* ci: add GitHub Release creation on tag push
* refactor: rename plan tool to create_plan
Rename plan → create_plan to resolve cross-provider tool selection
failures. Models consistently treated "plan" as a reasoning concept
rather than a callable tool. The new name is an unambiguous verb+noun
action. Also rename the parameter from prompt → goal for clarity,
add web_search to the default system prompt tool patterns
* feat: eval harness improvements inspired by autoresearch patterns
Major enhancements to turnstone-eval:
- Per-test timeout (--test-timeout, default 300s) and suite timeout
(--suite-timeout) prevent stuck runs from blocking the suite
- Fast-fail skips remaining runs after ceil(n/2) consecutive zeros
- Summary table with colored PASS/WEAK/FAIL and append-only TSV output
- Progress reporting with running pass rate, token count, and ETA
- Parallel test execution via ProcessPoolExecutor (--parallel N)
- Per-role model assignment: test/optimizer/observer can use different
models and providers (--optimizer-model, --observer-model, etc.)
with auto-detection from base URL
- Improved optimizer and observer system prompts with structured
failure-mode diagnosis, keep/discard rules, and trend analysis
- Fixed token counting (prompt tokens use last-turn value, not sum)
- Added math-calculation and web-search-query test cases
- Fixed multi-file-edit test (both files now contain the target string)
* fix: address Copilot review feedback
- Revert prompt token counting to sum (reflects billed usage)
- Add tool_args to fast-fail skipped run dicts for schema consistency
- Align approval_label with func_name ("create_plan")
- Add timeout to future.result() in parallel path (test_timeout + 30s)
- Document thread-leak trade-off on serial timeout path
* feat: watch tool — periodic command polling within workstreams
Add a new `watch` tool that lets the model (or user) set up periodic
polling of a shell command. Results inject as synthetic user messages
that trigger LLM turns, enabling reactive workflows like PR monitoring,
CI/CD status tracking, and deployment health checks.
Key design:
- Single tool with create/list/cancel actions
- Python expression DSL for stop conditions (restricted eval)
- Server-owned WatchRunner daemon (DB-persisted, survives eviction + restart)
- Three dispatch paths: idle, busy, and evicted workstream restore
- REST API for console visibility (GET /v1/api/watches, POST cancel)
- Migration 007, 8 storage CRUD methods, 75 new tests (1383 total)
* fix: address Copilot review — condition errors, restore deadlock, docs
- Condition eval errors now deactivate the watch immediately instead
of silently looping until max_polls
- Restored (evicted) workstreams set auto_approve=True to prevent
approval deadlocks with no connected user
- Tool description clarifies first-poll baseline behavior for change
detection mode
- Diagram updated: DELETE → POST /v1/api/watches/{id}/cancel
The _sse_generation mechanism assumed one SSE consumer per workstream,
but the bridge also maintains an SSE connection to each workstream.
When a new client connected (browser, proxy, or test), it incremented
the generation counter, killing the bridge's connection. The bridge
reconnected, killing the new client's connection — creating a
mutual-kill cascade that closed every SSE connection after one ping
cycle (5s).
Fix: remove _sse_generation entirely. sse-starlette handles disconnect
detection via its own ASGI task. Also remove the redundant
request.is_disconnected() check which raced with sse-starlette's
disconnect listener in Starlette 0.52.
Root cause confirmed via raw socket test: the server was sending
a zero-length chunked terminator (0\r\n\r\n) at exactly 5s,
cleanly ending the HTTP response body.
* fix: recovered workstreams invisible in console UI
Bridge startup recovery (_recover_workstreams) re-registered workstream
ownership but never published WorkstreamCreatedEvent to the cluster
channel. The collector's poll loop would pick up the workstream in its
internal state, but _apply_poll never fanned out SSE events to connected
browsers. Combined, this made channel-resumed workstreams invisible in
the console while remaining accessible through the proxied node UI.
- Bridge: emit WorkstreamCreatedEvent for each recovered workstream
- Collector: diff poll results and fan out synthetic ws_created/ws_closed
events for workstream additions and removals
- Skip workstreams with empty IDs in poll processing
- Add 4 tests for poll-diff fanout behavior
- Update console data-flow diagram and architecture docs
* fix: address PR review — filter empty ws IDs, stable event ordering
- Filter empty-string keys from old_ids to avoid phantom ws_closed
events if a previous poll inserted a workstream under key "".
- Sort set diffs before iterating so ws_created/ws_closed fanout
order is deterministic across poll cycles.
* feat: add ClusterSnapshot for instant console UI state rebuild
The console web UI was SSE-driven with no initial state — reloads and
navigation caused blank/loading gaps while waiting for API re-fetches.
Server-side: GET /v1/api/cluster/snapshot returns the full cluster state
(all nodes with workstreams + overview aggregates) built under a single
lock. The SSE stream now emits this snapshot as the first event on
connect (snapshot taken before listener registration to avoid race).
Frontend: local clusterState object mirrors the snapshot, patched
incrementally by SSE events. View navigation renders from local state
with no API round-trips. Fixes popstate/pushState history corruption
on Back/Forward navigation (pre-existing bug). Stable node sorting
with node_id tie-breaker on both server and client.
SDK: snapshot() method on Python (sync + async) and TypeScript console
clients. ClusterSnapshotEvent in event registries.
* fix: address review feedback and SSE proxy reconnect bug
Copilot review fixes:
- Atomic snapshot+register: new get_snapshot_and_register() acquires
both state and listener locks, eliminating the event gap between
snapshot read and listener registration.
- Debounce patch renders: patchClusterState uses requestAnimationFrame
to batch rapid SSE events into a single recompute+render cycle.
- Fix health type: dict[str, str] → dict[str, Any] on all three
console schema models (ClusterNodeInfo, NodeDetailResponse,
ClusterSnapshotNode) since /health payloads contain nested objects.
- TypeScript ClusterSnapshotEvent: use concrete ClusterSnapshotNode[]
and ClusterOverviewResponse types instead of Record<string, unknown>.
SSE proxy reconnect fix:
- _proxy_sse raw_stream now emits `: proxy-ping` comments every 3s
when no upstream data arrives, preventing the browser EventSource
from dropping idle connections. The raw byte passthrough refactor
(4d11078) removed the proxy's independent keepalive — this restores
it without reverting to EventSourceResponse.
* feat: add vision/image support to read_file tool
read_file now detects image files (PNG, JPEG, GIF, WebP, BMP, TIFF, ICO)
and returns base64-encoded content parts for vision-capable models.
Non-vision models receive a text description instead. A new
supports_vision flag on ModelCapabilities gates the feature, with
config.toml [models.*.capabilities] overrides for local models
(vLLM, llama.cpp, NIM).
* fix: address PR review feedback
- Discard _read_files on no-vision OSError path, include exception detail
- Discard _read_files on oversized image error (not a successful read)
- Validate capabilities type from config.toml (reject non-dict)
- Clarify tool description re: vision behavior and offset/limit scope
- Remove unused os import in tests, fix import sort order
- Handle list content (image tool results) in eval.py tool result loop
* refactor: use raw streaming for SSE proxy to preserve event framing
- Replace httpx_sse aconnect_sse with raw httpx.stream for SSE proxy
- Stream bytes verbatim to preserve server-side ping comments and event framing
- Add StreamingResponse with proper headers (Cache-Control, X-Accel-Buffering)
- Update compose.yaml to add 'cluster' profile to the service
* Refactor SSE proxy to raw byte passthrough
- turnstone/console/server.py: Replace aconnect_sse + EventSourceResponse with
httpx.stream() + StreamingResponse for raw byte passthrough. Server pings,
events, and comments now flow through verbatim. Added per-request timeout
override (read=None, pool=None) for long-lived SSE streams.
- tests/test_console.py: Add 3 new tests for SSE proxy:
- Ping and event preservation
- Upstream error status handling
- Client disconnect handling
- docs/console.md: Update SSE Proxy section to reflect raw byte passthrough
approach.
* Add dynamic tool search with native defer_loading for Anthropic/OpenAI
When MCP tools push the total tool count past a configurable threshold
(default 20), tool definitions are deferred to reduce token overhead and
improve tool selection accuracy. Three-tier approach mirrors the existing
web search pattern:
- Anthropic (Claude 4.x): native defer_loading + server-side BM25 search
- OpenAI (GPT-5.4+): native defer_loading + hosted search
- vLLM/llama/NIM: client-side BM25 fallback via synthetic tool_search tool
New module turnstone/core/tool_search.py with BM25Index (pure-Python,
zero deps) and ToolSearchManager (session-scoped visibility, expansion,
server hint generation). Discovered tools persist for the session lifetime
so the model only searches once per capability needed.
Config: [tools] search/search_threshold/search_max_results
CLI: --tool-search {auto,on,off}, --tool-search-threshold, --tool-search-max-results
Agents (plan/task) exempt — their scoped tool sets are always small.
43 new tests (1253 total). All diagrams regenerated with PlantUML 1.2025.2.
* Fix Copilot review feedback on tool search
- Fix _MCP_PREFIX_RE to handle underscores in server names (non-greedy match)
- Use ordered dict for _expanded to preserve tool discovery order
- Avoid constructing ToolSearchManager when below threshold in auto mode
- Return empty string from _mcp_server_summary when no servers (not "none")
- Fix CLI help text to reference threshold generically, not hardcoded "20"
- Fix agent exemption docs to accurately describe scoped tool sets
- Fix README to not hardcode "30+" threshold number
Multiple containers starting simultaneously race on Alembic migrations
against shared PostgreSQL. Use pg_advisory_lock so they wait in line.
Also update SQLite bootstrap to detect post-migration databases.
* Normalize session_id into ws_id as sole persistent identity
Eliminate the separate session_id concept. The workstream ID (ws_id) is
now the single identity used for both real-time routing and conversation
persistence, removing a layer of indirection that was 1:1 in practice
and buggy on resume (stale pointers, orphaned rows).
Schema changes (migration 006):
- Drop sessions table; add alias/title columns to workstreams
- Rename conversations.session_id → ws_id
- Rename session_config table → workstream_config (ws_id column)
- Data migration remaps existing conversations to ws_id
Storage/API renames:
- register_session → register_workstream (already existed, merged)
- save_message/load_messages now keyed by ws_id
- resolve_session → resolve_workstream
- ChatSession.session_id property → ws_id
- ChatSession.resume_session() → resume()
- resume_session field → resume_ws
- SessionResumedEvent → WorkstreamResumedEvent
- /api/sessions → /api/workstreams/saved
- /sessions slash command → /workstreams
- --session-retention-days → --retention-days
Channel eviction recovery simplified: reuses old ws_id directly
instead of get_session_id_by_ws() reverse lookup.
* Fix Copilot review feedback: stale session wording in docs, regenerate OpenAPI spec
- docs/channels.md: "resumes the session" → "resumes the workstream",
"Session resumed:" → "Resumed:", "old session was pruned" → "old
workstream was pruned"
- docs/api-reference.md: "Each session object" → "Each saved workstream
object", field descriptions updated, removed stale node_id field
- sdk/typescript/openapi-server.json: fully regenerated from Python
models — removes all stale session_id properties from WorkstreamInfo,
DashboardWorkstream, CreateWorkstreamResponse schemas
* Add GPT-5.3, GPT-5.4, and pro model capabilities
Add capability entries for gpt-5-pro (272k output, high-only reasoning),
gpt-5.2-pro, gpt-5.3, gpt-5.4 (1.05M context), and gpt-5.4-pro.
* Validate reasoning_effort against model capabilities
_apply_model_params now falls back to caps.default_reasoning_effort when
the requested value is not in caps.reasoning_effort_values. Prevents
sending unsupported effort levels to models like gpt-5-pro (high only).
Add documentation and SDK support for the scheduled task system
(cron/at scheduling via console API). Includes Python SDK methods
(async + sync), TypeScript SDK methods, console.md API reference,
sdk.md table update, and architecture.md module map entry.
Two runtime bugs:
1. Channel gateway advertised http://127.0.0.1:8091 which is
unreachable from other Docker containers. Add
TURNSTONE_CHANNEL_ADVERTISE_URL env var override for Docker/K8s
environments, set to http://channel:8091 in compose.yaml, and
pass --http-host=0.0.0.0 so the gateway listens on all interfaces.
2. Console proxy service JWT had only "write" scope but the approval
endpoint requires "approve". Tool approval buttons in the server
web UI silently failed when accessed through the console proxy.
Changed proxy token scopes to read+write+approve.
Replace single-node Mermaid diagram with a 3-node cluster layout
showing bridge+server pairs per node, shared Redis MQ, console, and
channel gateway. Remove the verbose directory tree listing.
GitHub renders Mermaid natively as an interactive SVG. The new diagram
shows all client entry points (CLI, browser, SDK, Discord), the full
cluster topology including the channel gateway and notify path, and
the LLM provider layer.
* Add channel notification tool with security hardening
Implements the `notify` tool allowing the LLM to send notifications to
Discord channels/users via the channel gateway. Includes fixes for 11
review findings: JWT auth on the gateway endpoint, first-healthy gateway
delivery with retry+backoff, rate limiting only on success, SSRF URL
scheme validation, Discord mention sanitization, SQLite ON CONFLICT
upsert preserving created timestamps, advertise URL resolution for
0.0.0.0 bind, randomized service IDs, generic error messages to prevent
internal state leakage, and partial direct-target validation.
Service registry with heartbeat-based health filtering (migration 005).
Channel gateway registers on startup, heartbeats every 30s, deregisters
on shutdown. 70 new tests covering tool prepare/execute, HTTP endpoint
auth (static + JWT), storage CRUD, and retry behavior.
* Add notify documentation, diagrams, and review fixes
Documentation:
- New sequence diagram 17-notify-flow.puml showing end-to-end delivery
- Updated 16-channel-architecture.puml with services table, notify HTTP
path, and Notification Flow note
- channels.md: Notifications section (targeting, delivery flow, service
registry, security) and new config table entries
- tools.md: notify tool reference, updated counts/tables (14→15 tools)
- security.md: channel gateway row in service-to-service auth table
- architecture.md: notification subsystem paragraph
Review fixes (copilot):
- _http.py: fail closed when auth unconfigured (401 instead of pass-
through), strip whitespace on message/title, generic error messages
for user-not-found vs no-linked-channels
- session.py: parse gateway response JSON and require at least one
result with status=="sent" before counting as success
- _postgresql.py: use index_elements instead of constraint for upsert
* Add scheduled task system with cron/at scheduling, admin API, and console UI
Console-integrated background scheduler dispatches workstreams on recurring
cron expressions or one-shot ISO8601 timestamps. Four target modes: auto
(best node by headroom), pool (shared queue), all (fan-out), or specific
node. Redis distributed lock with unique owner + Lua conditional release
prevents duplicate dispatch in multi-console deployments.
Storage: scheduled_tasks + scheduled_task_runs tables (migration 004),
9 protocol methods on both SQLite and PostgreSQL backends, field allowlist
on updates, run history auto-pruned at 90 days.
API: 6 CRUD endpoints under /v1/api/admin/schedules with croniter
validation, ISO8601 future-time checks, field length bounds, schedule
count cap (200), and OpenAPI spec entries with Pydantic models.
UI: Schedules tab in admin panel with create/edit/delete modals, run
history modal, cron/at type toggle, target mode select, status dots for
accessibility, responsive grid, keyboard navigation, and focus management.
Security: fan-out capped at 20 nodes/task/tick, auto-approve dispatches
logged at WARNING with created_by attribution, user_id propagated in
CreateWorkstreamMessage for audit trail.
46 tests across storage, scheduler engine, and API endpoints.
* Add croniter to test extras for CI compatibility
CI installs [test] extras but not [console], so croniter was missing
when schedule API tests import console/server.py validation functions.
* Address Copilot review: timezone validation, focus trap, enabled flag
- Reject naive at_time timestamps — require timezone offset (e.g. +00:00 or Z)
- UI appends +00:00 to datetime-local values for explicit UTC
- Fix datetime-local normalization: check length before appending seconds
- Add textarea to modal focus trap selector (prevents focus escape)
- Fix _normalize_task_dict not called in update response
- Persist enabled=false on create (storage defaults to enabled=1)
- Validate at_time is still in future when re-enabling a one-shot task
- broker._redis coupling acknowledged as tracked tech debt
* Add JWT auth security hardening (6 fixes)
- Secure cookie flag: make_set_cookie defaults Secure=True, max_age=24h
- Login brute-force protection: LoginRateLimiter (5 attempts/5min per key)
- JWT aud/iss claims: create_jwt/validate_jwt support audience validation
- Service JWT auto-rotation: ServiceTokenManager with 1h expiry, 80% refresh
- CORS restriction: configurable via TURNSTONE_CORS_ORIGINS env var
- JWT secret strength: warning on secrets shorter than 32 chars
- Hard fail for bridge/console when TURNSTONE_JWT_SECRET is missing
* Refactor duplicated code into shared utilities and fix 3 UI bugs
Code deduplication (~235 net lines removed):
- Extract AuthMiddleware + 4 auth endpoint handlers to core/auth.py
- Create core/web_helpers.py (require_storage_or_503, read_json_or_400,
parse_cors_origins, cors_middleware)
- Extract add_redis_args/broker_from_args to mq/broker.py
- Extract add_log_args/configure_logging_from_args to core/log.py
- Remove dead _CSS/_JS loads, duplicate states dict, _read_json helper,
unused required_role(), duplicate detect_model() wrapper
Bug fixes:
- Fix console proxy forwarding user's JWT_AUD_CONSOLE token to server
nodes (use ServiceTokenManager with JWT_AUD_SERVER instead)
- Fix login form autofill: wrap inputs in <form>, add name attributes,
set type=submit on button
- Fix SSE reconnecting flash: add onopen handler to clear status
immediately on connection (not waiting for first message)
- Fix chat scroll: add min-height:0 to flex containers, overflow:hidden
on body to constrain viewport height
* Address CI typecheck failure and Copilot review feedback
- Fix mypy arg-type: use Any for jwt.decode options (PyJWT stubs vary)
- Bridge SSE loops: use event_hooks for auth header refresh on reconnect
instead of static headers that go stale after token rotation
- Login form: remove javascript:void(0) action (CSP anti-pattern)
- Use JWT_AUD_SERVER/JWT_AUD_CONSOLE constants instead of string literals
in middleware builder calls to prevent drift
* Add user identity, JWT auth, and admin console UI (#23)
JWT-based authentication with three token types: config-file (hmac,
backward-compat), API tokens (ts_ prefix, SHA-256 hashed), and JWTs
(HS256, 24h expiry). Username:password login via bcrypt. Hierarchical
scopes: read < write < approve.
New tables: users (username, password_hash), api_tokens (token_hash,
scopes, expires), channel_users (future channel integrations). user_id
column added to sessions and workstreams for attribution.
Console owns admin CRUD (6 endpoints under /api/admin/). Server
validates JWTs locally with shared signing secret. Public /api/auth/setup
endpoint for first-time admin creation (atomic, only works with zero
users). turnstone-admin CLI for user/token management.
Admin console UI: Users and Tokens tabs with full CRUD modals, scope
badges, token show-once with clipboard copy, keyboard accessibility
(focus traps, Escape, arrow key tabs, ARIA roles).
Login UI redesigned: username:password primary, token toggle for legacy,
setup wizard auto-detected via /api/auth/status. Python + TypeScript
SDKs updated with login(username, password), authStatus(), setup().
New docs/security.md + diagram 15-auth-architecture.puml. All existing
docs updated. OpenAPI specs include all new endpoints. 64 new tests
(1023 total). Dependencies: PyJWT, bcrypt.
* Fix auth bugs, XSS vector, and doc inaccuracies from PR #23 review
Address Copilot review feedback: escape double quotes in escapeHtml()
to prevent XSS in HTML attributes, add JWT validation fallback so
config tokens containing dots still work, add user_id to
AuthLoginResponse schema, return created field from admin_create_user,
and correct five documentation files to match actual API behavior.
Replace ad-hoc logging.basicConfig() calls across all 6 entry points with
a centralized configure_logging() function backed by structlog. JSON output
when stderr is not a TTY (production/Docker), colored console output otherwise.
- New turnstone/core/log.py: configure_logging(), get_logger(), contextvars
for node_id/ws_id/user_id/request_id auto-injected into every log event
- All entry points (server, bridge, console, sim, cli, migrate) call
configure_logging() with --log-level and --log-format CLI flags
- Server operational print() calls replaced with structured log.info()
- LogContextMiddleware sets request_id + ws_id per HTTP request with
token-based reset to prevent context leaking across requests
- Bridge _run_in_context() helper propagates ctx_node_id to child threads
- Env var overrides: TURNSTONE_LOG_LEVEL, TURNSTONE_LOG_FORMAT
- 18 new tests (959 total passing)
* Add cluster-scale schema, fix console proxy UX, harden SDK sync runner
Schema redesign for multi-node deployments:
- New `workstreams` table with node_id, state, lifecycle tracking
- Add node_id + ws_id columns to sessions table with indexes
- Full UUID (32 hex) for session_id and ws_id (was truncated 12/8)
- Server generates and owns node_id, bridge retrieves via /health
- Bridge retries with exponential backoff, fatal on auth errors
- WorkstreamManager persists workstreams and state changes to storage
- /health endpoint exposes node_id for bridge discovery
Console proxy UX fixes:
- Remove duplicate turnstone branding from proxy banner
- Same-tab navigation for Open Node UI and workstream deep links
SDK _SyncRunner fix:
- Sentinel pattern for StopAsyncIteration across thread boundary
Remove misplaced PNGs from docs/diagrams/ (correct copies in png/ subdir).
* Address PR #22 review feedback
- Fix CLI session_factory signature (ws_id param) — CI typecheck failure
- First-phase eviction in create() now calls _cleanup_ui + record_eviction
- close() persists "closed" state to storage via update_workstream_state
- Fix noqa comment in test to pragma: no cover
* Fix console proxy regressions and add workstream task field (#21)
Bug fixes:
- Fix collector polling unversioned /api/dashboard (404 after API
versioning PR) — nodes showed red/unreachable, no workstreams
- Fix SSE proxy dropping all data events — upstream sends \r\n line
endings but proxy split on \n\n only; normalize before parsing
- Fix workstream state stuck on idle — on_state_change() only
broadcasted via SSE but never updated ws.state on the Workstream
object; dashboard polling now sees correct attention/running states
- Fix deep-link switchTab early return — when ?ws_id matched the
only workstream, switchTab bailed (wsId === currentWsId) before
establishing SSE connection; inline init instead of delegating
- Fix console banner covering dashboard overlay — inject <style>
offsetting .dashboard-overlay below the 32px banner
Enhancements:
- Add turnstone branding to console proxy banner (turnstone │ Console │ node-id)
- Add initial_message field to CreateWorkstreamMessage protocol and
console "New Workstream" modal (Task textarea, sent as first message)
- Refactor SSE proxy to use shared httpx client with 30s read timeout
instead of per-request client creation
- Increase approval timeout default from 300s to 3600s (1 hour)
Updated: Python SDK, TypeScript SDK, OpenAPI specs, MQ client,
API schemas, MQ protocol diagram, SDK docs.
* Address PR #21 review feedback (4 items)
- Log unknown state strings in on_state_change instead of silently
swallowing; remove unnecessary KeyError catch
- Wrap initial_message POST in _handle_create_ws with error handling
so workstream creation success isn't masked by send failure
- Strip all \r from SSE chunks instead of replacing \r\n, fixing
chunk-boundary split edge case
- Add tests for initial_message wiring in directed and pool targeting
* Refactor SSE proxy to use httpx-sse aconnect_sse
Replace manual SSE chunk buffering/parsing with httpx_sse.aconnect_sse()
which handles line endings, event types, and all SSE spec edge cases.
Eliminates the \r\n chunk-boundary bug class entirely. Event types are
now always forwarded (sse.event defaults to "message" per spec).
str(engine.url) in SQLAlchemy 2.x masks the password as '***',
causing SCRAM-SHA-256 authentication to fail when Alembic creates
its own engine from the config URL.
* Add Python and TypeScript client SDKs for server and console APIs
Python SDK (turnstone/sdk/) with sync + async clients for both server
and console APIs. Returns Pydantic models directly, streams SSE events
as typed dataclasses. 27 event types with registry-based deserialization.
High-level send_and_wait() for request-response patterns.
TypeScript SDK (sdk/typescript/) with zero browser dependencies. Uses
fetch + ReadableStream for SSE parsing. Discriminated union event types
with type guards. Same API surface as Python SDK.
63 Python tests, 21 TypeScript tests (vitest). Comprehensive docs at
docs/sdk.md with SDK architecture diagram.
* Address PR #19 review feedback + fix lint
- Fix consume_task leak in send_and_wait when send() raises (try/finally)
- Fix TS sendAndWait: open SSE before send, plumb AbortSignal for timeout
- Add signal param to TS streamSSE for cancellation support
- Fix SSE parser: join multi-line data: fields with \n per spec, handle CRLF
- Fix generate-types.py sys.path (parents[3] not parents[2])
- Document token ignored when httpx_client provided
- Document TS timeout units as milliseconds
- Fix stale docstring in test_sdk_sse.py
- Fix import sorting (ruff I001)
* Extract shared frontend design system into turnstone/shared_static/
The server UI and console UI had ~60% CSS overlap and significant JS
duplication. Extract shared assets into a new turnstone/shared_static/
package mounted at /shared/ in both servers:
- base.css: design tokens, reset, typography, login/toast/kb overlays,
dashboard table, state dots, health bar, scrollbar, reduced motion
- auth.js: authFetch, login overlay with focus trap, logout (hooks for
page-specific post-login/logout callbacks)
- theme.js: dark/light toggle with system preference detection
- toast.js: notification queue with configurable timeout
- utils.js: escapeHtml, formatTokens, ctxClass, formatUptime, formatCount
- kb.js: keyboard shortcuts overlay with configurable content, focus
management, and focus restore on dismiss
Console proxy updated: JS shim injection moved from proxy_static (app.js
prepend) to proxy_index (inline <script> in HTML) so it runs before any
external scripts. New /shared/ path rewriting and proxy_shared_static
route added. ~1540 lines removed from page-specific files, 775 lines in
shared package. 13 new tests (788 total).
* Fix /shared/ auth and remove __init__.py from shared_static
Address PR #17 review feedback:
1. Add /shared/ to PUBLIC_PREFIXES in auth.py so shared CSS/JS
loads before authentication (required for login overlay to render)
2. Remove turnstone/shared_static/__init__.py to prevent exposing
Python package internals (__init__.py, __pycache__) via the
StaticFiles mount. Not needed for packaging since pyproject.toml
uses explicit glob includes.
3 new auth tests for /shared/ public path access.
* Add node version tracking and drift detection to console dashboard
Surface the version field from each node's /health endpoint in the
console dashboard. Collector extracts version into get_overview()
(version_drift + versions fields), promotes it to top-level in
get_nodes(), and adds get_version_info() for per-node detail. Console
/health endpoint includes drift fields.
Frontend adds a VER column to the 7-column node table grid, shows
per-node version strings, tracks versions per group with "mixed" +
yellow drift badge when nodes disagree, and displays a DRIFT warning
or single version in the status bar. Column hidden on mobile (<700px).
ARIA labels include version info for accessibility.
10 new tests (745 total). Docs and diagram updated.
* Fix drift tooltip text: show 'Versions detected' not 'Nodes running'
* Fix circuit breaker, rate limiter, and Anthropic web search correctness (#15)
Three tech debt items addressing correctness and security gaps:
Circuit breaker HALF_OPEN single-request permit:
- Rename should_allow_request property to acquire_request_permit() method
to make the side-effecting, non-idempotent nature explicit
- Add _half_open_permit flag: exactly one probe request in HALF_OPEN,
subsequent callers blocked until probe completes
- Explicitly reset permit on all state transitions (record_success,
record_failure) for clean state machine invariants
- Session uses BaseException catch to ensure record_failure always fires,
preventing permanent circuit deadlock on probe crash
Rate limiter X-Forwarded-For support:
- Add resolve_client_ip() with rightmost-untrusted XFF parsing
- Configurable trusted_proxies via --ratelimit-trusted-proxies CLI flag
and [ratelimit] trusted_proxies config (comma-separated CIDRs)
- IPv4-mapped IPv6 normalization (::ffff:x.x.x.x → IPv4) for dual-stack
- Clientless requests (request.client is None) pass through instead of
sharing a single "unknown" bucket
- Log warning for invalid CIDR entries in trusted_proxies config
- Show trusted proxies in startup log when enabled
Anthropic web search multi-turn encrypted content:
- Capture raw provider content blocks during streaming via _block_to_dict()
using model_dump(exclude_none=True) to avoid Anthropic API rejection
- Accumulate thinking_delta into raw_blocks (was silently empty on replay)
- Store _provider_content on assistant messages, pass through verbatim in
_convert_messages() so encrypted_content/encrypted_index survive turns
- Persist to SQLite via new provider_data column (auto-migrated)
- Add thinking/signature to _block_to_dict fallback attribute list
23 new tests (735 total), ruff + mypy clean.
* Fix Copilot PR #15 review issues: provider data, circuit breaker, IP normalization
- Persist assistant message when provider_data exists even if text
content is empty — prevents losing Anthropic web search encrypted
content needed for multi-turn replay (session.py)
- Re-raise KeyboardInterrupt/SystemExit immediately after recording
failure instead of attempting fallback models (session.py)
- Consume HALF_OPEN permit for the transition caller — prevents two
concurrent probe requests when only one should be allowed
(healthcheck.py)
- Normalize IPv4-mapped IPv6 addresses consistently in
resolve_client_ip() — prevents duplicate rate-limit buckets for
::ffff:x.x.x.x vs x.x.x.x (ratelimit.py)
Patrick Buckley