["list_feedback"]
         
         # Test with valid optional parameters
@@ -318,7 +319,7 @@ class TestToolValidation:
         """Test update_feedback_status parameter validation."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         update_tool = tools["update_feedback_status"]
         
         # Test with missing required parameters
@@ -329,7 +330,7 @@ class TestToolValidation:
         """Test delete_feedback parameter validation."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         delete_tool = tools["delete_feedback"]
         
         # Test with missing required parameters
@@ -348,9 +349,9 @@ class TestServerComposition:
         feedback_server = create_feedback_server("Feedback Service")
         
         # Import feedback server with prefix
-        await main_server.import_server(feedback_server, prefix="feedback")
+        main_server.mount(feedback_server, "feedback")
         
-        tools = await main_server.get_tools()
+        tools = await tool_map(main_server)
         tool_names = list(tools.keys())
         
         # Should have feedback tools with prefix
@@ -364,10 +365,10 @@ class TestServerComposition:
         user_feedback = create_feedback_server("User Feedback")
         admin_feedback = create_feedback_server("Admin Feedback")
         
-        await main_server.import_server(user_feedback, prefix="user")
-        await main_server.import_server(admin_feedback, prefix="admin")
+        main_server.mount(user_feedback, "user")
+        main_server.mount(admin_feedback, "admin")
         
-        tools = await main_server.get_tools()
+        tools = await tool_map(main_server)
         tool_names = list(tools.keys())
         
         # Should have tools from both servers
@@ -386,9 +387,9 @@ class TestServerComposition:
         # Implementation would need to support this feature
         # FastMCP import_server doesn't support selective tool import
         # but we can test the full import with prefix
-        await main_server.import_server(feedback_server, prefix="public")
+        main_server.mount(feedback_server, "public")
         
-        tools = await main_server.get_tools()
+        tools = await tool_map(main_server)
         tool_names = list(tools.keys())
         
         # All tools should be imported with prefix
@@ -416,7 +417,7 @@ class TestToolPerformance:
         assert performance_timer.duration_ms < 1000  # 1 second
         
         # Verify all tools were registered
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         assert len(tools) >= 5
     
     async def test_multiple_server_creation_performance(self, performance_timer):
@@ -436,14 +437,14 @@ class TestToolPerformance:
         
         # Each server should be functional
         for server in servers:
-            tools = await server.get_tools()
+            tools = await tool_map(server)
             assert len(tools) >= 5
     
     async def test_tool_execution_performance(self, mock_fastmcp_server, memory_db_url, performance_timer):
         """Test performance of tool execution."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         list_tool = tools["list_feedback"]
         
         performance_timer.start()
@@ -467,7 +468,7 @@ class TestToolConfiguration:
         """Test that tools have proper descriptions."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         
         for tool_name, tool_obj in tools.items():
             # Each tool should have a description
@@ -480,7 +481,7 @@ class TestToolConfiguration:
         """Test tool metadata and categorization."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         feedback_tools = [name for name in tools.keys() if "feedback" in name]
         
         # Should have categorized the tools appropriately
@@ -490,7 +491,7 @@ class TestToolConfiguration:
         """Test tool parameter schemas."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         submit_tool = tools["submit_feedback"]
         
         # Tool should have parameter schema defined
@@ -510,7 +511,7 @@ class TestToolErrorHandling:
         # Use invalid database URL
         add_feedback_tools(server, database_url="sqlite:///nonexistent/path/db.sqlite")
         
-        tools = await server.get_tools()
+        tools = await tool_map(server)
         list_tool = tools["list_feedback"]
         
         # Tool execution should handle database errors gracefully
@@ -523,7 +524,7 @@ class TestToolErrorHandling:
         """Test tool handling of invalid parameters."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         submit_tool = tools["submit_feedback"]
         
         # Test with malformed request
@@ -534,7 +535,7 @@ class TestToolErrorHandling:
         """Test concurrent execution of tools."""
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         list_tool = tools["list_feedback"]
         
         import asyncio

tests/unit/test_tools_comprehensive.py

@@ -23,6 +23,7 @@ from fastmcp_feedback.tools import (
 )
 from fastmcp_feedback.database import FeedbackDatabase
 from fastmcp_feedback.insights import FeedbackInsights
+from tests._compat import tool_map
 
 
 @pytest.mark.unit
@@ -34,7 +35,7 @@ class TestSubmissionTools:
         """Test adding submission tools with basic configuration."""
         add_submission_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have submission-related tools
@@ -51,7 +52,7 @@ class TestSubmissionTools:
             prefix="user"
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "user_submit_feedback" in tool_names
@@ -65,14 +66,14 @@ class TestSubmissionTools:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) > 0
     
     async def test_add_submission_tools_without_database_url(self, mock_fastmcp_server):
         """Test adding submission tools without database URL (uses default)."""
         add_submission_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert "submit_feedback" in tools
     
     @patch('fastmcp_feedback.tools.FeedbackDatabase')
@@ -105,7 +106,7 @@ class TestSubmissionTools:
             prefix="api_"  # With trailing underscore
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should strip trailing underscore
@@ -121,7 +122,7 @@ class TestRetrievalTools:
         """Test adding retrieval tools with basic configuration."""
         add_retrieval_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have retrieval-related tools
@@ -139,7 +140,7 @@ class TestRetrievalTools:
             prefix="public"
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "public_list_feedback" in tool_names
@@ -154,14 +155,14 @@ class TestRetrievalTools:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) > 0
     
     async def test_add_retrieval_tools_without_database_url(self, mock_fastmcp_server):
         """Test adding retrieval tools without database URL (uses default)."""
         add_retrieval_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert "list_feedback" in tools
         assert "get_feedback_statistics" in tools
     
@@ -197,7 +198,7 @@ class TestManagementTools:
         """Test adding management tools with basic configuration."""
         add_management_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have management-related tools
@@ -215,7 +216,7 @@ class TestManagementTools:
             prefix="admin"
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "admin_update_feedback_status" in tool_names
@@ -230,14 +231,14 @@ class TestManagementTools:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) > 0
     
     async def test_add_management_tools_without_database_url(self, mock_fastmcp_server):
         """Test adding management tools without database URL (uses default)."""
         add_management_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert "update_feedback_status" in tools
         assert "delete_feedback" in tools
     
@@ -347,7 +348,7 @@ class TestAdvancedIntegrationPatterns:
         
         create_multi_tenant_tools(mock_fastmcp_server, tenants)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have tools for each tenant with prefixes
@@ -365,7 +366,7 @@ class TestAdvancedIntegrationPatterns:
         
         create_multi_tenant_tools(mock_fastmcp_server, tenants, insights=test_insights)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) >= 10  # At least 5 tools per tenant
     
     async def test_create_multi_tenant_tools_empty_tenants(self, mock_fastmcp_server):
@@ -374,7 +375,7 @@ class TestAdvancedIntegrationPatterns:
         
         create_multi_tenant_tools(mock_fastmcp_server, tenants)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         # Should complete without error but not add any tools
         assert len(tools) == 0
     
@@ -394,7 +395,7 @@ class TestAdvancedIntegrationPatterns:
         """Test creating role-based tools."""
         create_role_based_tools(mock_fastmcp_server, database_url=memory_db_url)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have public tools (submission and retrieval)
@@ -416,14 +417,14 @@ class TestAdvancedIntegrationPatterns:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) >= 7  # Public + admin tools
     
     async def test_create_role_based_tools_without_database(self, mock_fastmcp_server):
         """Test creating role-based tools without database URL."""
         create_role_based_tools(mock_fastmcp_server)
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         assert "public_submit_feedback" in tool_names
@@ -465,7 +466,7 @@ class TestMigrationHelpers:
         mock_fastmcp_server.remove_tool.assert_any_call("old_list_tool")
         
         # Should have new tools added
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         assert "submit_feedback" in tool_names
         assert "list_feedback" in tool_names
@@ -501,7 +502,7 @@ class TestMigrationHelpers:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) >= 5
     
     async def test_migrate_tools_to_mixins_empty_list(self, mock_fastmcp_server, memory_db_url):
@@ -515,7 +516,7 @@ class TestMigrationHelpers:
         )
         
         # Should still add new tools
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         assert len(tools) >= 5
     
     @patch('fastmcp_feedback.tools.add_feedback_tools')
@@ -757,7 +758,7 @@ class TestErrorHandlingAndEdgeCases:
         
         # Verify all servers have tools
         for server in servers:
-            tools = await server.get_tools()
+            tools = await tool_map(server)
             assert "submit_feedback" in tools
             assert "public_list_feedback" in tools
             assert "admin_update_feedback_status" in tools
@@ -774,7 +775,7 @@ class TestErrorHandlingAndEdgeCases:
         # Multiple underscores
         add_management_tools(mock_fastmcp_server, database_url=memory_db_url, prefix="admin___")
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should handle edge cases gracefully
@@ -812,7 +813,7 @@ class TestIntegrationWithExistingTests:
         # Add all tools
         add_feedback_tools(mock_fastmcp_server, database_url=memory_db_url, prefix="complete")
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         tool_names = list(tools.keys())
         
         # Should have both individual and complete sets
@@ -830,7 +831,7 @@ class TestIntegrationWithExistingTests:
             insights=test_insights
         )
         
-        tools = await mock_fastmcp_server.get_tools()
+        tools = await tool_map(mock_fastmcp_server)
         submit_tool = tools["submit_feedback"]
         
         # Should work with existing sample data
@@ -848,9 +849,9 @@ class TestIntegrationWithExistingTests:
         add_retrieval_tools(feedback_server, prefix="readonly")
         
         # Import with prefix
-        await main_server.import_server(feedback_server, prefix="external")
+        main_server.mount(feedback_server, "external")
         
-        tools = await main_server.get_tools()
+        tools = await tool_map(main_server)
         tool_names = list(tools.keys())
         
         # Should have properly composed tool names