* 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
* 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 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.
* 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 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.
* 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).
* 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)
* Add console workstream creation + server reverse proxy (#14)
Enable the console dashboard to create workstreams and proxy server UIs,
so users only need network access to the console port.
Workstream creation via MQ:
- POST /api/cluster/workstreams/new with three targeting modes:
specific node (directed queue), auto (best node by capacity),
or general pool (shared queue, any bridge picks up)
- Console pushes CreateWorkstreamMessage to Redis; bridge handles
the rest (server creation, ownership registration, SSE events)
Reverse proxy for server UIs:
- /node/{node_id}/ serves the server's HTML with static path rewriting
and a console-return banner injected after <body>
- JS proxy shim prepended to app.js overrides fetch() and EventSource()
to route root-relative URLs through /node/{id}/api/...
- SSE streams proxied via httpx.AsyncClient(timeout=None) with per-
connection clients for long-lived streams
- GET/POST API requests forwarded with body and auth token
Security:
- Proxy write paths checked against WRITE_PATHS to prevent read-token
escalation (read tokens cannot POST /api/send through proxy)
- html.escape() on node_id in banner HTML to prevent XSS
- String length limits on name/model inputs
Frontend:
- "+ new" button in header opens creation modal with node dropdown
(Auto / General pool / specific nodes with capacity display)
- Modal has focus trap, backdrop dismiss, scroll lock, keyboard handling
- Workstream rows and node links deep-link via proxy paths
- Custom select arrow, Instrument Panel modal styling
Documentation:
- docs/console.md rewritten with proxy and creation API docs
- docs/architecture.md console section updated
- PlantUML diagrams 01, 11, 12 updated + PNGs re-rendered
- README.md updated
28 new tests (741 total), ruff + mypy clean.
* Fix Copilot PR #14 review issues: auth bypass, XSS, proxy robustness
- Normalize trailing slashes in required_role() to prevent write-role
bypass via /api/send/ or /node/{id}/api/send/ (auth.py)
- Validate node_id format in proxy handlers (alphanumeric, dot, dash,
underscore only) to prevent injection vectors
- Use json.dumps() for JS proxy shim prefix to prevent script injection
- URL-quote node_id in HTML attribute contexts (proxy_index, proxy_static)
- Check upstream status in _proxy_sse() — emit error event on non-200
instead of keeping a dead SSE connection open
- Check upstream status in proxy_index() — propagate non-2xx errors
- Forward query string in _proxy_post() (consistency with _proxy_get)
- Handle JSON null values in create_workstream() — treat null as empty,
reject non-string types with 400
- Fix docs/diagram LPUSH → RPUSH to match actual broker implementation
* Add provider-native web search with Tavily fallback
Replace client-side Tavily web search with provider-native implementations:
- Anthropic: inject web_search_20250305 server-side tool, handle
server_tool_use / web_search_tool_result streaming blocks, emit
info_delta for search status display
- OpenAI: inject web_search_options for gpt-5-search-api, format
url_citation annotations as footnote sources
- Local/vLLM: preserve existing Tavily-based web_search tool as fallback
Add supports_web_search to ModelCapabilities and info_delta to StreamChunk.
Remove end-of-life GPT-4o model entries from capability tables.
Update docs, diagrams, and README. 88 provider tests (32 new).
* Fix Copilot PR #13 review: capture streaming url_citation annotations
Accumulate url_citation annotations during OpenAI streaming and emit
formatted citations as a final info_delta chunk after the stream ends.
Previously annotations were only captured in non-streaming mode, so
search model users in the interactive path never saw citation sources.
* Add multi-provider LLM adapter with model capability flags
Introduce a provider abstraction layer between ChatSession and LLM SDK
clients, enabling native support for Anthropic alongside OpenAI-compatible
APIs. Each provider translates at the API boundary while the internal
message format remains OpenAI-like throughout session history and persistence.
- LLMProvider protocol with StreamChunk/CompletionResult normalized types
- OpenAIProvider: GPT-4o, GPT-5.x, O-series capability tables with
conditional temperature, reasoning_effort, and token param handling
- AnthropicProvider: native streaming, message/tool format conversion,
adaptive vs manual thinking modes, effort parameter for 4.6 models
- ModelCapabilities per-model flags: temperature support, token param name,
thinking mode, effort levels, context window, max output
- Smart auto-detect: latest Opus for Anthropic, latest base GPT for OpenAI
- --provider CLI flag for both turnstone and turnstone-server
- anthropic SDK as optional dependency (pip install turnstone[anthropic])
- 56 new provider tests, 672 total passing
- Updated architecture docs and 4 PlantUML diagrams
* Fix Copilot PR #12 review: reasoning_effort gating, Anthropic thinking, provider factory
- Default reasoning_effort_values to () so unknown/local models don't
receive unsupported top-level reasoning_effort param. Models that need
it (GPT-5.x, search models) have explicit capability declarations.
- Fix Anthropic _reasoning_params: "none" and "" effort now return {}
instead of enabling thinking with 4096 budget.
- Use create_provider("openai") singleton instead of OpenAIProvider()
in ChatSession fallback for consistency with registry path.
- Add 8 parameter gating tests: unknown model no reasoning_effort,
GPT-5 no temperature, GPT-5.1 conditional temperature, O-series
no temperature, Anthropic none/empty/low effort.
* Migrate HTTP servers from stdlib to Starlette/ASGI + uvicorn
Replace Python stdlib http.server (ThreadedHTTPServer, BaseHTTPRequestHandler)
with Starlette ASGI applications served by uvicorn across all three HTTP
entry points. SSE endpoints use sse-starlette EventSourceResponse with
async generators that bridge sync queue.Queue via run_in_executor().
Bridge SSE parser replaced with httpx-sse EventSource.
- turnstone/server.py: Starlette app factory with create_app(), pure ASGI
middleware (auth, rate limit, metrics, CORS), async route handlers,
lifespan context manager for startup/shutdown. WebUI and ChatSession
remain fully synchronous — worker threads unchanged.
- turnstone/console/server.py: Same pattern, simpler (no ChatSession).
Path params replace manual string slicing for node detail route.
- turnstone/mq/bridge.py: _iter_sse_data() uses httpx_sse.EventSource
instead of hand-rolled line parser.
- Tests: All ThreadedHTTPServer fixtures replaced with
starlette.testclient.TestClient via create_app() factories.
- Docs: Updated architecture.md, api-reference.md, README.md, and
PlantUML diagrams (03, 11) + regenerated PNGs.
* Fix Copilot PR #11 review: TestClient cleanup, JSON error handling, SSE timeout
- Close TestClient in teardown for TestConsoleAuth and TestConsoleLogin to avoid lifespan/resource leaks
- Close TestClient via yield/finally in TestConsoleHTTPEndpoints fixture
- Add _read_json() helper for safe JSON body parsing (returns {} on invalid JSON instead of 500, matching old stdlib handler behavior)
- Apply same try/except pattern to console auth_login endpoint
- Increase SSE queue.get timeout from 1s to 5s to align with sse-starlette ping interval, reducing executor task churn
* Add operational features: health degradation, rate limiting, workstream eviction
Backend health monitor with circuit breaker (CLOSED/OPEN/HALF_OPEN) probes
LLM backend periodically; /health returns "degraded" when unreachable.
Token-bucket per-IP rate limiter with 429 + Retry-After responses;
/health and /metrics exempt. Workstream auto-eviction of oldest idle
when at configurable max_workstreams capacity.
New modules: healthcheck.py (BackendHealthMonitor, CircuitState),
ratelimit.py (TokenBucket, RateLimiter). 5 new Prometheus metrics.
Both UIs: health indicator, 429 retry with toast, eviction notifications,
node degradation badges (console), circuit state in dashboard footer.
Config: [health] and [ratelimit] TOML sections, max_workstreams in [server].
Docs: README, architecture, API reference, PlantUML diagrams updated.
616 tests pass (35 new), mypy clean, ruff clean.
* Fix Copilot PR #10 review: version import, capacity check order, validations, docs
- Use turnstone.__version__ instead of hard-coded "0.2.1" in /health and
/metrics endpoints
- Move capacity check/eviction before session creation in
WorkstreamManager.create() to avoid wasted work when at capacity
- Validate rate > 0 and burst >= 1 in RateLimiter when enabled
- Validate max_workstreams >= 1 in WorkstreamManager.__init__
- Parse do_POST path with urlparse for consistent rate limit exemptions
and metrics labeling
- Fix should_allow_request docstring: HALF_OPEN allows requests through
(not just one probe)
- Fix /health docstring: degraded when circuit is not CLOSED (includes
HALF_OPEN)
- Add class="health-ok" to health indicator HTML to prevent visible
empty pill before first poll
- Update PlantUML: remove stale MAX_WORKSTREAMS constant, fix
RateLimiter.check and TokenBucket signatures; regenerate PNG
* Add multi-model support with ModelRegistry, fallback routing, and per-workstream selection
Introduces a ModelRegistry that holds named model configurations loaded from
[models.*] sections in config.toml. Each workstream can select its model at
creation time or switch mid-session via /model <alias>. When the primary model
is unreachable, a configurable fallback chain tries alternative models. Sub-agents
(plan/task) can optionally use a cheaper model via the agent_model setting.
Core changes:
- New turnstone/core/model_registry.py: ModelConfig (frozen, api_key redacted from
repr), ModelRegistry (thread-safe lazy client creation, resolve, fallback chain),
load_model_registry() with backwards-compatible config loading
- session.py: registry/model_alias params, /model show+switch command, fallback in
_create_stream_with_retry (extracted _try_stream), agent model override in _run_agent
- workstream.py: factory signature accepts optional model_alias, create() gains model param
- cli.py + server.py: build registry, updated session factories, banner, shutdown
- protocol.py: model field on CreateWorkstreamMessage
- bridge.py: pass model through workstream creation chain
Frontend:
- MODEL column added to dashboard tables in both server and console UIs
- Responsive: hidden alongside NODE at narrow viewports
- ARIA labels include model info, title attributes for truncated text
- SSE connected event includes model_alias
Documentation:
- README: architecture tree, Multi-Model Support section, config keys
- docs/architecture.md: module map, Multi-Model Registry subsection
- docs/api-reference.md: model field in workstream creation, model_alias in SSE
- PlantUML diagrams 02 + 03 updated with ModelRegistry
Tests: 43 new tests (576 total), mypy clean, ruff clean.
* Fix Copilot PR #9 review: model_alias property, preserve manual tool_truncation
- Expose model_alias as a public @property on ChatSession instead of
accessing the private _model_alias from server.py and tests
- Track _manual_tool_truncation flag so /model switch only recomputes
tool_truncation when it was auto-derived, preserving --tool-truncation
overrides
- Update PlantUML diagram to reflect the public property
* Add console-to-server deep linking via ?ws_id= query parameter
Server UI parses ?ws_id= on load (both direct init and post-login) and
auto-selects the matching workstream instead of showing the dashboard.
URL is cleaned from the address bar via history.replaceState after
navigation. Defers initial SSE connection to avoid redundant connect
when deep-linking switches tabs immediately.
Console workstream rows are now clickable — opens the node's server UI
in a new tab with ?ws_id= targeting that workstream. Uses URL constructor
for safe URL building. External-link indicator (↗) appears on hover.
Rows without server_url have role/tabindex removed to avoid broken
affordance. currentServerUrl reset on showOverview() to prevent stale
fallback across views.
Collector injects server_url into workstream dicts in both the poll path
and ws_created event path so deep links work immediately.
* Fix Copilot PR #7 review: deep-link duplicate history entry, server_url test coverage
- Suppress history.pushState in switchTab() during deep-link navigation by
setting _historyNavigation=true around both call sites (post-login and
direct init). Fixes Back button appearing to do nothing on first press.
- Add server_url assertions to poll and ws_created collector tests to
prevent regressions of deep-link functionality.
* Add call_id routing for streaming tool output during parallel execution
Thread call_id through tool_info, approve_request, and tool_result SSE
events so the browser can route streaming output chunks and final results
to the correct tool div when multiple bash tools run in parallel.
Server: include call_id in serialized approval items and tool_result events.
Protocol: add call_id to on_tool_result signature (session, cli, eval, server)
and ToolResultEvent dataclass; pass through MQ bridge.
Client: set data-call-id on tool divs, match by call_id in appendToolOutputChunk
and appendToolOutput with func_name fallback; extract makeCollapsible
helper; use CSS.escape for querySelector safety; fix replayHistory
\\n typo and missing keyboard accessibility on collapsed output.
Bridge: fix pre-existing bug using "name" instead of "func_name" for
auto-approval matching; include call_id in _build_history for replay.
Also adds on_tool_result calls to write_file and edit_file exec methods.
* Update docs/tools.md
Replace subprocess.run() with Popen for bash tool execution, streaming
stdout line-by-line through a new on_tool_output_chunk callback. Web UI
renders chunks incrementally with a pulsing amber border indicator.
Core:
- Add on_tool_output_chunk(call_id, chunk) to SessionUI protocol
- Rewrite _exec_bash() with Popen, process-group kill via
start_new_session + os.killpg, background stderr drain thread,
threading.Event-based timeout detection
- Guard UI callback with contextlib.suppress so errors don't
interrupt output collection
Server/CLI/eval:
- Add tool_output_chunk SSE event type in WebUI
- No-op implementations in TerminalUI, BackgroundTerminalUI, SilentUI
MQ:
- Add ToolOutputChunkEvent to mq/protocol.py and _OUTBOUND_REGISTRY
- Handle tool_output_chunk in bridge._handle_ws_event
Web UI:
- Add appendToolOutputChunk() with call_id-keyed DOM elements,
inner auto-scroll, ARIA attributes, and empty chunk guards
- Fix appendToolOutput() streaming cleanup using adjacency matching
- Make collapsed output keyboard-accessible (tabindex, role, keydown)
- Improve stripAnsi() to handle CSI, OSC, and two-byte escapes;
use it consistently in replayHistory, addInfoMessage, addErrorMessage
- Add .tool-output-stream CSS with soft pulse animation, mobile
max-height cap, and consolidated prefers-reduced-motion support
Docs & diagrams:
- Document tool_output_chunk SSE event in api-reference.md
- Update SessionUI protocol (14 methods) in architecture.md
- Update Phase 3 execution flow in tools.md
- Add on_tool_output_chunk to 03-core-engine-classes.puml
- Update 04-conversation-turn.puml, 05-tool-pipeline.puml
- Add ToolOutputChunkEvent to 06-mq-protocol.puml
- Add to event list in 07-message-routing.puml
- Regenerate all 5 affected PNG diagrams
* Quality overhaul: code tooling, CI/CD, architecture diagrams, UI redesign, and legacy cleanup
- Add ruff (lint+format) and mypy (strict) with zero errors across 37 source files
- Add GitHub Actions CI (lint, typecheck, test matrix 3.11/3.12/3.13) and PyPI publish workflow
- Create 12 PlantUML architecture diagrams with PNG renders covering all subsystems
- Refresh README and docs with badges, diagram links, and current descriptions
- Refactor test_server_live.py with mock streaming helpers for deterministic CI testing
- Update dependencies to current versions (openai>=2.24, httpx>=0.28, redis>=7.2)
Console dashboard:
- Move state indicators from top cards to fixed bottom status bar with cluster metrics
- Replace flat 50-node list with hostname-prefix grouped nodes (expand/collapse, up to 1000)
- Apply "Instrument Panel" visual redesign: IBM Plex Mono + Outfit fonts, warm amber accent,
LED glow state indicators, deep charcoal surfaces, WCAG AA contrast compliance
- Add render cache, stale indicator, active filter highlight, loading states
Server web UI:
- Apply matching Instrument Panel aesthetic for visual consistency with console
- Fix branding (pcode → turnstone), extract inline styles to CSS classes
- Rename pcode localStorage keys and history state to turnstone
Legacy cleanup:
- Remove persona-model-specific --persona flag and /persona slash command
- Remove model_identity from chat_template_kwargs (vLLM-specific mechanism)
- Refactor plan agent to use standard developer message instead of model_identity
- Remove dead code (unused date/has_tools variables, noqa suppressions)
* Fix CI typecheck: add mypy overrides for optional sympy/numpy imports
The math sandbox optionally imports sympy and numpy at runtime (try/except
ImportError). In CI these packages are not installed, so mypy raises
import-not-found rather than import-untyped. Add mypy overrides to
ignore missing imports for these optional dependencies.
* Fix Copilot review findings: ARIA role, status bar cache, and pulse opacity
- Change #node-table from role="tree" to role="list" and group elements
from role="treeitem" to role="listitem" (proper ARIA semantics)
- Include currentView and currentFilter.state in renderStatusBar cache key
so active pill highlight updates when switching views
- Align pulse animation to 0.35 opacity (already applied in CSS)
Patrick Buckley