mirror of
https://github.com/turnstonelabs/turnstone.git
synced 2026-08-24 21:04:48 -06:00
ef13f40cf5e2f0664ded1a5497ee6bb17fbdb921
21 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Patrick Buckley
|
54ebb24374 |
feat(personas): core stamping, four-lever application, create/spawn/SDK threading; remove /creative; add --persona
The persona resolved at creation is snapshotted into workstream_config (five keys, all-or-none) and applied ONLY from the stamp — the personas table is never read post-create, so edits/archives never touch existing workstreams, and a corrupt stamp fails construction loudly instead of silently reverting to a default envelope. Legacy pre-063 workstreams carry no keys and keep today's behavior byte-for-byte. The four levers (turnstone/core/personas.py holds the codec): 1. Base override — compose_system_message(base_override=...) replaces exactly the BASE module; ENV/CONTEXT/TOOLS/POLICIES keep composing so mandatory prompt policies ride on top of every persona. This also closes the old /creative hole where the fork bypassed composition (no CONTEXT, no DB policies). 2. Tool visibility — the allowlist intersects both the composition name set (TOOLS block self-suppresses, tool-gated policies drop, the memory advisory drops) and the END of _get_active_tools so the wire never advertises hidden tools. tool_search in the set = soft (discovered tools union with the allowlist via the session's expanded-names set); absent = hard (the whole pathway is disabled, covering provider-native defer_loading, which has no synthetic name to filter). Persona sets force client-side tool search. 3. MCP gate (session-wide) — an MCP-off persona drops the client reference at construction: no merge into _tools OR _task_tools, no listeners, refresh callbacks inert, resource/prompt catalogs gone. 4. Memory (own hands only) — no recall injection, memory-directed nudges suppressed (MEMORY_NUDGE_TYPES; behavioural nudges keep firing), memory tool hidden. _task_tools is NOT filtered; compaction spill/markers are never persona-gated, and the post-compaction recall pointer is emitted only when the recall tool is actually visible. Threading: the create handler resolves once (explicit name -> 400 on unknown/disabled/kind-mismatch; empty -> the kind's default; pre-seed DB -> unstamped legacy) and stamps via constructor kwargs + config keys + the workstreams.persona column; SessionManager.open threads the stamp pre-construction exactly like the saved model alias. Non-fork resume adopts the target's stamp so _save_config can't clobber it. spawn / spawn_batch gain a persona arg with prep-time validation (children are interactive-kind; omitted = kind default, never the parent's). Python + TS SDKs, OpenAPI specs, the picker feed GET /v1/api/personas (authed, no perm), and console admin CRUD /api/admin/personas (persona.* perms, archive-only — no DELETE) round out the surface. BREAKING: /creative is removed (the REPL command now points at the writer persona); turnstone --persona <name> is the replacement. Also fixes the CLI session factory, which TypeErrored on the project_id kwarg the shared InteractiveAdapter passes unconditionally. |
||
|
Patrick Buckley
|
110d44b07e |
refactor(tools): remove man, math, and plan_agent built-in tools
`man` and `math` duplicated capabilities already reachable through `bash`; `plan_agent` is better expressed as a `task_agent` running a planning skill, and carried a large amount of special-case machinery (plan-review gate, refinement loop, per-kind model routing). Removing all three shrinks the tool surface and cuts per-call token cost. Also removed, as dead-once-the-tools-are-gone: - the `math` sandbox executor (`turnstone.core.sandbox`) and its `[sandbox]` extra; the eval analyst now runs bash-only - the read-only `AGENT_TOOLS` sub-agent tool set and the `agent` tool-metadata key (`task_agent`/`TASK_AGENT_TOOLS` retained) - the plan-review protocol end to end: the `on_plan_review` UI hook, `resolve_plan`, `POST /v1/api/plan` + `POST /v1/api/route/plan`, the `plan_review`/`plan_resolved` SSE events, and their Python SDK / TypeScript SDK / OpenAPI / frontend / Discord+Slack bindings - the `model.plan_alias` / `model.plan_effort` settings and the registry `plan_model` / `plan_effort` routing fields TOOLS 31->28, TASK_AGENT_TOOLS 13->11; COORDINATOR_TOOLS unchanged. BREAKING CHANGE: removes the `man`, `math`, `plan_agent` tools, the plan-review SSE/HTTP/SDK surface, and the plan_* model-routing settings from the experimental 1.6 line. |
||
|
Patrick Buckley
|
3233719856 |
feat(judge): output_guard LLM stage with capability gate (#560 mitigation #1)
Adds a second, LLM-driven stage to the output guard so domain-camouflaged prompt-injection payloads that the regex stage misses (arXiv:2605.22001 — Llama 3.1 8B evades the existing regex set on ~90% of camouflaged prompts) get caught before the tool output lands in the assistant's context. ## Surface * New `OutputGuardJudge` in `turnstone/core/output_guard_judge.py` — synchronous, single-shot LLM call. Inlines the alias-resolution + client-config + JSON-parsing helpers (copied verbatim from `IntentJudge` at `judge.py:917-969` / `1604-1659`) rather than going through a shared module — when `IntentJudge` lifts its own helpers, both copies move together. * JSON-in-content verdict with a 3-strategy parser (direct / markdown fence / balanced braces). `IntentJudge` ships a 4th regex-field fallback; OutputGuardJudge deliberately doesn't, because strategy-4 hits on broken LLM output can extract a "verdict" from the model's reasoning quote that lands in storage looking identical to a clean strategy-1 result. Failure of all three returns `error="unparseable_verdict"` and the heuristic stage stands. * `OutputJudgeVerdict` is a frozen dataclass with: `risk_level` (none/low/medium/high — normalises `critical`→`high` and `info[rmational]`→`low` for IntentJudge-echo safety), `flags: tuple[str, ...]`, `reasoning`, `confidence: float` (0.0-1.0, parsed + clamped from the LLM's self-report; pass-through to audit, no threshold gating), `judge_model`, `latency_ms`, `error`. * Real wall-clock timeout via `ThreadPoolExecutor.shutdown(wait=False, cancel_futures=True)` on the timeout/cancel path — `with ... as ex:` would block return until the worker drained. 1s `cancel_event` poll mirrors `IntentJudge._run_judge` at `judge.py:1117-1118`. * HTTP client lazy-init + reuse for the judge instance's lifetime. Session-side model swap drops the entire judge, dropping the client with it. * Untrusted tool output wrapped in per-call random-nonced `<tool_output_NONCE>...</tool_output_NONCE>` fence. Closing-tag substrings in the raw text are case-insensitively backslash-escaped first (`</tool_output` → `<\/tool_output`) so an attacker can't break out even if they guess the nonce. System prompt classifies the fenced region as UNTRUSTED DATA so directives inside are evaluated as content, not obeyed. * Judge user prompt carries the heuristic verdict (risk + flags + annotations), the tool description (looked up from the session's tools registry), and the tool args (truncated to 500 chars, also classified UNTRUSTED in the system prompt since they may be caller-supplied). Lets the judge defer to the regex on credential leaks and focus on injection signals the regex set misses; also enables output-vs-request plausibility reasoning. ## Session integration * `_evaluate_output(call_id, output, func_name, *, tool_args="")` — heuristic always runs; LLM stage runs when `judge.output_guard_llm` is enabled. When the LLM produces a usable verdict and the heuristic didn't detect credentials, the LLM verdict is acted on; otherwise the heuristic stands. * Credential redaction is a regex-only signal. When `heuristic. sanitized` is non-None, the heuristic owns the acted assessment regardless of what the LLM said — an LLM asked about prompt- injection can correctly label a credential-bearing output as "none" risk for injection, but the secret still needs redaction. * `_batch_evaluate_outputs` runs the per-tool guard concurrently (4-worker pool) when LLM is enabled and there are ≥2 string outputs — collapses N×LLM-latency to ⌈N/4⌉×latency on the common 5-20 tool-calls-per-turn turn. * Per-session `TokenBucket(rate=1.0, burst=60)` caps adversarial LLM-fan-out cost at 60 calls/min/session. * Pre-truncation: the per-tool loop truncates output before the judge sees it, so the judge evaluates exactly what enters the assistant's context (no wasted tokens on text that won't land). * Both heuristic and LLM tier rows persisted to `output_assessments` when the LLM ran (audit completeness); heuristic-only rows skip when matched-clean to keep the table focused. ## Storage Migration 057 extends `output_assessments` with five LLM-tier columns: `tier` (`heuristic` / `llm`, backfilled to `heuristic`), `reasoning`, `judge_model`, `latency_ms`, `confidence`. Tie-break on `(created DESC, tier='llm' first)` so downstream consumers see the acted verdict first when the two rows tie at second resolution. `StorageBackend.record_output_assessment` + sqlite/pg implementations + `SessionUIBase.record_output_assessment` + `SessionUI` protocol + the test stub overrides (cli, eval, 9 test files) all take the new LLM-tier kwargs. ## Config surface Three new judge.* settings in `settings_registry`: * `judge.output_guard_llm` (bool, default False) — capability gate. Default off; operators opt in once a small/fast model is pointed at `output_guard_model`. * `judge.output_guard_model` (str, default "") — alias for the LLM stage. Empty inherits the session model (same fallback shape as `judge.model`). * `judge.output_guard_llm_timeout` (float, default 30.0, min 1.0) — wall-clock budget per call. Both `server.py` and `console/session_factory.py` wire these into the `JudgeConfig` they hand to `ChatSession`. ## Notes * No backwards-compatibility shims — the LLM stage is purely additive. * No reasoning/threshold gating on confidence; it rides as an audit-only signal per maintainer direction. Surface it in the `on_output_warning` dict so live UI / cluster broadcast can sort flagged outputs by judge certainty. * Tests: 392 lines of judge-only coverage (`test_output_guard_judge. py`) + 629 lines of session-integration coverage in `test_session. py`, plus the storage and stub-shape updates. |
||
|
Patrick Buckley
|
29b850919f |
feat(sse): refresh-resume for mid-stream page reloads
Refreshing a coordinator or interactive workstream pane while the LLM is mid-stream now restores the partial assistant text + reasoning immediately and flips the composer back to stop-mode, instead of showing nothing until the response completes. Per-turn inflight buffers (`_ws_inflight_content`, `_ws_inflight_reasoning`, `_ws_inflight_seq`) on `SessionUIBase` are kept separate from the existing multi-turn `_ws_turn_content` buffer that drives the dashboard's IDLE-piggyback payload. New `on_turn_start` (top of send-loop, defensive) and `on_turn_committed` (right after `messages.append(assistant_msg)`, primary) lifecycle hooks reset inflight at turn boundaries. The seq counter is monotonic across turns so a long-lived subscriber's `snap_seq` cutoff stays valid for the lifetime of the connection — resetting per-turn would silently drop turn N+1's first M tokens (M = whatever was streamed pre-snapshot in turn N). `snapshot_and_consume_state_payload` also drains inflight at idle/error so cancel and exception paths don't leak stale text. New `register_listener_with_in_progress_snapshot` atomically registers a listener and snapshots the inflight buffers; `make_events_handler` emits a `state_change` event (so the JS busy machine flips to stop-mode) followed by a one-shot `in_progress_snapshot` after the kind-specific replay, then strips the internal `_seq` field from yielded live events while filtering against `snap_seq`. A per-listener shallow `dict` copy in the live drain prevents the multi-tab race where one listener's `del event["_seq"]` would corrupt another listener's filter view. `_synthesize_cancelled_results` now emits synthetic `on_tool_result` events for each cancelled tool so live coord tabs can drop the newly-additive `coord-tool-batch--running` indicator cleanly. The indicator now coexists with `--auto`/`--approved` (applied on `tool_info` and `approval_resolved` approved; removed when every row in the batch has a result), making live tool execution visually parallel to the replay-time orphan rendering. Frontend handlers in `app.js` (interactive) and `coordinator.js` (coord) absorb EventSource auto-reconnect re-replays via a length-based prefix check on the in-progress buffer. New `InProgressSnapshotEvent` + `StateChangeEvent` dataclasses in the Python and TypeScript SDKs with type guards. `_MAX_TURN_CONTENT_CHARS` lifted 256 KiB → 512 KiB (single constant for both buffers — headroom for current commercial models). Regression tests cover race-free composition under concurrent writers, seq-filter dedup invariants, the cross-turn seq monotonic invariant, idle/error inflight drain, synthesized `on_tool_result` on cancel (including UI-hook failure isolation), and the multi-listener shared-dict invariant. |
||
|
Patrick Buckley
|
c837e3fa6d |
feat(core): Stage 1 SessionManager unification (#408)
* feat(core): scaffold SessionManager + SessionKindAdapter Protocol Stage 1 step 1 — pure addition, no production wiring. Defines the shape later steps will port the shared mechanics onto: slot accounting, per-ws-id refcounted rehydrate locks, kind-agnostic lifecycle; kind-specific event transport + session construction on the adapter. Pruned from the earlier Protocol draft (see design brief): per-kind permission_scope (static handler map is simpler), allows_child_spawn / quota_policy (deleted in #403), on_child_spawned (coordinator tool owns children registry), allows_active_focus / active_id / switch (frontend owns the active-tab state). * feat(core): port shared session-lifecycle mechanics onto SessionManager Stage 1 step 2. Adds create / open / close / set_state / close_idle / get / list_all / count on top of the Step 1 scaffolding. Pure addition — still no production wiring; the new class doesn't replace any call sites yet. Concurrency shape is ported from CoordinatorManager (the more- complete side): single-phase slot reservation under the manager lock, per-ws refcounted open-lock to serialize concurrent lazy rehydrate, placeholder workstreams count toward max_active but can't evict each other. WSM's two-phase eviction outside the lock is not carried over; it had a window where a burst of creates could silently exceed max_active. Deletions (vs. the union of the two old managers): - "refuse to close last workstream" guard — handled by the dashboard; only existed to protect the now-deleted default startup workstream. - active_id / switch / get_active — frontend owns focus; server-side duplicate state is gone. - _active_coords presence cache — defer measurement to Step 4; if it pays for itself at realistic cluster sizes, the CoordinatorAdapter can maintain it by observing emit_* calls. - Children registry + reverse index — coordinator tool owns this, manager stays kind-agnostic. Skill resolution (name → template_id + applied_version) is now shared via SessionManager._resolve_skill, so WSM's pre-resolve-at- callsite pattern and CM's internal-lookup pattern converge. Callers pass the skill name; the manager does the lookup once. 26 smoke tests cover create eviction + overflow, concurrent-create cap, persist/session rollback, open for missing/deleted/wrong- kind/wrong-user rows, concurrent-open serialization, close unblocks UI + emits closed, set_state + storage + adapter observer, close_idle, list_all ordering, count, eviction fires adapter transport, node_id passthrough. * feat(core): add InteractiveAdapter for SessionManager Stage 1 step 3. Adapter that bridges SessionManager to the node's interactive transport: - emit_created/state/closed → pushes onto the process-wide SSE global_queue (same shape current server.py handlers produce inline) - cleanup_ui → ports WorkstreamManager._cleanup_ui body: unblock _approval_event / _plan_event / _fg_event, broadcast ws_closed to per-UI listener queues (with full-queue fallback), cancel + close the session - build_ui/build_session → delegate to injected factories (ui_factory builds WebUI, session_factory is the existing closure from server.py with judge_model + memory_config captures) Also extends SessionKindAdapter.build_session with **extra passthrough so interactive callers can pass judge_model per-call without polluting the manager API; and adds a reason= kwarg to emit_closed so the frontend's "evicted" special-case keeps working (frontend doesn't differentiate "idle" from "closed", so close_idle collapses into close()). 14 new adapter tests cover wire payload shape, queue.Full tolerance, cleanup_ui event unblocking + listener broadcast + queue-full fallback, session cancel+close, graceful handling of stub UIs / None session, and kwarg passthrough to the session factory. * feat(console): add CoordinatorAdapter for SessionManager Stage 1 step 4. Coordinator-side SessionKindAdapter implementation: - emit_created/state/closed → delegate to the existing ClusterCollector.emit_console_ws_* methods (same wire shape the old CoordinatorManager emitted inline) - cleanup_ui → ports the listener-queue + approval/plan event unblocks from CoordinatorManager._cleanup, with queue-full fallback so an unresponsive browser tab can't wedge close - build_ui/build_session → delegate to injected factories; session factory doesn't accept client_type so we strip it at the adapter boundary Collector emission exceptions are swallowed (same policy as today's inline fan-out — dashboard lag on one tick is preferable to breaking the lifecycle path). Intentionally out of scope: the children registry (_children / _child_to_coord) stays in the coordinator tool when wired in Step 5; the _active_coords lock-free presence cache is deferred pending a measurement at realistic cluster sizes. 10 new tests cover transport payloads, collector-exception tolerance, cleanup_ui event unblock + listener broadcast + queue-full eviction, construction passthrough. * feat(server): wire interactive server.py to SessionManager Stage 1 step 5a. Production-path swap: WorkstreamManager → SessionManager(InteractiveAdapter(...)). - Construction at server startup: build the adapter with the process-wide global_queue, a WebUI ui_factory closure, and the existing session_factory. SessionManager gets storage + max_active. - Default startup workstream wiring removed (the CLI-REPL leftover flagged in the handoff's "Convergence is also a pruning opportunity" section). --resume now lazily creates a workstream scoped to the resumed content; no workstream at all if --resume isn't given. The dashboard handles the 0-ws state. - HTTP handler mgr.create() calls switched to the new kw-only signature (user_id, name, model, skill, ws_id, client_type, judge_model, parent_ws_id). ui_factory/skill_id/skill_version/kind no longer threaded through — adapter handles UI construction and manager resolves skill internally. - Dropped the mgr.last_evicted block in the /new handler (adapter emits ws_closed:evicted automatically on capacity eviction). - mgr.max_workstreams → mgr.max_active. - Added active_id / switch / switch_by_index / get_active / index_of / eviction_count to SessionManager because turnstone/cli.py uses them extensively; the handoff's "delete unless there's a live caller" rule flips here — CLI is a live caller. Test fixtures across 9 files updated to build SessionManager + InteractiveAdapter rather than WorkstreamManager. test_workstream.py stays unchanged (it tests WSM directly; it'll be deleted in step 5d alongside the class itself). Full pytest: 4528 passed. Ruff + mypy clean. Next: 5b (console-side wiring, with the children-registry relocation to the coordinator tool). * feat(console): wire console server to SessionManager Stage 1 step 5b. Production-path swap: CoordinatorManager → SessionManager(CoordinatorAdapter(...)). - CoordinatorAdapter now owns the coord-specific bits that were bolted onto the old CoordinatorManager: the children registry (forward + reverse index), the lock-free active-coords presence cache, the cluster-event fan-out thread, and the worker-dispatch path (send / _spawn_worker). The shared SessionManager stays kind-agnostic. - Added CoordinatorAdapter.attach(mgr) for late-binding the owning manager (the manager's ctor takes the adapter, so the dependency has to break here). Used inside _rebuild_children_registry for the tenant- filtered SQL query, inside send/dispatch for mgr.get(ws_id), and inside the fan-out seed path for mgr.list_all(). - emit_created now seeds the children registry + active-coords slot AND calls _rebuild_children_registry (covers both create — empty query — and open/rehydrate, where the subtree is persisted). emit_closed drops both entries. Collapses the three old call-sites in CoordinatorManager's create/open/close into one per-event hook. - Console server.py builds the manager via: coord_adapter = CoordinatorAdapter(collector=..., ...) coord_mgr = SessionManager(coord_adapter, storage=..., max_active=..., node_id=ClusterCollector.CONSOLE_PSEUDO_NODE_ID) coord_adapter.attach(coord_mgr) ConsoleCoordinatorUI._coord_mgr = coord_mgr app.state.coord_adapter = coord_adapter - HTTP handler call-site updates: - coord_mgr.create drops initial_message; the handler now calls coord_adapter.send(ws.id, initial_message) after create so the worker spawn stays out of the shared manager. - coord_mgr.open_admin(ws_id) → coord_mgr.open(ws_id, user_id="", admin=True). Matches SessionManager.open's unified signature. - coord_mgr.list_for_user(uid) inlined as a list comp on list_all() (SessionManager doesn't expose the filter; two callers). - coord_mgr.children_snapshot / send → coord_adapter.*. - coord_mgr.cancel stays (now lives on SessionManager from 5a). - ConsoleCoordinatorUI.on_state_change now flows state transitions through ConsoleCoordinatorUI._coord_mgr.set_state, mirroring the WebUI pattern. The old _on_state_observer / _on_rename_observer closures the manager used to install are dead code now; leaving the fields in place for 5d cleanup. - Lifespan shutdown calls coord_adapter.shutdown() (was coord_mgr. shutdown()) and resets ConsoleCoordinatorUI._coord_mgr on teardown. Test fixture updates in _coord_test_helpers, test_coordinator_end_to_end, test_coordinator_endpoints, test_phase6_endpoints: build SessionManager + CoordinatorAdapter in _build_mgr, set app.state.coord_adapter, switch mgr.register_children / mgr.children_snapshot tests to mgr._adapter.*, and rewrite test_open_admin_uses_open_admin to assert the unified open(user_id="", admin=True) call shape. Full pytest: 4486 passed. Ruff + mypy clean. Next: 5d (remove CoordinatorManager + WorkstreamManager class bodies and their test files). * feat(core): delete WorkstreamManager + CoordinatorManager classes Stage 1 step 5c + 5d. Final step of the unification — the legacy classes and their test files go away now that every production caller has been ported. - Delete turnstone/console/coordinator.py entirely (CoordinatorManager class + the _enqueue_on_ui helper, which CoordinatorAdapter now hosts its own copy of). - Trim turnstone/core/workstream.py to just the Workstream dataclass + WorkstreamKind + WorkstreamState. ~385 lines of WorkstreamManager logic gone; the remaining shape is pure data types shared by both managers. - Delete tests/test_workstream.py (WSM-specific) and tests/test_coordinator_manager.py (CM-specific). - Wire turnstone/cli.py to SessionManager + InteractiveAdapter, same pattern as turnstone/server.py. The CLI's WorkstreamTerminalUI uses manager.set_state + manager.active_id — both preserved on SessionManager (CLI is a live caller that keeps the focus API honest, per the handoff's "delete unless it pulls its weight" rule). - Add an optional manager-level ``_on_state_change`` observer hook restored for the CLI's background-attention notification (the web path uses the adapter's emit_state; this hook covers callers that don't consume SSE). - Drop dead ``_on_state_observer`` / ``_on_rename_observer`` fields from ConsoleCoordinatorUI — the old CoordinatorManager installed them; SessionManager/CoordinatorAdapter handle fan-out directly. Vulture @ 80% confidence: zero unused symbols across the new SessionManager + adapter files. Ruff + mypy clean (170 files). Full pytest (excluding tests/live): 4414 passed. Net across the whole Stage 1 branch: one unified SessionManager + adapter Protocol replaces two ~500-line parallel managers + a ~600-line CoordinatorManager, and the interactive + coordinator transports stay cleanly separated at the adapter boundary. * refactor(auth): drop workstream row-level ownership gates Turnstone is a trusted-team tool (per #400). user_id stays as metadata for audit + display; it no longer rejects requests. Scope- level auth via admin.workstreams / admin.coordinator tokens is the only gate now. Solves sec-1 (cross-tenant delete via collision on caller-supplied ws_id, because the gate was half-implemented) and sec-2 (blank-sub JWT bypass on empty-owner rows). Net: 359 lines of defensive empty-string comparisons and admin=True bypass plumbing deleted. * fix(core): serialize set_state vs close + worker spawn Three concurrency fixes from the multi-stage review: - bug-3: set_state now looks up ws under self._lock and gates its storage write on ws._closed (a new tombstone flag). close() sets ws._closed=True and does its storage write under ws._lock. A set_state that acquires ws._lock after close sees the tombstone and skips its write instead of resurrecting the closed row. - bug-1: _spawn_worker wraps the check-and-spawn in ws._lock so two concurrent send() HTTP requests can't both observe "no live worker" and start duplicate worker threads on the same ChatSession. - bug-2: replaces Thread.is_alive() as the reuse gate with an explicit ws._worker_running flag. The flag is set before the worker thread starts and cleared in its finally block — both under ws._lock. Using is_alive() left a narrow window where the worker could exit between the check and a queue_message call, stranding the user's message with no consumer. perf-2 (lock-held-across-DB-write) is accepted as-is: per-ws serialization of state transitions behind a DB round-trip is real cost but bounded — a given ws's state flips happen sequentially on its worker thread anyway. Dropping ws._lock around the DB write would reintroduce the bug-3 race. Full pytest: 4401 passed. Ruff + mypy clean. * refactor(core): drop _resolve_skill from SessionManager Skill resolution (name → template_id + applied_version) moves out of the shared manager and back to the HTTP handlers that own the create request. The interactive handler already resolved skill_data + applied_skill_version for other purposes (model override, judge config, post-create session seed) and was passing the name to SessionManager which then redundantly re-resolved via get_skill_by_name + count_skill_versions — two wasted DB round-trips per create on a user-visible latency path. - SessionManager.create: accepts skill_id + skill_version as already-resolved kwargs; _resolve_skill helper deleted. - turnstone/server.py create_workstream: passes the skill_id / applied_skill_version it already computed. - turnstone/console/server.py coordinator_create: pre-resolves inline (parity with interactive) before calling coord_mgr.create. Fixes perf-1 (redundant skill queries per create), q-4 (divergent skill-version computation between manager and handler), q-5 (coordinator-specific lookup on the shared manager surface). Full pytest: 4401 passed. Ruff + mypy clean. * refactor(adapters): extract shared cleanup_ui + drop dead child-registry methods Both InteractiveAdapter.cleanup_ui and CoordinatorAdapter.cleanup_ui (plus their _broadcast_ws_closed_to_listeners helpers) were byte-identical. Pull them into turnstone/core/adapters/_ui_cleanup.py:cleanup_session_ui so the two adapters delegate to one implementation. Also drop CoordinatorAdapter.register_children (only test callers — now use _seed_children in tests/_coord_test_helpers.py) and _add_child (zero callers anywhere). * refactor(adapters): symmetric attach() + fail-loud on unattached manager Add InteractiveAdapter.attach(manager) + .manager property mirroring the coord-side pattern. CLI (cli.py) now uses cli_adapter.attach(manager) instead of the _mgr_ref list-ref late-binding hack; server.py picks up the same call for consistency. CoordinatorAdapter.send / _rebuild_children_registry / _prime_children_from_snapshot no longer silently return when self._manager is None — raise RuntimeError so a forgotten attach() at startup fails loud instead of dropping the whole fan-out. * docs: replace stale WorkstreamManager / CoordinatorManager references Both classes were deleted in 965e0b6; prose docstrings across the codebase still named them. Update to SessionManager (or describe the collapsed-into-one-class architecture where the distinction matters). Leaves the 'Ported from …' historical markers in session_manager.py / coordinator_adapter.py / interactive_adapter.py intact — those are deliberate pointers back to the pre-unification code. * fix(core): atomic close_if_idle + batch pop under one lock bug-5: SessionManager.close_idle re-checked ws.state == IDLE outside the lock, so a pending tool result could flip state IDLE→RUNNING between the snapshot and close() acquiring self._lock. Add _close_if_idle_locked that tests state + pops under self._lock. perf-5: drop the per-victim self._lock acquisition; collect + pop the whole batch in one acquisition, then run cleanup_ui / storage write / emit_closed outside the lock. * perf(coord): split emit_created / emit_rehydrated to skip storage query on fresh creates CoordinatorAdapter.emit_created was unconditionally calling _rebuild_children_registry (storage.list_workstreams with parent_ws_id=... limit=10001) on every create, even for fresh-create paths that provably have zero children. Add emit_rehydrated to the SessionKindAdapter Protocol. SessionManager .create still calls emit_created; .open (lazy rehydrate) now calls emit_rehydrated. CoordinatorAdapter.emit_created seeds the registry + fan-out but skips the rebuild; emit_rehydrated seeds + rebuilds + fans out. InteractiveAdapter.emit_rehydrated delegates to emit_created (no children-registry on the interactive transport). * perf(coord): fold _active_coords into _children_lock + mutate payload in place perf-4: _active_coords used a copy-on-write dict-swap pattern so the fan-out dispatch could read it lock-free, but _dispatch_child_event already re-validates the parent under _children_lock anyway — the lock-free snapshot was premature. Replace with a plain dict read+write both under _children_lock; install and remove collapse to one-liners. Value also drops the user_id half — dead after |
||
|
Patrick Buckley
|
2b93598d68 |
feat: multi-model health tracking with runtime default and DB-only st… (#304)
* feat: multi-model health tracking with runtime default and DB-only startup Replace active-probe circuit breaker with passive per-backend health tracking. Backends are marked degraded after consecutive failures and recover when a request succeeds — requests are never blocked. - Add model.default_alias ConfigStore setting for runtime default model - Make load_model_registry CLI args optional for DB-only startup - Per-(provider, base_url) health trackers via HealthTrackerRegistry - Two-pass fallback: prefer healthy backends, then try degraded - Remove BackendHealthMonitor, CircuitState, probe threads, cooldown - Remove circuit_state from API schema, SDK events, metrics, frontends * feat: add "Set Default" button to Model Definitions admin panel Show a "default" badge on the current default model alias and a "set default" action button on all other models. Clicking it writes model.default_alias via the settings API. The list endpoint now includes default_alias in the response so the UI can highlight it. * fix: address review feedback — metric scoping, effective default, session alias - Move turnstone_backend_up metric out of BackendHealthTracker into server callback; only the effective default backend drives the gauge - _build_health_dict resolves effective default via ConfigStore override - session_factory computes selected_alias once before registry.resolve - admin model-definitions endpoint returns effective default (not just override) so UI shows correct badge when ConfigStore is empty - Rename circuitTitle → healthTitle in console JS - Fix ruff SIM117 lint in test * fix: validate effective default against enabled models, degraded label, log normalization - admin model-definitions endpoint validates default_alias against enabled models using same fallback rules as load_model_registry - UI text "backend down" → "backend degraded" to match advisory semantics - Health tracker log uses normalized base_url from key, not raw argument |
||
|
Patrick Buckley
|
f978e7facd |
fix: skip chat_template_kwargs for commercial OpenAI API (#297)
* fix: skip chat_template_kwargs for commercial OpenAI API
OpenAI rejects chat_template_kwargs as an unknown parameter — it's only
meaningful for local model servers (vLLM, llama.cpp, SGLang).
Split OpenAIProvider into separate singletons for "openai" vs
"openai-compatible" so _provider_extra_params can gate on provider_name
instead of inspecting base_url. Also deduplicates agent inline code into
the same method and fixes pre-existing test pollution where
get_capabilities was mutated on the singleton without cleanup.
* feat: add OpenAI Responses API provider for commercial models
Split the OpenAI provider into three concrete implementations behind the
LLMProvider protocol:
- _openai_chat.py: Chat Completions API for local model servers
(vLLM, llama.cpp, SGLang)
- _openai_responses.py: Responses API for commercial OpenAI
(GPT-5.x, O-series)
- _openai_common.py: shared capability table, temperature/reasoning
gating, cache retention, citations, usage extraction
The Responses API handles reasoning_effort as a {"effort": value} dict,
system messages as an instructions field, and tool format translation at
the provider boundary. ChatSession is unchanged — the provider abstracts
the API difference.
Also fixes diff_file direction when comparing against provided content.
* fix: Responses API input format and local model provider routing
- Assistant input messages use plain string content (not output_text)
- Tool call argument deltas match on item_id, not call_id
- Auto-detect openai-compatible provider for non-api.openai.com URLs
- Fix diff_file direction when comparing against provided content
* fix: resolve env vars before provider auto-detection in config.toml models
Config-file model entries using ${ENV_VAR} placeholders in base_url were
not resolving env vars before _resolve_openai_provider(), causing
commercial OpenAI configs to be misclassified as openai-compatible.
|
||
|
Patrick Buckley
|
62d2a0fe6a |
fix: remove non-auth support from bootstrap wizard (#274)
* fix: remove non-auth support from bootstrap wizard Auth is now mandatory for all deployments. Remove the TURNSTONE_AUTH_ENABLED toggle and make JWT_SECRET and AUTH_TOKEN required in the wizard's system prompt. * fix: remove auth disable support from runtime and infra Remove AuthConfig.enabled field — auth is always on. Drop TURNSTONE_AUTH_ENABLED env var, config toggle, and the check_request bypass. Update compose.yaml, Helm chart, Terraform, docs, and tests to match. * feat: deprecate config tokens, require JWT secret, prefer JWT auth Phase 1 of config-token removal: - load_jwt_secret() now exits with error if no secret is configured (was: silently auto-generated ephemeral secret) - _authenticate_token() logs deprecation warning on config token use - CLI /cluster commands use ServiceTokenManager when JWT secret is set - turnstone-admin tls-list uses ServiceTokenManager when JWT secret is set - Update bootstrap wizard, docker.md, security.md to mark TURNSTONE_AUTH_TOKEN as deprecated and JWT_SECRET as required - Console test fixtures use auth token + headers (auth always enforced) * feat: add service scope for inter-service JWT auth Add "service" to VALID_SCOPES and SCOPE_HIERARCHY. Service tokens bypass require_permission() RBAC checks, replacing the old empty-user-id bypass that config tokens relied on. All ServiceTokenManager instances that need admin access now include "service" in their scopes (console proxy, channel gateway, CLI, admin CLI). Read-only services (collector, notification) unchanged. * feat: phase 2 config token deprecation - SDK doc examples now show API tokens (ts_) instead of config tokens - Remove _get_config_token() from admin CLI (dead code) - Block config token exchange in handle_auth_login — only password and API token login allowed - Update login tests to use password-based auth instead of config token exchange * feat: phase 3 — remove config tokens entirely Complete removal of config-file token authentication: - Delete AuthConfig.tokens, check(), _ROLE_TO_SCOPES, hmac dispatch branch, and config token loading from load_auth_config() - Remove auth_config parameter from _authenticate_token() and check_request() — callers updated throughout - Remove TURNSTONE_AUTH_TOKEN from compose.yaml, Helm charts, Terraform, turnstone.example.toml - Remove --auth-token CLI flags from turnstone, turnstone-admin, and turnstone-console - Simplify console main() — always use ServiceTokenManager (no fallback to static tokens) - Delete config-token-specific tests, rewrite check_request and integration tests to use JWT auth with proper audience claims - Remove all config token references from docs (security.md, docker.md, sdk.md, console.md, architecture.md, bootstrap prompt) * fix: address code review findings - Fix 33 broken tests: add JWT auth to test_api_versioning, test_console_routing_proxy, test_tls_admin, test_tls_manager, test_server_live (jwt_secret + audience-scoped auth headers) - Add TestRequirePermissionServiceScope: 4 tests covering the service scope RBAC bypass path - Remove stale comments referencing config tokens in auth.py and console/server.py - Remove dead proxy_auth_token parameter from console create_app() and static token fallback in _proxy_auth_headers() - Remove TURNSTONE_AUTH_TOKEN from env.py scrub list * fix: address Copilot review — JWT audience, compose require secret - CLI /cluster: add audience=JWT_AUD_CONSOLE to ServiceTokenManager (console validates audience, JWTs without it were rejected) - Admin CLI tls-list: same audience fix - compose.yaml: TURNSTONE_JWT_SECRET now uses :? to fail fast if unset - SDK console: fix default port from 8081 to 8090 * test: add auth enforcement tests for TLS admin endpoints 5 new tests: unauthenticated requests return 401 (list, renew, delete), read-only-scoped requests return 403 (renew, delete). Closes the TLS auth enforcement test gap noted in PROGRESS.md. * fix: address remaining Copilot review feedback - Fix token_source="config" → "test" in TLS test fixtures - Fix AuthResult.token_source docstring to include service origins - Require TURNSTONE_JWT_SECRET in cluster compose profile (:?) - Helm: add auth.jwtSecret + auth.existingSecret values, wire TURNSTONE_JWT_SECRET into secret.yaml and both deployments - Terraform: replace auth_token with jwt_secret variable + secret, remove orphaned auth_token resources and IAM reference - Remove [[auth.tokens]] from security.md config example * fix: address full code review — 10 findings Critical: - Terraform: replace concat(common_env, auth_env) with common_env (auth_env local was removed but still referenced) - Channel gateway: remove hmac static token auth from _check_auth(), use JWT-only validation. Remove --auth-token CLI arg from channel - Rebalancer: add token_manager support so migration requests carry JWT auth (was sending unauthenticated POST to /internal/migrate) Major: - Guard _permissions_to_scopes() against "service" privilege escalation from DB role permissions - Remove dead AuthConfig class, load_auth_config(), and all auth_config parameters from create_app() signatures - Helm: inject JWT secret for both inline and existingSecret paths Minor: - Remove dead auth_token param from ClusterCollector - Remove empty TestLoadAuthConfig class - Short JWT secret now exits instead of warning - Compose: add generation command comment above JWT_SECRET - Clean stale config token references from 6 doc files - Clean stale AUTH_TOKEN reference from bootstrap wizard prompt * fix: remove remaining stale config token references from docs - channels.md: remove --auth-token from options table - oidc.md: remove "config-file tokens still work" claim - security.md: remove config token section, fix JWT secret docs (now required/exits, no ephemeral fallback), remove hmac from ASCII diagram, remove --auth-token reference |
||
|
Patrick Buckley
|
f74aa2264e |
refactor: add is_error to on_tool_result protocol, remove text heuris… (#207)
* refactor: add is_error to on_tool_result protocol, remove text heuristics Add is_error keyword arg to SessionUI.on_tool_result() so tools report errors structurally. Server and JS client no longer guess from output text prefixes — each tool sets the flag at the source. Bash tool: exit code >= 2 is error, exit code 1 is ambiguous (grep no-match). History reconstruction keeps text heuristic as fallback for pre-migration data. Update SDKs (Python + TypeScript), test mocks, docs, and diagrams. * fix: infinite recursion in _report_tool_result, signal exits, stale docs * fix: add _tool_error_flags to test_load_skill ChatSession stubs |
||
|
Patrick Buckley
|
ec3454ee2e |
fix: wire resume_ws through console + expose max_ws in heartbeat (#124)
* fix: wire resume_ws through console + expose max_ws in heartbeat Console create_workstream handler now reads resume_ws from the request body and passes it to CreateWorkstreamMessage on all three dispatch paths (pool, auto, explicit). Previously resume only worked via channel router and direct CLI — the console layer never plumbed it through. Server /health now includes max_ws from WorkstreamManager. Bridge reads it on startup and includes it in heartbeat metadata so the console's _pick_best_node gets accurate capacity instead of always defaulting to 10. Collector also updates max_ws on subsequent heartbeats (not just discovery). Schemas, Python SDK, TypeScript SDK, and OpenAPI specs updated. Test mocks fixed for new max_workstreams property access in /health. * fix: address PR #124 review — resume_ws tests + max_ws fetch on pre-set node_id Add _fetch_server_metadata() so bridge reads max_ws from /health even when node_id is pre-set (skipping _fetch_node_id). Without this, heartbeats would advertise max_ws=10 regardless of actual server config. Add 3 test cases verifying resume_ws flows through all three console dispatch paths (directed, pool, auto-select). |
||
|
Patrick Buckley
|
5378b33641 |
feat: output guard — evaluate tool results before they enter context (#109)
* feat: output guard — evaluate tool results before they enter context Add turnstone/core/output_guard.py — a time-budgeted heuristic that evaluates tool execution results after execution but before they enter the conversation context window. Priority-ordered detection (5s budget, highest priority first): 1. Prompt injection: override phrases, role injection, instruction override markers, meta-injection patterns 2. Credential leakage: API keys (OpenAI/GitHub/AWS/Google), PEM private key blocks, connection strings, .env secret format 3. Encoded payloads: script data URIs, hex shellcode sequences 4. Adversarial URLs: cloud metadata endpoints, credential query params 5. System info disclosure: private IPs, sensitive file paths Annotates and optionally redacts (credentials → [REDACTED:<type>]). Does NOT gate — surfaces warnings via on_output_warning callback. Integration: - Wired into session.py tool result loop via _evaluate_output() - JudgeConfig gains output_guard + redact_secrets fields (both default true) - SessionUI protocol gains on_output_warning callback - 25 compiled regex patterns, pure function, no I/O 29 tests covering all detection categories, benign output false positive checks, credential redaction, and time budget behavior. * fix: address PR #109 review — protocol, config, and guard fixes Copilot review feedback: - Replace _CLEAN singleton with _clean() factory to prevent mutable shared state (OutputAssessment has list fields) - Remove redundant second _CREDENTIAL_PATTERNS loop in _check_credentials - Evaluate text parts of list outputs (images) not just string outputs - Wire output_guard + redact_secrets through ConfigStore settings registry and _build_judge_config() so operators can configure via admin Settings tab - Remove --no-output-guard CLI flag claim from docs (use Settings tab) Typecheck fix: - Add on_output_warning to all SessionUI implementations: NullUI (eval, 5 test files), WebUI (server — emits SSE event), TerminalUI (CLI — ANSI colored warning), RecordingUI, FakeUI |
||
|
Patrick Buckley
|
fb190f8977 |
Normalize session_id into ws_id as sole persistent identity (#29)
* 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 |
||
|
Patrick Buckley
|
2b58c127b1 |
Add pluggable storage backend (SQLite + PostgreSQL) and deployment packaging (#20)
* Add pluggable storage backend (SQLite + PostgreSQL) and deployment packaging Database abstraction: StorageBackend protocol with 21 methods, SQLAlchemy Core schema, SQLite backend (FTS5), PostgreSQL backend (tsvector/ILIKE), Alembic migrations, singleton registry. memory.py reduced to thin facade. Session.py open_db() calls replaced with generic KV methods. [database] config section with env var support. Deployment: Docker Compose production profile with PostgreSQL, Dockerfile with postgres extras and migration entrypoint, Helm chart with bitnami subcharts, Terraform AWS ECS/Fargate module with RDS + ElastiCache + ALB. 39 new storage tests (934 total). mypy strict clean. Docs and diagrams updated. * Address PR #20 review feedback (16 items) - Backends only call create_all() when Alembic migrations are disabled - Helm configmap uses correct TURNSTONE_DB_BACKEND env var; DB URL constructed via env expansion with secret reference instead of ConfigMap - Migration errors fail fast for PostgreSQL (only non-fatal for SQLite) - save_memory/delete_memory wrapped in exception handling like other facade fns - pool_size passed through from config/env to init_storage() in cli + server - Terraform: DB URL moved to Secrets Manager, auth enabled flag set, optional TLS listeners with certificate_arn, Redis transit encryption on - Docker entrypoint no longer suppresses migration output - Diagram fixes: removed StaticPool claim, removed non-existent migration ref - compose.yaml/README: clarified production profile requires DB env vars |
||
|
Patrick Buckley
|
62a4ceac96 |
Dev/api versioning openapi (#18)
* Add API versioning under /v1/ prefix with OpenAPI 3.1 spec
All API endpoints move to /v1/api/* (clean break, no unversioned
aliases). Non-API routes (/, /health, /metrics, /static, /shared,
/node proxy) stay unversioned.
New turnstone/api/ package:
- Pydantic v2 models for all request/response schemas (server +
console) used for OpenAPI spec generation
- Programmatic OpenAPI 3.1 spec builder with EndpointSpec catalog
- /openapi.json serves machine-readable spec, /docs serves Swagger UI
Route changes:
- Both servers use Mount("/v1", routes=[...API routes...])
- Auth middleware strips /v1/ prefix before path classification
(PUBLIC_PATHS/WRITE_PATHS stay unversioned internally)
- Console proxy handles /node/{id}/v1/api/ upstream forwarding
- Bridge and CLI HTTP clients updated to /v1/api/ paths
- /openapi.json and /docs added to PUBLIC_PATHS and rate limiter
EXEMPT_PATHS
Security fix from review: required_role() now correctly handles
/node/{id}/v1/api/{path} proxy routes (previously the v1 segment
caused write-path detection to fail, allowing read-only token
escalation).
42 new tests (830 total). All frontend JS, docs, and diagrams updated.
* Fix mypy type errors in turnstone/api/ package
- Add generic type params to dict fields in console_schemas.py
- Add return type annotations to docs.py handler factories
- Move type-only imports (BaseModel, Callable, Awaitable) into
TYPE_CHECKING blocks to satisfy TC002/TC003 ruff rules
* Address PR #18 review feedback + fix mypy errors
Review fixes:
- Add pydantic>=2.0 as explicit dependency in pyproject.toml
(was only transitively available via openai/mcp)
- Auto-detect path parameters from {param} segments in OpenAPI
spec builder (fixes missing required path params)
- Use startswith() with concrete prefix for proxy version
detection instead of fragile substring check
- Make Swagger UI base URL configurable via swagger_ui_base_url
parameter for air-gapped deployments
Mypy fixes:
- Add generic type params to dict fields in console_schemas
- Add return type annotations to docs.py handler factories
- Move type-only imports into TYPE_CHECKING blocks
|
||
|
Patrick Buckley
|
a1f00092f5 |
Migrate HTTP servers from stdlib to Starlette/ASGI + uvicorn (#11)
* 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 |
||
|
Patrick Buckley
|
167d63b385 |
Add operational features: health degradation, rate limiting, workstre… (#10)
* 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 |
||
|
Patrick Buckley
|
7fbcb70ec1 |
Add call_id routing for streaming tool output during parallel execution (#6)
* 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
|
||
|
Patrick Buckley
|
7ebc04d1cc |
Fix Copilot PR #3 review: timeout race, ANSI stripping, streaming perf (#5)
- Fix timeout race in _exec_bash: check proc.poll() before setting timed_out flag; fall back to proc.kill() if process group kill fails - Remove stderr_thread.join(timeout=5) — after proc.wait() the pipe is closed so join completes promptly without risk of truncation - Fix CSI final byte range in stripAnsi: [A-Za-z] → [@-~] to handle sequences like \x1b[1~ (Home key) that end in non-letter bytes - Use appendChild(createTextNode()) instead of textContent += for O(1) chunk appending in streaming output (avoids O(n²) on large output) - Use var(--accent-dim) in stream-pulse keyframe instead of hardcoded rgba() so pulse color adapts to light/dark theme - Record tool_output_chunk calls in RecordingUI for test assertions |
||
|
Patrick Buckley
|
14a9ff9513 |
Stream bash tool output incrementally via SSE
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 |
||
|
Patrick Buckley
|
9be155b97a |
Quality overhaul: code tooling, CI/CD, architecture diagrams, UI rede… (#1)
* 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
|
0d6252dd7d | Initial commit — turnstone multi-node AI orchestration platform. |