fix: only gate-created approvals unlock code execution; Code Studio re-sends approval_id

A low-risk execute_code request filed via POST /api/approvals is auto-approved by the default policy and could be used as approval_id. Require risk_level=critical (what the gate records). Code Studio now re-submits the pending approval_id for the same code/language so Run works after approval. Co-Authored-By: Claude Opus 5.5 <[email protected]>
fix: require recorded approval before /api/code/execute runs code (fixes #311 )
2026-11-07 05:56:17 -10:00 · 2026-10-24 01:56:08 +00:00 · 2026-10-24 01:22:01 +00:00
58 changed files with 452 additions and 8044 deletions
@@ -27,7 +27,7 @@ jobs:
    permissions:
      issues: write
      pull-requests: write
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].17
    secrets: inherit
    with:
-      hub_ref: v1.1.20
+      hub_ref: v1.1.17
@@ -16,8 +16,8 @@ permissions:

 jobs:
  recover:
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].17
    secrets: inherit
    with:
-      hub_ref: v1.1.20
+      hub_ref: v1.1.17
      pr_number: ${{ github.event.inputs.pr_number || '' }}
@@ -25,8 +25,8 @@ permissions:

 jobs:
  detect-and-trigger:
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].17
    secrets: inherit
    with:
-      hub_ref: v1.1.20
+      hub_ref: v1.1.17
      pr_number: ${{ github.event.inputs.pr_number || '' }}
@@ -43,9 +43,9 @@ jobs:
      id-token: write
    steps:
      - uses: actions/checkout@v4
-      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].20
+      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].17
        with:
-          hub_ref: v1.1.20
+          hub_ref: v1.1.17
      - name: Generate GitHub App token
        id: app-token
        uses: actions/create-github-app-token@v1
@@ -88,9 +88,9 @@ jobs:
      actions: read
      id-token: write
      statuses: write   # the assess job records security/outsider-review
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].17
    secrets: inherit
    with:
-      hub_ref: v1.1.20
+      hub_ref: v1.1.17
      pr_number: ${{ github.event.inputs.pr_number || github.event.client_payload.pr_number || '' }}
      merge_method: ${{ github.event.inputs.merge_method || 'merge' }}
@@ -18,7 +18,7 @@ jobs:
      issues: write
      actions: read
      id-token: write
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].17
    secrets: inherit
    with:
-      hub_ref: v1.1.20
+      hub_ref: v1.1.17
@@ -25,9 +25,9 @@ jobs:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
-      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].20
+      - uses: MervinPraison/github-automation-template/.github/actions/[email protected].17
        with:
-          hub_ref: v1.1.20
+          hub_ref: v1.1.17
      - name: Detect conflicting PRs and trigger Claude
        uses: actions/github-script@v7
        with:
@@ -13,7 +13,7 @@ permissions:

 jobs:
  sync:
-    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].20
+    uses: MervinPraison/github-automation-template/.github/workflows/[email protected].17
    secrets: inherit
    with:
-      hub_ref: v1.1.20
+      hub_ref: v1.1.17
@@ -1,94 +0,0 @@
-# ADR 0001: PraisonAI Replay view, a clean-room design
-
- **Status:** accepted
- **Date:** 2026-10-26
- **Scope:** `src/praisonaiui/features/replay.py`, `features/_trace_jsonl.py`,
-  `templates/frontend/plugins/views/replay-core.js`, `templates/frontend/plugins/views/replay.js`
-
-## Context
-
-PraisonAI records agent runs as context-trace JSONL (one `ContextEvent.to_dict()` per
-line). People need to see what a team or flow did: who did what, when, why, and at what
-cost, both after the fact and live. Other tools have shown that a graph plus a trace is a
-useful way to look at agent runs. We want that value without copying anyone's product,
-code or look, and without adding dependencies.
-
-## Decision
-
-Build our own view, in plain DOM and SVG, with our own layout code, palette and words.
-
-### Ideas we took (ideas only)
-
-| Idea | Where it came from | What we did with it |
-|---|---|---|
-| Show the graph of a multi-agent program next to the trace of a run | The general concept behind LangGraph Studio's graph-plus-trace view, known from public talks and articles | A **Map** view drawn by our own layered layout (`layoutMap`); the default view is a **Timeline**, which Studio does not have |
-| Parallel voices on shared time, read left to right | Musical scores and swimlane diagrams | One lane per agent plus Manager and You; parallel branches as sub-lanes; tasks and steps as "chapters" across the top |
-| Vocabulary for LLM and tool spans, tokens and cost | OpenTelemetry GenAI semantic conventions (public specification) | Block kinds (LLM, tool), token and cost totals; the wrapper's OTLP export uses the conventions, the UI only borrows the concepts |
-
-### What we did not use
-
- **No third-party UI code, CSS, icons, layouts or screenshots** were used to build this
-  view. Shapes, palette, spacing, wording ("Brief", "Delivered", "Waiting for you") and
-  the layout algorithm are our own.
- **LangGraph's server (Elastic License 2.0) and the proprietary LangGraph Studio were
-  not consulted for code**, and none of their assets, markup or styles were copied. We
-  do not use the name "Studio", any "Lang…" naming, or `__start__`/`__end__` pills.
- No Mermaid, D3, React Flow, dagre, ELK or other graph libraries. The dashboard's
-  existing Mermaid CDN plugin is not used by Replay.
-
-### How it is built
-
- `replay-core.js`: pure functions (`buildModel`, `narrate`, `layoutMap`,
-  `deriveGraph`). No DOM, no network. Tested with `node --test`.
- `replay.js`: DOM/SVG rendering, keyboard handling, SSE follow and approvals. It also
-  boots by itself when `window.__REPLAY_DATA__ = {events, graph}` is set, which is how
-  the wrapper's single-file HTML export works (`standalone_html()` inlines both files).
- `layoutMap` is a textbook layered layout written from scratch: depth-first search to
-  find back edges (loops), longest-path layering, one virtual waypoint per crossed layer
-  for long edges, and a few barycentre sweeps to order each layer. It is deterministic.
- Narration is template text, chosen per event type. No LLM, no randomness.
-
-## Palette and accessibility rationale
-
-| Role | Fill | Shape | Why |
-|---|---|---|---|
-| Agent | `#8B0000` | circle | PraisonAI's brand red; white text on it is 10.0:1 |
-| Tool | `#0F7287` | rounded rectangle | Teal kept from the brand but darkened from `#189AB4` (white text on `#189AB4` fails AA); white on `#0F7287` is 5.6:1 |
-| You (human) | `#8A5A00` | diamond | Amber distinct from red and teal for common colour-vision deficiencies; white on it is 5.9:1 |
-| Manager | `#3C4A5C` | square | Neutral slate, so the manager reads as coordination, not work; white on it is 9.0:1 |
-
- **Never colour alone.** Every lane, block, node and step has a shape and a text label;
-  arrows differ by dash pattern and carry words ("hands off", "delegates", "routes").
-  Heat in the cost/latency overlay is a bar whose height and shade both grow, plus the
-  value in text.
- **Theme.** Follows the system setting (`prefers-color-scheme`) by default, with a
-  Light/Dark override; the light theme is the design baseline.
- **Light theme first.** Text tokens are at least 6.9:1 on their backgrounds in light mode
-  and 7.7:1 in dark mode. In dark mode the palette fills keep white text at AA, and get a
-  light 2 px outline so each shape's boundary stays above 3:1 against the dark page.
- **Keyboard throughout.** ← → (and ↑ ↓ in the step list) move the replay cursor, Home
-  and End jump to the ends, tabs follow the ARIA tabs pattern, map nodes use a roving
-  tab stop, and every action has a real button.
- **Screen readers.** The narration column is a real ordered list and is the main way
-  through a run. Timeline blocks and map nodes are named buttons whose names start with
-  their visible text (WCAG 2.5.3). Live updates are announced through a polite live
-  region, throttled.
- **Motion.** The only animation (the live dot) runs only under
-  `prefers-reduced-motion: no-preference`; scrolling is instant when motion is reduced.
- Checked with axe-core against WCAG 2.0, 2.1 and 2.2 A/AA in both themes (dev-only test
-  in `tests/browser/`).
-
-## Dependency licences
-
-No new runtime or build dependencies. The Python side uses only the standard library and
-Starlette, which aiui already depends on. The browser side is plain ES modules with no
-imports beyond our own file. Dev-only test tools that are not shipped: Playwright
-(Apache-2.0, already used in this environment) and axe-core (MPL-2.0, loaded from a path
-given by `AXE_CORE_JS`; not vendored).
-
-## Consequences
-
- We own the look and the layout code, and can change them without licence questions.
- The layout is simpler than a dedicated graph engine. It is fine for the team and flow
-  sizes we see (tens of nodes). Very large graphs may need a better crossing-reduction
-  step later.
@@ -1,176 +0,0 @@
-# Replay
-
-**PraisonAI Replay** shows a recorded agent run as a story: who did what, when, why, and
-at what cost. It works for finished runs and for runs that are still going.
-
-## Record a run, then open it
-
-```bash
-praisonai replay view agents.yaml      # records the run and opens Replay on it
-```
-
-or from Python:
-
-```python
-from praisonai.replay import record
-
-with record(live=True):
-    team.start()
-```
-
-Every recorded run is a file `<id>.jsonl` in the traces folder. Replay reads it from
-`$PRAISONAI_TRACES_DIR`, else `$PRAISON_HOME/traces`, else `~/.praison/traces`.
-
-To open aiui on Replay yourself:
-
-```bash
-aiui run "$(python -c 'import praisonaiui.replay_app as m; print(m.__file__)')" \
-    --style dashboard --host 127.0.0.1 --port 8090
-# then open http://127.0.0.1:8090/replay?run=<id>
-```
-
-`/#/replay?run=<id>` works too. In a full dashboard, Replay is in the sidebar under
-**Control**.
-
-## Watch a run live: the Run button
-
-For learning, demos and debugging, open a page with a **Run** button. Each click records
-a new run, and the page draws it as it happens:
-
-```python
-from praisonai.replay import watch
-
-watch(flow, input="solar sails")   # an Agent, AgentTeam, AgentFlow or agents.yaml
-```
-
-```bash
-praisonai replay watch agents.yaml
-```
-
-On the **Map**, each step and agent shows where the run is: dashed means not reached,
-blue (pulsing) means running now, green means done and red means failed. After a run,
-**▶ Play** moves through it again one step at a time, and the map rewinds with it. One
-run goes at a time. Each run of a team starts its tasks afresh; an Agent keeps its chat
-history between runs.
-
-## Show progress inside your own app
-
-`create_replay_app()` is the same view as a small ASGI app, without the dashboard. Mount
-it in any FastAPI or Starlette app:
-
-```python
-from praisonai.replay import record, replay_app
-
-app.mount("/replay", replay_app())         # read-only: shows recorded runs
-
-# wherever your app starts work:
-with record(run_id, live=True):
-    team.start()
-```
-
-Then show one run, live, in your page, for example in an `<iframe>`:
-
-```html
-<iframe src="/replay/?run=RUN_ID" style="width:100%;height:640px"></iframe>
-```
-
-| URL | Shows |
-|---|---|
-| `/replay/` | The run list and the selected run |
-| `/replay/?run=<id>` | Only that run, no list. A run that has not started yet is waited for. |
-
-`replay_app(team)` adds the Run box to the mounted page. Without the PraisonAI wrapper,
-pass any `run(input, run_id)` callable to `praisonaiui.features.replay.create_replay_app`;
-it must record the run under `run_id`. For a page you build yourself, the view is one
-module:
-
-```html
-<div id="progress"></div>
-<script type="module">
-  import { render } from "/replay/replay.js";
-  render(document.getElementById("progress"), { base: "/replay", run: "RUN_ID", approve: false });
-</script>
-```
-
-`render()` options: `base` (where the API is mounted), `run` (show only this run),
-`runner` (`{input, placeholder, ask}` to show the Run box) and `approve` (`false` hides
-the approve and deny buttons; the embedded app has no approvals API, so answer approvals
-where your app asks for them).
-
-Anyone who can reach the mounted app can read the runs, and with a runner can start one.
-Keep it on localhost or behind your app's login. `POST /api/replay/run` only accepts
-`Content-Type: application/json`, so another website cannot start a run from a visitor's
-browser.
-
-## What you see
-
-| Part | What it shows |
-|---|---|
-| **Runs** | Recorded runs, newest first. A run that is still being written has a **Live** badge. |
-| **Timeline** (default) | One lane per agent, plus **Manager** and **You**. Time runs left to right. LLM calls and tool calls are blocks in their agent's lane. Arrows show hand-offs, delegation, routing and approval requests. Parallel branches get their own sub-lanes. A call or step repeated back to back is one block marked ×N. Tasks and steps run across the top. |
-| **Map** | The team or flow as a graph, drawn from the graph recorded at the start of the run and fitted to the page (−, Fit and + zoom; drag to pan). Agents that took part but are not in the graph, for example after a hand-off to an agent outside the team, appear in an **Outside the team** group with their hand-offs. Older recordings without a graph get a "who talked to whom" map built from the events. Each node shows its state at the cursor: dashed means not reached, blue means running, green means done (×N when it ran more than once) and red means failed; the node the cursor is on has a bold outline. |
-| **What happened** | One plain sentence per step, for example *"Researcher asked web_search for 'solar sail facts' — 1.2 s, $0.002."* Hovering or focusing a sentence highlights its block, and the other way round. |
-| **Details** | Three tabs for the selected step. **What happened**: when, who, how long, cost, tokens, output. **Why**: only what the recording holds, such as the input given to a tool, the context passed in a hand-off and its reason, the manager's task snapshot, the route a step chose, and an approval's decision and where an automatic approval came from. **Raw JSON**: the events themselves. |
-| **Cost & latency** | Adds a bar under each block (taller and darker means more cost, or more time) and per-agent totals in the lane labels. |
-
-Shapes always carry meaning as well as colour: agents are circles, tools are rounded
-rectangles, you are a diamond and the manager is a square. In each lane, LLM calls sit on
-the top row and that agent's tool calls on a thinner row under them, so a long LLM call
-never hides its tools. Labels that do not fit end in "…"; hover or focus a block to see the
-whole label.
-
-The **Theme** menu follows your system's light or dark setting by default; choose Light or
-Dark to override it. On a phone the run list, timeline and steps stack in one column.
-
-## Moving through a run
-
-Replay opens at the end of the run, so you see everything. Move the cursor to replay it:
-anything after the cursor is drawn as an outline.
-
-| Key | Action |
-|---|---|
-| ← → | Previous / next step |
-| ↑ ↓ | Previous / next step in the step list; previous / next node in the map |
-| Home / End | First / last step |
-| Enter or Space | Open the focused block or node |
-| ← → in the tabs | Switch between What happened, Why and Raw JSON |
-
-The scrubber under the timeline does the same with a mouse or touch, and **▶ Play** steps
-through on its own. On a live run the
-cursor follows new events; if you step back, **Jump to live** takes you to the latest.
-
-## Approving from Replay
-
-When an agent asks for approval and the run uses aiui's approval store, a **Waiting for
-you** card appears above the timeline:
-
- **Approve** or **Deny**, with an optional reason.
- **Edit arguments…** opens the arguments as JSON (taken from the server, not the redacted
-  recording when the server has them). The JSON must be an object; mistakes are shown
-  as you type. **Approve with these arguments** sends them as `modified_args`.
-
-These buttons call `POST /api/approvals/{id}/approve` and `/deny`. The agent waits until
-you answer, and is denied if nobody answers before the approval timeout.
-
-## Sharing a run as one file
-
-`praisonai replay export RUN --format html` writes a single HTML file with the run and
-this viewer inside. It needs no server and no network. Approvals cannot be answered from
-an exported file.
-
-## HTTP API
-
-| Endpoint | Returns |
-|---|---|
-| `GET /api/replay/runs` | `[{run_id, session_id, path, started_at, ended_at?, status, kind, name, agents, events, cost_usd, live}]`, newest first |
-| `GET /api/replay/runs/{id}/events?after_seq=N` | `{events, graph, run}`; `after_seq` keeps only events with a larger `sequence_num`; `wait=1` answers `{events: [], graph: null, run: null}` instead of 404 for a run that has not started yet |
-| `GET /api/replay/runs/{id}/stream` | Server-sent events: `event: ctx` per trace event (with `id:` = `sequence_num`), `ping` every 15 s, `end` once the run has finished and gone quiet for 2 s. Honours `after_seq` and `Last-Event-ID`. |
-
-With a runner (`create_replay_app(run=...)`), `POST /api/replay/run` with
-`{"input": "..."}` starts a run and returns `{run_id}` (409 while one is going).
-
-Run ids must match `^[A-Za-z0-9._-]+$`. Replay never writes trace files itself. Half-written last lines, unknown fields and unknown event types are skipped
-safely, and schema 1.0 recordings still open.
-
-The **Traces** page reads the same files: each run is a trace, and its spans come from
-matching start and end events.
@@ -100,7 +100,6 @@ nav:
    - BeautifulUI Upstream Pin: frontend/BEAUTIFULUI_UPSTREAM.md
  - Features:
    - Dashboard: features/dashboard.md
-    - Replay: features/replay.md
    - Gateway Chat: features/gateway-chat.md
    - Attachments: features/attachments.md
    - Theme System: features/theme-system.md
@@ -1,6 +1,6 @@
 [project]
 name = "aiui"
-version = "0.3.151"
+version = "0.3.147"
 description = "YAML-driven website generator - CLI and compiler"
 readme = "README.md"
 license = {text = "MIT"}
@@ -82,6 +82,20 @@
        }
      }
    },
+    "node_modules/@a2ui/markdown-it": {
+      "version": "0.0.4",
+      "resolved": "https://registry.npmjs.org/@a2ui/markdown-it/-/markdown-it-0.0.4.tgz",
+      "integrity": "sha512-uaYNywdiHDH4i//pHpyckFnApvOshiUNT2Xl8awceNjL1XAX/gqtki9GRUJQ26RE7id2+aPNgOy1W6mXNBxriQ==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "dependencies": {
+        "dompurify": "^3.3.1",
+        "markdown-it": "^14.1.0"
+      },
+      "peerDependencies": {
+        "@a2ui/web_core": "^0.9.2"
+      }
+    },
    "node_modules/@a2ui/react": {
      "version": "0.10.0",
      "resolved": "https://registry.npmjs.org/@a2ui/react/-/react-0.10.0.tgz",
@@ -115,16 +129,16 @@
      }
    },
    "node_modules/@a2ui/web_core": {
-      "version": "0.10.2",
-      "resolved": "https://registry.npmjs.org/@a2ui/web_core/-/web_core-0.10.2.tgz",
-      "integrity": "sha512-IfS4K7baTL9P9AzUOzKRWzL9A9/+Z7TCgMY2GPwsZ0H7LgY/9/uJnlbReNhpHsAfN12KZtW9iERWkw5HOf71GA==",
+      "version": "0.10.0",
+      "resolved": "https://registry.npmjs.org/@a2ui/web_core/-/web_core-0.10.0.tgz",
+      "integrity": "sha512-pSieKxaB6aZWBL2LjZfKo4/1v4xMWylczpzte1ehuGH0kfNGf/iTd73PKsIKYx3b0FNWTbD8gAloOM4JCVqUig==",
      "dev": true,
      "license": "Apache-2.0",
      "dependencies": {
-        "@preact/signals-core": "^1.14.2",
-        "date-fns": "^4.4.0",
+        "@preact/signals-core": "^1.13.0",
+        "date-fns": "^4.1.0",
        "zod": "^3.25.76",
-        "zod-to-json-schema": "^3.25.2"
+        "zod-to-json-schema": "^3.25.1"
      }
    },
    "node_modules/@a2ui/web_core/node_modules/zod": {
@@ -5488,9 +5502,9 @@
      }
    },
    "node_modules/date-fns": {
-      "version": "4.4.0",
-      "resolved": "https://registry.npmjs.org/date-fns/-/date-fns-4.4.0.tgz",
-      "integrity": "sha512-+1UMbeh68lH1SegH83CGWwpb6OHHbpSgr3+s5Eww5M4CAgswBpoWS0AjTOfEJ33HiYKz1hdj/KTFprzXHmq/6w==",
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/date-fns/-/date-fns-4.1.0.tgz",
+      "integrity": "sha512-Ukq0owbQXxa/U3EGtsdVBkR1w7KOQ5gIBqdH2hkvknzZPYvBxb/aa6E8L7tmjFtkwZBu3UXBbjIgPo/Ez4xaNg==",
      "license": "MIT",
      "funding": {
        "type": "github",
@@ -9733,84 +9747,6 @@
        "type": "github",
        "url": "https://github.com/sponsors/wooorm"
      }
-    },
-    "node_modules/@a2ui/react/node_modules/@a2ui/markdown-it": {
-      "version": "0.0.4",
-      "resolved": "https://registry.npmjs.org/@a2ui/markdown-it/-/markdown-it-0.0.4.tgz",
-      "integrity": "sha512-uaYNywdiHDH4i//pHpyckFnApvOshiUNT2Xl8awceNjL1XAX/gqtki9GRUJQ26RE7id2+aPNgOy1W6mXNBxriQ==",
-      "dev": true,
-      "license": "Apache-2.0",
-      "dependencies": {
-        "dompurify": "^3.3.1",
-        "markdown-it": "^14.1.0"
-      },
-      "peerDependencies": {
-        "@a2ui/web_core": "^0.9.2"
-      }
-    },
-    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/core": {
-      "version": "1.8.1",
-      "dev": true,
-      "inBundle": true,
-      "license": "MIT",
-      "optional": true,
-      "dependencies": {
-        "@emnapi/wasi-threads": "1.1.0",
-        "tslib": "^2.4.0"
-      }
-    },
-    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/runtime": {
-      "version": "1.8.1",
-      "dev": true,
-      "inBundle": true,
-      "license": "MIT",
-      "optional": true,
-      "dependencies": {
-        "tslib": "^2.4.0"
-      }
-    },
-    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/wasi-threads": {
-      "version": "1.1.0",
-      "dev": true,
-      "inBundle": true,
-      "license": "MIT",
-      "optional": true,
-      "dependencies": {
-        "tslib": "^2.4.0"
-      }
-    },
-    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@napi-rs/wasm-runtime": {
-      "version": "1.1.1",
-      "dev": true,
-      "inBundle": true,
-      "license": "MIT",
-      "optional": true,
-      "dependencies": {
-        "@emnapi/core": "^1.7.1",
-        "@emnapi/runtime": "^1.7.1",
-        "@tybys/wasm-util": "^0.10.1"
-      },
-      "funding": {
-        "type": "github",
-        "url": "https://github.com/sponsors/Brooooooklyn"
-      }
-    },
-    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@tybys/wasm-util": {
-      "version": "0.10.1",
-      "dev": true,
-      "inBundle": true,
-      "license": "MIT",
-      "optional": true,
-      "dependencies": {
-        "tslib": "^2.4.0"
-      }
-    },
-    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/tslib": {
-      "version": "2.8.1",
-      "dev": true,
-      "inBundle": true,
-      "license": "0BSD",
-      "optional": true
    }
  }
 }
@@ -38,7 +38,7 @@ interface ActionButtonsProps {
 */
 export function ActionButtons({ actions, messageId, sessionId }: ActionButtonsProps) {
    const [pendingActions, setPendingActions] = useState<Set<string>>(new Set())
-    const [hiddenActions] = useState<Set<string>>(new Set())
+    const [hiddenActions, setHiddenActions] = useState<Set<string>>(new Set())

    const handleActionClick = useCallback(async (action: ActionButton) => {
        if (pendingActions.has(action.id) || hiddenActions.has(action.id)) {
@@ -73,7 +73,7 @@ export function AskActionPrompt({

            {/* Action buttons */}
            <div className="space-y-3">
-                {actions.map((action) => (
+                {actions.map((action, index) => (
                    <button
                        key={action.name}
                        type="button"
@@ -15,7 +15,7 @@ import { Textarea } from '../components/ui/textarea';
 import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '../components/ui/select';
 import { Slider } from '../components/ui/slider';
 import { Switch } from '../components/ui/switch';
-import { Card, CardContent } from '../components/ui/card';
+import { Card, CardContent, CardHeader, CardTitle, CardDescription } from '../components/ui/card';
 import { Sheet, SheetContent, SheetHeader, SheetTitle, SheetDescription } from '../components/ui/sheet';

 interface SettingsWidget {
@@ -74,7 +74,7 @@ const WidgetRenderer: React.FC<{
              id={name}
              placeholder={placeholder}
              value={value || ''}
-              onChange={(e: React.ChangeEvent<HTMLTextAreaElement>) => onChange(e.target.value)}
+              onChange={(e) => onChange(e.target.value)}
              maxLength={widget.maxLength}
              rows={4}
            />
@@ -20,16 +20,43 @@ interface CustomElementProps {
  onError?: (error: Error) => void;
 }

+interface CustomComponentModule {
+  default: React.ComponentType<any>;
+}
+
 // Registry of loaded components (cache)
 const componentCache = new Map<string, Promise<React.ComponentType<any>>>();

-// Custom components available to <CustomElementHost name="..." />. The example
-// widgets this once listed (ExampleWidget, UserCard, ...) were never added, and
-// importing them broke the build. Register real components here as they land:
-//   const MyWidget = React.lazy(() => import('../components/custom/MyWidget'));
-//   componentMap.MyWidget = MyWidget;
-const componentMap: Record<string, React.ComponentType<any>> = {};
-const availableComponents = new Set(Object.keys(componentMap));
+// List of available custom components (in practice, this would be populated from backend)
+const availableComponents = new Set([
+  'ExampleWidget',
+  'UserCard',
+  'DataChart', 
+  'FormBuilder',
+  'CodeEditor',
+  'ImageGallery',
+  'ChatEmbed'
+]);
+
+// Static imports for build-tool compatibility
+const ExampleWidget = React.lazy(() => import('../components/custom/ExampleWidget'));
+const UserCard = React.lazy(() => import('../components/custom/UserCard'));
+const DataChart = React.lazy(() => import('../components/custom/DataChart'));
+const FormBuilder = React.lazy(() => import('../components/custom/FormBuilder'));
+const CodeEditor = React.lazy(() => import('../components/custom/CodeEditor'));
+const ImageGallery = React.lazy(() => import('../components/custom/ImageGallery'));
+const ChatEmbed = React.lazy(() => import('../components/custom/ChatEmbed'));
+
+// Static mapping of component names to imports
+const componentMap: Record<string, React.ComponentType<any>> = {
+  ExampleWidget,
+  UserCard,
+  DataChart,
+  FormBuilder,
+  CodeEditor,
+  ImageGallery,
+  ChatEmbed,
+};

 /**
 * Load a custom component with static mapping for build-tool compatibility
@@ -4,6 +4,7 @@
 * Shows live-updating task lists with states, progress bars, and click-to-jump functionality.
 */

+import React from 'react'
 import { ChevronRight, ChevronDown, CheckCircle, Clock, XCircle, Circle, ExternalLink } from 'lucide-react'
 import { useTaskState, setTasksCollapsed, type Task, type TaskList, type TaskStatus } from '../state/tasks'
 import { cn } from '../lib/utils'
@@ -1,44 +0,0 @@
-import * as React from "react"
-import { cva, type VariantProps } from "class-variance-authority"
-
-import { cn } from "@/lib/utils"
-
-const alertVariants = cva(
-  "relative w-full rounded-lg border px-4 py-3 text-sm [&>svg+div]:translate-y-[-3px] [&>svg]:absolute [&>svg]:left-4 [&>svg]:top-4 [&>svg]:text-foreground [&>svg~*]:pl-7",
-  {
-    variants: {
-      variant: {
-        default: "bg-background text-foreground",
-        destructive:
-          "border-destructive/50 text-destructive dark:border-destructive [&>svg]:text-destructive",
-      },
-    },
-    defaultVariants: {
-      variant: "default",
-    },
-  }
-)
-
-const Alert = React.forwardRef<
-  HTMLDivElement,
-  React.HTMLAttributes<HTMLDivElement> & VariantProps<typeof alertVariants>
->(({ className, variant, ...props }, ref) => (
-  <div ref={ref} role="alert" className={cn(alertVariants({ variant }), className)} {...props} />
-))
-Alert.displayName = "Alert"
-
-const AlertTitle = React.forwardRef<HTMLParagraphElement, React.HTMLAttributes<HTMLHeadingElement>>(
-  ({ className, ...props }, ref) => (
-    <h5 ref={ref} className={cn("mb-1 font-medium leading-none tracking-tight", className)} {...props} />
-  )
-)
-AlertTitle.displayName = "AlertTitle"
-
-const AlertDescription = React.forwardRef<HTMLParagraphElement, React.HTMLAttributes<HTMLParagraphElement>>(
-  ({ className, ...props }, ref) => (
-    <div ref={ref} className={cn("text-sm [&_p]:leading-relaxed", className)} {...props} />
-  )
-)
-AlertDescription.displayName = "AlertDescription"
-
-export { Alert, AlertTitle, AlertDescription }
@@ -1,19 +0,0 @@
-import * as React from "react"
-
-import { cn } from "@/lib/utils"
-
-const Textarea = React.forwardRef<HTMLTextAreaElement, React.ComponentProps<"textarea">>(
-  ({ className, ...props }, ref) => (
-    <textarea
-      className={cn(
-        "flex min-h-[60px] w-full rounded-md border border-input bg-transparent px-3 py-2 text-base shadow-sm placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-ring disabled:cursor-not-allowed disabled:opacity-50 md:text-sm",
-        className
-      )}
-      ref={ref}
-      {...props}
-    />
-  )
-)
-Textarea.displayName = "Textarea"
-
-export { Textarea }
@@ -183,7 +183,7 @@ export function useMicStream(options: UseMicStreamOptions = {}): UseMicStreamRet
      onConnectionChangeRef.current?.(false);
    };
    
-    ws.onerror = () => {
+    ws.onerror = (error) => {
      onErrorRef.current?.(new Error('WebSocket error'));
      setConnected(false);
      onConnectionChangeRef.current?.(false);
@@ -5,33 +5,8 @@
 * incoming messages from parent.
 */

-import { useEffect, useCallback, useRef, useState } from 'react';
-
-interface EventSourceOptions {
-  enabled?: boolean;
-  onMessage?: (event: MessageEvent) => void;
-  onOpen?: () => void;
-  onError?: () => void;
-}
-
-/**
- * Minimal EventSource subscription. (useSSE in this package is the chat
- * streaming store, not a generic SSE hook, so it cannot open this stream.)
- */
-function useEventSource(url: string, { enabled = true, onMessage, onOpen, onError }: EventSourceOptions) {
-  const [connected, setConnected] = useState(false);
-  const handlers = useRef({ onMessage, onOpen, onError });
-  handlers.current = { onMessage, onOpen, onError };
-  useEffect(() => {
-    if (!enabled || typeof EventSource === 'undefined') return;
-    const source = new EventSource(url);
-    source.onopen = () => { setConnected(true); handlers.current.onOpen?.(); };
-    source.onmessage = (event) => handlers.current.onMessage?.(event);
-    source.onerror = () => { setConnected(false); handlers.current.onError?.(); };
-    return () => { source.close(); setConnected(false); };
-  }, [url, enabled]);
-  return { connected };
-}
+import { useEffect, useCallback, useRef } from 'react';
+import { useSSE } from './useSSE';

 export interface WindowMessageData {
  type: string;
@@ -110,7 +85,7 @@ export function useWindowMessage(options: UseWindowMessageOptions = {}): UseWind
  const isIframe = window !== window.parent;
  
  // SSE connection for outbound messages
-  const { connected } = useEventSource('/sse/window-message', {
+  const { connected } = useSSE('/sse/window-message', {
    enabled: enabled && isIframe,
    onMessage: (event) => {
      try {
@@ -7,7 +7,9 @@ import React, { useState } from 'react';
 import { Button } from '../components/ui/button';
 import { Input } from '../components/ui/input';
 import { Label } from '../components/ui/label';
+import { Select, SelectContent, SelectItem, SelectTrigger, SelectValue } from '../components/ui/select';
 import { Dialog, DialogContent, DialogDescription, DialogHeader, DialogTitle, DialogFooter } from '../components/ui/dialog';
+import { Separator } from '../components/ui/separator';
 import { Tabs, TabsContent, TabsList, TabsTrigger } from '../components/ui/tabs';

 interface AddMCPServerModalProps {
@@ -1,7 +1,7 @@
 import { useEffect, useState } from 'react';
+import { useParams } from 'react-router-dom';
 import { Eye, AlertCircle } from 'lucide-react';
 import { ChatMessages } from '../chat/ChatMessages';
-import type { ChatMessage } from '../types';
 import { Button } from '../components/ui/button';

 interface SharedThreadData {
@@ -11,13 +11,18 @@ interface SharedThreadData {
    title: string;
    created_at: string;
  };
-  messages: ChatMessage[];
+  messages: Array<{
+    id: string;
+    role: string;
+    content: string;
+    timestamp: string;
+    toolCalls?: any[];
+  }>;
  read_only: boolean;
 }

 export function SharedThread() {
-  // Served at /shared/{token} (server.py); this app has no client-side router.
-  const token = decodeURIComponent(window.location.pathname.split('/shared/')[1]?.split('/')[0] ?? '');
+  const { token } = useParams<{ token: string }>();
  const [threadData, setThreadData] = useState<SharedThreadData | null>(null);
  const [isLoading, setIsLoading] = useState(true);
  const [error, setError] = useState<string>('');
@@ -123,13 +128,10 @@ export function SharedThread() {
        <div className="bg-white rounded-lg shadow-sm border border-gray-200 overflow-hidden">
          {threadData.messages.length > 0 ? (
            <div className="divide-y divide-gray-100">
-              <ChatMessages
+              <ChatMessages 
                messages={threadData.messages}
                sessionId={threadData.thread_id}
-                currentResponse=""
-                thinkingSteps={[]}
-                toolCalls={[]}
-                isStreaming={false}
+                isSharedView={true}
              />
            </div>
          ) : (
@@ -1,3 +1,3 @@
 """Version information."""

-__version__ = "0.3.151"
+__version__ = "0.3.147"
@@ -80,7 +80,6 @@ def auto_register_defaults() -> None:
        (".tts", "TTSFeature"),
        (".usage", "UsageFeature"),
        (".realtime", "RealtimeFeature"),
-        (".replay", "ReplayFeature"),
        (".workflows", "WorkflowsFeature"),
        (".guardrails", "GuardrailsFeature"),
        (".eval", "EvalFeature"),
@@ -1,517 +0,0 @@
-"""Stdlib reader for PraisonAI context-trace JSONL files (Replay contract v1, section 1).
-
-One file per run at ``<traces dir>/<run_or_session_id>.jsonl``; one JSON object
-(``ContextEvent.to_dict()``) per line, in append order.  Readers must tolerate:
-
-* a partially written last line (it is skipped until it is complete);
-* unknown fields and unknown ``event_type`` values (passed through untouched);
-* schema 1.0 files (no ``run_id`` / ``parent_seq`` / ``node_id``).
-
-Shared by the ``replay`` feature (runs, events, SSE tail) and the ``tracing``
-feature (spans from start/end pairs).  No third-party imports.
-"""
-
-from __future__ import annotations
-
-import json
-import os
-import re
-import threading
-import time
-from pathlib import Path
-from typing import Any, Dict, Iterable, List, Optional, Tuple
-
-__all__ = [
-    "RUN_ID_RE",
-    "LIVE_WINDOW_S",
-    "traces_dir",
-    "is_valid_run_id",
-    "run_path",
-    "list_run_files",
-    "read_events",
-    "TailReader",
-    "EndTracker",
-    "find_graph",
-    "summarize_run",
-    "build_spans",
-]
-
-#: Allowed run ids: one path segment, no separators (path-traversal safe).
-RUN_ID_RE = re.compile(r"^[A-Za-z0-9._-]+$")
-
-#: A run without an end marker counts as live while its file changed this recently.
-LIVE_WINDOW_S = 15 * 60
-
-#: start event type -> the end event type that closes it.
-START_END: Dict[str, str] = {
-    "session_start": "session_end",
-    "workflow_start": "workflow_end",
-    "task_start": "task_end",
-    "step_start": "step_end",
-    "agent_start": "agent_end",
-    "tool_call_start": "tool_call_end",
-    "llm_request": "llm_response",
-    "approval_requested": "approval_decided",
-}
-END_START: Dict[str, str] = {v: k for k, v in START_END.items()}
-
-_SPAN_KIND = {
-    "session_start": "session",
-    "workflow_start": "workflow",
-    "task_start": "task",
-    "step_start": "step",
-    "agent_start": "agent",
-    "tool_call_start": "tool",
-    "llm_request": "llm",
-    "approval_requested": "approval",
-}
-
-
-# ── Location ──────────────────────────────────────────────────────────
-
-
-def traces_dir() -> Path:
-    """Resolve the traces directory.
-
-    Precedence: ``$PRAISONAI_TRACES_DIR`` > ``$PRAISON_HOME/traces`` > ``~/.praison/traces``.
-    Never creates the directory (this module is read-only).
-    """
-    override = os.environ.get("PRAISONAI_TRACES_DIR")
-    if override:
-        return Path(override).expanduser()
-    home = os.environ.get("PRAISON_HOME")
-    base = Path(home).expanduser() if home else Path.home() / ".praison"
-    return base / "traces"
-
-
-def is_valid_run_id(run_id: Any) -> bool:
-    """True when *run_id* is a single safe path segment."""
-    return (
-        isinstance(run_id, str)
-        and 0 < len(run_id) <= 200
-        and run_id not in (".", "..")
-        and bool(RUN_ID_RE.match(run_id))
-    )
-
-
-def run_path(run_id: str, directory: Optional[Path] = None) -> Optional[Path]:
-    """Return the JSONL path for *run_id*, or ``None`` when the id is unsafe.
-
-    The resolved path is additionally checked to sit directly inside the
-    traces directory, so a symlinked or odd id can never escape it.
-    """
-    if not is_valid_run_id(run_id):
-        return None
-    base = directory or traces_dir()
-    candidate = base / f"{run_id}.jsonl"
-    try:
-        if candidate.resolve().parent != base.resolve():
-            return None
-    except OSError:
-        return None
-    return candidate
-
-
-def list_run_files(directory: Optional[Path] = None) -> List[Path]:
-    """All ``*.jsonl`` files with a valid id, newest (mtime) first."""
-    base = directory or traces_dir()
-    if not base.is_dir():
-        return []
-    items: List[Tuple[float, Path]] = []
-    for p in base.iterdir():
-        if p.suffix != ".jsonl" or not is_valid_run_id(p.stem):
-            continue
-        try:
-            st = p.stat()
-        except OSError:
-            continue
-        if p.is_file():
-            items.append((st.st_mtime, p))
-    items.sort(key=lambda it: (it[0], it[1].name), reverse=True)
-    return [p for _, p in items]
-
-
-# ── Reading ───────────────────────────────────────────────────────────
-
-
-def _parse_line(raw: bytes) -> Optional[Dict[str, Any]]:
-    raw = raw.strip()
-    if not raw:
-        return None
-    try:
-        obj = json.loads(raw.decode("utf-8"))
-    except (UnicodeDecodeError, ValueError):
-        return None
-    return obj if isinstance(obj, dict) else None
-
-
-class TailReader:
-    """Incrementally read complete JSON lines from a growing file.
-
-    Keeps a byte offset; each :meth:`poll` returns only events whose line is
-    complete.  A trailing fragment without a newline is consumed only when it
-    already parses as a JSON object (a proper prefix of a JSON object never
-    does), so a half-written line is never surfaced.  If the file shrinks
-    (the writer truncates on restart), reading restarts from the top.
-    """
-
-    def __init__(self, path: Path) -> None:
-        self.path = Path(path)
-        self.offset = 0
-
-    def poll(self) -> List[Dict[str, Any]]:
-        try:
-            size = self.path.stat().st_size
-        except OSError:
-            return []
-        if size < self.offset:
-            self.offset = 0
-        if size == self.offset:
-            return []
-        try:
-            with open(self.path, "rb") as fh:
-                fh.seek(self.offset)
-                chunk = fh.read(size - self.offset)
-        except OSError:
-            return []
-        events: List[Dict[str, Any]] = []
-        consumed = 0
-        start = 0
-        while True:
-            nl = chunk.find(b"\n", start)
-            if nl < 0:
-                break
-            ev = _parse_line(chunk[start:nl])
-            if ev is not None:
-                events.append(ev)
-            start = nl + 1
-            consumed = start
-        tail = chunk[start:]
-        if tail.strip():
-            ev = _parse_line(tail)
-            if ev is not None:  # complete object, newline not written yet
-                events.append(ev)
-                consumed = len(chunk)
-        self.offset += consumed
-        return events
-
-
-_CACHE_LOCK = threading.Lock()
-_EVENT_CACHE: Dict[str, Tuple[Tuple[int, int], List[Dict[str, Any]]]] = {}
-_SUMMARY_CACHE: Dict[str, Tuple[Tuple[int, int, int], Dict[str, Any]]] = {}
-_EVENT_CACHE_MAX = 8
-_SUMMARY_CACHE_MAX = 512
-
-
-def _sig(path: Path) -> Optional[Tuple[int, int]]:
-    try:
-        st = path.stat()
-    except OSError:
-        return None
-    return (st.st_mtime_ns, st.st_size)
-
-
-def _seq(ev: Dict[str, Any], default: int = -1) -> int:
-    s = ev.get("sequence_num")
-    return s if isinstance(s, int) and not isinstance(s, bool) else default
-
-
-def read_events(path: Path, after_seq: Optional[int] = None) -> List[Dict[str, Any]]:
-    """All complete events in *path* (append order), optionally ``sequence_num > after_seq``."""
-    path = Path(path)
-    sig = _sig(path)
-    if sig is None:
-        return []
-    key = str(path)
-    with _CACHE_LOCK:
-        hit = _EVENT_CACHE.get(key)
-    if hit and hit[0] == sig:
-        events = hit[1]
-    else:
-        events = TailReader(path).poll()
-        with _CACHE_LOCK:
-            _EVENT_CACHE.pop(key, None)
-            _EVENT_CACHE[key] = (sig, events)
-            while len(_EVENT_CACHE) > _EVENT_CACHE_MAX:
-                _EVENT_CACHE.pop(next(iter(_EVENT_CACHE)))
-    if after_seq is None:
-        return list(events)
-    return [ev for ev in events if _seq(ev) > after_seq]
-
-
-# ── Interpretation ────────────────────────────────────────────────────
-
-
-class EndTracker:
-    """Decide when a run has finished, feeding events one at a time.
-
-    The outermost scope is the first ``session_start`` or, failing that, the
-    first top-level ``workflow_start``.  The run has ended once that scope's
-    end event arrives (``session_end`` always ends it).
-    """
-
-    def __init__(self) -> None:
-        self.outer: Optional[Tuple[str, int]] = None
-        self.first_workflow: Optional[int] = None
-        self.ended = False
-        self.status: Optional[str] = None
-        self.ended_at: Optional[float] = None
-
-    def feed(self, ev: Dict[str, Any]) -> None:
-        et = ev.get("event_type")
-        seq = _seq(ev)
-        if et == "session_start" and self.outer is None:
-            self.outer = ("session", seq)
-        elif et == "workflow_start":
-            if self.first_workflow is None:
-                self.first_workflow = seq
-            if self.outer is None and ev.get("parent_seq") is None:
-                self.outer = ("workflow", seq)
-        elif et == "workflow_end":
-            data = ev.get("data") or {}
-            ps = ev.get("parent_seq")
-            if ps is None or ps == self.first_workflow:
-                if isinstance(data, dict) and data.get("status"):
-                    self.status = str(data["status"])
-            if self.outer is None or (self.outer[0] == "workflow" and ps in (None, self.outer[1])):
-                self._end(ev)
-        elif et == "session_end":
-            self._end(ev)
-
-    def _end(self, ev: Dict[str, Any]) -> None:
-        self.ended = True
-        ts = ev.get("timestamp")
-        if isinstance(ts, (int, float)):
-            self.ended_at = float(ts)
-
-
-def find_graph(events: Iterable[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
-    """The graph from the first ``workflow_start`` carrying one, else ``None``."""
-    for ev in events:
-        if ev.get("event_type") == "workflow_start":
-            data = ev.get("data")
-            if isinstance(data, dict) and isinstance(data.get("graph"), dict):
-                return data["graph"]
-    return None
-
-
-def _num(v: Any) -> float:
-    return float(v) if isinstance(v, (int, float)) and not isinstance(v, bool) else 0.0
-
-
-def summarize_run(path: Path, now: Optional[float] = None) -> Optional[Dict[str, Any]]:
-    """Run-picker row for one trace file (cached on mtime/size)."""
-    path = Path(path)
-    try:
-        st = path.stat()
-    except OSError:
-        return None
-    now = time.time() if now is None else now
-    sig = (st.st_mtime_ns, st.st_size, int(now - st.st_mtime < LIVE_WINDOW_S))
-    key = str(path)
-    with _CACHE_LOCK:
-        hit = _SUMMARY_CACHE.get(key)
-    if hit and hit[0] == sig:
-        return dict(hit[1])
-
-    events = read_events(path)
-    tracker = EndTracker()
-    agents: List[str] = []
-    cost = 0.0
-    session_id = None
-    event_run_id = None
-    started_at = None
-    kind, name, process = "session", None, None
-    schema = None
-    for ev in events:
-        tracker.feed(ev)
-        if session_id is None and ev.get("session_id"):
-            session_id = ev.get("session_id")
-        if event_run_id is None and ev.get("run_id"):
-            event_run_id = ev.get("run_id")
-        if schema is None and ev.get("schema_version"):
-            schema = str(ev.get("schema_version"))
-        ts = ev.get("timestamp")
-        if started_at is None and isinstance(ts, (int, float)):
-            started_at = float(ts)
-        agent = ev.get("agent_name")
-        if isinstance(agent, str) and agent and agent not in agents:
-            agents.append(agent)
-        cost += _num(ev.get("cost_usd"))
-        if ev.get("event_type") == "workflow_start" and name is None:
-            data = ev.get("data") if isinstance(ev.get("data"), dict) else {}
-            kind = str(data.get("kind") or "workflow")
-            name = data.get("name")
-            process = data.get("process")
-    live = (not tracker.ended) and (now - st.st_mtime) < LIVE_WINDOW_S
-    if tracker.ended:
-        status = tracker.status or "completed"
-    else:
-        status = "running" if live else "incomplete"
-    summary: Dict[str, Any] = {
-        "run_id": path.stem,
-        "session_id": session_id,
-        "path": str(path),
-        "started_at": started_at,
-        "status": status,
-        "kind": kind,
-        "name": name or (agents[0] if agents else path.stem),
-        "agents": agents,
-        "events": len(events),
-        "cost_usd": round(cost, 6),
-        "live": live,
-        "schema_version": schema,
-    }
-    if tracker.ended_at is not None:
-        summary["ended_at"] = tracker.ended_at
-    if process:
-        summary["process"] = process
-    if event_run_id and event_run_id != path.stem:
-        summary["event_run_id"] = event_run_id
-    with _CACHE_LOCK:
-        _SUMMARY_CACHE[key] = (sig, summary)
-        while len(_SUMMARY_CACHE) > _SUMMARY_CACHE_MAX:
-            _SUMMARY_CACHE.pop(next(iter(_SUMMARY_CACHE)))
-    return dict(summary)
-
-
-def _span_name(ev: Dict[str, Any]) -> str:
-    et = ev.get("event_type")
-    data = ev.get("data") if isinstance(ev.get("data"), dict) else {}
-    agent = ev.get("agent_name") or ""
-    if et == "tool_call_start":
-        return str(data.get("tool_name") or "tool")
-    if et == "llm_request":
-        model = data.get("model")
-        return f"llm {model}" if model else "llm"
-    if et == "approval_requested":
-        return f"approval {data.get('tool') or ''}".strip()
-    if et in ("task_start", "step_start", "workflow_start"):
-        return str(data.get("name") or ev.get("node_id") or et.split("_")[0])
-    if et == "agent_start":
-        return agent or "agent"
-    return "session"
-
-
-def _match_key(ev: Dict[str, Any]) -> Tuple[Any, ...]:
-    """Identity used to pair a start with its end when ``parent_seq`` is absent."""
-    et = ev.get("event_type")
-    data = ev.get("data") if isinstance(ev.get("data"), dict) else {}
-    base = END_START.get(et, et)
-    extra: Any = None
-    if base == "tool_call_start":
-        extra = data.get("tool_name")
-    elif base == "approval_requested":
-        extra = data.get("approval_id")
-    elif base in ("task_start", "step_start"):
-        extra = ev.get("node_id") or data.get("name")
-    agent = ev.get("agent_name") or ""
-    if base in ("approval_requested", "session_start", "workflow_start"):
-        agent = ""  # decisions/ends are often emitted by a different emitter name
-    return (base, agent, ev.get("branch_id"), extra)
-
-
-def build_spans(events: List[Dict[str, Any]], trace_id: str) -> List[Dict[str, Any]]:
-    """Spans from start/end pairs.
-
-    Schema 1.1: an end event's ``parent_seq`` names its start; a start's
-    ``parent_seq`` names the enclosing span.  Schema 1.0 (no ``parent_seq``):
-    ends pair with the oldest open start of the same kind/agent/tool, and the
-    parent is the innermost span open when the start was seen (sequence order).
-    ``llm_response`` is a point event whose ``parent_seq`` is its enclosing
-    scope, so LLM spans always pair by order.
-    """
-    ordered = sorted(enumerate(events), key=lambda it: (_seq(it[1], it[0]), it[0]))
-    spans: Dict[int, Dict[str, Any]] = {}
-    start_type: Dict[int, str] = {}
-    start_key: Dict[int, Tuple[Any, ...]] = {}
-    open_by_key: Dict[Tuple[Any, ...], List[int]] = {}
-    stack: List[int] = []
-    order: List[int] = []
-
-    for idx, ev in ordered:
-        et = ev.get("event_type")
-        seq = _seq(ev, idx)
-        ts = _num(ev.get("timestamp"))
-        if et in START_END:
-            parent = ev.get("parent_seq")
-            if not (isinstance(parent, int) and parent in spans):
-                parent = next((s for s in reversed(stack) if spans[s]["status"] == "open"), None)
-            data = ev.get("data") if isinstance(ev.get("data"), dict) else {}
-            span = {
-                "id": f"{trace_id}:{seq}",
-                "trace_id": trace_id,
-                "parent_span_id": f"{trace_id}:{parent}" if parent is not None else None,
-                "agent_id": ev.get("agent_name") or "",
-                "name": _span_name(ev),
-                "kind": _SPAN_KIND[et],
-                "status": "open",
-                "start_time": ts,
-                "end_time": None,
-                "duration_ms": None,
-                "timestamp": ts,
-                "attributes": {
-                    k: v
-                    for k, v in {
-                        "node_id": ev.get("node_id"),
-                        "branch_id": ev.get("branch_id"),
-                        "start_seq": seq,
-                        "input": data.get("tool_args") if et == "tool_call_start" else None,
-                    }.items()
-                    if v is not None
-                },
-                "events": [],
-            }
-            spans[seq] = span
-            start_type[seq] = et
-            start_key[seq] = _match_key(ev)
-            order.append(seq)
-            stack.append(seq)
-            open_by_key.setdefault(start_key[seq], []).append(seq)
-            continue
-        if et not in END_START:
-            continue
-        start_seq = None
-        ps = ev.get("parent_seq")
-        key = _match_key(ev)
-        if (
-            et != "llm_response"
-            and isinstance(ps, int)
-            and ps in spans
-            and spans[ps]["status"] == "open"
-            and START_END.get(start_type[ps]) == et
-        ):
-            start_seq = ps
-        else:
-            queue = open_by_key.get(key) or []
-            while queue and spans[queue[0]]["status"] != "open":
-                queue.pop(0)
-            if queue:
-                start_seq = queue[0]
-        if start_seq is None:
-            continue
-        q = open_by_key.get(start_key[start_seq])
-        if q and start_seq in q:
-            q.remove(start_seq)
-        span = spans[start_seq]
-        data = ev.get("data") if isinstance(ev.get("data"), dict) else {}
-        dur = data.get("duration_ms")
-        span["end_time"] = ts
-        span["duration_ms"] = (
-            float(dur) if isinstance(dur, (int, float)) and not isinstance(dur, bool)
-            else round(max(0.0, ts - span["start_time"]) * 1000, 3)
-        )
-        failed = bool(data.get("error")) or data.get("status") == "failed" or data.get("approved") is False
-        span["status"] = "error" if failed else "ok"
-        attrs = span["attributes"]
-        for k in ("cost_usd", "prompt_tokens", "completion_tokens"):
-            v = ev.get(k)
-            if isinstance(v, (int, float)) and not isinstance(v, bool) and v:
-                attrs[k] = v
-        if data.get("error"):
-            attrs["error"] = data.get("error")
-        if start_seq in stack:
-            stack.remove(start_seq)
-
-    return [spans[s] for s in order]
-
@@ -13,7 +13,6 @@ from __future__ import annotations

 import asyncio
 import logging
-import threading
 import time
 import uuid
 from abc import ABC, abstractmethod
@@ -67,13 +66,7 @@ class ApprovalProtocol(ABC):
    @abstractmethod
    def approve(
        self, approval_id: str, reason: str = "", approver: str = "user", always: bool = False
-    ) -> Optional[Dict[str, Any]]:
-        """Approve a pending request.
-
-        Implementations may also accept ``modified_args: dict`` (replacement
-        tool arguments); the HTTP handler only passes it when the client sent it.
-        """
-        ...
+    ) -> Optional[Dict[str, Any]]: ...

    @abstractmethod
    def deny(
@@ -93,66 +86,6 @@ class ApprovalProtocol(ABC):
        return {"status": "ok", "provider": self.__class__.__name__}


-# ── Decision waiter ──────────────────────────────────────────────────
-
-
-class _DecisionWaiter:
-    """One pending decision that both threads and coroutines can wait on.
-
-    ``set()`` may be called from any thread (normally the server's event loop
-    handling ``POST /api/approvals/{id}/approve``); sync waiters block on a
-    ``threading.Event`` and async waiters get their future resolved on their
-    own loop via ``call_soon_threadsafe``, so neither blocks the other.
-    """
-
-    def __init__(self) -> None:
-        self._event = threading.Event()
-        self._lock = threading.Lock()
-        self._result: Optional[Dict[str, Any]] = None
-        self._futures: List[tuple] = []
-
-    @property
-    def done(self) -> bool:
-        return self._event.is_set()
-
-    def set(self, entry: Dict[str, Any]) -> None:
-        with self._lock:
-            if self._event.is_set():
-                return
-            self._result = entry
-            self._event.set()
-            futures, self._futures = self._futures, []
-        for loop, fut in futures:
-            try:
-                loop.call_soon_threadsafe(_resolve_future, fut, entry)
-            except RuntimeError:  # loop already closed
-                pass
-
-    def wait(self, timeout: Optional[float]) -> Optional[Dict[str, Any]]:
-        return self._result if self._event.wait(timeout) else None
-
-    async def wait_async(self, timeout: Optional[float]) -> Optional[Dict[str, Any]]:
-        loop = asyncio.get_running_loop()
-        fut = loop.create_future()
-        with self._lock:
-            if self._event.is_set():
-                return self._result
-            self._futures.append((loop, fut))
-        try:
-            return await asyncio.wait_for(fut, timeout)
-        except asyncio.TimeoutError:
-            return None
-        finally:
-            with self._lock:
-                if (loop, fut) in self._futures:
-                    self._futures.remove((loop, fut))
-
-
-def _resolve_future(fut: "asyncio.Future", value: Any) -> None:
-    if not fut.done():
-        fut.set_result(value)
-
-
 # ── Simple Approval Manager ──────────────────────────────────────────


@@ -162,8 +95,6 @@ class SimpleApprovalManager(ApprovalProtocol):
    def __init__(self) -> None:
        self._pending: Dict[str, Dict[str, Any]] = {}
        self._history: deque = deque(maxlen=500)
-        self._lock = threading.RLock()
-        self._waiters: Dict[str, _DecisionWaiter] = {}
        self._policies: Dict[str, Any] = {
            "auto_approve_tools": [],
            "always_deny_tools": [],
@@ -205,67 +136,44 @@ class SimpleApprovalManager(ApprovalProtocol):
            entry.get("agent_name", ""),
            entry.get("risk_level", "medium"),
        )
-        with self._lock:
-            if auto:
-                entry["status"] = auto
-                entry["resolved_at"] = time.time()
-                entry["approver"] = "auto-policy"
-                entry["reason"] = f"Auto-{auto} by policy"
-                self._history.appendleft(entry)
-            else:
-                self._pending[approval_id] = entry
-                self._waiters.setdefault(approval_id, _DecisionWaiter())
+        if auto:
+            entry["status"] = auto
+            entry["resolved_at"] = time.time()
+            entry["approver"] = "auto-policy"
+            entry["reason"] = f"Auto-{auto} by policy"
+            self._history.appendleft(entry)
+        else:
+            self._pending[approval_id] = entry
        return entry

-    def waiter(self, approval_id: str) -> Optional[_DecisionWaiter]:
-        """The waiter for a pending request (``None`` once it is resolved)."""
-        with self._lock:
-            return self._waiters.get(approval_id)
-
-    def _signal(self, approval_id: str, entry: Dict[str, Any]) -> None:
-        waiter = self._waiters.pop(approval_id, None)
-        if waiter is not None:
-            waiter.set(entry)
-
    def approve(
-        self,
-        approval_id: str,
-        reason: str = "",
-        approver: str = "user",
-        always: bool = False,
-        modified_args: Optional[Dict[str, Any]] = None,
+        self, approval_id: str, reason: str = "", approver: str = "user", always: bool = False
    ) -> Optional[Dict[str, Any]]:
-        with self._lock:
-            if approval_id not in self._pending:
-                return None
-            entry = self._pending.pop(approval_id)
-            entry["status"] = "approved"
-            entry["reason"] = reason
-            entry["resolved_at"] = time.time()
-            entry["approver"] = approver
-            if modified_args is not None:
-                entry["modified_args"] = dict(modified_args)
-            if always and entry["tool_name"] not in self._policies["auto_approve_tools"]:
-                self._policies["auto_approve_tools"].append(entry["tool_name"])
-            self._history.appendleft(entry)
-            self._signal(approval_id, entry)
+        if approval_id not in self._pending:
+            return None
+        entry = self._pending.pop(approval_id)
+        entry["status"] = "approved"
+        entry["reason"] = reason
+        entry["resolved_at"] = time.time()
+        entry["approver"] = approver
+        if always and entry["tool_name"] not in self._policies["auto_approve_tools"]:
+            self._policies["auto_approve_tools"].append(entry["tool_name"])
+        self._history.appendleft(entry)
        return entry

    def deny(
        self, approval_id: str, reason: str = "", approver: str = "user", always: bool = False
    ) -> Optional[Dict[str, Any]]:
-        with self._lock:
-            if approval_id not in self._pending:
-                return None
-            entry = self._pending.pop(approval_id)
-            entry["status"] = "denied"
-            entry["reason"] = reason
-            entry["resolved_at"] = time.time()
-            entry["approver"] = approver
-            if always and entry["tool_name"] not in self._policies["always_deny_tools"]:
-                self._policies["always_deny_tools"].append(entry["tool_name"])
-            self._history.appendleft(entry)
-            self._signal(approval_id, entry)
+        if approval_id not in self._pending:
+            return None
+        entry = self._pending.pop(approval_id)
+        entry["status"] = "denied"
+        entry["reason"] = reason
+        entry["resolved_at"] = time.time()
+        entry["approver"] = approver
+        if always and entry["tool_name"] not in self._policies["always_deny_tools"]:
+            self._policies["always_deny_tools"].append(entry["tool_name"])
+        self._history.appendleft(entry)
        return entry

    def get(self, approval_id: str) -> Optional[Dict[str, Any]]:
@@ -329,14 +237,9 @@ class SDKApprovalManager(ApprovalProtocol):
        return result

    def approve(
-        self,
-        approval_id: str,
-        reason: str = "",
-        approver: str = "user",
-        always: bool = False,
-        modified_args: Optional[Dict[str, Any]] = None,
+        self, approval_id: str, reason: str = "", approver: str = "user", always: bool = False
    ) -> Optional[Dict[str, Any]]:
-        entry = self._simple.approve(approval_id, reason, approver, always, modified_args)
+        entry = self._simple.approve(approval_id, reason, approver, always)
        if entry and always and entry.get("tool_name"):
            self._registry.add_requirement(entry["tool_name"], entry.get("risk_level", "high"))
        return entry
@@ -370,121 +273,31 @@ class SDKApprovalManager(ApprovalProtocol):


 class _UIStoreBackend:
-    """Routes agent approval requests into the UI store and waits for a human.
+    """Routes agent approval requests into the UI SimpleApprovalManager."""

-    Each request becomes a pending entry keyed by ``request.approval_id`` and
-    the caller blocks (sync: on a ``threading.Event``; async: on a future of
-    its own loop) until ``POST /api/approvals/{id}/approve|deny`` resolves it.
-    No answer within the timeout is a denial (fail-closed) and the entry is
-    resolved as ``denied`` with ``approver="timeout"`` so the queue stays honest.
-    """
-
-    def __init__(self, store: SimpleApprovalManager, timeout: Optional[float] = None) -> None:
+    def __init__(self, store: SimpleApprovalManager) -> None:
        self._store = store
-        self._timeout = timeout

-    def _effective_timeout(self, timeout: Optional[float]) -> float:
-        if timeout is not None:
-            return float(timeout)
-        if self._timeout is not None:
-            return float(self._timeout)
-        try:
-            from praisonaiagents.approval import get_approval_registry
-
-            return float(getattr(get_approval_registry(), "timeout", 300.0))
-        except Exception:
-            return 300.0
-
-    def _submit(self, request) -> Dict[str, Any]:
-        entry: Dict[str, Any] = {
-            "tool_name": request.tool_name,
-            "agent_name": getattr(request, "agent_name", "") or "",
-            "risk_level": request.risk_level or "medium",
-            "arguments": request.arguments or {},
-        }
-        approval_id = getattr(request, "approval_id", None)
-        if approval_id:
-            entry["id"] = str(approval_id)
-        session_id = getattr(request, "session_id", None)
-        if session_id:
-            entry["session_id"] = session_id
-        return self._store.request_approval(entry)
-
-    @staticmethod
-    def _decision(entry: Optional[Dict[str, Any]]) -> Any:
+    def request_approval_sync(self, request) -> Any:
        from praisonaiagents.approval.protocols import ApprovalDecision

-        if entry is None:
-            return ApprovalDecision(
-                approved=False, reason="Timed out waiting for UI approval", approver="timeout"
-            )
-        if entry.get("status") == "approved":
-            return ApprovalDecision(
-                approved=True,
-                reason=entry.get("reason", ""),
-                modified_args=dict(entry.get("modified_args") or {}),
-                approver=entry.get("approver"),
-            )
-        return ApprovalDecision(
-            approved=False,
-            reason=entry.get("reason") or "denied",
-            approver=entry.get("approver"),
+        entry = self._store.request_approval(
+            {
+                "tool_name": request.tool_name,
+                "agent_name": getattr(request, "agent_name", "") or "",
+                "risk_level": request.risk_level or "medium",
+                "arguments": request.arguments or {},
+            }
        )
-
-    def _expire(
-        self,
-        approval_id: str,
-        reason: str = "Timed out waiting for UI approval",
-        approver: str = "timeout",
-    ) -> Optional[Dict[str, Any]]:
-        """Deny a request nobody answered; return the entry if a human won the race."""
-        denied = self._store.deny(approval_id, reason=reason, approver=approver)
-        if denied is not None:
-            return None
-        return self._store.get(approval_id)
-
-    def request_approval_sync(self, request, timeout: Optional[float] = None) -> Any:
-        from praisonaiagents.approval.protocols import ApprovalDecision
-
-        entry = self._submit(request)
-        if entry.get("status") != "pending":
-            return self._decision(entry)
-        approval_id = entry["id"]
-        try:
-            asyncio.get_running_loop()
-        except RuntimeError:
-            pass
-        else:
-            # Blocking here would freeze this thread's event loop (and with it,
-            # possibly the very server that has to deliver the answer).
-            reason = "UI approval cannot block an event-loop thread; use the async approval path"
-            self._expire(approval_id, reason=reason, approver="ui")
-            return ApprovalDecision(approved=False, reason=reason, approver="ui")
-        waiter = self._store.waiter(approval_id)
-        result = waiter.wait(self._effective_timeout(timeout)) if waiter else self._store.get(approval_id)
-        if result is None:
-            result = self._expire(approval_id)
-        return self._decision(result)
+        status = entry.get("status", "pending")
+        if status == "approved":
+            return ApprovalDecision(approved=True, reason=entry.get("reason", ""))
+        if status == "denied":
+            return ApprovalDecision(approved=False, reason=entry.get("reason", "denied"))
+        return ApprovalDecision(approved=False, reason="Awaiting UI approval")

    async def request_approval(self, request) -> Any:
-        entry = self._submit(request)
-        if entry.get("status") != "pending":
-            return self._decision(entry)
-        approval_id = entry["id"]
-        waiter = self._store.waiter(approval_id)
-        try:
-            result = (
-                await waiter.wait_async(self._effective_timeout(None))
-                if waiter
-                else self._store.get(approval_id)
-            )
-        except asyncio.CancelledError:
-            # The registry's own wait_for timed out (or the turn was cancelled).
-            self._expire(approval_id)
-            raise
-        if result is None:
-            result = self._expire(approval_id)
-        return self._decision(result)
+        return self.request_approval_sync(request)


 # ── Manager singleton ────────────────────────────────────────────────
@@ -636,15 +449,11 @@ class ApprovalsFeature(BaseFeatureProtocol):
        mgr = get_approval_manager()
        approval_id = request.path_params["approval_id"]
        body = await request.json() if request.headers.get("content-length") else {}
-        modified_args = body.get("modified_args")
-        if modified_args is not None and not isinstance(modified_args, dict):
-            return JSONResponse({"error": "modified_args must be an object"}, status_code=400)
        entry = mgr.approve(
            approval_id,
            reason=body.get("reason", ""),
            approver=body.get("approver", "user"),
            always=body.get("always", False),
-            **({"modified_args": modified_args} if modified_args is not None else {}),
        )
        if entry is None:
            return JSONResponse({"error": "Approval not found"}, status_code=404)
@@ -141,6 +141,81 @@ def set_execution_manager(manager: CodeExecutionProtocol) -> None:
    _execution_manager = manager


+# ── Approval gate ────────────────────────────────────────────────────
+
+
+async def _approval_gate(
+    code: str, language: str, approval_id: Optional[str]
+) -> Optional[JSONResponse]:
+    """Return None if execution is approved, else the response to send.
+
+    Each run is recorded via the approvals feature as a ``critical``
+    ``execute_code`` request. A pending request returns 202 with its id;
+    re-submit with ``approval_id`` once approved (single use, bound to
+    the exact code/language).
+    """
+    from .approvals import _notify_subscribers, get_approval_manager
+
+    approvals = get_approval_manager()
+    arguments = {"code": code, "language": language}
+
+    if approval_id:
+        entry = approvals.get(approval_id)
+        if (
+            entry
+            and entry.get("tool_name") == "execute_code"
+            and entry.get("risk_level") == "critical"
+            and entry.get("status") == "approved"
+            and entry.get("arguments") == arguments
+            and not entry.get("consumed")
+        ):
+            entry["consumed"] = True
+            return None
+        return JSONResponse(
+            {
+                "status": "error",
+                "language": language,
+                "error": "Approval not found, not approved, already used, "
+                "or does not match this code",
+            },
+            status_code=403,
+        )
+
+    entry = approvals.request_approval(
+        {
+            "tool_name": "execute_code",
+            "arguments": arguments,
+            "risk_level": "critical",
+            "description": f"Execute {language} code ({len(code)} chars)",
+        }
+    )
+    status = entry.get("status")
+    await _notify_subscribers("new" if status == "pending" else "resolved", entry)
+    if status == "approved":
+        entry["consumed"] = True
+        return None
+    if status == "denied":
+        return JSONResponse(
+            {
+                "status": "error",
+                "language": language,
+                "approval_id": entry["id"],
+                "error": entry.get("reason") or "Code execution denied",
+            },
+            status_code=403,
+        )
+    return JSONResponse(
+        {
+            "status": "pending_approval",
+            "language": language,
+            "approval_id": entry["id"],
+            "output": f"Awaiting approval {entry['id']}. Approve it, then re-run "
+            "with this approval_id.",
+        },
+        status_code=202,
+    )
+
+
 # ── Feature class ────────────────────────────────────────────────────


@@ -173,9 +248,20 @@ class CodeExecutionFeature(BaseFeatureProtocol):
    async def _execute(self, request: Request) -> JSONResponse:
        mgr = get_execution_manager()
        body = await request.json()
+        code = body.get("code", "")
+        language = body.get("language", "python")
+        allowed = {lang["id"] for lang in mgr.list_languages()}
+        if language not in allowed:
+            return JSONResponse(
+                {"status": "error", "error": f"Language '{language}' not allowed"},
+                status_code=400,
+            )
+        blocked = await _approval_gate(code, language, body.get("approval_id"))
+        if blocked is not None:
+            return blocked
        result = mgr.execute(
-            code=body.get("code", ""),
-            language=body.get("language", "python"),
+            code=code,
+            language=language,
            timeout=body.get("timeout", 30),
        )
        status = 200 if result.get("status") != "error" else 400
@@ -1,441 +0,0 @@
-"""PraisonAI Replay feature: read-only access to recorded agent runs.
-
-Routes (contract v1, section 5):
-
-* ``GET /api/replay/runs``                       run picker rows, newest first
-* ``GET /api/replay/runs/{run_id}/events``       ``{events, graph, run}``; ``?after_seq=N``;
-  ``?wait=1`` answers ``{events: [], graph: null, run: null}`` (not 404) for a run
-  that has not written its first event yet
-* ``GET /api/replay/runs/{run_id}/stream``       SSE tail of the JSONL file
-
-The trace directory is ``$PRAISONAI_TRACES_DIR``, else ``$PRAISON_HOME/traces``,
-else ``~/.praison/traces``.  Run ids must match ``^[A-Za-z0-9._-]+$``.
-
-The browser side lives in ``templates/frontend/plugins/views/replay-core.js``
-(pure functions) and ``replay.js`` (DOM/SVG).  :func:`standalone_html` inlines
-both into one self-contained page for ``praisonai replay export --format html``.
-
-:func:`create_replay_app` is the same view as a small ASGI app (no dashboard) to
-mount inside your own app, optionally with a Run box that starts runs::
-
-    app.mount("/replay", create_replay_app(run=my_runner))
-"""
-
-from __future__ import annotations
-
-import asyncio
-import html
-import inspect
-import json
-import logging
-import threading
-import time
-import uuid
-from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional
-from urllib.parse import quote
-
-from starlette.concurrency import run_in_threadpool
-from starlette.requests import Request
-from starlette.responses import FileResponse, HTMLResponse, JSONResponse, StreamingResponse
-from starlette.routing import Route
-
-from . import _trace_jsonl as tj
-from ._base import BaseFeatureProtocol
-
-logger = logging.getLogger(__name__)
-
-#: Page id of the dashboard view; open ``/replay?run=<id>`` (or ``/#/replay?run=<id>``).
-REPLAY_PAGE_ID = "replay"
-
-#: Replay's own mark (three lanes and a cursor), used as the page's ``icon_svg``.
-REPLAY_MARK_SVG = (
-    '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16" width="1em" height="1em" '
-    'aria-hidden="true" focusable="false" '
-    'style="display:inline-block;vertical-align:-0.125em">'
-    '<rect x="1" y="3" width="8" height="2.2" rx="1.1" fill="currentColor"/>'
-    '<rect x="3" y="7" width="10" height="2.2" rx="1.1" fill="currentColor"/>'
-    '<rect x="1" y="11" width="6" height="2.2" rx="1.1" fill="currentColor"/>'
-    '<rect x="11.2" y="1" width="1.6" height="14" rx="0.8" fill="currentColor" opacity="0.55"/>'
-    "</svg>"
-)
-
-#: Pages a replay-only app should whitelist (Replay first, then its companions).
-REPLAY_PAGES = ("replay", "approvals", "traces")
-
-_VIEWS_DIR = Path(__file__).resolve().parent.parent / "templates" / "frontend" / "plugins" / "views"
-#: Stable on-disk locations of the renderer (also served at /plugins/views/...).
-REPLAY_CORE_JS = _VIEWS_DIR / "replay-core.js"
-REPLAY_VIEW_JS = _VIEWS_DIR / "replay.js"
-
-
-def configure_replay_app() -> None:
-    """Configure aiui as a Replay-first dashboard (call before the server starts).
-
-    Equivalent to ``aiui.set_style("dashboard")`` plus
-    ``aiui.set_pages(["replay", "approvals", "traces"])``; Replay sorts first,
-    so ``/`` lands on it.  Used by ``praisonaiui/replay_app.py``.
-    """
-    from praisonaiui.server import set_pages, set_style
-
-    set_style("dashboard")
-    set_pages(list(REPLAY_PAGES))
-
-
-def _json_for_script(obj: Any) -> str:
-    """JSON that is safe inside an inline ``<script>`` element."""
-    text = json.dumps(obj, default=str, separators=(",", ":"))
-    return (
-        text.replace("<", "\\u003c")
-        .replace(">", "\\u003e")
-        .replace("&", "\\u0026")
-        .replace("\u2028", "\\u2028")
-        .replace("\u2029", "\\u2029")
-    )
-
-
-def standalone_html(
-    events: List[Dict[str, Any]],
-    graph: Optional[Dict[str, Any]] = None,
-    title: str = "PraisonAI Replay",
-) -> str:
-    """One self-contained HTML page (no CDN, no network) rendering *events*.
-
-    Inlines ``replay-core.js`` and ``replay.js`` and sets
-    ``window.__REPLAY_DATA__ = {events, graph}``; the view boots itself.
-    Approval buttons are hidden because there is no server to answer them.
-    """
-    core = REPLAY_CORE_JS.read_text(encoding="utf-8").replace("</script", "<\\/script")
-    view = REPLAY_VIEW_JS.read_text(encoding="utf-8").replace("</script", "<\\/script")
-    if graph is None:
-        graph = tj.find_graph(events)
-    data = _json_for_script({"events": list(events), "graph": graph})
-    safe_title = (
-        str(title).replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
-    )
-    return (
-        "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n"
-        "<meta name=\"viewport\" content=\"width=device-width, initial-scale=1\">\n"
-        f"<title>{safe_title}</title>\n"
-        "<style>body{margin:0;font-family:system-ui,-apple-system,'Segoe UI',sans-serif}</style>\n"
-        "</head>\n<body>\n<main id=\"replay-root\"></main>\n"
-        f"<script>window.__REPLAY_DATA__ = {data};</script>\n"
-        f"<script type=\"module\">\n{core}\n</script>\n"
-        f"<script type=\"module\">\n{view}\n</script>\n"
-        "</body>\n</html>\n"
-    )
-
-
-def _bad_request(msg: str) -> JSONResponse:
-    return JSONResponse({"error": msg}, status_code=400)
-
-
-def _parse_after_seq(request: Request) -> tuple[Optional[int], Optional[JSONResponse]]:
-    """``?after_seq=N``; an SSE reconnect's ``Last-Event-ID`` wins when it is later."""
-    values = []
-    for raw, strict in (
-        (request.query_params.get("after_seq"), True),
-        (request.headers.get("last-event-id"), False),
-    ):
-        if raw in (None, ""):
-            continue
-        try:
-            values.append(int(raw))
-        except (TypeError, ValueError):
-            if strict:
-                return None, _bad_request("after_seq must be an integer")
-    return (max(values) if values else None), None
-
-
-def _resolve(request: Request) -> tuple[Optional[Path], Optional[JSONResponse]]:
-    run_id = request.path_params.get("run_id", "")
-    path = tj.run_path(run_id)
-    if path is None:
-        return None, _bad_request("invalid run id (allowed: A-Z a-z 0-9 . _ -)")
-    if not path.is_file():
-        return None, JSONResponse({"error": "run not found"}, status_code=404)
-    return path, None
-
-
-def _seq_of(ev: Dict[str, Any]) -> Optional[int]:
-    s = ev.get("sequence_num")
-    return s if isinstance(s, int) and not isinstance(s, bool) else None
-
-
-class ReplayFeature(BaseFeatureProtocol):
-    """Recorded-run timeline, map and live tail (PraisonAI Replay)."""
-
-    feature_name = "replay"
-    feature_description = "Replay recorded agent runs (timeline, map, live tail)"
-
-    # Stream timings; instance attributes so tests can shorten them.
-    poll_interval = 0.25
-    ping_interval = 15.0
-    quiet_period = 2.0
-
-    @property
-    def name(self) -> str:
-        return self.feature_name
-
-    @property
-    def description(self) -> str:
-        return self.feature_description
-
-    def routes(self) -> List[Route]:
-        return [
-            Route("/api/replay/runs", self._runs, methods=["GET"]),
-            Route("/api/replay/runs/{run_id}/events", self._events, methods=["GET"]),
-            Route("/api/replay/runs/{run_id}/stream", self._stream, methods=["GET"]),
-        ]
-
-    async def health(self) -> Dict[str, Any]:
-        d = tj.traces_dir()
-        return {
-            "status": "ok",
-            "feature": self.name,
-            "traces_dir": str(d),
-            "runs": len(tj.list_run_files(d)),
-        }
-
-    def cli_commands(self) -> List[Dict[str, Any]]:
-        return [
-            {
-                "name": "replay",
-                "help": "List recorded runs (PraisonAI Replay)",
-                "commands": {"list": {"help": "List recorded runs", "handler": self._cli_list}},
-            }
-        ]
-
-    # ── data ──────────────────────────────────────────────────────────
-
-    @staticmethod
-    def list_runs(limit: int = 200) -> List[Dict[str, Any]]:
-        rows = []
-        now = time.time()
-        for path in tj.list_run_files()[: max(1, limit)]:
-            row = tj.summarize_run(path, now=now)
-            if row is not None:
-                rows.append(row)
-        rows.sort(key=lambda r: (r.get("started_at") or 0.0, r["run_id"]), reverse=True)
-        return rows
-
-    def _cli_list(self) -> str:
-        rows = self.list_runs()
-        if not rows:
-            return f"No recorded runs in {tj.traces_dir()}"
-        lines = [f"Runs ({len(rows)}):"]
-        for r in rows:
-            live = " LIVE" if r.get("live") else ""
-            lines.append(
-                f"  {r['run_id']}  {r.get('name')}  {r['status']}{live}  "
-                f"events={r['events']}  ${r['cost_usd']:.4f}"
-            )
-        return "\n".join(lines)
-
-    # ── handlers ──────────────────────────────────────────────────────
-
-    async def _runs(self, request: Request) -> JSONResponse:
-        try:
-            limit = int(request.query_params.get("limit", "200"))
-        except ValueError:
-            return _bad_request("limit must be an integer")
-        rows = await run_in_threadpool(self.list_runs, limit)
-        return JSONResponse(rows)
-
-    async def _events(self, request: Request) -> JSONResponse:
-        path, err = _resolve(request)
-        if err is not None:
-            if err.status_code == 404 and request.query_params.get("wait") == "1":
-                return JSONResponse({"events": [], "graph": None, "run": None})
-            return err
-        after_seq, err = _parse_after_seq(request)
-        if err is not None:
-            return err
-
-        def load() -> Dict[str, Any]:
-            all_events = tj.read_events(path)
-            events = all_events if after_seq is None else tj.read_events(path, after_seq)
-            return {
-                "events": events,
-                "graph": tj.find_graph(all_events),
-                "run": tj.summarize_run(path),
-            }
-
-        return JSONResponse(await run_in_threadpool(load))
-
-    async def _stream(self, request: Request) -> StreamingResponse:
-        path, err = _resolve(request)
-        if err is not None:
-            return err  # type: ignore[return-value]
-        after_seq, err = _parse_after_seq(request)
-        if err is not None:
-            return err  # type: ignore[return-value]
-
-        poll, ping, quiet = self.poll_interval, self.ping_interval, self.quiet_period
-
-        async def gen():
-            tail = tj.TailReader(path)
-            tracker = tj.EndTracker()
-            last_seq = after_seq
-            loop = asyncio.get_running_loop()
-            last_activity = last_ping = loop.time()
-            yield "retry: 3000\n\n"
-            while True:
-                events = await run_in_threadpool(tail.poll)
-                now = loop.time()
-                if events:
-                    last_activity = now
-                for ev in events:
-                    tracker.feed(ev)
-                    seq = _seq_of(ev)
-                    if last_seq is not None and seq is not None and seq <= last_seq:
-                        continue
-                    if seq is not None:
-                        last_seq = seq
-                    sid = f"id: {seq}\n" if seq is not None else ""
-                    yield f"{sid}event: ctx\ndata: {json.dumps(ev, default=str)}\n\n"
-                idle = now - last_activity
-                if tracker.ended and idle >= quiet:
-                    yield "event: end\ndata: {}\n\n"
-                    return
-                if not path.exists() or idle >= tj.LIVE_WINDOW_S:
-                    yield 'event: end\ndata: {"reason": "stale"}\n\n'
-                    return
-                if now - last_ping >= ping:
-                    last_ping = now
-                    yield "event: ping\ndata: {}\n\n"
-                await asyncio.sleep(poll)
-
-        return StreamingResponse(
-            gen(),
-            media_type="text/event-stream",
-            headers={"Cache-Control": "no-cache", "Connection": "keep-alive", "X-Accel-Buffering": "no"},
-        )
-
-
-# ── embeddable app ─────────────────────────────────────────────────────
-
-#: Longest input the Run box accepts (characters).
-MAX_RUN_INPUT = 20_000
-
-
-def _embed_page(base: str, title: str, cfg: Dict[str, Any]) -> str:
-    """The page at the app's root: the view, mounted with *cfg*, and nothing else."""
-    return (
-        "<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n"
-        "<meta name=\"viewport\" content=\"width=device-width, initial-scale=1\">\n"
-        f"<title>{html.escape(title)}</title>\n"
-        f"<link rel=\"icon\" href=\"data:image/svg+xml,{quote(REPLAY_MARK_SVG.replace('currentColor', '#1A56DB'))}\">\n"
-        "<style>body{margin:0;font-family:system-ui,-apple-system,'Segoe UI',sans-serif}"
-        "#replay-root{padding:12px;box-sizing:border-box;max-width:100%}</style>\n"
-        "</head>\n<body>\n<main id=\"replay-root\"></main>\n"
-        "<script type=\"module\">\n"
-        f"import {{ render }} from {_json_for_script(base + '/replay.js')};\n"
-        f"render(document.getElementById('replay-root'), {_json_for_script(cfg)});\n"
-        "</script>\n</body>\n</html>\n"
-    )
-
-
-def create_replay_app(
-    run: Optional[Callable[[str, str], Any]] = None,
-    *,
-    title: str = "PraisonAI Replay",
-    input: Optional[str] = "",
-    placeholder: str = "",
-):
-    """PraisonAI Replay as a small ASGI app to mount in your own app.
-
-    Serves the view at ``/`` (no dashboard around it), its two scripts, and the
-    ``/api/replay/...`` routes, all relative to where it is mounted::
-
-        from fastapi import FastAPI
-        from praisonaiui.features.replay import create_replay_app
-
-        app = FastAPI()
-        app.mount("/replay", create_replay_app())
-        # <iframe src="/replay/?run=RUN_ID"> shows one run live; /replay/ lists runs
-
-    Args:
-        run: Optional ``run(input, run_id)``. When given, the page shows an
-            input box and a **Run** button; each click calls it in a worker
-            thread with a new ``run_id``, and the page follows that run live.
-            It must record the run under ``run_id`` (``praisonai.replay.app()``
-            does this for an agent, team or flow). One run at a time.
-        title: Page title.
-        input: Text the input box starts with; ``None`` for no input box
-            (just a Run button, e.g. for a YAML file that has its own topic).
-        placeholder: Placeholder text for the input box.
-
-    Traces are read from the same folder as the rest of Replay
-    (``$PRAISONAI_TRACES_DIR`` > ``$PRAISON_HOME/traces`` > ``~/.praison/traces``).
-    Anyone who can reach the app can read the runs (and, with ``run``, start
-    them): keep it on localhost or behind your app's auth.
-    """
-    from starlette.applications import Starlette
-
-    feature = ReplayFeature()
-    busy = threading.Lock()
-
-    async def page(request: Request) -> HTMLResponse:
-        base = str(request.scope.get("root_path", "")).rstrip("/")
-        cfg: Dict[str, Any] = {"base": base, "approve": False}
-        wanted = request.query_params.get("run")
-        if wanted and tj.is_valid_run_id(wanted):
-            cfg["run"] = wanted
-        if run is not None:
-            cfg["runner"] = {"input": input or "", "placeholder": placeholder, "ask": input is not None}
-        return HTMLResponse(_embed_page(base, title, cfg), headers={"Cache-Control": "no-store"})
-
-    def script(path: Path):
-        async def serve(request: Request) -> FileResponse:
-            return FileResponse(path, media_type="text/javascript", headers={"Cache-Control": "no-cache"})
-        return serve
-
-    def _call(text: str, run_id: str) -> None:
-        try:
-            result = run(text, run_id)  # type: ignore[misc]
-            if inspect.isawaitable(result):
-                asyncio.run(result)
-        except Exception:
-            logger.exception("replay run %s failed", run_id)
-        finally:
-            busy.release()
-
-    async def start(request: Request) -> JSONResponse:
-        # JSON only: a cross-site form post cannot set this content type without
-        # a CORS preflight, which this app never answers.
-        if not request.headers.get("content-type", "").lower().startswith("application/json"):
-            return JSONResponse({"error": "send JSON: {\"input\": \"...\"}"}, status_code=415)
-        try:
-            body = await request.json()
-        except ValueError:
-            return _bad_request("body must be JSON")
-        text = body.get("input", "") if isinstance(body, dict) else None
-        if not isinstance(text, str) or len(text) > MAX_RUN_INPUT:
-            return _bad_request(f"input must be a string of at most {MAX_RUN_INPUT} characters")
-        if not busy.acquire(blocking=False):
-            return JSONResponse({"error": "a run is already going; wait for it to finish"}, status_code=409)
-        run_id = f"run-{uuid.uuid4().hex[:12]}"
-        try:
-            threading.Thread(target=_call, args=(text, run_id), name=f"replay-{run_id}", daemon=True).start()
-        except Exception:
-            busy.release()
-            raise
-        # Answer once the trace file exists (usually milliseconds), so the page
-        # can open the run straight away; it waits on its own if this times out.
-        path = tj.run_path(run_id)
-        for _ in range(40):
-            if path is not None and path.is_file():
-                break
-            await asyncio.sleep(0.05)
-        return JSONResponse({"run_id": run_id})
-
-    routes = [
-        Route("/", page, methods=["GET"]),
-        Route("/replay.js", script(REPLAY_VIEW_JS), methods=["GET"]),
-        Route("/replay-core.js", script(REPLAY_CORE_JS), methods=["GET"]),
-        *feature.routes(),
-    ]
-    if run is not None:
-        routes.append(Route("/api/replay/run", start, methods=["POST"]))
-    return Starlette(routes=routes)
@@ -2,8 +2,8 @@

 Architecture:
    TracingProtocol (ABC)          <- any backend implements this
-      ├── SimpleTracingManager     <- in-memory (no deps)
-      └── JsonlTracingManager      <- recorded runs (context-trace JSONL) + in-memory
+      ├── SimpleTracingManager     <- default in-memory (no deps)
+      └── SDKTracingManager        <- wraps praisonaiagents.obs + trace

    PraisonAITracing (BaseFeatureProtocol)
      └── delegates to active TracingProtocol implementation
@@ -110,112 +110,56 @@ class SimpleTracingManager(TracingProtocol):
        }


-# ── JSONL Tracing Manager ────────────────────────────────────────────
+# ── SDK Tracing Manager ──────────────────────────────────────────────


-class JsonlTracingManager(TracingProtocol):
-    """Reads recorded runs from the context-trace JSONL directory.
-
-    One ``<id>.jsonl`` file is one trace; spans come from start/end event
-    pairs (``parent_seq`` on schema 1.1, sequence order on 1.0).  The
-    directory is ``$PRAISONAI_TRACES_DIR`` > ``$PRAISON_HOME/traces`` >
-    ``~/.praison/traces`` (shared with the ``replay`` feature).  Traces and
-    spans posted to ``/api/traces/record`` stay in memory alongside.
-    """
-
-    #: Upper bound on files scanned for an unfiltered span listing.
-    MAX_FILES_FOR_SPANS = 20
+class SDKTracingManager(TracingProtocol):
+    """Wraps praisonaiagents.obs + trace for production use."""

    def __init__(self) -> None:
+        self._trace_available = False
+        self._obs_available = False
+        try:
+            from praisonaiagents.trace import ActionEvent  # noqa: F401
+
+            self._trace_available = True
+        except (ImportError, AttributeError):
+            pass
+        try:
+            from praisonaiagents.obs import Span, Trace  # noqa: F401
+
+            self._obs_available = True
+        except ImportError:
+            pass
+        if not (self._trace_available or self._obs_available):
+            raise ImportError("Neither praisonaiagents.trace nor praisonaiagents.obs available")
        self._simple = SimpleTracingManager()
-
-    # -- JSONL side ---------------------------------------------------
-
-    @staticmethod
-    def _trace_from_file(path) -> Optional[Dict[str, Any]]:
-        from . import _trace_jsonl as tj
-
-        row = tj.summarize_run(path)
-        if row is None:
-            return None
-        events = tj.read_events(path)
-        started = row.get("started_at") or 0.0
-        ended = row.get("ended_at")
-        last_ts = max(
-            (e["timestamp"] for e in events if isinstance(e.get("timestamp"), (int, float))),
-            default=started,
+        logger.info(
+            "SDKTracingManager initialized (trace=%s, obs=%s)",
+            self._trace_available,
+            self._obs_available,
        )
-        agents = row.get("agents") or []
-        return {
-            "id": row["run_id"],
-            "agent_id": agents[0] if agents else "",
-            "agents": agents,
-            "name": row.get("name") or row["run_id"],
-            "status": row["status"],
-            "start_time": started,
-            "end_time": ended,
-            "timestamp": started,
-            "duration_ms": round(((ended or last_ts) - started) * 1000, 3),
-            "span_count": len(tj.build_spans(events, row["run_id"])),
-            "source": "jsonl",
-            "metadata": {
-                "path": row["path"],
-                "session_id": row.get("session_id"),
-                "kind": row.get("kind"),
-                "events": row["events"],
-                "cost_usd": row["cost_usd"],
-                "live": row["live"],
-            },
-        }
-
-    @staticmethod
-    def _files():
-        from . import _trace_jsonl as tj
-
-        return tj.list_run_files()

    def list_traces(
        self, *, limit: int = 50, agent_id: Optional[str] = None
    ) -> List[Dict[str, Any]]:
-        items: List[Dict[str, Any]] = []
-        for path in self._files():
-            if len(items) >= limit:
-                break
-            trace = self._trace_from_file(path)
-            if trace is None:
-                continue
-            if agent_id and agent_id not in trace["agents"]:
-                continue
-            items.append(trace)
-        remaining = max(0, limit - len(items))
-        if remaining:
-            items.extend(self._simple.list_traces(limit=remaining, agent_id=agent_id))
-        return items
+        sdk_traces = self._list_traces_from_sdk(limit=limit, agent_id=agent_id)
+        if sdk_traces is not None:
+            return sdk_traces
+        return self._simple.list_traces(limit=limit, agent_id=agent_id)

    def list_spans(
        self, *, limit: int = 100, trace_id: Optional[str] = None
    ) -> List[Dict[str, Any]]:
-        from . import _trace_jsonl as tj
-
-        if trace_id:
-            path = tj.run_path(trace_id)
-            if path is not None and path.is_file():
-                return tj.build_spans(tj.read_events(path), trace_id)[:limit]
-            return self._simple.list_spans(limit=limit, trace_id=trace_id)
-        spans: List[Dict[str, Any]] = []
-        for path in self._files()[: self.MAX_FILES_FOR_SPANS]:
-            spans.extend(tj.build_spans(tj.read_events(path), path.stem))
-            if len(spans) >= limit:
-                return spans[:limit]
-        spans.extend(self._simple.list_spans(limit=limit - len(spans)))
-        return spans[:limit]
+        sdk_spans = self._list_spans_from_sdk(limit=limit, trace_id=trace_id)
+        if sdk_spans is not None:
+            return sdk_spans
+        return self._simple.list_spans(limit=limit, trace_id=trace_id)

    def get_trace(self, trace_id: str) -> Optional[Dict[str, Any]]:
-        from . import _trace_jsonl as tj
-
-        path = tj.run_path(trace_id)
-        if path is not None and path.is_file():
-            return self._trace_from_file(path)
+        sdk_trace = self._get_trace_from_sdk(trace_id)
+        if sdk_trace is not None:
+            return sdk_trace
        return self._simple.get_trace(trace_id)

    def record_trace(self, trace: Dict[str, Any]) -> str:
@@ -224,34 +168,69 @@ class JsonlTracingManager(TracingProtocol):
    def record_span(self, span: Dict[str, Any]) -> str:
        return self._simple.record_span(span)

+    def _list_traces_from_sdk(
+        self, *, limit: int, agent_id: Optional[str]
+    ) -> Optional[List[Dict[str, Any]]]:
+        try:
+            from praisonaiagents import trace as trace_module
+
+            getter = getattr(trace_module, "list_traces", None)
+            if not callable(getter):
+                return None
+            items = getter(limit=limit, agent_id=agent_id)
+            return items if isinstance(items, list) else None
+        except Exception:
+            return None
+
+    def _list_spans_from_sdk(
+        self, *, limit: int, trace_id: Optional[str]
+    ) -> Optional[List[Dict[str, Any]]]:
+        try:
+            from praisonaiagents import trace as trace_module
+
+            getter = getattr(trace_module, "list_spans", None)
+            if not callable(getter):
+                return None
+            items = getter(limit=limit, trace_id=trace_id)
+            return items if isinstance(items, list) else None
+        except Exception:
+            return None
+
+    def _get_trace_from_sdk(self, trace_id: str) -> Optional[Dict[str, Any]]:
+        try:
+            from praisonaiagents import trace as trace_module
+
+            getter = getattr(trace_module, "get_trace", None)
+            if not callable(getter):
+                return None
+            trace = getter(trace_id)
+            return trace if isinstance(trace, dict) else None
+        except Exception:
+            return None
+
    def health(self) -> Dict[str, Any]:
-        from . import _trace_jsonl as tj
-
        h = self._simple.health()
-        files = self._files()
-        h["provider"] = self.__class__.__name__
-        h["source"] = "jsonl" if files else "memory"
-        h["traces_dir"] = str(tj.traces_dir())
-        h["jsonl_traces"] = len(files)
+        h["provider"] = "SDKTracingManager"
+        h["trace_available"] = self._trace_available
+        h["obs_available"] = self._obs_available
        return h


-#: Deprecated alias. The old class looked up ``praisonaiagents.trace.list_traces``
-#: / ``list_spans`` / ``get_trace``, which never existed, so it always fell back
-#: to the in-memory store.  Recorded runs are JSONL files; read those instead.
-SDKTracingManager = JsonlTracingManager
-
-
 # ── Manager singleton ────────────────────────────────────────────────

 _tracing_manager: Optional[TracingProtocol] = None


 def get_tracing_manager() -> TracingProtocol:
-    """Get the active tracing manager (recorded JSONL runs + in-memory records)."""
+    """Get the active tracing manager (SDK-first, fallback to Simple)."""
    global _tracing_manager
    if _tracing_manager is None:
-        _tracing_manager = JsonlTracingManager()
+        try:
+            _tracing_manager = SDKTracingManager()
+            logger.info("Using SDKTracingManager")
+        except Exception as e:
+            logger.debug("SDKTracingManager init failed (%s), using SimpleTracingManager", e)
+            _tracing_manager = SimpleTracingManager()
    return _tracing_manager


@@ -322,10 +301,12 @@ class TracingFeature(BaseFeatureProtocol):
        h = mgr.health()
        lines = ["Tracing Status:"]
        lines.append(f"  Provider: {h.get('provider', 'unknown')}")
-        if "source" in h:
-            lines.append(f"  Source: {h['source']} ({h.get('traces_dir', '')})")
        lines.append(f"  Total traces: {h.get('total_traces', 0)}")
        lines.append(f"  Total spans: {h.get('total_spans', 0)}")
+        if "trace_available" in h:
+            lines.append(f"  SDK trace: {'available' if h['trace_available'] else 'unavailable'}")
+        if "obs_available" in h:
+            lines.append(f"  SDK obs: {'available' if h['obs_available'] else 'unavailable'}")
        return "\n".join(lines)

    def _cli_list(self, limit: int = 20) -> str:
@@ -1,15 +0,0 @@
-"""Ready-made aiui app that opens straight to PraisonAI Replay.
-
-Usage (what ``praisonai replay view`` runs)::
-
-    aiui run "$(python -c 'import praisonaiui.replay_app as m; print(m.__file__)')" \
-        --style dashboard --host 127.0.0.1 --port 8090
-
-then open ``http://127.0.0.1:8090/replay?run=<run_id>`` (``/#/replay?run=<run_id>``
-is accepted too).  The trace directory follows ``PRAISONAI_TRACES_DIR`` >
-``PRAISON_HOME/traces`` > ``~/.praison/traces``.
-"""
-
-from praisonaiui.features.replay import configure_replay_app
-
-configure_replay_app()
@@ -1303,11 +1303,9 @@ async def patch_session(request: Request) -> JSONResponse:
        body = await request.json()
    except Exception:
        return JSONResponse({"error": "Invalid JSON"}, status_code=400)
-    title = body.get("title") if isinstance(body, dict) else None
+    title = body.get("title")
    if title is not None:
-        if not isinstance(title, str) or not title.strip():
-            return JSONResponse({"error": "title must be a non-empty string"}, status_code=400)
-        await _datastore.update_session(session_id, title=title.strip()[:200])
+        await _datastore.update_session(session_id, title=title)
    return JSONResponse({"status": "updated", "session_id": session_id})


@@ -3282,8 +3280,6 @@ def create_app(
        routes.extend(feature.routes())

    # Register built-in dashboard pages via the same protocol
-    from praisonaiui.features.replay import REPLAY_MARK_SVG
-
    _builtin_pages = [
        {
            "id": "overview",
@@ -3300,7 +3296,6 @@ def create_app(
            "group": "Agent",
            "description": "AI agent chat",
            "order": 1,
-            "layout": "full-bleed",
        },
        {
            "id": "chat-canvas",
@@ -3309,7 +3304,6 @@ def create_app(
            "group": "Agent",
            "description": "Chat with live A2UI preview panel",
            "order": 2,
-            "layout": "full-bleed",
        },
        {
            "id": "canvas",
@@ -3351,15 +3345,6 @@ def create_app(
            "description": "Run flight recorder — timeline debugger",
            "order": 22,
        },
-        {
-            "id": "replay",
-            "title": "Replay",
-            "icon": "⏮️",
-            "icon_svg": REPLAY_MARK_SVG,
-            "group": "Control",
-            "description": "Recorded agent runs, step by step: who did what, when, and at what cost",
-            "order": 21,
-        },
        {
            "id": "usage",
            "title": "Usage",
@@ -3597,7 +3582,6 @@ def create_app(
    _page_api_overrides = {
        "sessions": "/sessions",
        "runs": "/api/sessions",
-        "replay": "/api/replay/runs",
        "cron": "/api/schedules",
        "channels": "/api/channels",
        "mcp": "/api/mcp/servers",
@@ -147,7 +147,6 @@ const BUILTIN_VIEWS = {
  agents:         '/plugins/views/agents.js',
  sessions:       '/plugins/views/sessions.js',
  runs:           '/plugins/views/run-recorder.js',
-  replay:         '/plugins/views/replay.js',
  memory:         '/plugins/views/memory.js',
  knowledge:      '/plugins/views/knowledge.js',
  logs:           '/plugins/views/logs.js',
@@ -378,12 +377,8 @@ const DASHBOARD_STYLE = `
  .db-main { flex: 1; padding: 32px 40px; overflow-y: auto; min-width: 0; }
  .db-main.db-clean { padding: 0; display: flex; flex-direction: column; overflow: hidden; height: 100vh; }
  .db-main.db-clean > #db-page-content { flex: 1; display: flex; flex-direction: column; min-height: 0; }
-  /* Per-page full bleed (page.layout === 'full-bleed'): view fills the main column. */
-  .db-main.db-fill { display: flex; flex-direction: column; overflow: hidden; height: 100vh; box-sizing: border-box; }
-  .db-main.db-fill > #db-page-content { flex: 1; display: flex; flex-direction: column; min-height: 0; }
  .db-page-header { margin-bottom: 28px; }
  .db-page-title { font-size: 26px; font-weight: 700; letter-spacing: -0.02em; margin: 0 0 4px; }
-  .db-page-icon svg, .db-nav-icon svg { display: inline-block; vertical-align: -0.125em; }
  .db-page-desc { color: var(--db-text-dim); font-size: 14px; margin: 0; }

  /* Generic data viewer */
@@ -462,20 +457,10 @@ const DASHBOARD_STYLE = `
  .db-mobile-overlay { display: none; position: fixed; inset: 0; z-index: 35; background: rgba(0,0,0,0.5); }
  @media (max-width: 1023px) {
    .db-mobile-header { display: flex; }
-    /* !important: buildSidebar() sets an inline position:relative for its toggle,
-       which otherwise keeps the hidden sidebar's 260px in the flex row. */
-    .db-sidebar { position: fixed !important; top: 0; left: 0; z-index: 45; transform: translateX(-100%); transition: transform 0.2s ease; }
+    .db-sidebar { position: fixed; z-index: 45; transform: translateX(-100%); transition: transform 0.2s ease; }
    .db-sidebar.db-sidebar-open { transform: translateX(0); }
    .db-mobile-overlay.db-visible { display: block; }
    .db-main { padding-top: 48px; }
-    /* The shell header slot sits in the same flex row; give it its own line. */
-    #root.db-active { flex-wrap: wrap; }
-    #db-shell-header-slot { flex: 0 0 100%; margin-top: 48px; }
-    #db-shell-header-slot + .db-main { padding-top: 16px; }
-  }
-  @media (max-width: 600px) {
-    .db-main { padding: 64px 16px 16px; }
-    #db-shell-header-slot + .db-main { padding-top: 16px; }
  }
  .db-card {
    background: var(--db-card-bg); border: 1px solid var(--db-border);
@@ -1767,13 +1752,6 @@ async function buildDashboard() {
  renderSlot('shell:header', shellHeader);
  if (shellHeader.children.length) root.insertBefore(shellHeader, main);

-  // Hash deep links (e.g. /#/replay?run=<id> from `praisonai replay view`)
-  // become the path form (/replay?run=<id>) before the page is resolved.
-  const hashRoute = location.hash.match(/^#\/([A-Za-z0-9_-]+)(\?[^#]*)?$/);
-  if (hashRoute && pagesData.find(p => p.id === hashRoute[1])) {
-    history.replaceState(null, '', `/${hashRoute[1]}${hashRoute[2] || ''}`);
-  }
-
  // Resolve initial page from URL path or default to first page
  const pathId = location.pathname.replace(/^\//, '') || '';
  const initialPage = pathId && pagesData.find(p => p.id === pathId)
@@ -1790,29 +1768,6 @@ async function buildDashboard() {
  });
 }

-// Pages may carry an inline SVG mark (`icon_svg`) next to the text `icon`.
-// It is parsed as SVG and dropped if it holds scripts, foreignObject,
-// event handlers or javascript: URLs; otherwise the text icon is used.
-function safeSvgIcon(markup) {
-  if (typeof markup !== 'string' || !markup.trim().startsWith('<svg')) return null;
-  try {
-    const doc = new DOMParser().parseFromString(markup, 'image/svg+xml');
-    const svg = doc.documentElement;
-    if (!svg || svg.nodeName !== 'svg' || doc.querySelector('parsererror, script, foreignObject')) return null;
-    for (const el of [svg, ...svg.querySelectorAll('*')]) {
-      for (const a of [...el.attributes]) {
-        if (/^on/i.test(a.name) || /javascript:/i.test(a.value)) return null;
-      }
-    }
-    return document.importNode(svg, true);
-  } catch (e) { return null; }
-}
-
-function setPageIcon(span, page, fallback) {
-  const svg = safeSvgIcon(page.icon_svg);
-  if (svg) { span.textContent = ''; span.appendChild(svg); } else span.textContent = page.icon || fallback;
-}
-
 function buildSidebar(pages) {
  const sidebar = document.createElement('nav');
  sidebar.className = 'db-sidebar';
@@ -1911,7 +1866,7 @@ function buildSidebar(pages) {
      item.dataset.navId = page.id;
      const iconSpan = document.createElement('span');
      iconSpan.className = 'db-nav-icon';
-      setPageIcon(iconSpan, page, '📄');
+      iconSpan.textContent = page.icon || '📄';
      item.appendChild(iconSpan);
      item.appendChild(document.createTextNode(' ' + page.title));
      item.addEventListener('click', () => selectPage(page.id));
@@ -1933,7 +1888,7 @@ function buildSidebar(pages) {
      btn.className = 'db-nav-item';
      const iconSpan = document.createElement('span');
      iconSpan.className = 'db-nav-icon';
-      setPageIcon(iconSpan, page, '⚙');
+      iconSpan.textContent = page.icon || '⚙';
      btn.appendChild(iconSpan);
      btn.appendChild(document.createTextNode(' ' + page.title));
      btn.addEventListener('click', () => {
@@ -1995,18 +1950,14 @@ async function selectPage(pageId) {
    return;
  }

-  // Full-bleed pages (e.g. chat) fill the main column and carry their own chrome
-  const fullBleed = page.layout === 'full-bleed';
-  main.classList.toggle('db-fill', fullBleed);
-
  // Set page header (controlled by dashboard config protocol)
-  const showPageHeader = main.dataset.showPageHeader !== 'false' && !fullBleed;
+  const showPageHeader = main.dataset.showPageHeader !== 'false';
  const toolbarSlotId = `page:${pageId}:toolbar`;
  const headerHtml = showPageHeader ? `
    <div class="db-page-header">
      <div style="display:flex;align-items:flex-start;justify-content:space-between;gap:12px;flex-wrap:wrap">
        <div>
-          <h1 class="db-page-title">${page.icon_svg ? '<span class="db-page-icon"></span>' : (page.icon || '')} ${page.title}</h1>
+          <h1 class="db-page-title">${page.icon || ''} ${page.title}</h1>
          ${page.description ? `<p class="db-page-desc">${page.description}</p>` : ''}
        </div>
        <div id="db-page-toolbar-slot" class="db-slot-host" data-slot="${toolbarSlotId}"></div>
@@ -2014,8 +1965,6 @@ async function selectPage(pageId) {
    </div>
  ` : '';
  main.innerHTML = `${headerHtml}<div data-page="${pageId}" id="db-page-content"></div>`;
-  const pageIcon = main.querySelector('.db-page-icon');
-  if (pageIcon) setPageIcon(pageIcon, page, '');
  if (showPageHeader) {
    const toolbarHost = document.getElementById('db-page-toolbar-slot');
    if (toolbarHost && SLOT_REGISTRY[toolbarSlotId]) {
@@ -164,20 +164,6 @@ function renderProgressBar(percentage) {
  `;
 }

-function escapeAttr(value) {
-  return String(value).replace(/&/g, '&amp;').replace(/"/g, '&quot;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
-}
-
-// Navigate to Chat and load the job's linked session (same event the
-// session-search palette and run recorder use).
-function openJobSession(sessionId) {
-  if (!sessionId) return;
-  const nav = (typeof window.aiui?.selectPage === 'function') ? window.aiui.selectPage('chat') : null;
-  Promise.resolve(nav).finally(() => {
-    window.dispatchEvent(new CustomEvent('aiui:session-select', { detail: { sessionId } }));
-  });
-}
-
 function renderJobRow(job) {
  const status = job.status || 'queued';
  const isTerminal = ['succeeded', 'failed', 'cancelled'].includes(status);
@@ -213,7 +199,6 @@ function renderJobRow(job) {
        ` : `
          ${_jobsCfg.backend !== 'praisonai' ? `<button class="aiui-btn aiui-btn-sm aiui-btn-delete" onclick="window.aiuiDeleteJob('${job.id}')" title="Delete">🗑️</button>` : ''}
        `}
-        ${job.session_id ? `<button class="aiui-btn aiui-btn-sm aiui-btn-open-session" data-session-id="${escapeAttr(job.session_id)}" onclick="window.aiuiOpenJobSession(this.dataset.sessionId)" title="Open session in Chat">💬</button>` : ''}
        <button class="aiui-btn aiui-btn-sm aiui-btn-view" onclick="window.aiuiViewJob('${job.id}')" title="View Details">
          👁️
        </button>
@@ -614,7 +599,6 @@ function checkForJobsPage(root) {
 window.aiuiCancelJob = cancelJob;
 window.aiuiDeleteJob = deleteJob;
 window.aiuiViewJob = viewJob;
-window.aiuiOpenJobSession = openJobSession;

 export default {
  name: 'jobs',
@@ -21,7 +21,6 @@ function injectStyles() {
      overflow: hidden;
    }
    .db-clean .chat-canvas-root { height: 100vh; }
-    .db-fill .chat-canvas-root { flex: 1; min-height: 0; height: auto; }
    .chat-canvas-chat {
      flex: 1 1 60%;
      min-width: 0;
@@ -19,7 +19,6 @@ let isStreaming = false;
 let streamingSessionId = null;  // tracks which session is actively streaming
 let currentRunId = null;
 let agents = [];
-let allSessions = [];  // last fetched session list, filtered client-side by the rail search
 let messageQueue = [];
 let focusMode = false;
 let sessionSelectHandler = null;
@@ -222,11 +221,6 @@ function injectStyles() {
  style.textContent = `
    .chat-root { display:flex; height:calc(100vh - 140px); gap:0; border-radius:12px; overflow:hidden; border:1px solid var(--db-border); background:var(--db-card-bg); }
    .db-clean .chat-root { height:100%; border-radius:0; border:none; }
-    .db-fill .chat-root { flex:1; min-height:0; height:auto; }
-    @media (max-width:900px) {
-      .db-fill .chat-root { flex-direction:column; }
-      .db-fill .chat-sidebar-panel { width:100%; min-width:0; max-height:40vh; border-right:none; border-bottom:1px solid var(--db-border); }
-    }
    .chat-root.focus-mode .chat-sidebar-panel { display:none; }
    .chat-root.focus-mode .chat-main-panel { border-left:none; }

@@ -236,17 +230,12 @@ function injectStyles() {
    .chat-sidebar-agent { padding:10px 16px; border-bottom:1px solid var(--db-border); }
    .chat-sidebar-agent label { font-size:11px; color:var(--db-text-dim); display:block; margin-bottom:4px; text-transform:uppercase; font-weight:600; letter-spacing:.5px; }
    .chat-sidebar-agent select { width:100%; padding:6px 10px; background:var(--db-card-bg); border:1px solid var(--db-border); border-radius:6px; color:var(--db-text); font-size:13px; }
-    .chat-sess-search { padding:8px 16px 0; }
-    .chat-sess-search input { width:100%; box-sizing:border-box; padding:6px 10px; background:var(--db-card-bg); border:1px solid var(--db-border); border-radius:6px; color:var(--db-text); font-size:13px; }
    .chat-sess-list { flex:1; overflow-y:auto; padding:8px; }
    .chat-sess-item { padding:10px 12px; border-radius:8px; cursor:pointer; margin-bottom:4px; font-size:13px; transition:background .15s; display:flex; flex-direction:column; gap:2px; }
    .chat-sess-item:hover { background:rgba(var(--db-accent-rgb,100,100,255),.08); }
    .chat-sess-item.active { background:rgba(var(--db-accent-rgb,100,100,255),.15); }
    .chat-sess-item .sess-title { font-weight:500; white-space:nowrap; overflow:hidden; text-overflow:ellipsis; }
    .chat-sess-item .sess-meta { font-size:11px; color:var(--db-text-dim); }
-    .chat-sess-item { position:relative; }
-    .chat-sess-item .sess-rename { position:absolute; top:6px; right:6px; display:none; background:none; border:none; color:var(--db-text-dim); cursor:pointer; font-size:12px; padding:2px 4px; }
-    .chat-sess-item:hover .sess-rename, .chat-sess-item .sess-rename:focus { display:block; }

    .chat-main-panel { flex:1; display:flex; flex-direction:column; min-width:0; }
    .chat-top-bar { padding:10px 16px; border-bottom:1px solid var(--db-border); display:flex; align-items:center; justify-content:space-between; gap:10px; }
@@ -823,9 +812,6 @@ export async function render(container) {
          <label>Agent</label>
          <select id="chat-agent-selector"><option value="">Auto (default)</option></select>
        </div>
-        <div class="chat-sess-search">
-          <input type="search" id="chat-session-search" placeholder="Search sessions…" aria-label="Search sessions" autocomplete="off">
-        </div>
        <div class="chat-sess-list" id="chat-sessions-list"></div>
      </div>
      <div class="chat-main-panel">
@@ -906,8 +892,6 @@ export async function render(container) {
  const agentSelector = document.getElementById('chat-agent-selector');
  const attachBtn = document.getElementById('chat-attach-btn');
  const fileInput = document.getElementById('chat-file-input');
-  const sessionSearch = document.getElementById('chat-session-search');
-  if (sessionSearch) sessionSearch.addEventListener('input', renderSessionList);
  // Guard: if DOM elements aren't present yet (race condition), bail out
  if (!input || !sendBtn) {
    console.warn('[chat] DOM elements not ready — skipping event binding');
@@ -1055,92 +1039,47 @@ async function loadSessions() {
      resp = await fetch('/sessions');
    }
    const data = await resp.json();
-    const fetched = data.sessions || data || [];
-    allSessions = Array.isArray(fetched) ? fetched : [];
-    renderSessionList();
+    const sessions = data.sessions || data || [];
+    const list = document.getElementById('chat-sessions-list');
+    if (!list) return;
+    list.innerHTML = '';
+    if (sessions.length === 0) {
+      list.innerHTML = '<div style="padding:16px;text-align:center;color:var(--db-text-dim);font-size:12px">No sessions yet</div>';
+      return;
+    }
+    sessions.slice(0, 30).forEach((s) => {
+      const el = document.createElement('div');
+      const id = s.id || s.session_id || '';
+      el.className = 'chat-sess-item' + (id === currentSessionId ? ' active' : '');
+      // Show platform icon for channel sessions (e.g. Slack with SVG)
+      const platformName = s.platform || '';
+      const platSvg = _getPlatformSVG(platformName);
+      let title;
+      let titlePrefix = '';
+      if (platformName) {
+        const displayName = platformName.charAt(0).toUpperCase() + platformName.slice(1);
+        if (platSvg) {
+          titlePrefix = '<span class="sess-platform-icon ' + _getPlatformClass(platformName) + '">' + platSvg + '</span>';
+        }
+        title = displayName;
+      } else {
+        title = s.name || s.title || s.label || id.substring(0, 12) + '…';
+      }
+      const agent = s.agent_id || s.agent || '';
+      const time = timeAgo(s.created_at || s.updated_at);
+      el.innerHTML = `
+        <div class="sess-title">${titlePrefix}${escapeHtml(title)}</div>
+        <div class="sess-meta">${agent ? '🤖 ' + escapeHtml(agent) + ' · ' : ''}${time}</div>
+      `;
+      el.title = id;
+      el.addEventListener('click', () => loadSession(id));
+      list.appendChild(el);
+    });
  } catch (e) {
    console.warn('[Chat] Failed to load sessions:', e);
  }
 }

-function _sessionMatches(s, q) {
-  const fields = [s.id, s.session_id, s.name, s.title, s.label, s.agent_id, s.agent, s.platform];
-  return fields.some((v) => typeof v === 'string' && v.toLowerCase().includes(q));
-}
-
-function renderSessionList() {
-  const list = document.getElementById('chat-sessions-list');
-  if (!list) return;
-  const input = document.getElementById('chat-session-search');
-  const q = (input && input.value || '').trim().toLowerCase();
-  const sessions = q ? allSessions.filter((s) => _sessionMatches(s, q)) : allSessions;
-  list.innerHTML = '';
-  if (sessions.length === 0) {
-    const msg = q ? 'No matching sessions' : 'No sessions yet';
-    list.innerHTML = '<div style="padding:16px;text-align:center;color:var(--db-text-dim);font-size:12px">' + msg + '</div>';
-    return;
-  }
-  sessions.slice(0, 30).forEach((s) => {
-    const el = document.createElement('div');
-    const id = s.id || s.session_id || '';
-    el.className = 'chat-sess-item' + (id === currentSessionId ? ' active' : '');
-    // Show platform icon for channel sessions (e.g. Slack with SVG)
-    const platformName = s.platform || '';
-    const platSvg = _getPlatformSVG(platformName);
-    let title;
-    let titlePrefix = '';
-    if (platformName) {
-      const displayName = platformName.charAt(0).toUpperCase() + platformName.slice(1);
-      if (platSvg) {
-        titlePrefix = '<span class="sess-platform-icon ' + _getPlatformClass(platformName) + '">' + platSvg + '</span>';
-      }
-      title = displayName;
-    } else {
-      title = s.name || s.title || s.label || id.substring(0, 12) + '…';
-    }
-    const agent = s.agent_id || s.agent || '';
-    const time = timeAgo(s.created_at || s.updated_at);
-    el.innerHTML = `
-      <div class="sess-title">${titlePrefix}${escapeHtml(title)}</div>
-      <div class="sess-meta">${agent ? '🤖 ' + escapeHtml(agent) + ' · ' : ''}${time}</div>
-    `;
-    el.title = id;
-    el.addEventListener('click', () => loadSession(id));
-    if (!platformName && id) {
-      const btn = document.createElement('button');
-      btn.className = 'sess-rename';
-      btn.title = 'Rename session';
-      btn.setAttribute('aria-label', 'Rename session');
-      btn.textContent = '✎';
-      btn.addEventListener('click', (e) => { e.stopPropagation(); renameSession(id, title); });
-      el.appendChild(btn);
-    }
-    list.appendChild(el);
-  });
-}
-
-async function renameSession(sessionId, currentTitle) {
-  const next = (window.prompt('Rename session', currentTitle || '') || '').trim();
-  if (!next || next === currentTitle) return;
-  try {
-    const resp = await fetch('/sessions/' + encodeURIComponent(sessionId), {
-      method: 'PATCH',
-      headers: { 'Content-Type': 'application/json' },
-      body: JSON.stringify({ title: next }),
-    });
-    if (!resp.ok) throw new Error('HTTP ' + resp.status);
-    const s = allSessions.find((x) => (x.id || x.session_id) === sessionId);
-    if (s) { s.title = next; delete s.name; }
-    renderSessionList();
-    if (sessionId === currentSessionId) {
-      const header = document.getElementById('chat-header-title');
-      if (header) header.textContent = next;
-    }
-  } catch (e) {
-    console.warn('[Chat] Failed to rename session:', e);
-  }
-}
-
 async function loadSession(sessionId) {
  currentSessionId = sessionId;
  refreshStreamingUI();
@@ -1192,8 +1131,7 @@ async function loadSession(sessionId) {
        title.textContent = (sessionIcon || '📨') + ' ' + displayName;
      }
    } else if (title) {
-      const cached = allSessions.find((x) => (x.id || x.session_id) === sessionId);
-      title.textContent = (cached && (cached.name || cached.title)) || ('Session ' + sessionId.substring(0, 8));
+      title.textContent = 'Session ' + sessionId.substring(0, 8);
    }
  } catch (e) {
    console.warn('[Chat] Failed to load session:', e);
@@ -23,6 +23,7 @@ let editor = null;
 let monacoNs = null;
 let running = false;
 let timerId = null;
+let pendingApproval = null; // { id, language, code } awaiting approval
 const history = [];

 function escapeHtml(s) {
@@ -178,14 +179,19 @@ async function runCode(container) {
    runBtn.textContent = `Executing… ${((Date.now() - start) / 1000).toFixed(1)}s`;
  }, 100);

+  const p = pendingApproval;
+  const approval_id = p && p.language === lang && p.code === code ? p.id : undefined;
  let result;
  try {
    const res = await fetch('/api/code/execute', {
      method: 'POST',
      headers: { 'Content-Type': 'application/json' },
-      body: JSON.stringify({ language: lang, code, timeout: 30 }),
+      body: JSON.stringify({ language: lang, code, timeout: 30, approval_id }),
    });
    result = await res.json();
+    pendingApproval = result.status === 'pending_approval'
+      ? { id: result.approval_id, language: lang, code }
+      : null;
  } catch (e) {
    result = { status: 'failed', error: String(e), language: lang };
  } finally {
@@ -1,524 +0,0 @@
-"""Browser smoke + axe accessibility check for the Replay view (dev-only, never shipped).
-
-Opt-in:  RUN_BROWSER_TESTS=1 AXE_CORE_JS=/path/to/axe.min.js pytest tests/browser -o addopts=""
-
-* Needs the ``playwright`` Python package and a Chrome install (``channel="chrome"``)
-  or a Playwright Chromium (``python -m playwright install chromium``).
-* axe-core (MPL-2.0) is loaded from ``AXE_CORE_JS`` (e.g. ``npm i axe-core`` in
-  any scratch dir); the axe checks are skipped when it is not provided.
-"""
-
-from __future__ import annotations
-
-import json
-import os
-import shutil
-import socket
-import threading
-import time
-from pathlib import Path
-
-import pytest
-
-if os.environ.get("RUN_BROWSER_TESTS") != "1":
-    pytest.skip("browser tests are opt-in (RUN_BROWSER_TESTS=1)", allow_module_level=True)
-
-sync_api = pytest.importorskip("playwright.sync_api")
-
-ROOT = Path(__file__).resolve().parents[2]
-FIXTURES = ROOT / "tests" / "fixtures" / "replay"
-AXE = os.environ.get("AXE_CORE_JS")
-WCAG_TAGS = ["wcag2a", "wcag2aa", "wcag21a", "wcag21aa", "wcag22aa"]
-
-
-def _events(name: str) -> list[dict]:
-    return [json.loads(line) for line in (FIXTURES / f"{name}.jsonl").read_text(encoding="utf-8").splitlines() if line.strip()]
-
-
-@pytest.fixture(scope="module")
-def browser():
-    with sync_api.sync_playwright() as p:
-        try:
-            b = p.chromium.launch(channel="chrome")
-        except Exception:
-            try:
-                b = p.chromium.launch()
-            except Exception as exc:  # no browser available
-                pytest.skip(f"no Chromium/Chrome available: {exc}")
-        yield b
-        b.close()
-
-
-def _page(browser, scheme: str = "light", reduced: bool = False):
-    page = browser.new_page(
-        viewport={"width": 1366, "height": 1000},
-        color_scheme=scheme,
-        reduced_motion="reduce" if reduced else "no-preference",
-    )
-    errors: list[str] = []
-    page.on("pageerror", lambda e: errors.append(str(e)))
-    page.on("console", lambda m: errors.append(m.text) if m.type == "error" else None)
-    return page, errors
-
-
-def _axe(page, selector: str = ".rp-root") -> list[dict]:
-    if not AXE:
-        return []
-    page.add_script_tag(path=AXE)
-    result = page.evaluate(
-        """async ([sel, tags]) => {
-            const r = await axe.run(document.querySelector(sel), {runOnly: {type: 'tag', values: tags}});
-            return r.violations.map(v => ({id: v.id, impact: v.impact, help: v.help, nodes: v.nodes.slice(0, 3).map(n => n.target.join(' '))}));
-        }""",
-        [selector, WCAG_TAGS],
-    )
-    return result
-
-
-def _standalone(tmp_path: Path, name: str) -> str:
-    from praisonaiui.features.replay import standalone_html
-
-    out = tmp_path / f"{name}.html"
-    out.write_text(standalone_html(_events(name), title=name), encoding="utf-8")
-    return out.as_uri()
-
-
-def _current_index(page) -> int:
-    return int(page.get_attribute('.rp-step[aria-current="step"]', "data-i"))
-
-
-@pytest.mark.parametrize("name", ["team_handoff", "flow_parallel_loop", "legacy_v10", "team_outside"])
-def test_standalone_steps_with_arrow_keys(browser, tmp_path, name):
-    page, errors = _page(browser)
-    page.goto(_standalone(tmp_path, name))
-    page.wait_for_selector(".rp-step")
-    total = page.locator(".rp-step").count()
-    assert total > 5
-    assert _current_index(page) == total - 1  # opens at the end (whole run visible)
-
-    page.locator(".rp-step").nth(total - 1).focus()
-    page.keyboard.press("Home")
-    assert _current_index(page) == 0
-    for _ in range(3):
-        page.keyboard.press("ArrowRight")
-    assert _current_index(page) == 3
-    page.keyboard.press("ArrowLeft")
-    assert _current_index(page) == 2
-    # focus follows the cursor in the step list, the scrubber and the drawer agree
-    assert page.evaluate("document.activeElement.getAttribute('data-i')") == "2"
-    assert page.input_value("#rp-scrub-range") == "2"
-    step_text = page.locator('.rp-step[aria-current="step"] .rp-step-text').inner_text()
-    assert page.locator(".rp-drawer h3").inner_text() == step_text
-    # replay: later blocks are drawn as "not reached yet"
-    assert page.locator(".rp-block.rp-future").count() > 0
-    page.keyboard.press("End")
-    assert _current_index(page) == total - 1
-    assert page.locator(".rp-block.rp-future").count() == 0
-    assert not errors, errors
-
-
-def test_standalone_drawer_tabs_map_and_axe(browser, tmp_path):
-    page, errors = _page(browser)
-    page.goto(_standalone(tmp_path, "team_handoff"))
-    page.wait_for_selector(".rp-step")
-    # select the hand-off step and read the Why tab
-    page.locator(".rp-step", has_text="handed off to Writer").click()
-    page.locator('[role="tab"]', has_text="Why").click()
-    why = page.locator("#rp-tabpanel").inner_text()
-    assert "Hand-off reason" in why and "Facts gathered" in why
-    # keyboard on the tablist moves between tabs
-    page.keyboard.press("ArrowRight")
-    assert page.get_attribute('[role="tab"][aria-selected="true"]', "id") == "rp-tab-raw"
-    assert '"event_type": "agent_handoff"' in page.locator("#rp-tabpanel pre").inner_text()
-    # manager's task snapshot shows up for the delegated task
-    page.locator(".rp-step", has_text="Task 'research' went to Researcher").click()
-    page.locator('[role="tab"]', has_text="Why").click()
-    assert "Manager's task snapshot" in page.locator("#rp-tabpanel").inner_text()
-    # approval evidence
-    page.locator(".rp-step", has_text="You approved write_file").click()
-    assert "Decided by" in page.locator("#rp-tabpanel").inner_text()
-
-    violations = _axe(page)
-    assert violations == [], json.dumps(violations, indent=2)
-
-    page.click("[data-key='overlay']")
-    page.click("[data-key='view:map']")
-    page.wait_for_selector(".rp-node")
-    assert page.locator(".rp-node").count() == 10
-    labels = page.eval_on_selector_all(".rp-edge text", "els => els.map(e => e.textContent)")
-    assert "hands off" in labels and any(t.startswith("delegates") for t in labels)
-    page.locator(".rp-node").first.focus()
-    page.keyboard.press("ArrowDown")
-    page.keyboard.press("Enter")
-    assert page.locator(".rp-drawer h3").inner_text()
-    violations = _axe(page)
-    assert violations == [], json.dumps(violations, indent=2)
-
-    page.select_option("[data-key='theme']", "dark")
-    assert page.get_attribute(".rp-root", "data-theme") == "dark"
-    violations = _axe(page)
-    assert violations == [], json.dumps(violations, indent=2)
-    page.click("[data-key='view:timeline']")
-    violations = _axe(page)
-    assert violations == [], json.dumps(violations, indent=2)
-    assert not errors, errors
-
-
-def test_reduced_motion_has_no_animation(browser, tmp_path):
-    page, _ = _page(browser, reduced=True)
-    page.goto(_standalone(tmp_path, "flow_parallel_loop"))
-    page.wait_for_selector(".rp-step")
-    names = page.evaluate(
-        "[...document.querySelectorAll('.rp-root *')].map(e => getComputedStyle(e).animationName).filter(n => n && n !== 'none')"
-    )
-    assert names == []
-
-
-def _boxes(page, selector: str) -> list[dict]:
-    return page.eval_on_selector_all(
-        selector,
-        "els => els.map(e => { const r = e.getBoundingClientRect(); return {x: r.x, y: r.y, w: r.width, h: r.height, id: e.closest('[data-block]')?.getAttribute('data-block')}; })",
-    )
-
-
-@pytest.mark.parametrize("name", ["team_outside", "team_handoff", "flow_parallel_loop"])
-def test_timeline_blocks_never_overlap(browser, tmp_path, name):
-    """An LLM span encloses its tool calls in real runs; tools go on their own row."""
-    page, errors = _page(browser)
-    page.goto(_standalone(tmp_path, name))
-    page.wait_for_selector(".rp-block")
-    boxes = _boxes(page, ".rp-block .rp-body")
-    for i, a in enumerate(boxes):
-        for b in boxes[i + 1:]:
-            apart = a["x"] + a["w"] <= b["x"] + 0.5 or b["x"] + b["w"] <= a["x"] + 0.5 or a["y"] + a["h"] <= b["y"] + 0.5 or b["y"] + b["h"] <= a["y"] + 0.5
-            assert apart, f"{a['id']} overlaps {b['id']}"
-    # a label that does not fit is ellipsized, and the full text is in the title and name
-    llm = page.locator(".rp-block.rp-k-llm").first
-    name_attr = llm.get_attribute("aria-label")
-    title = llm.locator("title").text_content()
-    assert name_attr.startswith(title)
-    llm.focus()
-    assert page.locator(".rp-tip").get_attribute("visibility") == "visible"
-    assert page.locator(".rp-tip text").text_content() == title
-    assert not errors, errors
-
-
-def test_why_tab_by_role_and_keyboard(browser, tmp_path):
-    page, errors = _page(browser)
-    page.goto(_standalone(tmp_path, "team_outside"))
-    page.wait_for_selector(".rp-step")
-    page.locator(".rp-step", has_text="Triage handed off to Billing").click()
-    page.get_by_role("tab", name="Why").click()
-    assert page.get_by_role("tab", name="Why").get_attribute("aria-selected") == "true"
-    why = page.get_by_role("tabpanel").inner_text()
-    assert "Hand-off reason" in why and "Billing question" in why and "Context passed" in why
-    # the task input
-    page.locator(".rp-step", has_text="Task 'research' went to Researcher").click()
-    assert "Task description" in page.get_by_role("tabpanel").inner_text()
-    assert "Get one fact about electric vehicles" in page.get_by_role("tabpanel").inner_text()
-    # keyboard: focus the selected tab, arrow keys move between tabs
-    page.get_by_role("tab", name="Why").focus()
-    page.keyboard.press("ArrowLeft")
-    assert page.get_by_role("tab", name="What happened").get_attribute("aria-selected") == "true"
-    page.keyboard.press("ArrowRight")
-    assert page.get_by_role("tab", name="Why").get_attribute("aria-selected") == "true"
-    assert page.evaluate("document.activeElement.getAttribute('role')") == "tab"
-    # route chosen and approval decision
-    page.goto(_standalone(tmp_path, "flow_parallel_loop"))
-    page.wait_for_selector(".rp-step")
-    page.locator(".rp-step", has_text="chose route 'publish'").click()
-    page.get_by_role("tab", name="Why").click()
-    assert "Route chosen" in page.get_by_role("tabpanel").inner_text()
-    page.goto(_standalone(tmp_path, "team_handoff"))
-    page.wait_for_selector(".rp-step")
-    page.locator(".rp-step", has_text="You approved write_file").click()
-    page.get_by_role("tab", name="Why").click()
-    panel = page.get_by_role("tabpanel").inner_text()
-    assert "Decision" in panel and "Approved with edited arguments" in panel
-    assert not errors, errors
-
-
-def test_theme_follows_system_with_override(browser, tmp_path):
-    url = _standalone(tmp_path, "team_handoff")
-    bg = "getComputedStyle(document.querySelector('.rp-root')).backgroundColor"
-    page, _ = _page(browser, scheme="dark")
-    page.goto(url)
-    page.wait_for_selector(".rp-step")
-    assert page.get_attribute(".rp-root", "data-theme") == "system"
-    assert page.evaluate(bg) == "rgb(22, 23, 27)"
-    page.select_option("[data-key='theme']", "light")
-    assert page.evaluate(bg) == "rgb(255, 255, 255)"
-    page.close()
-    page, _ = _page(browser, scheme="light")
-    page.goto(url)
-    page.wait_for_selector(".rp-step")
-    assert page.evaluate(bg) == "rgb(255, 255, 255)"
-
-
-def test_map_fits_on_open_and_groups_outside_agents(browser, tmp_path):
-    page, errors = _page(browser)
-    page.goto(_standalone(tmp_path, "team_outside"))
-    page.wait_for_selector(".rp-step")
-    page.get_by_role("button", name="Map").click()
-    page.wait_for_selector(".rp-node")
-    box = page.evaluate("(() => { const c = document.querySelector('.rp-canvas'); const r = c.getBoundingClientRect(); return {l: r.left, r: r.right, sw: c.scrollWidth, cw: c.clientWidth}; })()")
-    assert box["sw"] <= box["cw"] + 1, "map overflows on open"
-    for n in _boxes(page, ".rp-node .rp-card"):
-        assert box["l"] - 1 <= n["x"] and n["x"] + n["w"] <= box["r"] + 1
-    assert "Outside the team" in page.locator(".rp-group text").text_content()
-    outside = page.get_by_role("group", name="Outside the team")
-    assert outside.locator(".rp-node").count() == 3
-    labels = page.eval_on_selector_all(".rp-edge text", "els => els.map(e => e.textContent)")
-    assert "hands off" in labels
-    before = float(page.get_attribute(".rp-canvas svg", "width"))
-    page.get_by_role("button", name="Zoom in").click()
-    assert float(page.get_attribute(".rp-canvas svg", "width")) == pytest.approx(before * 1.5, abs=2)
-    page.get_by_role("button", name="Fit").click()
-    assert float(page.get_attribute(".rp-canvas svg", "width")) == pytest.approx(before, abs=2)
-    assert not errors, errors
-
-
-@pytest.mark.parametrize("name", ["team_outside", "flow_parallel_loop"])
-def test_phone_width_has_no_page_scroll(browser, tmp_path, name):
-    page, errors = _page(browser)
-    page.set_viewport_size({"width": 400, "height": 860})
-    page.goto(_standalone(tmp_path, name))
-    page.wait_for_selector(".rp-step")
-    assert page.evaluate("document.documentElement.scrollWidth") <= 400
-    r = page.evaluate("(() => { const b = document.querySelector('.rp-root').getBoundingClientRect(); return [b.left, b.right]; })()")
-    assert r[0] == pytest.approx(16, abs=1) and r[1] == pytest.approx(384, abs=1)
-    page.get_by_role("button", name="Map").click()
-    assert page.evaluate("document.documentElement.scrollWidth") <= 400
-    assert not errors, errors
-
-
-@pytest.mark.parametrize("order", ["core-first", "view-first"])
-def test_wrapper_style_export_boots(browser, tmp_path, order):
-    """The wrapper inlines both files as module scripts into #replay-root (which holds
-    a fallback table) after window.__REPLAY_DATA__; the view must replace it."""
-    views = ROOT / "src" / "praisonaiui" / "templates" / "frontend" / "plugins" / "views"
-    core = (views / "replay-core.js").read_text(encoding="utf-8").replace("</", "<\\/")
-    view = (views / "replay.js").read_text(encoding="utf-8").replace("</", "<\\/")
-    scripts = [core, view] if order == "core-first" else [view, core]
-    data = json.dumps({"run_id": "team-outside-01", "events": _events("team_outside"), "graph": None}).replace("<", "\\u003c")
-    html = (
-        "<!doctype html><html lang=en><head><meta charset=utf-8><title>PraisonAI Replay: x</title></head><body>"
-        "<div id=replay-root><table><tr><td>fallback</td></tr></table></div>"
-        f"<script id=replay-data>window.__REPLAY_DATA__ = {data};</script>"
-        + "".join(f"<script type=module>\n{js}\n</script>" for js in scripts)
-        + "</body></html>"
-    )
-    out = tmp_path / f"export-{order}.html"
-    out.write_text(html, encoding="utf-8")
-    page, errors = _page(browser)
-    page.goto(out.as_uri())
-    page.wait_for_selector(".rp-step")
-    assert page.locator("#replay-root table").count() == 0
-    assert page.locator(".rp-title").inner_text() == "team-outside-01"
-    # graph:null -> taken from workflow_start.data.graph
-    page.get_by_role("button", name="Map").click()
-    assert page.locator(".rp-node").count() == 10
-    assert page.locator(".rp-ask").count() == 0
-    assert not errors, errors
-
-
-# ── dashboard + live run + approval through the You lane ─────────────
-
-
-_PROVIDER_KEYS = ("OPENAI_API_KEY", "ANTHROPIC_API_KEY", "GEMINI_API_KEY", "GOOGLE_API_KEY", "GROQ_API_KEY")
-
-
-def _no_provider_keys(monkeypatch) -> None:
-    """A real aiui server runs startup hooks; keep them from calling paid APIs."""
-    for key in _PROVIDER_KEYS:
-        monkeypatch.delenv(key, raising=False)
-
-
-def _free_port() -> int:
-    with socket.socket() as s:
-        s.bind(("127.0.0.1", 0))
-        return s.getsockname()[1]
-
-
-@pytest.fixture()
-def live_server(tmp_path, monkeypatch):
-    import uvicorn
-
-    import praisonaiui.server as server
-    from praisonaiui.features import approvals
-    from praisonaiui.features.replay import configure_replay_app
-
-    traces = tmp_path / "traces"
-    traces.mkdir()
-    for name in ("team_handoff", "flow_parallel_loop"):
-        shutil.copy(FIXTURES / f"{name}.jsonl", traces / f"{name}.jsonl")
-    lines = (FIXTURES / "team_handoff.jsonl").read_text(encoding="utf-8").splitlines(keepends=True)
-    cut = next(i for i, line in enumerate(lines) if '"approval_decided"' in line)
-    live = traces / "live-team.jsonl"
-    live.write_text("".join(lines[:cut]), encoding="utf-8")
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(traces))
-    monkeypatch.setenv("AIUI_DATA_DIR", str(tmp_path / "aiui-data"))
-    monkeypatch.setenv("PRAISONAI_HOME", str(tmp_path / "praisonai-home"))
-    _no_provider_keys(monkeypatch)
-    store = approvals.SimpleApprovalManager()
-    monkeypatch.setattr(approvals, "_approval_manager", store)
-
-    server.reset_state()
-    configure_replay_app()
-    app = server.create_app()
-    port = _free_port()
-    srv = uvicorn.Server(uvicorn.Config(app, host="127.0.0.1", port=port, log_level="warning"))
-    t = threading.Thread(target=srv.run, daemon=True)
-    t.start()
-    for _ in range(100):
-        if srv.started:
-            break
-        time.sleep(0.05)
-    yield {"url": f"http://127.0.0.1:{port}", "store": store, "live": live, "lines": lines, "cut": cut}
-    srv.should_exit = True
-    t.join(timeout=5)
-    server.reset_state()
-
-
-def test_dashboard_live_run_and_approval(browser, live_server):
-    pytest.importorskip("praisonaiagents.approval.protocols")
-    from praisonaiagents.approval.protocols import ApprovalRequest
-
-    from praisonaiui.features.approvals import _UIStoreBackend
-
-    store = live_server["store"]
-    backend = _UIStoreBackend(store, timeout=30)
-    box = {}
-    req = ApprovalRequest(tool_name="write_file", arguments={"path": "draft.md", "content": "hello"},
-                          risk_level="high", agent_name="Writer", approval_id="appr-0001")
-    t = threading.Thread(target=lambda: box.setdefault("d", backend.request_approval_sync(req)), daemon=True)
-    t.start()
-
-    page, errors = _page(browser)
-    page.goto(f"{live_server['url']}/#/replay?run=live-team")
-    page.wait_for_selector(".rp-run")
-    assert page.evaluate("location.pathname + location.search") == "/replay?run=live-team"
-    assert page.locator(".rp-run[aria-current='true']").inner_text().startswith("Solar sail brief")
-    assert page.locator(".rp-badge.rp-b-live").count() >= 1
-
-    card = page.locator(".rp-ask")
-    card.wait_for()
-    assert "Writer asks to run write_file" in card.inner_text()
-    page.get_by_role("button", name="Edit arguments…").click()
-    ta = page.locator(".rp-ask textarea")
-    ta.wait_for()
-    assert json.loads(ta.input_value()) == {"path": "draft.md", "content": "hello"}  # server-held args, not redacted
-    ta.fill("{not json")
-    assert ta.get_attribute("aria-invalid") == "true"
-    assert "Not valid JSON" in page.locator(".rp-ask .rp-err").inner_text()
-    ta.fill('{"path": "docs/draft.md", "content": "hello"}')
-    assert ta.get_attribute("aria-invalid") == "false"
-    violations = _axe(page)
-    assert violations == [], json.dumps(violations, indent=2)
-    page.get_by_role("button", name="Approve with these arguments").click()
-    t.join(timeout=10)
-    decision = box["d"]
-    assert decision.approved is True
-    assert decision.modified_args == {"path": "docs/draft.md", "content": "hello"}
-    page.locator(".rp-ask [role='status']").wait_for()
-
-    # the run continues: the rest of the file streams in over SSE
-    with open(live_server["live"], "a", encoding="utf-8") as fh:
-        fh.write("".join(live_server["lines"][live_server["cut"]:]))
-    page.wait_for_selector(".rp-step:has-text('You approved write_file')", timeout=10000)
-    page.wait_for_selector(".rp-step:has-text('Recording ended.')", timeout=10000)
-    assert page.locator(".rp-ask").count() == 0
-    page.wait_for_selector(".rp-bar .rp-b-completed", timeout=15000)
-    assert not [e for e in errors if "favicon" not in e], errors
-
-
-def test_empty_state_explains_how_to_record(browser, tmp_path, monkeypatch):
-    import uvicorn
-
-    import praisonaiui.server as server
-    from praisonaiui.features.replay import configure_replay_app
-
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(tmp_path / "empty"))
-    monkeypatch.setenv("AIUI_DATA_DIR", str(tmp_path / "aiui-data"))
-    monkeypatch.setenv("PRAISONAI_HOME", str(tmp_path / "praisonai-home"))
-    _no_provider_keys(monkeypatch)
-    server.reset_state()
-    configure_replay_app()
-    app = server.create_app()
-    port = _free_port()
-    srv = uvicorn.Server(uvicorn.Config(app, host="127.0.0.1", port=port, log_level="warning"))
-    th = threading.Thread(target=srv.run, daemon=True)
-    th.start()
-    try:
-        for _ in range(100):
-            if srv.started:
-                break
-            time.sleep(0.05)
-        page, _ = _page(browser)
-        page.goto(f"http://127.0.0.1:{port}/")
-        page.wait_for_selector(".rp-empty")
-        text = page.locator(".rp-empty").inner_text()
-        assert "praisonai replay view agents.yaml" in text
-        assert "with record(live=True):" in text
-        violations = _axe(page)
-        assert violations == [], json.dumps(violations, indent=2)
-    finally:
-        srv.should_exit = True
-        th.join(timeout=5)
-        server.reset_state()
-
-
-def test_embedded_run_box_draws_each_step_live_then_plays_back(browser, tmp_path, monkeypatch):
-    """create_replay_app(run=...) mounted in a host app: Run, watch the map, then Play."""
-    import uvicorn
-    from starlette.applications import Starlette
-    from starlette.routing import Mount
-
-    from praisonaiui.features.replay import create_replay_app
-
-    traces = tmp_path / "traces"
-    traces.mkdir()
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(traces))
-    lines = (FIXTURES / "flow_parallel_loop.jsonl").read_text(encoding="utf-8").splitlines(keepends=True)
-    seen = []
-
-    def runner(text, run_id):  # writes a recorded flow slowly, like a live run
-        seen.append(text)
-        with open(traces / f"{run_id}.jsonl", "w", encoding="utf-8") as fh:
-            for line in lines:
-                fh.write(line)
-                fh.flush()
-                time.sleep(0.08)
-
-    host = Starlette(routes=[Mount("/replay", app=create_replay_app(runner, input="weekly digest"))])
-    port = _free_port()
-    srv = uvicorn.Server(uvicorn.Config(host, host="127.0.0.1", port=port, log_level="warning"))
-    t = threading.Thread(target=srv.run, daemon=True)
-    t.start()
-    for _ in range(100):
-        if srv.started:
-            break
-        time.sleep(0.05)
-    try:
-        page, errors = _page(browser)
-        page.add_init_script("try{localStorage.setItem('rp-view','map')}catch(e){}")
-        page.goto(f"http://127.0.0.1:{port}/replay/")
-        page.wait_for_selector(".rp-empty h2:has-text('Nothing has run yet')")
-        page.get_by_role("button", name="▶ Run").click()
-        page.wait_for_selector(".rp-node.rp-st-running", timeout=10000)  # a step is drawn as running
-        assert page.locator(".rp-node.rp-unvisited").count() > 0  # later steps not reached yet
-        page.wait_for_selector(".rp-bar .rp-b-completed", timeout=20000)
-        assert seen == ["weekly digest"]
-        assert page.locator(".rp-node.rp-st-running").count() == 0
-        assert page.get_by_role("button", name="▶ Run").is_enabled()
-        page.get_by_role("button", name="▶ Play").click()  # from the end: restarts at step 1
-        page.wait_for_timeout(1300)
-        assert page.locator("[data-key=play]").inner_text() == "❚❚ Pause"
-        assert page.locator(".rp-node.rp-unvisited").count() > 0  # the map rewound with the cursor
-        page.locator("[data-key=play]").click()
-        violations = _axe(page)
-        assert violations == [], json.dumps(violations, indent=2)
-        assert not errors, errors
-    finally:
-        srv.should_exit = True
-        t.join(timeout=5)
@@ -1,42 +0,0 @@
-{"schema_version":"1.1","event_type":"session_start","timestamp":1767225600.0,"session_id":"sess-flow-01","agent_name":"","sequence_num":0,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01"}
-{"schema_version":"1.1","event_type":"workflow_start","timestamp":1767225600.02,"session_id":"sess-flow-01","agent_name":"","sequence_num":1,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"kind":"flow","name":"Weekly digest","process":"flow","graph":{"schema":"praisonai.graph/1","kind":"flow","name":"Weekly digest","process":"flow","nodes":[{"id":"start:begin","kind":"start","label":"Brief","parent":null,"meta":{}},{"id":"step:plan","kind":"step","label":"plan","parent":null,"meta":{"agent":"Planner"}},{"id":"step:gather","kind":"fork","label":"gather","parent":null,"meta":{"pattern":"parallel"}},{"id":"step:news","kind":"step","label":"news","parent":"step:gather","meta":{"agent":"Fetcher"}},{"id":"step:papers","kind":"step","label":"papers","parent":"step:gather","meta":{"agent":"Fetcher"}},{"id":"step:merge","kind":"join","label":"merge","parent":null,"meta":{}},{"id":"step:review_loop","kind":"step","label":"review_loop","parent":null,"meta":{"pattern":"loop"}},{"id":"step:polish","kind":"step","label":"polish","parent":"step:review_loop","meta":{"agent":"Editor"}},{"id":"step:decide","kind":"decision","label":"decide","parent":null,"meta":{"pattern":"route"}},{"id":"step:publish","kind":"step","label":"publish","parent":null,"meta":{"agent":"Publisher"}},{"id":"step:archive","kind":"step","label":"archive","parent":null,"meta":{}},{"id":"end:done","kind":"end","label":"Delivered","parent":null,"meta":{}}],"edges":[{"id":"start:begin->step:plan:next","source":"start:begin","target":"step:plan","kind":"next","label":null},{"id":"step:plan->step:gather:next","source":"step:plan","target":"step:gather","kind":"next","label":null},{"id":"step:gather->step:news:parallel","source":"step:gather","target":"step:news","kind":"parallel","label":null},{"id":"step:gather->step:papers:parallel","source":"step:gather","target":"step:papers","kind":"parallel","label":null},{"id":"step:news->step:merge:next","source":"step:news","target":"step:merge","kind":"next","label":null},{"id":"step:papers->step:merge:next","source":"step:papers","target":"step:merge","kind":"next","label":null},{"id":"step:merge->step:review_loop:next","source":"step:merge","target":"step:review_loop","kind":"next","label":null},{"id":"step:review_loop->step:polish:loop","source":"step:review_loop","target":"step:polish","kind":"loop","label":"until approved"},{"id":"step:polish->step:review_loop:loop","source":"step:polish","target":"step:review_loop","kind":"loop","label":null},{"id":"step:review_loop->step:decide:next","source":"step:review_loop","target":"step:decide","kind":"next","label":null},{"id":"step:decide->step:publish:routes","source":"step:decide","target":"step:publish","kind":"routes","label":"publish"},{"id":"step:decide->step:archive:routes","source":"step:decide","target":"step:archive","kind":"routes","label":"archive"},{"id":"step:publish->end:done:next","source":"step:publish","target":"end:done","kind":"next","label":null},{"id":"step:archive->end:done:next","source":"step:archive","target":"end:done","kind":"next","label":null}]}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":0}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225600.05,"session_id":"sess-flow-01","agent_name":"Planner","sequence_num":2,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"plan"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1,"node_id":"step:plan"}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225600.06,"session_id":"sess-flow-01","agent_name":"Planner","sequence_num":3,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":2,"node_id":"agent:Planner"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225600.1,"session_id":"sess-flow-01","agent_name":"Planner","sequence_num":4,"messages_count":3,"tokens_used":150,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":3,"node_id":"agent:Planner"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225600.9,"session_id":"sess-flow-01","agent_name":"Planner","sequence_num":5,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":60,"duration_ms":800.0,"finish_reason":"stop","model":"gpt-4o-mini"},"prompt_tokens":150,"completion_tokens":60,"cost_usd":5.9e-05,"run_id":"flow-loop-01","parent_seq":3,"node_id":"agent:Planner"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225600.95,"session_id":"sess-flow-01","agent_name":"Planner","sequence_num":6,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":3,"node_id":"agent:Planner"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225601.0,"session_id":"sess-flow-01","agent_name":"Planner","sequence_num":7,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":950.0,"output_preview":"Gather news and papers."},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":2,"node_id":"step:plan"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225601.05,"session_id":"sess-flow-01","agent_name":"","sequence_num":8,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"gather","pattern":"parallel"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1,"node_id":"step:gather"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225601.1,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":9,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"news"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/0","run_id":"flow-loop-01","parent_seq":8,"node_id":"step:news"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225601.1,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":10,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"papers"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/1","run_id":"flow-loop-01","parent_seq":8,"node_id":"step:papers"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225601.15,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":11,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"fetch_rss","tool_args":{"url":"https://example.org/news.rss"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/0","run_id":"flow-loop-01","parent_seq":9,"node_id":"tool:Fetcher/fetch_rss"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225601.16,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":12,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"search_papers","tool_args":{"query":"agent tracing"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/1","run_id":"flow-loop-01","parent_seq":10,"node_id":"tool:Fetcher/search_papers"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225602.4,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":13,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"fetch_rss","result":"12 items","duration_ms":1250.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/0","run_id":"flow-loop-01","parent_seq":11,"node_id":"tool:Fetcher/fetch_rss"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225603.0,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":14,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"search_papers","result":"5 papers","duration_ms":1840.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.001,"branch_id":"gather/1","run_id":"flow-loop-01","parent_seq":12,"node_id":"tool:Fetcher/search_papers"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225602.45,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":15,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":1350.0,"output_preview":"12 items"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/0","run_id":"flow-loop-01","parent_seq":9,"node_id":"step:news"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225603.05,"session_id":"sess-flow-01","agent_name":"Fetcher","sequence_num":16,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":1950.0,"output_preview":"5 papers"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"branch_id":"gather/1","run_id":"flow-loop-01","parent_seq":10,"node_id":"step:papers"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225603.1,"session_id":"sess-flow-01","agent_name":"","sequence_num":17,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":2050.0},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":8,"node_id":"step:gather"}
-{"schema_version":"1.1","event_type":"context_rebalance","timestamp":1767225603.12,"session_id":"sess-flow-01","agent_name":"","sequence_num":18,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"note":"future event type"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1,"future_field":{"x":1}}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225603.15,"session_id":"sess-flow-01","agent_name":"","sequence_num":19,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"review_loop","pattern":"loop"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1,"node_id":"step:review_loop"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225603.2,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":20,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"polish","iteration":1},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":19,"node_id":"step:polish"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225603.22,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":21,"messages_count":3,"tokens_used":400,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":20,"node_id":"agent:Editor"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225603.92,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":22,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":90,"duration_ms":700.0,"finish_reason":"stop","model":"gpt-4o-mini"},"prompt_tokens":400,"completion_tokens":90,"cost_usd":0.000114,"run_id":"flow-loop-01","parent_seq":20,"node_id":"agent:Editor"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225603.95,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":23,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":750.0,"output_preview":"Draft v2"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":20,"node_id":"step:polish"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225604.0,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":24,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"polish","iteration":2},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":19,"node_id":"step:polish"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225604.02,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":25,"messages_count":3,"tokens_used":450,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":24,"node_id":"agent:Editor"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225604.72,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":26,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":90,"duration_ms":700.0,"finish_reason":"stop","model":"gpt-4o-mini"},"prompt_tokens":450,"completion_tokens":90,"cost_usd":0.00012150000000000001,"run_id":"flow-loop-01","parent_seq":24,"node_id":"agent:Editor"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225604.75,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":27,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":750.0,"output_preview":"Draft v3"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":24,"node_id":"step:polish"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225604.8,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":28,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"polish","iteration":3},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":19,"node_id":"step:polish"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225604.82,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":29,"messages_count":3,"tokens_used":500,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":28,"node_id":"agent:Editor"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225605.52,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":30,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":90,"duration_ms":700.0,"finish_reason":"stop","model":"gpt-4o-mini"},"prompt_tokens":500,"completion_tokens":90,"cost_usd":0.00012900000000000002,"run_id":"flow-loop-01","parent_seq":28,"node_id":"agent:Editor"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225605.55,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":31,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":750.0,"output_preview":"Draft v4"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":28,"node_id":"step:polish"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225605.6,"session_id":"sess-flow-01","agent_name":"","sequence_num":32,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":2450.0},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":19,"node_id":"step:review_loop"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225605.65,"session_id":"sess-flow-01","agent_name":"","sequence_num":33,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"decide","pattern":"route"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1,"node_id":"step:decide"}
-{"schema_version":"1.1","event_type":"agent_handoff","timestamp":1767225605.7,"session_id":"sess-flow-01","agent_name":"Editor","sequence_num":34,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"from_agent":"Editor","to_agent":"Publisher","kind":"route","reason":"Draft approved by reviewer score 0.92","context_passed":{"score":0.92}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":33,"node_id":"step:decide"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225605.75,"session_id":"sess-flow-01","agent_name":"","sequence_num":35,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":100.0,"route":"publish"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":33,"node_id":"step:decide"}
-{"schema_version":"1.1","event_type":"step_start","timestamp":1767225605.8,"session_id":"sess-flow-01","agent_name":"Publisher","sequence_num":36,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"publish"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1,"node_id":"step:publish"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225605.85,"session_id":"sess-flow-01","agent_name":"Publisher","sequence_num":37,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"post_to_blog","tool_args":{"title":"Weekly digest"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":36,"node_id":"tool:Publisher/post_to_blog"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225606.45,"session_id":"sess-flow-01","agent_name":"Publisher","sequence_num":38,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"post_to_blog","result":"posted /digest/42","duration_ms":600.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":37,"node_id":"tool:Publisher/post_to_blog"}
-{"schema_version":"1.1","event_type":"step_end","timestamp":1767225606.5,"session_id":"sess-flow-01","agent_name":"Publisher","sequence_num":39,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":700.0,"output_preview":"posted"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":36,"node_id":"step:publish"}
-{"schema_version":"1.1","event_type":"workflow_end","timestamp":1767225606.55,"session_id":"sess-flow-01","agent_name":"","sequence_num":40,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":6530.0},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":1}
-{"schema_version":"1.1","event_type":"session_end","timestamp":1767225606.6,"session_id":"sess-flow-01","agent_name":"","sequence_num":41,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"flow-loop-01","parent_seq":0}
@@ -1,16 +0,0 @@
-{"schema_version":"1.0","event_type":"session_start","timestamp":1767225600.0,"session_id":"legacy-sess-10","agent_name":"","sequence_num":0,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"agent_start","timestamp":1767225600.1,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":1,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"role":"Assistant"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"message_added","timestamp":1767225600.15,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":2,"messages_count":1,"tokens_used":0,"tokens_budget":0,"data":{"role":"user","content":"What is 17 * 23?"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"llm_request","timestamp":1767225600.2,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":3,"messages_count":3,"tokens_used":90,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"llm_response","timestamp":1767225600.7,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":4,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":20,"duration_ms":500.0,"finish_reason":"tool_calls","model":"gpt-4o-mini"},"prompt_tokens":90,"completion_tokens":20,"cost_usd":2.6e-05,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"tool_call_start","timestamp":1767225600.75,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":5,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"calculator","tool_args":{"expression":"17*23"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"tool_call_end","timestamp":1767225600.76,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":6,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"calculator","result":"391","duration_ms":10.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"llm_request","timestamp":1767225600.8,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":7,"messages_count":3,"tokens_used":130,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"llm_response","timestamp":1767225601.2,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":8,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":12,"duration_ms":400.0,"finish_reason":"stop","model":"gpt-4o-mini"},"prompt_tokens":130,"completion_tokens":12,"cost_usd":2.7e-05,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"agent_handoff","timestamp":1767225601.25,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":9,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"from_agent":"Assistant","to_agent":"Checker","reason":"Double-check the arithmetic","context_passed":{"answer":391}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"agent_end","timestamp":1767225601.26,"session_id":"legacy-sess-10","agent_name":"Assistant","sequence_num":10,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"agent_start","timestamp":1767225601.3,"session_id":"legacy-sess-10","agent_name":"Checker","sequence_num":11,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"role":"Checker"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"llm_request","timestamp":1767225601.35,"session_id":"legacy-sess-10","agent_name":"Checker","sequence_num":12,"messages_count":3,"tokens_used":60,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"llm_response","timestamp":1767225601.8,"session_id":"legacy-sess-10","agent_name":"Checker","sequence_num":13,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":8,"duration_ms":450.0,"finish_reason":"stop","model":"gpt-4o-mini"},"prompt_tokens":60,"completion_tokens":8,"cost_usd":1.4e-05,"parent_seq":null,"node_id":null}
-{"schema_version":"1.0","event_type":"agent_end","timestamp":1767225601.85,"session_id":"legacy-sess-10","agent_name":"Checker","sequence_num":14,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
-{"schema_version":"1.0","event_type":"session_end","timestamp":1767225601.9,"session_id":"legacy-sess-10","agent_name":"","sequence_num":15,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0}
@@ -1,388 +0,0 @@
-"""Regenerate the PraisonAI Replay JSONL fixtures (contract v1, schema 1.1 + 1.0).
-
-Run from the repo root::
-
-    python tests/fixtures/replay/make_fixtures.py
-
-The output is deterministic (fixed timestamps, no uuids) so the files are
-committed and the tests compare against exact values.
-"""
-
-from __future__ import annotations
-
-import json
-from pathlib import Path
-
-HERE = Path(__file__).resolve().parent
-T0 = 1767225600.0  # 2026-01-01T00:00:00Z
-
-
-class _Run:
-    """Tiny emitter that mimics ContextTraceEmitter's to_dict() output."""
-
-    def __init__(self, session_id: str, run_id: str | None, schema: str = "1.1") -> None:
-        self.session_id = session_id
-        self.run_id = run_id
-        self.schema = schema
-        self.seq = 0
-        self.events: list[dict] = []
-
-    def emit(self, event_type: str, t: float, agent: str = "", data: dict | None = None, **kw) -> int:
-        ev = {
-            "schema_version": self.schema,
-            "event_type": event_type,
-            "timestamp": round(T0 + t, 3),
-            "session_id": self.session_id,
-            "agent_name": agent,
-            "sequence_num": self.seq,
-            "messages_count": kw.pop("messages_count", 0),
-            "tokens_used": kw.pop("tokens_used", 0),
-            "tokens_budget": kw.pop("tokens_budget", 0),
-            "data": data or {},
-            "prompt_tokens": kw.pop("prompt_tokens", 0),
-            "completion_tokens": kw.pop("completion_tokens", 0),
-            "cost_usd": kw.pop("cost_usd", 0.0),
-        }
-        for key in ("branch_id", "content_hash"):
-            if kw.get(key) is not None:
-                ev[key] = kw.pop(key)
-            else:
-                kw.pop(key, None)
-        if self.schema != "1.0":
-            if self.run_id:
-                ev["run_id"] = self.run_id
-            for key in ("parent_seq", "node_id"):
-                if kw.get(key) is not None:
-                    ev[key] = kw.pop(key)
-                else:
-                    kw.pop(key, None)
-        ev.update(kw)  # unknown/extra fields pass straight through
-        self.events.append(ev)
-        self.seq += 1
-        return ev["sequence_num"]
-
-    def llm(self, t: float, agent: str, dur: float, parent: int | None, *, prompt: int, completion: int,
-            cost: float, model: str = "gpt-4o-mini", finish: str = "stop", content: str = "",
-            branch: str | None = None, node: str | None = None) -> None:
-        self.emit("llm_request", t, agent, {"model": model}, parent_seq=parent, messages_count=3,
-                  tokens_used=prompt, tokens_budget=128000, branch_id=branch, node_id=node)
-        data = {"response_tokens": completion, "duration_ms": round(dur * 1000, 1),
-                "finish_reason": finish, "model": model}
-        if content:
-            data["response_content"] = content
-        self.emit("llm_response", t + dur, agent, data, parent_seq=parent, prompt_tokens=prompt,
-                  completion_tokens=completion, cost_usd=cost, branch_id=branch, node_id=node)
-
-    def tool(self, t: float, agent: str, name: str, args: dict, dur: float, parent: int | None, *,
-             result: str, cost: float = 0.0, error: str | None = None, branch: str | None = None) -> None:
-        node = f"tool:{agent}/{name}" if self.schema != "1.0" else None
-        s = self.emit("tool_call_start", t, agent, {"tool_name": name, "tool_args": args},
-                      parent_seq=parent, node_id=node, branch_id=branch)
-        self.emit("tool_call_end", t + dur, agent,
-                  {"tool_name": name, "result": result, "duration_ms": round(dur * 1000, 1), "error": error},
-                  parent_seq=s if self.schema != "1.0" else None, node_id=node, cost_usd=cost, branch_id=branch)
-
-    def write(self, name: str, *, partial_tail: str | None = None) -> None:
-        path = HERE / name
-        with open(path, "w", encoding="utf-8", newline="\n") as fh:
-            for ev in self.events:
-                fh.write(json.dumps(ev, separators=(",", ":")) + "\n")
-            if partial_tail:
-                fh.write(partial_tail)
-        print(f"wrote {path.name}: {len(self.events)} events")
-
-
-def team_handoff() -> None:
-    """Hierarchical 2-agent team: Manager delegates, Researcher hands off to Writer.
-
-    Researcher calls web_search three times in a row (collapses to x3); Writer
-    asks for approval to run write_file, the human approves with edited args.
-    """
-    r = _Run("sess-team-01", "team-handoff-01")
-    graph = {
-        "schema": "praisonai.graph/1", "kind": "team", "name": "Solar sail brief", "process": "hierarchical",
-        "nodes": [
-            {"id": "start:begin", "kind": "start", "label": "Brief", "parent": None, "meta": {}},
-            {"id": "manager:Manager", "kind": "manager", "label": "Manager", "parent": None, "meta": {}},
-            {"id": "task:research", "kind": "task", "label": "research", "parent": None, "meta": {}},
-            {"id": "task:write", "kind": "task", "label": "write", "parent": None, "meta": {}},
-            {"id": "agent:Researcher", "kind": "agent", "label": "Researcher", "parent": None, "meta": {}},
-            {"id": "agent:Writer", "kind": "agent", "label": "Writer", "parent": None, "meta": {}},
-            {"id": "tool:Researcher/web_search", "kind": "tool", "label": "web_search", "parent": None, "meta": {}},
-            {"id": "tool:Writer/write_file", "kind": "tool", "label": "write_file", "parent": None, "meta": {}},
-            {"id": "human:you", "kind": "human", "label": "You", "parent": None, "meta": {}},
-            {"id": "end:done", "kind": "end", "label": "Delivered", "parent": None, "meta": {}},
-        ],
-        "edges": [
-            {"id": "start:begin->manager:Manager:next", "source": "start:begin", "target": "manager:Manager", "kind": "next", "label": None},
-            {"id": "manager:Manager->task:research:delegates", "source": "manager:Manager", "target": "task:research", "kind": "delegates", "label": None},
-            {"id": "manager:Manager->task:write:delegates", "source": "manager:Manager", "target": "task:write", "kind": "delegates", "label": None},
-            {"id": "task:write->task:research:depends_on", "source": "task:write", "target": "task:research", "kind": "depends_on", "label": None},
-            {"id": "task:research->agent:Researcher:assigned", "source": "task:research", "target": "agent:Researcher", "kind": "assigned", "label": None},
-            {"id": "task:write->agent:Writer:assigned", "source": "task:write", "target": "agent:Writer", "kind": "assigned", "label": None},
-            {"id": "agent:Researcher->agent:Writer:handoff", "source": "agent:Researcher", "target": "agent:Writer", "kind": "handoff", "label": None},
-            {"id": "agent:Researcher->tool:Researcher/web_search:uses", "source": "agent:Researcher", "target": "tool:Researcher/web_search", "kind": "uses", "label": None},
-            {"id": "agent:Writer->tool:Writer/write_file:uses", "source": "agent:Writer", "target": "tool:Writer/write_file", "kind": "uses", "label": None},
-            {"id": "human:you->tool:Writer/write_file:reviews", "source": "human:you", "target": "tool:Writer/write_file", "kind": "reviews", "label": None},
-            {"id": "agent:Writer->end:done:next", "source": "agent:Writer", "target": "end:done", "kind": "next", "label": None},
-        ],
-    }
-    s0 = r.emit("session_start", 0.0, "", {"source": "record"})
-    w = r.emit("workflow_start", 0.05, "", {"kind": "team", "name": "Solar sail brief", "process": "hierarchical",
-                                           "graph": graph}, parent_seq=s0)
-    r.emit("message_added", 0.1, "", {"role": "user", "content": "Write a short brief on solar sails."}, parent_seq=w)
-    r.llm(0.2, "Manager", 0.6, w, prompt=210, completion=48, cost=0.000060, node="manager:Manager",
-          content="Delegate research first, then writing.")
-    r.emit("agent_handoff", 0.85, "Manager", {
-        "from_agent": "Manager", "to_agent": "Researcher", "kind": "delegate",
-        "reason": "Research has to come before writing.",
-        "context_passed": {"task_snapshot": {"task": "research", "description": "Find three facts about solar sails",
-                                             "expected_output": "3 bullet facts", "status": "not started"}},
-    }, parent_seq=w, node_id="manager:Manager")
-    t1 = r.emit("task_start", 0.9, "Researcher", {"name": "research", "agent": "Researcher",
-                                                  "description_preview": "Find three facts about solar sails"},
-                parent_seq=w, node_id="task:research")
-    a1 = r.emit("agent_start", 0.95, "Researcher", {"role": "Researcher", "goal": "Find facts"},
-                parent_seq=t1, node_id="agent:Researcher")
-    r.emit("message_added", 1.0, "Researcher", {"role": "user", "content": "Find three facts about solar sails"},
-           parent_seq=a1)
-    r.llm(1.05, "Researcher", 0.9, a1, prompt=320, completion=40, cost=0.000072, finish="tool_calls",
-          node="agent:Researcher")
-    r.tool(2.0, "Researcher", "web_search", {"query": "solar sail facts"}, 1.2, a1,
-           result="IKAROS (2010) was the first interplanetary solar sail.", cost=0.002)
-    r.tool(3.25, "Researcher", "web_search", {"query": "solar sail missions"}, 1.1, a1,
-           result="LightSail 2 raised its orbit using sunlight in 2019.", cost=0.002)
-    r.tool(4.4, "Researcher", "web_search", {"query": "solar sail physics"}, 0.9, a1,
-           result="Photon pressure at 1 AU is about 9 micronewtons per square metre.", cost=0.002)
-    r.llm(5.35, "Researcher", 1.4, a1, prompt=880, completion=160, cost=0.000228, node="agent:Researcher",
-          content="1. IKAROS ... 2. LightSail 2 ... 3. ~9 uN/m^2")
-    r.emit("agent_end", 6.8, "Researcher", {"status": "completed"}, parent_seq=a1, node_id="agent:Researcher")
-    r.emit("task_end", 6.85, "Researcher", {"status": "completed", "retries": 0, "duration_ms": 5950.0,
-                                             "output_preview": "1. IKAROS ... 2. LightSail 2 ... 3. ~9 uN/m^2"},
-           parent_seq=t1, node_id="task:research")
-    r.emit("agent_handoff", 6.9, "Researcher", {
-        "from_agent": "Researcher", "to_agent": "Writer", "kind": "handoff",
-        "reason": "Facts gathered; needs drafting.",
-        "context_passed": {"facts": ["IKAROS 2010", "LightSail 2 2019", "~9 uN/m^2 at 1 AU"]},
-    }, parent_seq=w, node_id="agent:Researcher")
-    t2 = r.emit("task_start", 6.95, "Writer", {"name": "write", "agent": "Writer",
-                                               "description_preview": "Draft a 100-word brief into draft.md"},
-                parent_seq=w, node_id="task:write")
-    a2 = r.emit("agent_start", 7.0, "Writer", {"role": "Writer"}, parent_seq=t2, node_id="agent:Writer")
-    r.llm(7.05, "Writer", 1.6, a2, prompt=640, completion=220, cost=0.000228, finish="tool_calls",
-          node="agent:Writer")
-    ap = r.emit("approval_requested", 8.7, "Writer", {
-        "approval_id": "appr-0001", "tool": "write_file",
-        "args": {"path": "draft.md", "content": "[REDACTED]"}, "risk": "high", "kind": "tool_call",
-    }, parent_seq=a2, node_id="tool:Writer/write_file")
-    r.emit("approval_decided", 11.2, "", {
-        "approval_id": "appr-0001", "approved": True, "reason": "Use the docs folder.",
-        "approver": "user", "modified": True,
-    }, parent_seq=ap, node_id="tool:Writer/write_file")
-    r.tool(11.25, "Writer", "write_file", {"path": "docs/draft.md", "content": "[REDACTED]"}, 0.05, a2,
-           result="Wrote 642 bytes to docs/draft.md")
-    r.llm(11.35, "Writer", 0.7, a2, prompt=900, completion=30, cost=0.000153, node="agent:Writer",
-          content="Saved the brief to docs/draft.md.")
-    r.emit("agent_end", 12.1, "Writer", {"status": "completed"}, parent_seq=a2, node_id="agent:Writer")
-    r.emit("task_end", 12.15, "Writer", {"status": "completed", "retries": 0, "duration_ms": 5200.0,
-                                          "output_preview": "Saved the brief to docs/draft.md."},
-           parent_seq=t2, node_id="task:write")
-    r.emit("workflow_end", 12.2, "", {"status": "completed", "duration_ms": 12150.0}, parent_seq=w)
-    r.emit("session_end", 12.25, "", {}, parent_seq=s0)
-    r.write("team_handoff.jsonl")
-
-
-def flow_parallel_loop() -> None:
-    """AgentFlow: plan -> parallel(gather news, papers) -> loop(polish x3) -> route(decide) -> publish.
-
-    Both parallel branches run the same agent (Fetcher) so they must appear as
-    two sub-lanes. Includes an unknown event type and an unknown field to prove
-    readers tolerate them.
-    """
-    r = _Run("sess-flow-01", "flow-loop-01")
-    graph = {
-        "schema": "praisonai.graph/1", "kind": "flow", "name": "Weekly digest", "process": "flow",
-        "nodes": [
-            {"id": "start:begin", "kind": "start", "label": "Brief", "parent": None, "meta": {}},
-            {"id": "step:plan", "kind": "step", "label": "plan", "parent": None, "meta": {"agent": "Planner"}},
-            {"id": "step:gather", "kind": "fork", "label": "gather", "parent": None, "meta": {"pattern": "parallel"}},
-            {"id": "step:news", "kind": "step", "label": "news", "parent": "step:gather", "meta": {"agent": "Fetcher"}},
-            {"id": "step:papers", "kind": "step", "label": "papers", "parent": "step:gather", "meta": {"agent": "Fetcher"}},
-            {"id": "step:merge", "kind": "join", "label": "merge", "parent": None, "meta": {}},
-            {"id": "step:review_loop", "kind": "step", "label": "review_loop", "parent": None, "meta": {"pattern": "loop"}},
-            {"id": "step:polish", "kind": "step", "label": "polish", "parent": "step:review_loop", "meta": {"agent": "Editor"}},
-            {"id": "step:decide", "kind": "decision", "label": "decide", "parent": None, "meta": {"pattern": "route"}},
-            {"id": "step:publish", "kind": "step", "label": "publish", "parent": None, "meta": {"agent": "Publisher"}},
-            {"id": "step:archive", "kind": "step", "label": "archive", "parent": None, "meta": {}},
-            {"id": "end:done", "kind": "end", "label": "Delivered", "parent": None, "meta": {}},
-        ],
-        "edges": [
-            {"id": "start:begin->step:plan:next", "source": "start:begin", "target": "step:plan", "kind": "next", "label": None},
-            {"id": "step:plan->step:gather:next", "source": "step:plan", "target": "step:gather", "kind": "next", "label": None},
-            {"id": "step:gather->step:news:parallel", "source": "step:gather", "target": "step:news", "kind": "parallel", "label": None},
-            {"id": "step:gather->step:papers:parallel", "source": "step:gather", "target": "step:papers", "kind": "parallel", "label": None},
-            {"id": "step:news->step:merge:next", "source": "step:news", "target": "step:merge", "kind": "next", "label": None},
-            {"id": "step:papers->step:merge:next", "source": "step:papers", "target": "step:merge", "kind": "next", "label": None},
-            {"id": "step:merge->step:review_loop:next", "source": "step:merge", "target": "step:review_loop", "kind": "next", "label": None},
-            {"id": "step:review_loop->step:polish:loop", "source": "step:review_loop", "target": "step:polish", "kind": "loop", "label": "until approved"},
-            {"id": "step:polish->step:review_loop:loop", "source": "step:polish", "target": "step:review_loop", "kind": "loop", "label": None},
-            {"id": "step:review_loop->step:decide:next", "source": "step:review_loop", "target": "step:decide", "kind": "next", "label": None},
-            {"id": "step:decide->step:publish:routes", "source": "step:decide", "target": "step:publish", "kind": "routes", "label": "publish"},
-            {"id": "step:decide->step:archive:routes", "source": "step:decide", "target": "step:archive", "kind": "routes", "label": "archive"},
-            {"id": "step:publish->end:done:next", "source": "step:publish", "target": "end:done", "kind": "next", "label": None},
-            {"id": "step:archive->end:done:next", "source": "step:archive", "target": "end:done", "kind": "next", "label": None},
-        ],
-    }
-    s0 = r.emit("session_start", 0.0, "", {})
-    w = r.emit("workflow_start", 0.02, "", {"kind": "flow", "name": "Weekly digest", "process": "flow",
-                                           "graph": graph}, parent_seq=s0)
-    sp = r.emit("step_start", 0.05, "Planner", {"name": "plan"}, parent_seq=w, node_id="step:plan")
-    a = r.emit("agent_start", 0.06, "Planner", {}, parent_seq=sp, node_id="agent:Planner")
-    r.llm(0.1, "Planner", 0.8, a, prompt=150, completion=60, cost=0.000059, node="agent:Planner")
-    r.emit("agent_end", 0.95, "Planner", {}, parent_seq=a, node_id="agent:Planner")
-    r.emit("step_end", 1.0, "Planner", {"status": "completed", "duration_ms": 950.0,
-                                         "output_preview": "Gather news and papers."}, parent_seq=sp, node_id="step:plan")
-    g = r.emit("step_start", 1.05, "", {"name": "gather", "pattern": "parallel"}, parent_seq=w, node_id="step:gather")
-    # two branches interleaved in time, same agent
-    b0 = r.emit("step_start", 1.1, "Fetcher", {"name": "news"}, parent_seq=g, node_id="step:news", branch_id="gather/0")
-    b1 = r.emit("step_start", 1.1, "Fetcher", {"name": "papers"}, parent_seq=g, node_id="step:papers", branch_id="gather/1")
-    r.emit("tool_call_start", 1.15, "Fetcher", {"tool_name": "fetch_rss", "tool_args": {"url": "https://example.org/news.rss"}},
-           parent_seq=b0, node_id="tool:Fetcher/fetch_rss", branch_id="gather/0")
-    r.emit("tool_call_start", 1.16, "Fetcher", {"tool_name": "search_papers", "tool_args": {"query": "agent tracing"}},
-           parent_seq=b1, node_id="tool:Fetcher/search_papers", branch_id="gather/1")
-    r.emit("tool_call_end", 2.4, "Fetcher", {"tool_name": "fetch_rss", "result": "12 items", "duration_ms": 1250.0, "error": None},
-           parent_seq=r.seq - 2, node_id="tool:Fetcher/fetch_rss", branch_id="gather/0")
-    r.emit("tool_call_end", 3.0, "Fetcher", {"tool_name": "search_papers", "result": "5 papers", "duration_ms": 1840.0, "error": None},
-           parent_seq=r.seq - 2, node_id="tool:Fetcher/search_papers", branch_id="gather/1", cost_usd=0.001)
-    r.emit("step_end", 2.45, "Fetcher", {"status": "completed", "duration_ms": 1350.0, "output_preview": "12 items"},
-           parent_seq=b0, node_id="step:news", branch_id="gather/0")
-    r.emit("step_end", 3.05, "Fetcher", {"status": "completed", "duration_ms": 1950.0, "output_preview": "5 papers"},
-           parent_seq=b1, node_id="step:papers", branch_id="gather/1")
-    r.emit("step_end", 3.1, "", {"status": "completed", "duration_ms": 2050.0}, parent_seq=g, node_id="step:gather")
-    # an event type this reader has never heard of, plus an unknown field
-    r.emit("context_rebalance", 3.12, "", {"note": "future event type"}, parent_seq=w, future_field={"x": 1})
-    lp = r.emit("step_start", 3.15, "", {"name": "review_loop", "pattern": "loop"}, parent_seq=w, node_id="step:review_loop")
-    t = 3.2
-    for i in range(3):
-        ps = r.emit("step_start", t, "Editor", {"name": "polish", "iteration": i + 1}, parent_seq=lp, node_id="step:polish")
-        r.llm(t + 0.02, "Editor", 0.7, ps, prompt=400 + 50 * i, completion=90, cost=0.000114 + 0.0000075 * i,
-              node="agent:Editor")
-        r.emit("step_end", t + 0.75, "Editor", {"status": "completed", "duration_ms": 750.0,
-                                                 "output_preview": f"Draft v{i + 2}"}, parent_seq=ps, node_id="step:polish")
-        t += 0.8
-    r.emit("step_end", t, "", {"status": "completed", "duration_ms": round((t - 3.15) * 1000, 1)},
-           parent_seq=lp, node_id="step:review_loop")
-    d = r.emit("step_start", t + 0.05, "", {"name": "decide", "pattern": "route"}, parent_seq=w, node_id="step:decide")
-    r.emit("agent_handoff", t + 0.1, "Editor", {"from_agent": "Editor", "to_agent": "Publisher", "kind": "route",
-                                                "reason": "Draft approved by reviewer score 0.92",
-                                                "context_passed": {"score": 0.92}}, parent_seq=d, node_id="step:decide")
-    r.emit("step_end", t + 0.15, "", {"status": "completed", "duration_ms": 100.0, "route": "publish"},
-           parent_seq=d, node_id="step:decide")
-    pb = r.emit("step_start", t + 0.2, "Publisher", {"name": "publish"}, parent_seq=w, node_id="step:publish")
-    r.tool(t + 0.25, "Publisher", "post_to_blog", {"title": "Weekly digest"}, 0.6, pb, result="posted /digest/42")
-    r.emit("step_end", t + 0.9, "Publisher", {"status": "completed", "duration_ms": 700.0, "output_preview": "posted"},
-           parent_seq=pb, node_id="step:publish")
-    r.emit("workflow_end", t + 0.95, "", {"status": "completed", "duration_ms": round((t + 0.93) * 1000, 1)}, parent_seq=w)
-    r.emit("session_end", t + 1.0, "", {}, parent_seq=s0)
-    r.write("flow_parallel_loop.jsonl")
-
-
-def legacy_v10() -> None:
-    """A schema 1.0 file: no run_id, parent_seq, node_id; no workflow events."""
-    r = _Run("legacy-sess-10", None, schema="1.0")
-    r.emit("session_start", 0.0, "", {})
-    r.emit("agent_start", 0.1, "Assistant", {"role": "Assistant"})
-    r.emit("message_added", 0.15, "Assistant", {"role": "user", "content": "What is 17 * 23?"}, messages_count=1)
-    r.llm(0.2, "Assistant", 0.5, None, prompt=90, completion=20, cost=0.000026, finish="tool_calls")
-    r.tool(0.75, "Assistant", "calculator", {"expression": "17*23"}, 0.01, None, result="391")
-    r.llm(0.8, "Assistant", 0.4, None, prompt=130, completion=12, cost=0.000027)
-    r.emit("agent_handoff", 1.25, "Assistant", {"from_agent": "Assistant", "to_agent": "Checker",
-                                                "reason": "Double-check the arithmetic", "context_passed": {"answer": 391}})
-    r.emit("agent_end", 1.26, "Assistant", {})
-    r.emit("agent_start", 1.3, "Checker", {"role": "Checker"})
-    r.llm(1.35, "Checker", 0.45, None, prompt=60, completion=8, cost=0.000014)
-    r.emit("agent_end", 1.85, "Checker", {})
-    r.emit("session_end", 1.9, "", {})
-    r.write("legacy_v10.jsonl")
-
-
-def team_outside() -> None:
-    """Shape of a real recorded run: each agent's LLM span encloses its tool
-    calls (llm_request -> tool -> llm_response), and after the team finishes a
-    Triage agent hands off to Billing, neither of which is in the team graph.
-    """
-    r = _Run("sess-outside-01", "team-outside-01")
-    graph = {
-        "schema": "praisonai.graph/1", "kind": "team", "name": "EV brief", "process": "sequential",
-        "nodes": [
-            {"id": "start:begin", "kind": "start", "label": "Brief", "parent": None, "meta": {}},
-            {"id": "task:research", "kind": "task", "label": "research", "parent": None, "meta": {}},
-            {"id": "task:write", "kind": "task", "label": "write", "parent": None, "meta": {}},
-            {"id": "agent:Researcher", "kind": "agent", "label": "Researcher", "parent": None, "meta": {}},
-            {"id": "agent:Writer", "kind": "agent", "label": "Writer", "parent": None, "meta": {}},
-            {"id": "tool:Researcher/lookup_fact", "kind": "tool", "label": "lookup_fact", "parent": None, "meta": {}},
-            {"id": "end:done", "kind": "end", "label": "Delivered", "parent": None, "meta": {}},
-        ],
-        "edges": [
-            {"id": "start:begin->task:research:next", "source": "start:begin", "target": "task:research", "kind": "next", "label": None},
-            {"id": "task:research->task:write:next", "source": "task:research", "target": "task:write", "kind": "next", "label": None},
-            {"id": "task:research->agent:Researcher:assigned", "source": "task:research", "target": "agent:Researcher", "kind": "assigned", "label": None},
-            {"id": "task:write->agent:Writer:assigned", "source": "task:write", "target": "agent:Writer", "kind": "assigned", "label": None},
-            {"id": "agent:Researcher->tool:Researcher/lookup_fact:uses", "source": "agent:Researcher", "target": "tool:Researcher/lookup_fact", "kind": "uses", "label": None},
-            {"id": "task:write->end:done:next", "source": "task:write", "target": "end:done", "kind": "next", "label": None},
-        ],
-    }
-    s0 = r.emit("session_start", 0.0, "", {})
-    w = r.emit("workflow_start", 0.01, "", {"kind": "team", "name": "EV brief", "process": "sequential", "graph": graph}, parent_seq=s0)
-    t1 = r.emit("task_start", 0.02, "Researcher", {"name": "research", "agent": "Researcher",
-                                                   "description_preview": "Get one fact about electric vehicles"},
-                parent_seq=w, node_id="task:research")
-    a1 = r.emit("agent_start", 0.03, "Researcher", {}, parent_seq=t1, node_id="agent:Researcher")
-    r.emit("llm_request", 0.05, "Researcher", {"model": "gpt-4o-mini"}, parent_seq=a1, node_id="agent:Researcher")
-    ts = r.emit("tool_call_start", 2.6, "Researcher", {"tool_name": "lookup_fact", "tool_args": {"topic": "electric vehicles"}},
-                parent_seq=a1, node_id="tool:Researcher/lookup_fact")
-    r.emit("tool_call_end", 3.5, "Researcher", {"tool_name": "lookup_fact", "result": "EV sales passed 17 million in 2024",
-                                                 "duration_ms": 880.0, "error": None},
-           parent_seq=ts, node_id="tool:Researcher/lookup_fact")
-    r.emit("llm_response", 5.0, "Researcher", {"response_tokens": 14, "duration_ms": 4950.0, "model": "gpt-4o-mini",
-                                                "response_content": "EV sales passed 17 million in 2024."},
-           parent_seq=a1, node_id="agent:Researcher", prompt_tokens=310, completion_tokens=14, cost_usd=0.000055)
-    r.emit("agent_end", 5.01, "Researcher", {}, parent_seq=a1, node_id="agent:Researcher")
-    r.emit("task_end", 5.02, "Researcher", {"status": "completed", "retries": 0, "duration_ms": 5000.0,
-                                             "output_preview": "EV sales passed 17 million in 2024."}, parent_seq=t1, node_id="task:research")
-    t2 = r.emit("task_start", 5.03, "Writer", {"name": "write", "agent": "Writer",
-                                               "description_preview": "Write one sentence using the fact"},
-                parent_seq=w, node_id="task:write")
-    a2 = r.emit("agent_start", 5.04, "Writer", {}, parent_seq=t2, node_id="agent:Writer")
-    r.llm(5.05, "Writer", 1.05, a2, prompt=200, completion=25, cost=0.000045, node="agent:Writer",
-          content="Global EV sales passed 17 million in 2024.")
-    r.emit("agent_end", 6.11, "Writer", {}, parent_seq=a2, node_id="agent:Writer")
-    r.emit("task_end", 6.12, "Writer", {"status": "completed", "retries": 0, "duration_ms": 1090.0,
-                                         "output_preview": "Global EV sales passed 17 million in 2024."}, parent_seq=t2, node_id="task:write")
-    r.emit("workflow_end", 6.13, "", {"status": "completed", "duration_ms": 6120.0}, parent_seq=w)
-    a3 = r.emit("agent_start", 6.2, "Triage", {}, parent_seq=s0, node_id="agent:Triage")
-    r.emit("llm_request", 6.25, "Triage", {"model": "gpt-4o-mini"}, parent_seq=a3, node_id="agent:Triage")
-    tt = r.emit("tool_call_start", 7.7, "Triage", {"tool_name": "transfer_to_billing", "tool_args": {}},
-                parent_seq=a3, node_id="tool:Triage/transfer_to_billing")
-    r.emit("agent_handoff", 7.71, "Triage", {"from_agent": "Triage", "to_agent": "Billing", "kind": "handoff",
-                                             "reason": "Billing question", "context_passed": {"context_policy": "summary"}},
-           parent_seq=tt, node_id="agent:Billing")
-    a4 = r.emit("agent_start", 7.72, "Billing", {}, parent_seq=tt, node_id="agent:Billing")
-    r.llm(7.75, "Billing", 0.92, a4, prompt=150, completion=19, cost=0.00003, node="agent:Billing",
-          content="Please check your statement for a duplicate charge.")
-    r.emit("agent_end", 8.68, "Billing", {}, parent_seq=a4, node_id="agent:Billing")
-    r.emit("tool_call_end", 8.7, "Triage", {"tool_name": "transfer_to_billing", "result": "Handoff successful",
-                                             "duration_ms": 1000.0, "error": None},
-           parent_seq=tt, node_id="tool:Triage/transfer_to_billing")
-    r.emit("llm_response", 9.6, "Triage", {"response_tokens": 22, "duration_ms": 3350.0, "model": "gpt-4o-mini"},
-           parent_seq=a3, node_id="agent:Triage", prompt_tokens=240, completion_tokens=22, cost_usd=0.00005)
-    r.emit("agent_end", 9.61, "Triage", {}, parent_seq=a3, node_id="agent:Triage")
-    r.emit("session_end", 9.7, "", {}, parent_seq=s0)
-    r.write("team_outside.jsonl")
-
-
-if __name__ == "__main__":
-    team_handoff()
-    flow_parallel_loop()
-    legacy_v10()
-    team_outside()
@@ -1,36 +0,0 @@
-{"schema_version":"1.1","event_type":"session_start","timestamp":1767225600.0,"session_id":"sess-team-01","agent_name":"","sequence_num":0,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"source":"record"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01"}
-{"schema_version":"1.1","event_type":"workflow_start","timestamp":1767225600.05,"session_id":"sess-team-01","agent_name":"","sequence_num":1,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"kind":"team","name":"Solar sail brief","process":"hierarchical","graph":{"schema":"praisonai.graph/1","kind":"team","name":"Solar sail brief","process":"hierarchical","nodes":[{"id":"start:begin","kind":"start","label":"Brief","parent":null,"meta":{}},{"id":"manager:Manager","kind":"manager","label":"Manager","parent":null,"meta":{}},{"id":"task:research","kind":"task","label":"research","parent":null,"meta":{}},{"id":"task:write","kind":"task","label":"write","parent":null,"meta":{}},{"id":"agent:Researcher","kind":"agent","label":"Researcher","parent":null,"meta":{}},{"id":"agent:Writer","kind":"agent","label":"Writer","parent":null,"meta":{}},{"id":"tool:Researcher/web_search","kind":"tool","label":"web_search","parent":null,"meta":{}},{"id":"tool:Writer/write_file","kind":"tool","label":"write_file","parent":null,"meta":{}},{"id":"human:you","kind":"human","label":"You","parent":null,"meta":{}},{"id":"end:done","kind":"end","label":"Delivered","parent":null,"meta":{}}],"edges":[{"id":"start:begin->manager:Manager:next","source":"start:begin","target":"manager:Manager","kind":"next","label":null},{"id":"manager:Manager->task:research:delegates","source":"manager:Manager","target":"task:research","kind":"delegates","label":null},{"id":"manager:Manager->task:write:delegates","source":"manager:Manager","target":"task:write","kind":"delegates","label":null},{"id":"task:write->task:research:depends_on","source":"task:write","target":"task:research","kind":"depends_on","label":null},{"id":"task:research->agent:Researcher:assigned","source":"task:research","target":"agent:Researcher","kind":"assigned","label":null},{"id":"task:write->agent:Writer:assigned","source":"task:write","target":"agent:Writer","kind":"assigned","label":null},{"id":"agent:Researcher->agent:Writer:handoff","source":"agent:Researcher","target":"agent:Writer","kind":"handoff","label":null},{"id":"agent:Researcher->tool:Researcher/web_search:uses","source":"agent:Researcher","target":"tool:Researcher/web_search","kind":"uses","label":null},{"id":"agent:Writer->tool:Writer/write_file:uses","source":"agent:Writer","target":"tool:Writer/write_file","kind":"uses","label":null},{"id":"human:you->tool:Writer/write_file:reviews","source":"human:you","target":"tool:Writer/write_file","kind":"reviews","label":null},{"id":"agent:Writer->end:done:next","source":"agent:Writer","target":"end:done","kind":"next","label":null}]}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":0}
-{"schema_version":"1.1","event_type":"message_added","timestamp":1767225600.1,"session_id":"sess-team-01","agent_name":"","sequence_num":2,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"role":"user","content":"Write a short brief on solar sails."},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225600.2,"session_id":"sess-team-01","agent_name":"Manager","sequence_num":3,"messages_count":3,"tokens_used":210,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1,"node_id":"manager:Manager"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225600.8,"session_id":"sess-team-01","agent_name":"Manager","sequence_num":4,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":48,"duration_ms":600.0,"finish_reason":"stop","model":"gpt-4o-mini","response_content":"Delegate research first, then writing."},"prompt_tokens":210,"completion_tokens":48,"cost_usd":6e-05,"run_id":"team-handoff-01","parent_seq":1,"node_id":"manager:Manager"}
-{"schema_version":"1.1","event_type":"agent_handoff","timestamp":1767225600.85,"session_id":"sess-team-01","agent_name":"Manager","sequence_num":5,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"from_agent":"Manager","to_agent":"Researcher","kind":"delegate","reason":"Research has to come before writing.","context_passed":{"task_snapshot":{"task":"research","description":"Find three facts about solar sails","expected_output":"3 bullet facts","status":"not started"}}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1,"node_id":"manager:Manager"}
-{"schema_version":"1.1","event_type":"task_start","timestamp":1767225600.9,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":6,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"research","agent":"Researcher","description_preview":"Find three facts about solar sails"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1,"node_id":"task:research"}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225600.95,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":7,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"role":"Researcher","goal":"Find facts"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":6,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"message_added","timestamp":1767225601.0,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":8,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"role":"user","content":"Find three facts about solar sails"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225601.05,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":9,"messages_count":3,"tokens_used":320,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225601.95,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":10,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":40,"duration_ms":900.0,"finish_reason":"tool_calls","model":"gpt-4o-mini"},"prompt_tokens":320,"completion_tokens":40,"cost_usd":7.2e-05,"run_id":"team-handoff-01","parent_seq":7,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225602.0,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":11,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"web_search","tool_args":{"query":"solar sail facts"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7,"node_id":"tool:Researcher/web_search"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225603.2,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":12,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"web_search","result":"IKAROS (2010) was the first interplanetary solar sail.","duration_ms":1200.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.002,"run_id":"team-handoff-01","parent_seq":11,"node_id":"tool:Researcher/web_search"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225603.25,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":13,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"web_search","tool_args":{"query":"solar sail missions"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7,"node_id":"tool:Researcher/web_search"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225604.35,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":14,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"web_search","result":"LightSail 2 raised its orbit using sunlight in 2019.","duration_ms":1100.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.002,"run_id":"team-handoff-01","parent_seq":13,"node_id":"tool:Researcher/web_search"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225604.4,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":15,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"web_search","tool_args":{"query":"solar sail physics"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7,"node_id":"tool:Researcher/web_search"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225605.3,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":16,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"web_search","result":"Photon pressure at 1 AU is about 9 micronewtons per square metre.","duration_ms":900.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.002,"run_id":"team-handoff-01","parent_seq":15,"node_id":"tool:Researcher/web_search"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225605.35,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":17,"messages_count":3,"tokens_used":880,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225606.75,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":18,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":160,"duration_ms":1400.0,"finish_reason":"stop","model":"gpt-4o-mini","response_content":"1. IKAROS ... 2. LightSail 2 ... 3. ~9 uN/m^2"},"prompt_tokens":880,"completion_tokens":160,"cost_usd":0.000228,"run_id":"team-handoff-01","parent_seq":7,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225606.8,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":19,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":7,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"task_end","timestamp":1767225606.85,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":20,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","retries":0,"duration_ms":5950.0,"output_preview":"1. IKAROS ... 2. LightSail 2 ... 3. ~9 uN/m^2"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":6,"node_id":"task:research"}
-{"schema_version":"1.1","event_type":"agent_handoff","timestamp":1767225606.9,"session_id":"sess-team-01","agent_name":"Researcher","sequence_num":21,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"from_agent":"Researcher","to_agent":"Writer","kind":"handoff","reason":"Facts gathered; needs drafting.","context_passed":{"facts":["IKAROS 2010","LightSail 2 2019","~9 uN/m^2 at 1 AU"]}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"task_start","timestamp":1767225606.95,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":22,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"write","agent":"Writer","description_preview":"Draft a 100-word brief into draft.md"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1,"node_id":"task:write"}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225607.0,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":23,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"role":"Writer"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":22,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225607.05,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":24,"messages_count":3,"tokens_used":640,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":23,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225608.65,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":25,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":220,"duration_ms":1600.0,"finish_reason":"tool_calls","model":"gpt-4o-mini"},"prompt_tokens":640,"completion_tokens":220,"cost_usd":0.000228,"run_id":"team-handoff-01","parent_seq":23,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"approval_requested","timestamp":1767225608.7,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":26,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"approval_id":"appr-0001","tool":"write_file","args":{"path":"draft.md","content":"[REDACTED]"},"risk":"high","kind":"tool_call"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":23,"node_id":"tool:Writer/write_file"}
-{"schema_version":"1.1","event_type":"approval_decided","timestamp":1767225611.2,"session_id":"sess-team-01","agent_name":"","sequence_num":27,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"approval_id":"appr-0001","approved":true,"reason":"Use the docs folder.","approver":"user","modified":true},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":26,"node_id":"tool:Writer/write_file"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225611.25,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":28,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"write_file","tool_args":{"path":"docs/draft.md","content":"[REDACTED]"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":23,"node_id":"tool:Writer/write_file"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225611.3,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":29,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"write_file","result":"Wrote 642 bytes to docs/draft.md","duration_ms":50.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":28,"node_id":"tool:Writer/write_file"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225611.35,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":30,"messages_count":3,"tokens_used":900,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":23,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225612.05,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":31,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":30,"duration_ms":700.0,"finish_reason":"stop","model":"gpt-4o-mini","response_content":"Saved the brief to docs/draft.md."},"prompt_tokens":900,"completion_tokens":30,"cost_usd":0.000153,"run_id":"team-handoff-01","parent_seq":23,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225612.1,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":32,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":23,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"task_end","timestamp":1767225612.15,"session_id":"sess-team-01","agent_name":"Writer","sequence_num":33,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","retries":0,"duration_ms":5200.0,"output_preview":"Saved the brief to docs/draft.md."},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":22,"node_id":"task:write"}
-{"schema_version":"1.1","event_type":"workflow_end","timestamp":1767225612.2,"session_id":"sess-team-01","agent_name":"","sequence_num":34,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":12150.0},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":1}
-{"schema_version":"1.1","event_type":"session_end","timestamp":1767225612.25,"session_id":"sess-team-01","agent_name":"","sequence_num":35,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-handoff-01","parent_seq":0}
@@ -1,29 +0,0 @@
-{"schema_version":"1.1","event_type":"session_start","timestamp":1767225600.0,"session_id":"sess-outside-01","agent_name":"","sequence_num":0,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01"}
-{"schema_version":"1.1","event_type":"workflow_start","timestamp":1767225600.01,"session_id":"sess-outside-01","agent_name":"","sequence_num":1,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"kind":"team","name":"EV brief","process":"sequential","graph":{"schema":"praisonai.graph/1","kind":"team","name":"EV brief","process":"sequential","nodes":[{"id":"start:begin","kind":"start","label":"Brief","parent":null,"meta":{}},{"id":"task:research","kind":"task","label":"research","parent":null,"meta":{}},{"id":"task:write","kind":"task","label":"write","parent":null,"meta":{}},{"id":"agent:Researcher","kind":"agent","label":"Researcher","parent":null,"meta":{}},{"id":"agent:Writer","kind":"agent","label":"Writer","parent":null,"meta":{}},{"id":"tool:Researcher/lookup_fact","kind":"tool","label":"lookup_fact","parent":null,"meta":{}},{"id":"end:done","kind":"end","label":"Delivered","parent":null,"meta":{}}],"edges":[{"id":"start:begin->task:research:next","source":"start:begin","target":"task:research","kind":"next","label":null},{"id":"task:research->task:write:next","source":"task:research","target":"task:write","kind":"next","label":null},{"id":"task:research->agent:Researcher:assigned","source":"task:research","target":"agent:Researcher","kind":"assigned","label":null},{"id":"task:write->agent:Writer:assigned","source":"task:write","target":"agent:Writer","kind":"assigned","label":null},{"id":"agent:Researcher->tool:Researcher/lookup_fact:uses","source":"agent:Researcher","target":"tool:Researcher/lookup_fact","kind":"uses","label":null},{"id":"task:write->end:done:next","source":"task:write","target":"end:done","kind":"next","label":null}]}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":0}
-{"schema_version":"1.1","event_type":"task_start","timestamp":1767225600.02,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":2,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"research","agent":"Researcher","description_preview":"Get one fact about electric vehicles"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":1,"node_id":"task:research"}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225600.03,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":3,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":2,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225600.05,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":4,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":3,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225602.6,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":5,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"lookup_fact","tool_args":{"topic":"electric vehicles"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":3,"node_id":"tool:Researcher/lookup_fact"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225603.5,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":6,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"lookup_fact","result":"EV sales passed 17 million in 2024","duration_ms":880.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":5,"node_id":"tool:Researcher/lookup_fact"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225605.0,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":7,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":14,"duration_ms":4950.0,"model":"gpt-4o-mini","response_content":"EV sales passed 17 million in 2024."},"prompt_tokens":310,"completion_tokens":14,"cost_usd":5.5e-05,"run_id":"team-outside-01","parent_seq":3,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225605.01,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":8,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":3,"node_id":"agent:Researcher"}
-{"schema_version":"1.1","event_type":"task_end","timestamp":1767225605.02,"session_id":"sess-outside-01","agent_name":"Researcher","sequence_num":9,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","retries":0,"duration_ms":5000.0,"output_preview":"EV sales passed 17 million in 2024."},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":2,"node_id":"task:research"}
-{"schema_version":"1.1","event_type":"task_start","timestamp":1767225605.03,"session_id":"sess-outside-01","agent_name":"Writer","sequence_num":10,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"name":"write","agent":"Writer","description_preview":"Write one sentence using the fact"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":1,"node_id":"task:write"}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225605.04,"session_id":"sess-outside-01","agent_name":"Writer","sequence_num":11,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":10,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225605.05,"session_id":"sess-outside-01","agent_name":"Writer","sequence_num":12,"messages_count":3,"tokens_used":200,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":11,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225606.1,"session_id":"sess-outside-01","agent_name":"Writer","sequence_num":13,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":25,"duration_ms":1050.0,"finish_reason":"stop","model":"gpt-4o-mini","response_content":"Global EV sales passed 17 million in 2024."},"prompt_tokens":200,"completion_tokens":25,"cost_usd":4.5e-05,"run_id":"team-outside-01","parent_seq":11,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225606.11,"session_id":"sess-outside-01","agent_name":"Writer","sequence_num":14,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":11,"node_id":"agent:Writer"}
-{"schema_version":"1.1","event_type":"task_end","timestamp":1767225606.12,"session_id":"sess-outside-01","agent_name":"Writer","sequence_num":15,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","retries":0,"duration_ms":1090.0,"output_preview":"Global EV sales passed 17 million in 2024."},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":10,"node_id":"task:write"}
-{"schema_version":"1.1","event_type":"workflow_end","timestamp":1767225606.13,"session_id":"sess-outside-01","agent_name":"","sequence_num":16,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"status":"completed","duration_ms":6120.0},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":1}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225606.2,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":17,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":0,"node_id":"agent:Triage"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225606.25,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":18,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":17,"node_id":"agent:Triage"}
-{"schema_version":"1.1","event_type":"tool_call_start","timestamp":1767225607.7,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":19,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"transfer_to_billing","tool_args":{}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":17,"node_id":"tool:Triage/transfer_to_billing"}
-{"schema_version":"1.1","event_type":"agent_handoff","timestamp":1767225607.71,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":20,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"from_agent":"Triage","to_agent":"Billing","kind":"handoff","reason":"Billing question","context_passed":{"context_policy":"summary"}},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":19,"node_id":"agent:Billing"}
-{"schema_version":"1.1","event_type":"agent_start","timestamp":1767225607.72,"session_id":"sess-outside-01","agent_name":"Billing","sequence_num":21,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":19,"node_id":"agent:Billing"}
-{"schema_version":"1.1","event_type":"llm_request","timestamp":1767225607.75,"session_id":"sess-outside-01","agent_name":"Billing","sequence_num":22,"messages_count":3,"tokens_used":150,"tokens_budget":128000,"data":{"model":"gpt-4o-mini"},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":21,"node_id":"agent:Billing"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225608.67,"session_id":"sess-outside-01","agent_name":"Billing","sequence_num":23,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":19,"duration_ms":920.0,"finish_reason":"stop","model":"gpt-4o-mini","response_content":"Please check your statement for a duplicate charge."},"prompt_tokens":150,"completion_tokens":19,"cost_usd":3e-05,"run_id":"team-outside-01","parent_seq":21,"node_id":"agent:Billing"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225608.68,"session_id":"sess-outside-01","agent_name":"Billing","sequence_num":24,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":21,"node_id":"agent:Billing"}
-{"schema_version":"1.1","event_type":"tool_call_end","timestamp":1767225608.7,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":25,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"tool_name":"transfer_to_billing","result":"Handoff successful","duration_ms":1000.0,"error":null},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":19,"node_id":"tool:Triage/transfer_to_billing"}
-{"schema_version":"1.1","event_type":"llm_response","timestamp":1767225609.6,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":26,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{"response_tokens":22,"duration_ms":3350.0,"model":"gpt-4o-mini"},"prompt_tokens":240,"completion_tokens":22,"cost_usd":5e-05,"run_id":"team-outside-01","parent_seq":17,"node_id":"agent:Triage"}
-{"schema_version":"1.1","event_type":"agent_end","timestamp":1767225609.61,"session_id":"sess-outside-01","agent_name":"Triage","sequence_num":27,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":17,"node_id":"agent:Triage"}
-{"schema_version":"1.1","event_type":"session_end","timestamp":1767225609.7,"session_id":"sess-outside-01","agent_name":"","sequence_num":28,"messages_count":0,"tokens_used":0,"tokens_budget":0,"data":{},"prompt_tokens":0,"completion_tokens":0,"cost_usd":0.0,"run_id":"team-outside-01","parent_seq":0}
@@ -1,509 +0,0 @@
-// node --test tests/js/replay-core.test.mjs
-// Pure-function tests for the PraisonAI Replay model (no DOM, no network).
-import { test } from 'node:test';
-import assert from 'node:assert/strict';
-import fs from 'node:fs';
-import path from 'node:path';
-import { fileURLToPath, pathToFileURL } from 'node:url';
-
-const here = path.dirname(fileURLToPath(import.meta.url));
-const root = path.resolve(here, '..', '..');
-const coreUrl = pathToFileURL(path.join(root, 'src/praisonaiui/templates/frontend/plugins/views/replay-core.js'));
-const core = await import(coreUrl.href);
-const { buildModel, narrate, layoutMap, deriveGraph, formatCost, formatDuration } = core;
-
-function load(name) {
-  const text = fs.readFileSync(path.join(root, 'tests/fixtures/replay', `${name}.jsonl`), 'utf8');
-  const events = text.split('\n').filter(Boolean).map((l) => JSON.parse(l));
-  const ws = events.find((e) => e.event_type === 'workflow_start');
-  return { events, graph: ws && ws.data && ws.data.graph ? ws.data.graph : null };
-}
-
-// ── buildModel: lanes ────────────────────────────────────────────────
-
-test('team run: You and Manager lanes come first, agents follow graph order', () => {
-  const { events, graph } = load('team_handoff');
-  const m = buildModel(events, graph);
-  assert.deepEqual(m.lanes.map((l) => l.id), ['human:you', 'manager:Manager', 'agent:Researcher', 'agent:Writer']);
-  assert.deepEqual(m.lanes.map((l) => l.shape), ['diamond', 'square', 'circle', 'circle']);
-  assert.equal(m.lanes[0].label, 'You');
-});
-
-test('parallel branches of one agent become sub-lanes labelled by step', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  const m = buildModel(events, graph);
-  const subs = m.lanes.filter((l) => l.parent === 'agent:Fetcher');
-  assert.deepEqual(subs.map((l) => [l.id, l.branch, l.label]), [
-    ['agent:Fetcher#gather/0', 'gather/0', 'news'],
-    ['agent:Fetcher#gather/1', 'gather/1', 'papers'],
-  ]);
-  const tools = m.blocks.filter((b) => b.kind === 'tool' && b.agent === 'Fetcher');
-  assert.deepEqual(tools.map((b) => b.lane), ['agent:Fetcher#gather/0', 'agent:Fetcher#gather/1']);
-  // the two branches overlap in time: that is why they need their own rows
-  assert.ok(tools[1].start < tools[0].end);
-});
-
-test('a 1.0 legacy file still yields lanes, blocks and a hand-off', () => {
-  const { events } = load('legacy_v10');
-  const m = buildModel(events, null);
-  assert.deepEqual(m.lanes.map((l) => l.id), ['human:you', 'agent:Assistant', 'agent:Checker']);
-  assert.deepEqual(m.blocks.map((b) => `${b.kind}:${b.label}`), ['llm:gpt-4o-mini', 'tool:calculator', 'llm:gpt-4o-mini', 'llm:gpt-4o-mini']);
-  assert.equal(m.arrows.length, 1);
-  assert.equal(m.arrows[0].kind, 'handoff');
-  assert.equal(m.chapters.length, 0);
-});
-
-// ── buildModel: arrows ───────────────────────────────────────────────
-
-test('delegate and hand-off arrows connect the right lanes', () => {
-  const { events, graph } = load('team_handoff');
-  const m = buildModel(events, graph);
-  const flows = m.arrows.map((a) => `${a.kind}:${a.from}->${a.to}`);
-  assert.deepEqual(flows, [
-    'delegate:manager:Manager->agent:Researcher',
-    'handoff:agent:Researcher->agent:Writer',
-    'ask:agent:Writer->human:you',
-    'answer:human:you->agent:Writer',
-  ]);
-  assert.equal(m.arrows[0].label, 'delegates');
-  assert.equal(m.arrows[3].label, 'approved');
-});
-
-test('route arrows from a flow', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  const m = buildModel(events, graph);
-  assert.deepEqual(m.arrows.map((a) => [a.kind, a.from, a.to]), [['route', 'agent:Editor', 'agent:Publisher']]);
-});
-
-// ── buildModel: xN collapse ──────────────────────────────────────────
-
-test('three consecutive web_search calls collapse to one block x3', () => {
-  const { events, graph } = load('team_handoff');
-  const m = buildModel(events, graph);
-  const ws = m.blocks.filter((b) => b.label === 'web_search');
-  assert.equal(ws.length, 1);
-  assert.equal(ws[0].count, 3);
-  assert.equal(ws[0].members.length, 3);
-  assert.ok(Math.abs(ws[0].cost - 0.006) < 1e-9);
-  assert.ok(Math.abs(ws[0].durationMs - 3200) < 1e-6);
-  // every member's events map to the collapsed block
-  const lines = m.narration.filter((n) => n.text.includes('web_search'));
-  assert.equal(lines.length, 3);
-  assert.ok(lines.every((n) => n.blockId === ws[0].id));
-});
-
-test('loop passes collapse: polish chapter x3 and Editor LLM block x3', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  const m = buildModel(events, graph);
-  const polish = m.chapters.filter((c) => c.nodeId === 'step:polish');
-  assert.equal(polish.length, 1);
-  assert.equal(polish[0].count, 3);
-  assert.equal(polish[0].depth, 1);
-  const editor = m.blocks.filter((b) => b.agent === 'Editor');
-  assert.equal(editor.length, 1);
-  assert.equal(editor[0].count, 3);
-  assert.equal(editor[0].tokens, 490 + 540 + 590);
-});
-
-test('non-adjacent repeats are not collapsed', () => {
-  const { events, graph } = load('team_handoff');
-  const m = buildModel(events, graph);
-  const researcherLlm = m.blocks.filter((b) => b.agent === 'Researcher' && b.kind === 'llm');
-  assert.equal(researcherLlm.length, 2); // llm, tool x3, llm
-  assert.ok(researcherLlm.every((b) => b.count === 1));
-});
-
-// ── buildModel: chapters, approvals, totals, live ────────────────────
-
-test('chapters carry depth, rows and the chosen route', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  const m = buildModel(events, graph);
-  const byNode = Object.fromEntries(m.chapters.map((c) => [c.nodeId, c]));
-  assert.equal(byNode['step:gather'].depth, 0);
-  assert.equal(byNode['step:news'].depth, 1);
-  assert.notEqual(byNode['step:news'].row, byNode['step:papers'].row); // overlapping -> own rows
-  assert.equal(byNode['step:decide'].route, 'publish');
-  assert.equal(m.chapterRows, 3);
-});
-
-test('approval sits in the You lane with its decision', () => {
-  const { events, graph } = load('team_handoff');
-  const m = buildModel(events, graph);
-  const ap = m.blocks.find((b) => b.kind === 'approval');
-  assert.equal(ap.lane, 'human:you');
-  assert.equal(ap.status, 'approved');
-  assert.equal(ap.approvalId, 'appr-0001');
-  assert.equal(m.pending.length, 0);
-});
-
-test('a run cut before the decision has one pending approval and open blocks', () => {
-  const { events, graph } = load('team_handoff');
-  const cut = events.slice(0, events.findIndex((e) => e.event_type === 'approval_decided'));
-  const m = buildModel(cut, graph);
-  assert.equal(m.pending.length, 1);
-  assert.equal(m.pending[0].approvalId, 'appr-0001');
-  assert.equal(m.pending[0].open, true);
-  const half = events.slice(0, events.findIndex((e) => e.event_type === 'tool_call_end'));
-  const m2 = buildModel(half, graph);
-  const running = m2.blocks.find((b) => b.kind === 'tool');
-  assert.equal(running.open, true);
-  assert.equal(running.status, 'running');
-  assert.match(m2.narration.at(-1).text, /^Researcher is asking web_search for 'solar sail facts'…$/);
-});
-
-test('totals per agent and for the run', () => {
-  const { events, graph } = load('team_handoff');
-  const m = buildModel(events, graph);
-  assert.equal(m.totals.llm_calls, 5);
-  assert.equal(m.totals.tool_calls, 4);
-  assert.ok(Math.abs(m.totals.cost_usd - 0.006741) < 1e-9);
-  const r = m.totals.agents['agent:Researcher'];
-  assert.ok(Math.abs(r.cost_usd - (0.000072 + 0.006 + 0.000228)) < 1e-9);
-  assert.equal(r.tool_calls, 3);
-  assert.ok(Math.abs(m.totals.duration_ms - 12250) < 1e-6);
-});
-
-test('sub-lane work rolls up to the parent agent total', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  const m = buildModel(events, graph);
-  const f = m.totals.agents['agent:Fetcher'];
-  assert.equal(f.tool_calls, 2);
-  assert.ok(Math.abs(f.cost_usd - 0.001) < 1e-9);
-  assert.equal(m.totals.agents['agent:Fetcher#gather/0'], undefined);
-});
-
-test('unknown event types and fields are tolerated and skipped', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  assert.ok(events.some((e) => e.event_type === 'context_rebalance'));
-  const m = buildModel(events, graph);
-  assert.ok(!m.narration.some((n) => n.type === 'context_rebalance'));
-  assert.equal(m.events.length, events.length);
-});
-
-test('duplicates (same session:seq, e.g. after an SSE reconnect) are dropped; order follows sequence_num', () => {
-  const { events, graph } = load('legacy_v10');
-  const shuffled = [...events].reverse().concat(events.slice(0, 3));
-  const m = buildModel(shuffled, graph);
-  assert.equal(m.events.length, events.length);
-  assert.deepEqual(m.events.map((e) => e.sequence_num), events.map((e) => e.sequence_num));
-});
-
-test('empty input is fine', () => {
-  const m = buildModel([], null);
-  assert.equal(m.blocks.length, 0);
-  assert.equal(m.narration.length, 0);
-  assert.deepEqual(m.lanes.map((l) => l.id), ['human:you']);
-});
-
-// ── narrate ──────────────────────────────────────────────────────────
-
-const ev = (event_type, data = {}, extra = {}) => ({ event_type, data, agent_name: 'Researcher', timestamp: 100, sequence_num: 1, session_id: 's', ...extra });
-
-test('narrate: tool call with its end gives duration and cost', () => {
-  const start = ev('tool_call_start', { tool_name: 'web_search', tool_args: { query: 'X' } });
-  const end = ev('tool_call_end', { tool_name: 'web_search', duration_ms: 1200 }, { cost_usd: 0.002, timestamp: 101.2 });
-  assert.equal(narrate(start, end), "Researcher asked web_search for 'X' — 1.2 s, $0.002.");
-  assert.equal(narrate(start), "Researcher is asking web_search for 'X'…");
-  const failed = ev('tool_call_end', { tool_name: 'web_search', duration_ms: 300, error: 'HTTP 500' });
-  assert.equal(narrate(start, failed), "Researcher asked web_search for 'X' — failed after 300 ms: HTTP 500.");
-});
-
-test('narrate: hand-off kinds', () => {
-  assert.equal(
-    narrate(ev('agent_handoff', { from_agent: 'Researcher', to_agent: 'Writer', reason: 'Facts gathered.' })),
-    "Researcher handed off to Writer: 'Facts gathered'.",
-  );
-  assert.equal(narrate(ev('agent_handoff', { from_agent: 'Manager', to_agent: 'Writer', kind: 'delegate' }, { agent_name: 'Manager' })), 'Manager delegated to Writer.');
-  assert.equal(narrate(ev('agent_handoff', { from_agent: 'A', to_agent: 'B', kind: 'route' })), 'A routed to B.');
-  assert.equal(narrate(ev('agent_handoff', { from_agent: 'A', to_agent: 'B', kind: 'spawn' })), 'A spawned B.');
-  assert.equal(narrate(ev('agent_handoff', { from_agent: 'A', to_agent: 'B', kind: 'weird' })), 'A handed off to B.');
-});
-
-test('narrate: LLM response with model, tokens, cost', () => {
-  const r = ev('llm_response', { duration_ms: 900, model: 'gpt-4o-mini' }, { prompt_tokens: 120, completion_tokens: 40, cost_usd: 0.0004 });
-  assert.equal(narrate(r), 'Researcher thought with gpt-4o-mini — 900 ms, 160 tokens, $0.0004.');
-});
-
-test('narrate: approvals, human and automatic', () => {
-  const req = ev('approval_requested', { approval_id: 'a1', tool: 'write_file', risk: 'high', kind: 'tool_call' }, { agent_name: 'Writer' });
-  assert.equal(narrate(req), 'Writer asked you to approve write_file (high risk).');
-  assert.equal(narrate(ev('approval_decided', { approved: true, approver: 'user', modified: true }), req), 'You approved write_file with edited arguments.');
-  assert.equal(narrate(ev('approval_decided', { approved: true, approver: 'env' }), req), 'write_file was approved automatically (env).');
-  assert.equal(narrate(ev('approval_decided', { approved: false, approver: 'user', reason: 'Not now' }), req), "You denied write_file: 'Not now'.");
-  assert.equal(narrate(ev('approval_decided', { approved: false, approver: 'timeout' }), req), 'write_file was denied: no answer before the timeout.');
-});
-
-test('narrate: tasks, steps, routes, workflow', () => {
-  assert.equal(narrate(ev('task_start', { name: 'research', agent: 'Researcher' })), "Task 'research' went to Researcher.");
-  assert.equal(narrate(ev('task_end', { status: 'failed', duration_ms: 2500, retries: 2 }, { node_id: 'task:research' })), "Task 'research' failed after 2.5 s, 2 retries.");
-  assert.equal(narrate(ev('step_end', { route: 'publish' }), ev('step_start', { name: 'decide' })), "Step 'decide' chose route 'publish'.");
-  assert.equal(narrate(ev('step_end', { status: 'cached' }, { node_id: 'step:fetch' })), "Step 'fetch' reused a cached result.");
-  assert.equal(narrate(ev('step_start', { name: 'gather', pattern: 'parallel' })), "Step 'gather' fanned out in parallel.");
-  assert.equal(narrate(ev('workflow_start', { kind: 'team', name: 'Brief', process: 'hierarchical' })), "Team 'Brief' started (hierarchical).");
-  assert.equal(narrate(ev('workflow_end', { status: 'completed', duration_ms: 125000 })), 'The run completed after 2 min 05 s.');
-});
-
-test('narrate: unknown and quiet events give empty strings', () => {
-  assert.equal(narrate(ev('context_snapshot')), '');
-  assert.equal(narrate(ev('something_new')), '');
-  assert.equal(narrate(null), '');
-  assert.equal(narrate(ev('message_added', { role: 'assistant', content: 'hi' })), '');
-  assert.equal(narrate(ev('message_added', { role: 'user', content: 'Hello!' }, { agent_name: '' })), "You said: 'Hello'.");
-});
-
-test('narrate is deterministic', () => {
-  const { events, graph } = load('team_handoff');
-  const a = buildModel(events, graph).narration.map((n) => n.text);
-  const b = buildModel(events, graph).narration.map((n) => n.text);
-  assert.deepEqual(a, b);
-  assert.ok(a.includes("Researcher asked web_search for 'solar sail facts' — 1.2 s, $0.002."));
-});
-
-test('formatters', () => {
-  assert.equal(formatDuration(850), '850 ms');
-  assert.equal(formatDuration(1200), '1.2 s');
-  assert.equal(formatCost(0.002), '$0.002');
-  assert.equal(formatCost(0.00001), '<$0.0001');
-  assert.equal(formatCost(1.5), '$1.50');
-  assert.equal(formatCost(0), '');
-});
-
-// ── layoutMap / deriveGraph ──────────────────────────────────────────
-
-test('layoutMap: layers flow left to right and every node gets a box', () => {
-  const { graph } = load('team_handoff');
-  const lay = layoutMap(graph);
-  const byId = Object.fromEntries(lay.nodes.map((n) => [n.id, n]));
-  assert.equal(lay.nodes.length, graph.nodes.length);
-  assert.ok(byId['start:begin'].layer < byId['manager:Manager'].layer);
-  assert.ok(byId['manager:Manager'].layer < byId['task:research'].layer);
-  // depends_on (write depends on research) puts research first
-  assert.ok(byId['task:research'].layer < byId['task:write'].layer);
-  assert.ok(byId['agent:Researcher'].layer < byId['agent:Writer'].layer);
-  for (const n of lay.nodes) {
-    assert.ok(n.x >= 0 && n.y >= 0 && n.x + n.w <= lay.width && n.y + n.h <= lay.height, n.id);
-  }
-  assert.deepEqual([...new Set(lay.nodes.map((n) => n.shape))].sort(), ['chevron', 'circle', 'diamond', 'flag', 'note', 'rounded', 'square']);
-});
-
-test('layoutMap: no two nodes overlap', () => {
-  for (const name of ['team_handoff', 'flow_parallel_loop']) {
-    const lay = layoutMap(load(name).graph);
-    for (let i = 0; i < lay.nodes.length; i++) {
-      for (let j = i + 1; j < lay.nodes.length; j++) {
-        const a = lay.nodes[i];
-        const b = lay.nodes[j];
-        const apart = a.x + a.w <= b.x || b.x + b.w <= a.x || a.y + a.h <= b.y || b.y + b.h <= a.y;
-        assert.ok(apart, `${a.id} overlaps ${b.id}`);
-      }
-    }
-  }
-});
-
-test('layoutMap: a loop edge is a back edge, routed underneath, labels kept', () => {
-  const lay = layoutMap(load('flow_parallel_loop').graph);
-  const back = lay.edges.filter((e) => e.back);
-  assert.deepEqual(back.map((e) => e.id), ['step:polish->step:review_loop:loop']);
-  assert.equal(back[0].points.length, 4);
-  const routes = lay.edges.filter((e) => e.kind === 'routes').map((e) => e.label).sort();
-  assert.deepEqual(routes, ['archive', 'publish']);
-  assert.equal(core.edgeText(lay.edges.find((e) => e.kind === 'routes' && e.label === 'publish')), 'routes: publish');
-});
-
-test('layoutMap: deterministic and tolerant of bad input', () => {
-  const g = load('flow_parallel_loop').graph;
-  assert.deepEqual(layoutMap(g), layoutMap(g));
-  const empty = layoutMap(null);
-  assert.equal(empty.nodes.length, 0);
-  const dangling = layoutMap({ nodes: [{ id: 'agent:A', kind: 'agent' }], edges: [{ source: 'agent:A', target: 'nope', kind: 'next' }] });
-  assert.equal(dangling.edges.length, 0);
-});
-
-test('deriveGraph: who talked to whom for a 1.0 file', () => {
-  const g = deriveGraph(load('legacy_v10').events);
-  assert.equal(g.derived, true);
-  assert.deepEqual(g.nodes.map((n) => n.id).sort(), ['agent:Assistant', 'agent:Checker', 'tool:Assistant/calculator']);
-  assert.deepEqual(g.edges.map((e) => e.id).sort(), [
-    'agent:Assistant->agent:Checker:handoff',
-    'agent:Assistant->tool:Assistant/calculator:uses',
-  ]);
-  const lay = layoutMap(g);
-  assert.equal(lay.nodes.length, 3);
-});
-
-test('deriveGraph counts repeats and includes you for approvals', () => {
-  const { events } = load('team_handoff');
-  const g = deriveGraph(events);
-  const ws = g.edges.find((e) => e.id === 'agent:Researcher->tool:Researcher/web_search:uses');
-  assert.equal(ws.label, '×3');
-  assert.ok(g.nodes.some((n) => n.id === 'human:you' && n.kind === 'human'));
-  assert.ok(g.edges.some((e) => e.kind === 'delegates' && e.source === 'manager:Manager'));
-});
-
-test('module also registers itself on globalThis for the standalone build', () => {
-  assert.equal(typeof globalThis.PraisonReplayCore.buildModel, 'function');
-});
-
-// ── observed graph / run map ─────────────────────────────────────────
-
-test('observedGraph: agents seen in events but not in the graph are "outside"', () => {
-  const { events, graph } = load('team_outside');
-  const g = core.observedGraph(graph, events);
-  assert.deepEqual([...g.outside].sort(), ['agent:Billing', 'agent:Triage', 'tool:Triage/transfer_to_billing']);
-  // team members keep their recorded ids; nothing duplicated
-  assert.equal(g.nodes.filter((n) => n.id === 'agent:Researcher').length, 1);
-  assert.ok(g.edges.some((e) => e.id === 'agent:Triage->agent:Billing:handoff' && e.meta.observed));
-  // the recorded uses-edge is not added twice
-  assert.equal(g.edges.filter((e) => e.source === 'agent:Researcher' && e.target === 'tool:Researcher/lookup_fact').length, 1);
-});
-
-test('observedGraph without a recorded graph is the derived map', () => {
-  const { events } = load('legacy_v10');
-  assert.equal(core.observedGraph(null, events).derived, true);
-});
-
-test('layoutRunMap: outside agents form their own framed block under the team', () => {
-  const { events, graph } = load('team_outside');
-  const lay = core.layoutRunMap(graph, events);
-  assert.equal(lay.groups.length, 1);
-  const grp = lay.groups[0];
-  assert.equal(grp.label, 'Outside the team');
-  const inside = lay.nodes.filter((n) => !n.outside);
-  const outside = lay.nodes.filter((n) => n.outside);
-  assert.deepEqual(outside.map((n) => n.id).sort(), ['agent:Billing', 'agent:Triage', 'tool:Triage/transfer_to_billing']);
-  const teamBottom = Math.max(...inside.map((n) => n.y + n.h));
-  for (const n of outside) {
-    assert.ok(n.y > teamBottom, `${n.id} sits below the team`);
-    assert.ok(n.x >= grp.x && n.x + n.w <= grp.x + grp.w && n.y >= grp.y && n.y + n.h <= grp.y + grp.h, `${n.id} inside the frame`);
-  }
-  for (const n of lay.nodes) assert.ok(n.x + n.w <= lay.width && n.y + n.h <= lay.height, `${n.id} within bounds`);
-  assert.ok(lay.edges.some((e) => e.id === 'agent:Triage->agent:Billing:handoff'));
-});
-
-test('layoutRunMap: no outside group when the graph covers everyone', () => {
-  const { events, graph } = load('team_handoff');
-  const lay = core.layoutRunMap(graph, events);
-  assert.equal(lay.groups.length, 0);
-  assert.equal(lay.nodes.length, graph.nodes.length);
-});
-
-test('real-run shape: LLM span encloses the tool call in the same lane', () => {
-  const { events, graph } = load('team_outside');
-  const m = buildModel(events, graph);
-  const llm = m.blocks.find((b) => b.agent === 'Researcher' && b.kind === 'llm');
-  const tool = m.blocks.find((b) => b.agent === 'Researcher' && b.kind === 'tool');
-  assert.equal(llm.lane, tool.lane);
-  assert.ok(llm.start < tool.start && tool.end < llm.end); // the view must put them on separate rows
-  assert.ok(m.lanes.some((l) => l.id === 'agent:Triage') && m.lanes.some((l) => l.id === 'agent:Billing'));
-  assert.deepEqual(m.arrows.map((a) => `${a.kind}:${a.from}->${a.to}`), ['handoff:agent:Triage->agent:Billing']);
-});
-
-// ── nodeStates: the map at the cursor ─────────────────────────────────
-
-const sev = (seq, event_type, extra = {}) => ({ sequence_num: seq, timestamp: 100 + seq, event_type, ...extra });
-
-test('nodeStates: a step is running between its start and end, then done', () => {
-  const events = [
-    sev(0, 'workflow_start'),
-    sev(1, 'step_start', { node_id: 'step:research' }),
-    sev(2, 'step_end', { node_id: 'step:research', data: { status: 'completed' } }),
-    sev(3, 'step_start', { node_id: 'step:draft' }),
-  ];
-  const nodes = [{ id: 'start', kind: 'start' }, { id: 'step:research' }, { id: 'step:draft' }, { id: 'end', kind: 'end' }];
-  const at = (i) => Object.fromEntries([...core.nodeStates(events, i, nodes)].map(([k, v]) => [k, v.state]));
-  assert.deepEqual(at(1), { 'step:research': 'running', start: 'done' });
-  assert.deepEqual(at(2), { 'step:research': 'done', start: 'done' });
-  assert.deepEqual(at(3), { 'step:research': 'done', 'step:draft': 'running', start: 'done' });
-  assert.equal(core.nodeStates(events, -1, nodes).size, 0, 'nothing is reached before the first step');
-});
-
-test('nodeStates: end node is reached when the run ends; failed and skipped come from status', () => {
-  const events = [
-    sev(0, 'step_start', { node_id: 'step:a' }),
-    sev(1, 'step_end', { node_id: 'step:a', data: { status: 'failed' } }),
-    sev(2, 'step_start', { node_id: 'step:b' }),
-    sev(3, 'step_end', { node_id: 'step:b', data: { status: 'skipped' } }),
-    sev(4, 'workflow_end'),
-  ];
-  const st = core.nodeStates(events, Infinity, [{ id: 'end', kind: 'end' }]);
-  assert.equal(st.get('step:a').state, 'failed');
-  assert.equal(st.get('step:b').state, 'skipped');
-  assert.equal(st.get('end').state, 'done');
-});
-
-test('nodeStates: runs count only on the node an end event belongs to', () => {
-  const events = [
-    sev(0, 'task_start', { node_id: 'task:research', agent_name: 'Researcher' }),
-    sev(1, 'agent_start', { agent_name: 'Researcher' }),
-    sev(2, 'agent_end', { agent_name: 'Researcher' }),
-    sev(3, 'task_end', { node_id: 'task:research', agent_name: 'Researcher', data: { status: 'completed' } }),
-    sev(4, 'step_start', { node_id: 'step:loop' }),
-    sev(5, 'step_end', { node_id: 'step:loop' }),
-    sev(6, 'step_start', { node_id: 'step:loop' }),
-    sev(7, 'step_end', { node_id: 'step:loop' }),
-  ];
-  const st = core.nodeStates(events);
-  assert.equal(st.get('agent:Researcher').runs, 1, 'task_end must not count as another agent run');
-  assert.equal(st.get('task:research').runs, 1);
-  assert.equal(st.get('step:loop').runs, 2);
-  assert.equal(st.get('agent:Researcher').state, 'done');
-});
-
-test('nodeStates: a recorded flow fixture ends with every visited node done or failed', () => {
-  const { events, graph } = load('flow_parallel_loop');
-  const m = buildModel(events, graph);
-  const st = core.nodeStates(m.events, Infinity, graph.nodes);
-  assert.ok(st.size > 0);
-  for (const [id, v] of st) assert.notEqual(v.state, 'running', `${id} still running after the run ended`);
-});
-
-// ── unnamed agents (Agent(instructions=...), agent_name null) ────────────
-
-const unnamedRun = (newIds) => [
-  { sequence_num: 0, timestamp: 1, event_type: 'session_start', agent_name: null },
-  { sequence_num: 1, timestamp: 2, event_type: 'agent_start', agent_name: null, node_id: newIds ? 'agent:Agent' : null },
-  { sequence_num: 2, timestamp: 3, event_type: 'llm_request', agent_name: null, node_id: newIds ? 'agent:Agent' : null },
-  { sequence_num: 3, timestamp: 4, event_type: 'llm_response', agent_name: null, node_id: newIds ? 'agent:Agent' : null },
-  { sequence_num: 4, timestamp: 5, event_type: 'tool_call_start', agent_name: null, node_id: newIds ? 'tool:Agent/search' : 'tool:None/search', data: { tool_name: 'search' } },
-  { sequence_num: 5, timestamp: 6, event_type: 'tool_call_end', agent_name: null, node_id: newIds ? 'tool:Agent/search' : 'tool:None/search', data: { tool_name: 'search' } },
-  { sequence_num: 6, timestamp: 7, event_type: 'agent_end', agent_name: null, node_id: newIds ? 'agent:Agent' : null, data: newIds ? { status: 'completed' } : {} },
-  { sequence_num: 7, timestamp: 8, event_type: 'session_end', agent_name: null },
-];
-
-for (const newIds of [true, false]) {
-  test(`unnamed agent is mapped as "Agent" (${newIds ? 'new' : '4.7.19'} trace ids)`, () => {
-    const g = deriveGraph(unnamedRun(newIds));
-    assert.deepEqual(g.nodes.map((n) => [n.id, n.label]), [['agent:Agent', 'Agent'], ['tool:Agent/search', 'search']]);
-    assert.deepEqual(g.edges.map((e) => `${e.source}->${e.target}:${e.kind}`), ['agent:Agent->tool:Agent/search:uses']);
-    const st = core.nodeStates(unnamedRun(newIds), Infinity, g.nodes);
-    assert.equal(st.get('agent:Agent').state, 'done');
-    assert.equal(st.get('tool:Agent/search').state, 'done');
-    assert.ok(![...st.keys()].some((k) => k.includes('None')), 'no tool:None ids leak into the map');
-  });
-}
-
-test('a failed unnamed agent run is red on the map', () => {
-  const evs = unnamedRun(true);
-  evs[6] = { ...evs[6], data: { status: 'failed' } };
-  assert.equal(core.nodeStates(evs, Infinity, deriveGraph(evs).nodes).get('agent:Agent').state, 'failed');
-});
-
-test('unnamed agents do not reappear "outside" a recorded team graph', () => {
-  const graph = { schema: 'praisonai.graph/1', kind: 'team', nodes: [
-    { id: 'start:begin', kind: 'start', label: 'Brief' }, { id: 'task:t', kind: 'task', label: 't' }, { id: 'end:done', kind: 'end', label: 'Delivered' }],
-  edges: [{ source: 'start:begin', target: 'task:t', kind: 'next' }, { source: 'task:t', target: 'end:done', kind: 'next' }] };
-  const og = core.observedGraph(graph, unnamedRun(true));
-  assert.deepEqual(og.nodes.map((n) => n.id), ['start:begin', 'task:t', 'end:done']);
-  assert.deepEqual(og.outside, []);
-});
-
-test('named agents are unchanged', () => {
-  const evs = unnamedRun(true).map((e) => ({ ...e, agent_name: e.agent_name === null && e.event_type !== 'session_start' && e.event_type !== 'session_end' ? 'Writer' : e.agent_name, node_id: e.node_id && e.node_id.replace('Agent', 'Writer') }));
-  assert.deepEqual(deriveGraph(evs).nodes.map((n) => n.id), ['agent:Writer', 'tool:Writer/search']);
-});
-
-test('an unnamed agent is narrated as "Agent", not "The run"', () => {
-  const evs = unnamedRun(true);
-  assert.equal(narrate(evs[1]), 'Agent started.');
-  assert.equal(narrate(evs[7]).startsWith('Recording'), true);
-});
@@ -141,7 +141,7 @@ check("GET nonexistent plugin", client.get("/api/marketplace/plugins/nonexistent
 print("\n═══ Code Execution API ═══")
 check("GET /api/code/languages", client.get("/api/code/languages"), 200, ["languages", "count"])
 r = client.post("/api/code/execute", json={"code": "print('hello')", "language": "python"})
-check("POST /api/code/execute", r, 200, ["status", "language"])
+check("POST /api/code/execute (pending approval)", r, 202, ["status", "approval_id"])
 r = client.post("/api/code/execute", json={"code": "ls", "language": "ruby"})
 check("POST execute disallowed lang", r, 400, ["error"])

@@ -1,235 +0,0 @@
-"""_UIStoreBackend waits for a human decision (contract v1 §5, approvals).
-
-Before: request_approval_sync returned ``approved=False, "Awaiting UI
-approval"`` immediately, so a tool needing approval was always denied and the
-UI's Approve button did nothing for the agent; ``request.approval_id`` and
-``modified_args`` were dropped.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import threading
-import time
-
-import pytest
-from starlette.applications import Starlette
-from starlette.testclient import TestClient
-
-protocols = pytest.importorskip("praisonaiagents.approval.protocols")
-ApprovalRequest = protocols.ApprovalRequest
-
-
-def _request(approval_id: str = "appr-1", **kw) -> "ApprovalRequest":
-    return ApprovalRequest(
-        tool_name=kw.pop("tool_name", "write_file"),
-        arguments=kw.pop("arguments", {"path": "draft.md"}),
-        risk_level=kw.pop("risk_level", "high"),
-        agent_name=kw.pop("agent_name", "Writer"),
-        approval_id=approval_id,
-        **kw,
-    )
-
-
-@pytest.fixture()
-def store():
-    from praisonaiui.features.approvals import SimpleApprovalManager
-
-    return SimpleApprovalManager()
-
-
-@pytest.fixture()
-def backend(store):
-    from praisonaiui.features.approvals import _UIStoreBackend
-
-    return _UIStoreBackend(store, timeout=5.0)
-
-
-def _wait_pending(store, approval_id: str, timeout: float = 3.0) -> dict:
-    deadline = time.monotonic() + timeout
-    while time.monotonic() < deadline:
-        for entry in store.list_pending():
-            if entry["id"] == approval_id:
-                return entry
-        time.sleep(0.01)
-    raise AssertionError(f"{approval_id} never became pending")
-
-
-def _in_thread(fn, *args):
-    box = {}
-
-    def run():
-        box["result"] = fn(*args)
-
-    t = threading.Thread(target=run, daemon=True)
-    t.start()
-    return t, box
-
-
-def test_sync_blocks_until_approved_with_modified_args(store, backend):
-    t, box = _in_thread(backend.request_approval_sync, _request("appr-1"))
-    entry = _wait_pending(store, "appr-1")  # honours request.approval_id
-    assert entry["tool_name"] == "write_file" and entry["agent_name"] == "Writer"
-    time.sleep(0.1)
-    assert t.is_alive(), "backend must block while the decision is pending"
-    store.approve("appr-1", reason="Use docs/", modified_args={"path": "docs/draft.md"})
-    t.join(timeout=3)
-    assert not t.is_alive()
-    decision = box["result"]
-    assert decision.approved is True
-    assert decision.modified_args == {"path": "docs/draft.md"}
-    assert decision.reason == "Use docs/"
-
-
-def test_sync_deny_resolves_with_reason(store, backend):
-    t, box = _in_thread(backend.request_approval_sync, _request("appr-2"))
-    _wait_pending(store, "appr-2")
-    store.deny("appr-2", reason="Not today")
-    t.join(timeout=3)
-    assert box["result"].approved is False
-    assert box["result"].reason == "Not today"
-
-
-def test_sync_timeout_denies_and_clears_queue(store):
-    from praisonaiui.features.approvals import _UIStoreBackend
-
-    backend = _UIStoreBackend(store, timeout=0.2)
-    started = time.monotonic()
-    decision = backend.request_approval_sync(_request("appr-3"))
-    assert time.monotonic() - started >= 0.2
-    assert decision.approved is False
-    assert decision.approver == "timeout"
-    assert store.list_pending() == []
-    assert store.get("appr-3")["status"] == "denied"
-
-
-def test_per_id_isolation(store, backend):
-    t1, b1 = _in_thread(backend.request_approval_sync, _request("a"))
-    t2, b2 = _in_thread(backend.request_approval_sync, _request("b"))
-    _wait_pending(store, "a")
-    _wait_pending(store, "b")
-    store.approve("b")
-    t2.join(timeout=3)
-    assert b2["result"].approved is True
-    assert t1.is_alive(), "deciding b must not release a"
-    store.deny("a")
-    t1.join(timeout=3)
-    assert b1["result"].approved is False
-
-
-def test_async_waits_without_blocking_the_loop(store, backend):
-    async def main():
-        task = asyncio.create_task(backend.request_approval(_request("appr-4")))
-        ticks = 0
-        while not store.list_pending():
-            ticks += 1
-            await asyncio.sleep(0.01)
-        # the loop keeps running while waiting
-        for _ in range(5):
-            ticks += 1
-            await asyncio.sleep(0.01)
-        assert not task.done()
-        # decision arrives from another thread (the server handling POST /approve)
-        threading.Timer(0.05, lambda: store.approve("appr-4", modified_args={"x": 1})).start()
-        decision = await asyncio.wait_for(task, 3)
-        return decision, ticks
-
-    decision, ticks = asyncio.run(main())
-    assert decision.approved is True
-    assert decision.modified_args == {"x": 1}
-    assert ticks >= 5
-
-
-def test_async_decision_from_same_loop(store, backend):
-    async def main():
-        task = asyncio.create_task(backend.request_approval(_request("appr-5")))
-        while not store.list_pending():
-            await asyncio.sleep(0.01)
-        store.approve("appr-5")
-        return await asyncio.wait_for(task, 3)
-
-    assert asyncio.run(main()).approved is True
-
-
-def test_async_timeout_denies(store):
-    from praisonaiui.features.approvals import _UIStoreBackend
-
-    backend = _UIStoreBackend(store, timeout=0.15)
-    decision = asyncio.run(backend.request_approval(_request("appr-6")))
-    assert decision.approved is False
-    assert store.get("appr-6")["status"] == "denied"
-
-
-def test_async_cancel_by_registry_wait_for_expires_entry(store, backend):
-    async def main():
-        with pytest.raises(asyncio.TimeoutError):
-            await asyncio.wait_for(backend.request_approval(_request("appr-7")), 0.1)
-
-    asyncio.run(main())
-    assert store.list_pending() == []
-    assert store.get("appr-7")["status"] == "denied"
-
-
-def test_sync_call_on_event_loop_thread_fails_closed_fast(store, backend):
-    async def main():
-        started = time.monotonic()
-        decision = backend.request_approval_sync(_request("appr-8"))
-        return decision, time.monotonic() - started
-
-    decision, elapsed = asyncio.run(main())
-    assert decision.approved is False
-    assert elapsed < 1.0
-    assert store.list_pending() == []
-
-
-def test_auto_policy_still_resolves_immediately(store, backend):
-    store.update_policies({"auto_approve_tools": ["write_file"]})
-    decision = backend.request_approval_sync(_request("appr-9"))
-    assert decision.approved is True
-    assert decision.approver == "auto-policy"
-
-
-def test_approve_endpoint_passes_modified_args(store, backend, monkeypatch):
-    from praisonaiui.features import approvals
-
-    monkeypatch.setattr(approvals, "_approval_manager", store)
-    client = TestClient(Starlette(routes=approvals.ApprovalsFeature().routes()))
-    t, box = _in_thread(backend.request_approval_sync, _request("appr-10"))
-    _wait_pending(store, "appr-10")
-    assert client.get("/api/approvals/appr-10").json()["arguments"] == {"path": "draft.md"}
-    r = client.post("/api/approvals/appr-10/approve", json={"modified_args": {"path": "docs/x.md"}, "reason": "ok"})
-    assert r.status_code == 200
-    assert r.json()["modified_args"] == {"path": "docs/x.md"}
-    t.join(timeout=3)
-    assert box["result"].approved is True
-    assert box["result"].modified_args == {"path": "docs/x.md"}
-
-
-def test_approve_endpoint_rejects_non_object_modified_args(store, monkeypatch):
-    from praisonaiui.features import approvals
-
-    monkeypatch.setattr(approvals, "_approval_manager", store)
-    store.request_approval({"id": "z", "tool_name": "t", "risk_level": "high"})
-    client = TestClient(Starlette(routes=approvals.ApprovalsFeature().routes()))
-    r = client.post("/api/approvals/z/approve", json={"modified_args": [1, 2]})
-    assert r.status_code == 400
-    assert store.get("z")["status"] == "pending"
-    # plain approve without modified_args still works (and keeps old managers working)
-    assert client.post("/api/approvals/z/approve", json={}).status_code == 200
-
-
-def test_sdk_manager_approve_forwards_modified_args():
-    pytest.importorskip("praisonaiagents.approval")
-    from praisonaiagents.approval import get_approval_registry
-
-    from praisonaiui.features.approvals import SDKApprovalManager
-
-    registry = get_approval_registry()
-    previous = registry.get_backend()
-    try:
-        mgr = SDKApprovalManager()
-        mgr._simple.request_approval({"id": "s1", "tool_name": "t", "risk_level": "high"})
-        entry = mgr.approve("s1", modified_args={"k": "v"})
-        assert entry["modified_args"] == {"k": "v"}
-    finally:
-        registry.set_backend(previous)
@@ -1,54 +0,0 @@
-"""Regression tests for #322 — Chat must fill the dashboard main column.
-
-Chat pages declare ``layout: "full-bleed"``; ``selectPage()`` then adds
-``db-fill`` to ``#db-main-content`` and skips the duplicate page header, and
-``.chat-root`` sizes from flex allocation instead of ``calc(100vh - 140px)``.
-"""
-
-from __future__ import annotations
-
-import re
-from pathlib import Path
-
-PLUGINS = (
-    Path(__file__).resolve().parents[2]
-    / "src" / "praisonaiui" / "templates" / "frontend" / "plugins"
-)
-
-
-def _select_page_body() -> str:
-    src = (PLUGINS / "dashboard.js").read_text(encoding="utf-8")
-    m = re.search(r"async function selectPage\(pageId\)\s*\{(.*?)^}", src, re.DOTALL | re.MULTILINE)
-    assert m
-    return m.group(1)
-
-
-def test_chat_pages_declare_full_bleed():
-    from starlette.testclient import TestClient
-
-    from praisonaiui.server import create_app, reset_state
-
-    reset_state()  # isolate from page whitelists set by other tests
-    pages = {p["id"]: p for p in TestClient(create_app()).get("/api/pages").json()["pages"]}
-    for pid in ("chat", "chat-canvas"):
-        assert pages[pid].get("layout") == "full-bleed"
-    assert pages["overview"].get("layout") is None
-
-
-def test_select_page_toggles_fill_and_skips_header():
-    body = _select_page_body()
-    assert "page.layout === 'full-bleed'" in body
-    assert "classList.toggle('db-fill'" in body
-    assert re.search(r"showPageHeader = .*&& !fullBleed", body)
-
-
-def test_fill_css_defined():
-    src = (PLUGINS / "dashboard.js").read_text(encoding="utf-8")
-    assert ".db-main.db-fill > #db-page-content" in src
-
-
-def test_chat_root_fills_column_in_fill_mode():
-    chat = (PLUGINS / "views" / "chat.js").read_text(encoding="utf-8")
-    assert re.search(r"\.db-fill \.chat-root \{[^}]*flex:1;[^}]*min-height:0", chat)
-    canvas = (PLUGINS / "views" / "chat-canvas.js").read_text(encoding="utf-8")
-    assert ".db-fill .chat-canvas-root" in canvas
@@ -1,31 +0,0 @@
-"""Tests for the in-rail session search in the chat view (issue #324).
-
-The chat sidebar must expose a search input that filters the already
-fetched session list client-side, without refetching from the API.
-"""
-
-from pathlib import Path
-
-CHAT = Path("src/praisonaiui/templates/frontend/plugins/views/chat.js")
-
-
-class TestChatSessionRailSearch:
-    def test_search_input_rendered_in_rail(self):
-        src = CHAT.read_text()
-        assert 'id="chat-session-search"' in src
-        assert src.index('id="chat-session-search"') < src.index('id="chat-sessions-list"')
-
-    def test_input_wired_to_client_side_render(self):
-        src = CHAT.read_text()
-        assert "sessionSearch.addEventListener('input', renderSessionList)" in src
-
-    def test_load_sessions_caches_and_delegates_render(self):
-        src = CHAT.read_text()
-        assert "allSessions = Array.isArray(fetched) ? fetched : [];" in src
-        body = src.split("async function loadSessions()", 1)[1].split("\n}\n", 1)[0]
-        assert "renderSessionList();" in body
-
-    def test_filter_matches_title_and_id_fields(self):
-        src = CHAT.read_text()
-        assert "function _sessionMatches(s, q)" in src
-        assert "No matching sessions" in src
@@ -1,49 +0,0 @@
-"""Issue #331 — rename a session from the chat rail via the existing PATCH route."""
-
-from __future__ import annotations
-
-import asyncio
-from pathlib import Path
-
-from starlette.applications import Starlette
-from starlette.routing import Route
-from starlette.testclient import TestClient
-
-import praisonaiui.server as server
-from praisonaiui.datastore import MemoryDataStore
-
-CHAT = Path("src/praisonaiui/templates/frontend/plugins/views/chat.js")
-
-
-def _client(monkeypatch):
-    ds = MemoryDataStore()
-    monkeypatch.setattr(server, "_datastore", ds)
-    app = Starlette(routes=[Route("/sessions/{session_id}", server.patch_session, methods=["PATCH"])])
-    sid = asyncio.run(ds.create_session())["id"]
-    return TestClient(app), ds, sid
-
-
-def test_patch_renames_and_trims(monkeypatch):
-    client, ds, sid = _client(monkeypatch)
-    r = client.patch(f"/sessions/{sid}", json={"title": "  My chat  "})
-    assert r.status_code == 200
-    assert asyncio.run(ds.get_session(sid))["title"] == "My chat"
-
-
-def test_patch_rejects_blank_or_non_string_title(monkeypatch):
-    client, _, sid = _client(monkeypatch)
-    assert client.patch(f"/sessions/{sid}", json={"title": "   "}).status_code == 400
-    assert client.patch(f"/sessions/{sid}", json={"title": 123}).status_code == 400
-
-
-def test_patch_unknown_session_404(monkeypatch):
-    client, _, _ = _client(monkeypatch)
-    assert client.patch("/sessions/nope", json={"title": "x"}).status_code == 404
-
-
-def test_rail_has_rename_button_wired_to_patch():
-    src = CHAT.read_text()
-    assert "async function renameSession(sessionId, currentTitle)" in src
-    assert "method: 'PATCH'" in src
-    assert "renameSession(id, title)" in src
-    assert "e.stopPropagation()" in src
@@ -2,6 +2,7 @@

 from pathlib import Path

+import pytest
 from starlette.testclient import TestClient

 from praisonaiui.server import create_app
@@ -34,16 +35,87 @@ class TestCodeExecutionApi:
        d = r.json()
        assert "languages" in d and "count" in d

-    def test_execute(self):
+    @pytest.fixture(autouse=True)
+    def _fresh_approvals(self, monkeypatch):
+        from praisonaiui.features import approvals
+
+        monkeypatch.setattr(approvals, "_approval_manager", approvals.SimpleApprovalManager())
+        return approvals._approval_manager
+
+    def test_execute_requires_approval(self, _fresh_approvals):
        client = TestClient(create_app())
+        payload = {"code": "print('hi')", "language": "python", "timeout": 30}
+        r = client.post("/api/code/execute", json=payload)
+        assert r.status_code == 202
+        d = r.json()
+        assert d["status"] == "pending_approval"
+        approval_id = d["approval_id"]
+        assert _fresh_approvals.get(approval_id)["tool_name"] == "execute_code"
+
+        # Not yet approved
+        r = client.post("/api/code/execute", json={**payload, "approval_id": approval_id})
+        assert r.status_code == 403
+
+        assert client.post(f"/api/approvals/{approval_id}/approve", json={}).status_code == 200
+        # Approval is bound to the exact code
        r = client.post(
            "/api/code/execute",
-            json={"code": "print('hi')", "language": "python", "timeout": 30},
+            json={**payload, "code": "print('x')", "approval_id": approval_id},
        )
+        assert r.status_code == 403
+
+        r = client.post("/api/code/execute", json={**payload, "approval_id": approval_id})
        assert r.status_code == 200
        d = r.json()
        assert "status" in d and "language" in d

+        # Single use
+        r = client.post("/api/code/execute", json={**payload, "approval_id": approval_id})
+        assert r.status_code == 403
+
+    def test_execute_denied(self, _fresh_approvals):
+        client = TestClient(create_app())
+        r = client.post("/api/code/execute", json={"code": "1", "language": "python"})
+        approval_id = r.json()["approval_id"]
+        client.post(f"/api/approvals/{approval_id}/deny", json={})
+        r = client.post(
+            "/api/code/execute",
+            json={"code": "1", "language": "python", "approval_id": approval_id},
+        )
+        assert r.status_code == 403
+
+    def test_execute_rejects_non_gate_approval(self, _fresh_approvals):
+        # A low-risk request filed via /api/approvals is auto-approved by the
+        # default policy; it must not unlock execution.
+        client = TestClient(create_app())
+        r = client.post(
+            "/api/approvals",
+            json={
+                "tool_name": "execute_code",
+                "arguments": {"code": "1", "language": "python"},
+                "risk_level": "low",
+            },
+        )
+        assert r.json()["status"] == "approved"
+        r = client.post(
+            "/api/code/execute",
+            json={"code": "1", "language": "python", "approval_id": r.json()["id"]},
+        )
+        assert r.status_code == 403
+
+    def test_execute_auto_approved_by_policy(self, _fresh_approvals):
+        _fresh_approvals.update_policies({"auto_approve_tools": ["execute_code"]})
+        client = TestClient(create_app())
+        r = client.post("/api/code/execute", json={"code": "1", "language": "python"})
+        assert r.status_code == 200
+        assert _fresh_approvals.list_history()[0]["approver"] == "auto-policy"
+
+    def test_execute_disallowed_language(self, _fresh_approvals):
+        client = TestClient(create_app())
+        r = client.post("/api/code/execute", json={"code": "ls", "language": "ruby"})
+        assert r.status_code == 400
+        assert _fresh_approvals.list_pending() == []
+

 class TestCodeStudioFrontend:
    def test_view_file_exists(self):
@@ -1,31 +0,0 @@
-"""Issue #323 — Jobs rows link to their chat session when ``session_id`` is set.
-
-Source-parsing test, mirroring ``test_session_search_dashboard.py``.
-"""
-
-from __future__ import annotations
-
-from pathlib import Path
-
-JOBS_JS = (
-    Path(__file__).resolve().parents[2]
-    / "src" / "praisonaiui" / "templates" / "frontend" / "plugins" / "jobs.js"
-)
-
-
-def _src() -> str:
-    return JOBS_JS.read_text(encoding="utf-8")
-
-
-def test_open_session_button_only_when_session_id():
-    src = _src()
-    assert "job.session_id ? `<button" in src
-    assert 'data-session-id="${escapeAttr(job.session_id)}"' in src
-
-
-def test_open_session_reuses_session_select_event():
-    src = _src()
-    assert "function openJobSession(sessionId)" in src
-    assert "selectPage('chat')" in src
-    assert "'aiui:session-select'" in src
-    assert "window.aiuiOpenJobSession = openJobSession;" in src
@@ -1,166 +0,0 @@
-"""create_replay_app(): the Replay view mounted inside another app, with an optional Run box."""
-
-from __future__ import annotations
-
-import json
-import shutil
-import threading
-import time
-from pathlib import Path
-
-import pytest
-from starlette.applications import Starlette
-from starlette.routing import Mount
-from starlette.testclient import TestClient
-
-FIXTURES = Path(__file__).resolve().parents[1] / "fixtures" / "replay"
-
-
-@pytest.fixture()
-def traces(tmp_path, monkeypatch):
-    d = tmp_path / "traces"
-    d.mkdir()
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(d))
-    monkeypatch.delenv("PRAISON_HOME", raising=False)
-    return d
-
-
-def _host(sub) -> TestClient:
-    """A host app with the replay app mounted at /replay, like app.mount() in FastAPI."""
-    return TestClient(Starlette(routes=[Mount("/replay", app=sub)]))
-
-
-def _cfg(page: str) -> dict:
-    line = next(l for l in page.splitlines() if l.startswith("render("))
-    return json.loads(line[line.index(",") + 1 : line.rindex(")")].strip())
-
-
-def test_page_mounts_the_view_relative_to_the_mount(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    c = _host(create_replay_app())
-    r = c.get("/replay/")
-    assert r.status_code == 200
-    assert 'from "/replay/replay.js"' in r.text
-    cfg = _cfg(r.text)
-    assert cfg == {"base": "/replay", "approve": False}  # no run list pin, no Run box
-    assert "aiui" not in r.text.lower()  # no dashboard around it
-    for name in ("replay.js", "replay-core.js"):
-        js = c.get(f"/replay/{name}")
-        assert js.status_code == 200 and js.headers["content-type"].startswith("text/javascript")
-
-
-def test_page_pins_a_valid_run_and_ignores_a_bad_one(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    c = _host(create_replay_app())
-    assert _cfg(c.get("/replay/?run=run-abc").text)["run"] == "run-abc"
-    page = c.get("/replay/?run=../../etc/passwd").text
-    assert "run" not in _cfg(page) and "passwd" not in page
-
-
-def test_api_routes_answer_under_the_mount(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    shutil.copy(FIXTURES / "team_handoff.jsonl", traces / "team_handoff.jsonl")
-    c = _host(create_replay_app())
-    rows = c.get("/replay/api/replay/runs").json()
-    assert [r["run_id"] for r in rows] == ["team_handoff"]
-    assert c.get("/replay/api/replay/runs/team_handoff/events").json()["events"]
-
-
-def test_events_wait_param_answers_a_missing_run_without_404(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    c = _host(create_replay_app())
-    assert c.get("/replay/api/replay/runs/run-later/events").status_code == 404
-    r = c.get("/replay/api/replay/runs/run-later/events?wait=1")
-    assert r.status_code == 200 and r.json() == {"events": [], "graph": None, "run": None}
-
-
-def test_no_run_route_without_a_runner(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    c = _host(create_replay_app())
-    assert c.post("/replay/api/replay/run", json={"input": "x"}).status_code in (404, 405)
-
-
-def test_run_box_calls_the_runner_with_a_new_run_id(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    calls = []
-
-    def runner(text, run_id):
-        (traces / f"{run_id}.jsonl").write_text(json.dumps({"event_type": "session_start", "sequence_num": 0, "timestamp": time.time()}) + "\n")
-        calls.append((text, run_id))
-
-    c = _host(create_replay_app(runner, input="solar sails", placeholder="Topic"))
-    cfg = _cfg(c.get("/replay/").text)
-    assert cfg["runner"] == {"input": "solar sails", "placeholder": "Topic", "ask": True}
-    r = c.post("/replay/api/replay/run", json={"input": "comets"})
-    assert r.status_code == 200
-    run_id = r.json()["run_id"]
-    assert (traces / f"{run_id}.jsonl").is_file(), "answers once the trace exists"
-    for _ in range(100):
-        if calls:
-            break
-        time.sleep(0.01)
-    assert calls == [("comets", run_id)]
-    assert run_id.startswith("run-") and len(run_id) == 16
-
-
-def test_run_box_without_input_box(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    cfg = _cfg(_host(create_replay_app(lambda t, r: None, input=None)).get("/replay/").text)
-    assert cfg["runner"]["ask"] is False
-
-
-def test_run_rejects_non_json_bad_input_and_a_second_run(traces):
-    from praisonaiui.features.replay import MAX_RUN_INPUT, create_replay_app
-
-    gate = threading.Event()
-    c = _host(create_replay_app(lambda text, run_id: gate.wait(5)))
-    assert c.post("/replay/api/replay/run", data="input=x", headers={"content-type": "application/x-www-form-urlencoded"}).status_code == 415
-    assert c.post("/replay/api/replay/run", content="input=x", headers={"content-type": "text/plain"}).status_code == 415
-    assert c.post("/replay/api/replay/run", json={"input": 3}).status_code == 400
-    assert c.post("/replay/api/replay/run", json={"input": "x" * (MAX_RUN_INPUT + 1)}).status_code == 400
-    assert c.post("/replay/api/replay/run", json={"input": "a"}).status_code == 200
-    busy = c.post("/replay/api/replay/run", json={"input": "b"})
-    assert busy.status_code == 409 and "already" in busy.json()["error"]
-    gate.set()
-    for _ in range(100):  # the lock is released when the runner returns
-        r = c.post("/replay/api/replay/run", json={"input": "c"})
-        if r.status_code == 200:
-            break
-        time.sleep(0.02)
-    assert r.status_code == 200
-
-
-def test_a_failing_runner_frees_the_run_box(traces, caplog):
-    from praisonaiui.features.replay import create_replay_app
-
-    def boom(text, run_id):
-        raise RuntimeError("no key")
-
-    c = _host(create_replay_app(boom))
-    assert c.post("/replay/api/replay/run", json={"input": ""}).status_code == 200
-    for _ in range(100):
-        r = c.post("/replay/api/replay/run", json={"input": ""})
-        if r.status_code == 200:
-            break
-        time.sleep(0.02)
-    assert r.status_code == 200
-
-
-def test_async_runner_is_awaited(traces):
-    from praisonaiui.features.replay import create_replay_app
-
-    done = threading.Event()
-
-    async def runner(text, run_id):
-        done.set()
-
-    c = _host(create_replay_app(runner))
-    assert c.post("/replay/api/replay/run", json={"input": ""}).status_code == 200
-    assert done.wait(3)
@@ -1,439 +0,0 @@
-"""PraisonAI Replay feature: runs listing, events, SSE tail, safety (contract v1 §1, §5)."""
-
-from __future__ import annotations
-
-import json
-import shutil
-import threading
-import time
-from pathlib import Path
-
-import pytest
-from starlette.applications import Starlette
-from starlette.testclient import TestClient
-
-FIXTURES = Path(__file__).resolve().parents[1] / "fixtures" / "replay"
-NAMES = ("team_handoff", "flow_parallel_loop", "legacy_v10")
-
-
-def _lines(name: str) -> list[str]:
-    return (FIXTURES / f"{name}.jsonl").read_text(encoding="utf-8").splitlines(keepends=True)
-
-
-@pytest.fixture()
-def traces(tmp_path, monkeypatch):
-    d = tmp_path / "traces"
-    d.mkdir()
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(d))
-    monkeypatch.delenv("PRAISON_HOME", raising=False)
-    return d
-
-
-@pytest.fixture()
-def isolated_server(tmp_path, monkeypatch):
-    """create_app() writes a config store; keep it out of the developer's home."""
-    monkeypatch.setenv("AIUI_DATA_DIR", str(tmp_path / "aiui-data"))
-    monkeypatch.setenv("PRAISONAI_HOME", str(tmp_path / "praisonai-home"))
-
-
-@pytest.fixture()
-def feature():
-    from praisonaiui.features.replay import ReplayFeature
-
-    f = ReplayFeature()
-    f.poll_interval = 0.02
-    f.ping_interval = 0.15
-    f.quiet_period = 0.3
-    return f
-
-
-@pytest.fixture()
-def client(feature):
-    app = Starlette(routes=feature.routes())
-    return TestClient(app)
-
-
-def _copy_all(d: Path) -> None:
-    for name in NAMES:
-        dst = d / f"{name}.jsonl"
-        shutil.copy(FIXTURES / f"{name}.jsonl", dst)
-
-
-# ── traces dir resolution ────────────────────────────────────────────
-
-
-def test_traces_dir_precedence(tmp_path, monkeypatch):
-    from praisonaiui.features import _trace_jsonl as tj
-
-    monkeypatch.delenv("PRAISONAI_TRACES_DIR", raising=False)
-    monkeypatch.delenv("PRAISON_HOME", raising=False)
-    monkeypatch.setenv("HOME", str(tmp_path / "home"))
-    assert tj.traces_dir() == tmp_path / "home" / ".praison" / "traces"
-    monkeypatch.setenv("PRAISON_HOME", str(tmp_path / "ph"))
-    assert tj.traces_dir() == tmp_path / "ph" / "traces"
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(tmp_path / "explicit"))
-    assert tj.traces_dir() == tmp_path / "explicit"
-
-
-# ── /api/replay/runs ─────────────────────────────────────────────────
-
-
-def test_runs_lists_fixtures_newest_first(traces, client):
-    _copy_all(traces)
-    r = client.get("/api/replay/runs")
-    assert r.status_code == 200
-    rows = r.json()
-    assert isinstance(rows, list)
-    by_id = {row["run_id"]: row for row in rows}
-    assert set(by_id) == set(NAMES)
-    # newest first by started_at
-    started = [row["started_at"] for row in rows]
-    assert started == sorted(started, reverse=True)
-
-    team = by_id["team_handoff"]
-    assert team["session_id"] == "sess-team-01"
-    assert team["kind"] == "team"
-    assert team["name"] == "Solar sail brief"
-    assert team["status"] == "completed"
-    assert team["live"] is False
-    assert team["events"] == 36
-    assert team["agents"] == ["Manager", "Researcher", "Writer"]
-    assert team["cost_usd"] == pytest.approx(0.006741, abs=1e-9)
-    assert team["ended_at"] == pytest.approx(1767225612.25)
-    assert team["path"].endswith("team_handoff.jsonl")
-    assert team["event_run_id"] == "team-handoff-01"
-
-    legacy = by_id["legacy_v10"]  # schema 1.0: no workflow_start, still listed
-    assert legacy["kind"] == "session"
-    assert legacy["status"] == "completed"
-    assert legacy["schema_version"] == "1.0"
-    assert legacy["agents"] == ["Assistant", "Checker"]
-    assert legacy["events"] == 16
-
-
-def test_runs_empty_or_missing_dir(tmp_path, monkeypatch, client):
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(tmp_path / "nope"))
-    r = client.get("/api/replay/runs")
-    assert r.status_code == 200
-    assert r.json() == []
-
-
-def test_run_without_end_marker_is_live(traces, client):
-    lines = _lines("team_handoff")
-    (traces / "half.jsonl").write_text("".join(lines[:20]), encoding="utf-8")
-    row = client.get("/api/replay/runs").json()[0]
-    assert row["run_id"] == "half"
-    assert row["live"] is True
-    assert row["status"] == "running"
-    assert "ended_at" not in row
-
-
-def test_ignores_non_jsonl_and_unsafe_names(traces, client):
-    _copy_all(traces)
-    (traces / "notes.txt").write_text("x", encoding="utf-8")
-    (traces / "bad name.jsonl").write_text(_lines("legacy_v10")[0], encoding="utf-8")
-    ids = {row["run_id"] for row in client.get("/api/replay/runs").json()}
-    assert ids == set(NAMES)
-
-
-# ── /api/replay/runs/{id}/events ─────────────────────────────────────
-
-
-def test_events_and_graph(traces, client):
-    _copy_all(traces)
-    data = client.get("/api/replay/runs/team_handoff/events").json()
-    assert len(data["events"]) == 36
-    assert data["graph"]["schema"] == "praisonai.graph/1"
-    assert data["graph"]["process"] == "hierarchical"
-    assert data["run"]["run_id"] == "team_handoff"
-    legacy = client.get("/api/replay/runs/legacy_v10/events").json()
-    assert legacy["graph"] is None
-    assert len(legacy["events"]) == 16
-
-
-def test_events_after_seq(traces, client):
-    _copy_all(traces)
-    data = client.get("/api/replay/runs/team_handoff/events?after_seq=30").json()
-    assert [e["sequence_num"] for e in data["events"]] == [31, 32, 33, 34, 35]
-    # graph still comes from the (earlier) workflow_start
-    assert data["graph"] is not None
-    assert client.get("/api/replay/runs/team_handoff/events?after_seq=-1").json()["events"][0]["sequence_num"] == 0
-    assert client.get("/api/replay/runs/team_handoff/events?after_seq=abc").status_code == 400
-
-
-def test_unknown_event_types_and_fields_pass_through(traces, client):
-    _copy_all(traces)
-    events = client.get("/api/replay/runs/flow_parallel_loop/events").json()["events"]
-    odd = [e for e in events if e["event_type"] == "context_rebalance"]
-    assert len(odd) == 1
-    assert odd[0]["future_field"] == {"x": 1}
-
-
-def test_partial_last_line_ignored_until_complete(traces, client):
-    lines = _lines("legacy_v10")
-    path = traces / "growing.jsonl"
-    last = lines[-1]
-    path.write_text("".join(lines[:-1]) + last[:25], encoding="utf-8")
-    first = client.get("/api/replay/runs/growing/events").json()["events"]
-    assert len(first) == 15  # half-written session_end is not surfaced
-    assert first[-1]["event_type"] == "agent_end"
-    with open(path, "a", encoding="utf-8") as fh:
-        fh.write(last[25:])
-    second = client.get("/api/replay/runs/growing/events").json()["events"]
-    assert len(second) == 16
-    assert second[-1]["event_type"] == "session_end"
-
-
-def test_complete_last_line_without_newline_is_read(traces, client):
-    text = "".join(_lines("legacy_v10")).rstrip("\n")
-    (traces / "nonl.jsonl").write_text(text, encoding="utf-8")
-    events = client.get("/api/replay/runs/nonl/events").json()["events"]
-    assert len(events) == 16
-
-
-def test_garbage_lines_are_skipped(traces, client):
-    lines = _lines("legacy_v10")
-    (traces / "dirty.jsonl").write_text(lines[0] + "not json\n[1,2]\n\n" + "".join(lines[1:]), encoding="utf-8")
-    assert len(client.get("/api/replay/runs/dirty/events").json()["events"]) == 16
-
-
-# ── safety ───────────────────────────────────────────────────────────
-
-
-@pytest.mark.parametrize(
-    "run_id",
-    ["..", ".", "a b", "a;b", "%2e%2e", "..%2Fsecret", "x%00y", "ü"],
-)
-def test_path_traversal_ids_rejected(traces, client, run_id):
-    secret = traces.parent / "secret.jsonl"
-    secret.write_text(_lines("legacy_v10")[0], encoding="utf-8")
-    for suffix in ("events", "stream"):
-        r = client.get(f"/api/replay/runs/{run_id}/{suffix}")
-        assert r.status_code in (400, 404), (run_id, suffix, r.status_code)
-        assert "legacy-sess-10" not in r.text
-
-
-def test_run_path_validation_unit(tmp_path):
-    from praisonaiui.features import _trace_jsonl as tj
-
-    assert tj.run_path("../etc/passwd", tmp_path) is None
-    assert tj.run_path("..", tmp_path) is None
-    assert tj.run_path("a/b", tmp_path) is None
-    assert tj.run_path("ok-run_1.2", tmp_path) == tmp_path / "ok-run_1.2.jsonl"
-
-
-def test_symlink_escaping_dir_is_rejected(traces, client, tmp_path):
-    outside = tmp_path / "outside"
-    outside.mkdir()
-    target = outside / "x.jsonl"
-    target.write_text(_lines("legacy_v10")[0], encoding="utf-8")
-    link = traces / "sneaky.jsonl"
-    try:
-        link.symlink_to(target)
-    except (OSError, NotImplementedError):
-        pytest.skip("symlinks unavailable")
-    assert client.get("/api/replay/runs/sneaky/events").status_code == 400
-
-
-def test_unknown_run_is_404(traces, client):
-    assert client.get("/api/replay/runs/nope/events").status_code == 404
-    assert client.get("/api/replay/runs/nope/stream").status_code == 404
-
-
-# ── SSE stream ───────────────────────────────────────────────────────
-
-
-def _parse_sse(text: str) -> list[tuple[str, str, str | None]]:
-    out = []
-    for block in text.split("\n\n"):
-        if not block.strip():
-            continue
-        name, data, ident = "message", [], None
-        for line in block.split("\n"):
-            if line.startswith("event:"):
-                name = line[6:].strip()
-            elif line.startswith("data:"):
-                data.append(line[5:].strip())
-            elif line.startswith("id:"):
-                ident = line[3:].strip()
-        if data or name != "message":
-            out.append((name, "\n".join(data), ident))
-    return out
-
-
-def test_stream_tails_appended_lines(traces, client, monkeypatch):
-    """Lines written while the stream is open (including one written in two
-    halves) arrive exactly once, in order; the stream ends after session_end."""
-    from praisonaiui.features import _trace_jsonl as tj
-
-    monkeypatch.setattr(tj, "LIVE_WINDOW_S", 8)  # safety net: never hang the suite
-    lines = _lines("team_handoff")
-    path = traces / "live-run.jsonl"
-    path.write_text("".join(lines[:10]), encoding="utf-8")
-
-    def writer():
-        time.sleep(0.15)
-        for i, line in enumerate(lines[10:]):
-            with open(path, "a", encoding="utf-8") as fh:
-                if i == 5:  # a line split across two writes
-                    fh.write(line[:30])
-                    fh.flush()
-                    time.sleep(0.08)
-                    fh.write(line[30:])
-                else:
-                    fh.write(line)
-            time.sleep(0.01)
-
-    t = threading.Thread(target=writer, daemon=True)
-    t.start()
-    started = time.monotonic()
-    with client.stream("GET", "/api/replay/runs/live-run/stream") as r:
-        assert r.status_code == 200
-        assert r.headers["content-type"].startswith("text/event-stream")
-        body = "".join(r.iter_text())
-    elapsed = time.monotonic() - started
-    t.join(timeout=5)
-
-    msgs = _parse_sse(body)
-    ctx = [json.loads(d) for name, d, _ in msgs if name == "ctx"]
-    assert [e["sequence_num"] for e in ctx] == list(range(36))
-    assert [ident for name, _, ident in msgs if name == "ctx"] == [str(i) for i in range(36)]
-    assert msgs[-1][0] == "end"
-    assert any(name == "ping" for name, _, _ in msgs)
-    assert elapsed < 7, "stream should end shortly after session_end + quiet period"
-
-
-def test_stream_after_seq_and_last_event_id(traces, client):
-    shutil.copy(FIXTURES / "legacy_v10.jsonl", traces / "done.jsonl")
-    with client.stream("GET", "/api/replay/runs/done/stream?after_seq=12") as r:
-        body = "".join(r.iter_text())
-    seqs = [json.loads(d)["sequence_num"] for n, d, _ in _parse_sse(body) if n == "ctx"]
-    assert seqs == [13, 14, 15]
-    # reconnect: Last-Event-ID beats an older after_seq in the URL
-    with client.stream("GET", "/api/replay/runs/done/stream?after_seq=2", headers={"Last-Event-ID": "14"}) as r:
-        body = "".join(r.iter_text())
-    seqs = [json.loads(d)["sequence_num"] for n, d, _ in _parse_sse(body) if n == "ctx"]
-    assert seqs == [15]
-
-
-def test_stream_ends_for_stale_unfinished_file(traces, client, monkeypatch):
-    from praisonaiui.features import _trace_jsonl as tj
-
-    monkeypatch.setattr(tj, "LIVE_WINDOW_S", 0.4)
-    (traces / "stale.jsonl").write_text("".join(_lines("team_handoff")[:5]), encoding="utf-8")
-    with client.stream("GET", "/api/replay/runs/stale/stream") as r:
-        body = "".join(r.iter_text())
-    msgs = _parse_sse(body)
-    assert len([m for m in msgs if m[0] == "ctx"]) == 5
-    assert msgs[-1][0] == "end" and "stale" in msgs[-1][1]
-
-
-def test_stream_restarts_when_file_is_truncated(tmp_path):
-    from praisonaiui.features import _trace_jsonl as tj
-
-    path = tmp_path / "r.jsonl"
-    lines = _lines("legacy_v10")
-    path.write_text("".join(lines), encoding="utf-8")
-    tail = tj.TailReader(path)
-    assert len(tail.poll()) == 16
-    path.write_text(lines[0], encoding="utf-8")  # writer restarted the file
-    again = tail.poll()
-    assert len(again) == 1 and again[0]["sequence_num"] == 0
-
-
-# ── registration / entry point ───────────────────────────────────────
-
-
-def test_feature_registered_by_default():
-    from praisonaiui.features import auto_register_defaults, get_feature
-
-    auto_register_defaults()
-    f = get_feature("replay")
-    assert f is not None
-    paths = {r.path for r in f.routes()}
-    assert paths == {
-        "/api/replay/runs",
-        "/api/replay/runs/{run_id}/events",
-        "/api/replay/runs/{run_id}/stream",
-    }
-
-
-def test_replay_page_and_routes_mounted_in_server(traces, isolated_server):
-    import praisonaiui as aiui
-    import praisonaiui.server as server
-
-    _copy_all(traces)
-    server.reset_state()
-    aiui.set_style("dashboard")
-    app = server.create_app()
-    c = TestClient(app)
-    pages = c.get("/api/pages").json()["pages"]
-    page = next((p for p in pages if p["id"] == "replay"), None)
-    assert page is not None
-    assert page["title"] == "Replay"
-    assert page["group"] == "Control"
-    assert page["api_endpoint"] == "/api/replay/runs"
-    assert len(c.get("/api/replay/runs").json()) == 3
-    assert c.get("/plugins/views/replay.js").status_code == 200
-    assert c.get("/plugins/views/replay-core.js").status_code == 200
-
-
-def test_replay_app_whitelists_replay_first(traces, isolated_server):
-    import praisonaiui.server as server
-    from praisonaiui.features.replay import REPLAY_PAGES, configure_replay_app
-
-    server.reset_state()
-    configure_replay_app()
-    try:
-        app = server.create_app()
-        pages = TestClient(app).get("/api/pages").json()["pages"]
-        builtin = [p["id"] for p in pages if p["id"] in REPLAY_PAGES]
-        assert builtin[0] == "replay"
-        assert set(builtin) == set(REPLAY_PAGES)
-        assert "chat" not in {p["id"] for p in pages}
-    finally:
-        server.reset_state()
-
-
-def test_replay_app_module_is_importable_and_documented():
-    import importlib
-
-    src = (Path(__file__).resolve().parents[2] / "src" / "praisonaiui" / "replay_app.py").read_text(encoding="utf-8")
-    assert "aiui run" in src and "/replay?run=" in src
-    import praisonaiui.server as server
-
-    try:
-        importlib.import_module("praisonaiui.replay_app")
-        assert server.get_style() == "dashboard"
-    finally:
-        server.reset_state()
-
-
-def test_cli_list(traces, feature):
-    _copy_all(traces)
-    out = feature._cli_list()
-    assert "team_handoff" in out and "Solar sail brief" in out
-
-
-# ── standalone export helper ─────────────────────────────────────────
-
-
-def test_standalone_html_is_self_contained():
-    from praisonaiui.features.replay import standalone_html
-
-    events = [json.loads(line) for line in _lines("team_handoff")]
-    events[3]["data"]["evil"] = "</script><script>alert(1)</script>"
-    html = standalone_html(events, title="Run <1>")
-    assert html.count("<script") == 3  # data + core + view, nothing injected
-    assert "</script><script>alert" not in html
-    assert "window.__REPLAY_DATA__" in html
-    assert "export function buildModel" in html and "export async function render" in html
-    assert "<title>Run &lt;1&gt;</title>" in html
-    for banned in ("http://", "https://", "cdn"):
-        # SVG namespace URI is a name, not a fetch
-        assert banned not in html.replace("http://www.w3.org/2000/svg", ""), banned
-    # graph is picked up from workflow_start when not passed
-    payload = html.split("window.__REPLAY_DATA__ = ", 1)[1].split(";</script>", 1)[0]
-    data = json.loads(payload)
-    assert data["graph"]["schema"] == "praisonai.graph/1"
-    assert len(data["events"]) == 36
@@ -1,149 +0,0 @@
-"""PraisonAI Replay dashboard view: registration and wiring (source-grep, like test_run_recorder)."""
-
-from __future__ import annotations
-
-import re
-import shutil
-import subprocess
-from pathlib import Path
-
-import pytest
-
-ROOT = Path(__file__).resolve().parents[2]
-FRONTEND = ROOT / "src" / "praisonaiui" / "templates" / "frontend" / "plugins"
-VIEWS = FRONTEND / "views"
-CORE = VIEWS / "replay-core.js"
-VIEW = VIEWS / "replay.js"
-
-
-def test_view_files_exist():
-    assert CORE.exists()
-    assert VIEW.exists()
-
-
-def test_replay_registered_in_builtin_views():
-    source = (FRONTEND / "dashboard.js").read_text(encoding="utf-8")
-    block = source.split("const BUILTIN_VIEWS = {", 1)[1].split("};", 1)[0]
-    assert re.search(r"^\s*replay:\s*'/plugins/views/replay\.js',", block, re.M)
-
-
-def test_dashboard_accepts_hash_deep_links():
-    source = (FRONTEND / "dashboard.js").read_text(encoding="utf-8")
-    assert "location.hash.match(" in source
-    assert "history.replaceState(null, '', `/${hashRoute[1]}" in source
-
-
-def test_core_exports_pure_api():
-    source = CORE.read_text(encoding="utf-8")
-    for fn in (
-        "export function buildModel",
-        "export function narrate",
-        "export function layoutMap",
-        "export function deriveGraph",
-    ):
-        assert fn in source, fn
-    assert "globalThis.PraisonReplayCore = api" in source
-    # pure: no DOM and no network
-    for banned in ("document.", "window.", "fetch(", "EventSource", "localStorage"):
-        assert banned not in source, banned
-
-
-def test_view_exports_render_and_cleanup():
-    source = VIEW.read_text(encoding="utf-8")
-    assert "export async function render" in source
-    assert "export function cleanup" in source
-    assert "abort" in source.lower()
-    assert "es.close()" in source
-
-
-def test_view_uses_contract_endpoints():
-    source = VIEW.read_text(encoding="utf-8")
-    for url in (
-        "/api/replay/runs",
-        "/api/replay/runs/${encodeURIComponent(id)}/events",
-        "/api/replay/runs/${encodeURIComponent(id)}/stream",
-        "/api/approvals/${encodeURIComponent(b.approvalId)}/${action}",
-        "modified_args",
-    ):
-        assert url in source, url
-
-
-def test_no_cdn_or_third_party_assets():
-    for path in (CORE, VIEW):
-        text = path.read_text(encoding="utf-8")
-        stripped = text.replace("http://www.w3.org/2000/svg", "")
-        assert "http://" not in stripped and "https://" not in stripped, path.name
-        assert not re.search(r"cdn[\w-]*\.[a-z]{2,}", stripped.lower()), path.name
-        assert "mermaid" not in stripped.lower(), path.name
-        assert not re.search(r"^\s*import .* from ['\"](?!\./|/plugins/)", text, re.M), path.name
-
-
-def test_palette_and_shapes_follow_contract():
-    core = CORE.read_text(encoding="utf-8")
-    for colour in ("#8B0000", "#0F7287", "#8A5A00", "#3C4A5C"):
-        assert colour in core
-    assert "#189AB4" not in core + VIEW.read_text(encoding="utf-8")
-    for pair in ("agent: 'circle'", "tool: 'rounded'", "human: 'diamond'", "manager: 'square'"):
-        assert pair in core
-
-
-def test_accessibility_hooks_present():
-    view = VIEW.read_text(encoding="utf-8")
-    assert "prefers-reduced-motion" in view
-    assert ":focus-visible" in view
-    assert "aria-live" in view
-    assert "role: 'tablist'" in view and "role: 'tab'" in view and "role: 'tabpanel'" in view
-    assert "aria-current" in view
-    assert "'ArrowLeft'" in view and "'ArrowRight'" in view
-    assert "praisonai replay view agents.yaml" in view
-    assert "with record(" in view
-    assert "Studio" not in view and "__start__" not in view
-
-
-def test_standalone_boot_contract():
-    view = VIEW.read_text(encoding="utf-8")
-    assert "globalThis.__REPLAY_DATA__" in view
-    assert "replay-root" in view
-    assert "globalThis.PraisonReplayCore" in view
-
-
-def test_replay_core_node_suite():
-    """Runs tests/js/replay-core.test.mjs (buildModel, narrate, layoutMap) when Node is present."""
-    node = shutil.which("node")
-    if not node:
-        pytest.skip("node not installed")
-    proc = subprocess.run(
-        [node, "--test", str(ROOT / "tests" / "js" / "replay-core.test.mjs")],
-        cwd=ROOT,
-        capture_output=True,
-        text=True,
-        timeout=120,
-    )
-    assert proc.returncode == 0, proc.stdout[-4000:] + proc.stderr[-2000:]
-    assert re.search(r"# fail 0", proc.stdout)
-
-
-def test_replay_page_uses_own_svg_mark_not_emoji_heading():
-    from praisonaiui.features.replay import REPLAY_MARK_SVG
-
-    assert REPLAY_MARK_SVG.startswith('<svg xmlns="http://www.w3.org/2000/svg"')
-    for banned in ("<script", "foreignObject", "onload", "javascript:"):
-        assert banned not in REPLAY_MARK_SVG
-    server_src = (ROOT / "src" / "praisonaiui" / "server.py").read_text(encoding="utf-8")
-    assert '"icon_svg": REPLAY_MARK_SVG' in server_src
-    dash = (FRONTEND / "dashboard.js").read_text(encoding="utf-8")
-    assert "function safeSvgIcon" in dash and "parsererror, script, foreignObject" in dash
-    assert "setPageIcon(iconSpan, page" in dash
-
-
-def test_dashboard_mobile_shell_gives_content_the_width():
-    dash = (FRONTEND / "dashboard.js").read_text(encoding="utf-8")
-    assert ".db-sidebar { position: fixed !important;" in dash
-    assert "#db-shell-header-slot { flex: 0 0 100%;" in dash
-    assert ".db-main { padding: 64px 16px 16px; }" in dash
-
-
-def test_theme_defaults_to_system():
-    view = VIEW.read_text(encoding="utf-8")
-    assert "@media (prefers-color-scheme:dark){.rp-root[data-theme=\"system\"]" in view
-    assert "'Theme: system'" in view
@@ -1,153 +0,0 @@
-"""Tracing feature reads recorded runs from the context-trace JSONL directory.
-
-The old SDKTracingManager looked up ``praisonaiagents.trace.list_traces`` /
-``list_spans`` / ``get_trace``, which do not exist, so recorded runs never
-showed up and it silently fell back to an empty in-memory store.
-"""
-
-from __future__ import annotations
-
-import shutil
-from pathlib import Path
-
-import pytest
-from starlette.applications import Starlette
-from starlette.testclient import TestClient
-
-FIXTURES = Path(__file__).resolve().parents[1] / "fixtures" / "replay"
-
-
-@pytest.fixture()
-def traces(tmp_path, monkeypatch):
-    d = tmp_path / "traces"
-    d.mkdir()
-    for name in ("team_handoff", "flow_parallel_loop", "legacy_v10"):
-        shutil.copy(FIXTURES / f"{name}.jsonl", d / f"{name}.jsonl")
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(d))
-    from praisonaiui.features import tracing
-
-    monkeypatch.setattr(tracing, "_tracing_manager", None)
-    return d
-
-
-@pytest.fixture()
-def client(traces):
-    from praisonaiui.features.tracing import TracingFeature
-
-    return TestClient(Starlette(routes=TracingFeature().routes()))
-
-
-def test_recorded_runs_are_listed_as_traces(client):
-    data = client.get("/api/traces").json()
-    ids = {t["id"] for t in data["traces"]}
-    assert {"team_handoff", "flow_parallel_loop", "legacy_v10"} <= ids
-    team = next(t for t in data["traces"] if t["id"] == "team_handoff")
-    assert team["source"] == "jsonl"
-    assert team["name"] == "Solar sail brief"
-    assert team["status"] == "completed"
-    assert team["duration_ms"] == pytest.approx(12250, abs=1)
-    assert team["span_count"] > 0
-    assert team["metadata"]["session_id"] == "sess-team-01"
-
-
-def test_agent_filter(client):
-    data = client.get("/api/traces?agent_id=Checker").json()
-    assert [t["id"] for t in data["traces"]] == ["legacy_v10"]
-
-
-def test_spans_from_start_end_pairs_via_parent_seq(client):
-    spans = client.get("/api/traces/spans?trace_id=team_handoff&limit=500").json()["spans"]
-    kinds = {}
-    for s in spans:
-        kinds[s["kind"]] = kinds.get(s["kind"], 0) + 1
-    assert kinds == {"session": 1, "workflow": 1, "llm": 5, "agent": 2, "task": 2, "tool": 4, "approval": 1}
-    by_id = {s["id"]: s for s in spans}
-    # tool span nests under the agent span that was open (parent_seq on the start)
-    tool = next(s for s in spans if s["kind"] == "tool" and s["name"] == "write_file")
-    parent = by_id[tool["parent_span_id"]]
-    assert parent["kind"] == "agent" and parent["agent_id"] == "Writer"
-    assert tool["status"] == "ok"
-    assert tool["duration_ms"] == pytest.approx(50.0)
-    assert tool["attributes"]["input"] == {"path": "docs/draft.md", "content": "[REDACTED]"}
-    # approval pairs requested -> decided by parent_seq even though the decision has no agent
-    appr = next(s for s in spans if s["kind"] == "approval")
-    assert appr["status"] == "ok"
-    assert appr["end_time"] == pytest.approx(1767225611.2)
-    # every span closed
-    assert all(s["status"] != "open" for s in spans)
-    assert all(s["trace_id"] == "team_handoff" for s in spans)
-
-
-def test_spans_for_legacy_file_fall_back_to_sequence_order(client):
-    spans = client.get("/api/traces/spans?trace_id=legacy_v10").json()["spans"]
-    by_id = {s["id"]: s for s in spans}
-    names = [(s["kind"], s["agent_id"]) for s in spans]
-    assert names == [
-        ("session", ""),
-        ("agent", "Assistant"),
-        ("llm", "Assistant"),
-        ("tool", "Assistant"),
-        ("llm", "Assistant"),
-        ("agent", "Checker"),
-        ("llm", "Checker"),
-    ]
-    calc = next(s for s in spans if s["kind"] == "tool")
-    assert by_id[calc["parent_span_id"]]["kind"] == "agent"
-    assert by_id[calc["parent_span_id"]]["agent_id"] == "Assistant"
-    checker_llm = spans[-1]
-    assert by_id[checker_llm["parent_span_id"]]["agent_id"] == "Checker"
-    assert all(s["status"] == "ok" for s in spans)
-
-
-def test_parallel_branch_spans_pair_within_branch(client):
-    spans = client.get("/api/traces/spans?trace_id=flow_parallel_loop&limit=500").json()["spans"]
-    tools = {s["name"]: s for s in spans if s["kind"] == "tool"}
-    assert tools["fetch_rss"]["duration_ms"] == pytest.approx(1250.0)
-    assert tools["search_papers"]["duration_ms"] == pytest.approx(1840.0)
-    assert tools["search_papers"]["attributes"]["branch_id"] == "gather/1"
-    assert tools["search_papers"]["attributes"]["cost_usd"] == pytest.approx(0.001)
-
-
-def test_get_trace_and_unknown(client):
-    r = client.get("/api/traces/legacy_v10")
-    assert r.status_code == 200
-    body = r.json()
-    assert body["trace"]["id"] == "legacy_v10"
-    assert len(body["spans"]) == 7
-    assert client.get("/api/traces/does-not-exist").status_code == 404
-    assert client.get("/api/traces/../../etc/passwd").status_code == 404
-
-
-def test_health_reports_source(client, tmp_path, monkeypatch):
-    status = client.get("/api/traces/status").json()
-    assert status["source"] == "jsonl"
-    assert status["jsonl_traces"] == 3
-    from praisonaiui.features import tracing
-
-    monkeypatch.setenv("PRAISONAI_TRACES_DIR", str(tmp_path / "empty"))
-    monkeypatch.setattr(tracing, "_tracing_manager", None)
-    assert client.get("/api/traces/status").json()["source"] == "memory"
-
-
-def test_recorded_in_memory_traces_still_work(client):
-    r = client.post("/api/traces/record", json={"type": "trace", "id": "mem-1", "name": "manual"})
-    assert r.status_code == 200
-    ids = [t["id"] for t in client.get("/api/traces?limit=100").json()["traces"]]
-    assert "mem-1" in ids and "team_handoff" in ids
-    assert client.get("/api/traces/mem-1").json()["trace"]["name"] == "manual"
-
-
-def test_no_dead_sdk_lookups_remain():
-    src = (Path(__file__).resolve().parents[2] / "src" / "praisonaiui" / "features" / "tracing.py").read_text(encoding="utf-8")
-    for dead in ('"list_traces", None', '"list_spans", None', '"get_trace", None', "trace_module"):
-        assert dead not in src
-    from praisonaiui.features.tracing import JsonlTracingManager, SDKTracingManager
-
-    assert SDKTracingManager is JsonlTracingManager  # deprecated alias kept for imports
-
-
-def test_cli_status_mentions_source(traces):
-    from praisonaiui.features.tracing import TracingFeature
-
-    out = TracingFeature()._cli_status()
-    assert "Source: jsonl" in out
@@ -1,5 +1,5 @@
 version = 1
-revision = 5
+revision = 3
 requires-python = ">=3.10"
 resolution-markers = [
    "python_full_version >= '3.14' and sys_platform == 'win32'",
@@ -207,7 +207,7 @@ wheels = [

 [[package]]
 name = "aiui"
-version = "0.3.151"
+version = "0.3.147"
 source = { editable = "." }
 dependencies = [
    { name = "pydantic" },