fable-engine 1.3.3__tar.gz → 1.3.5__tar.gz

{fable_engine-1.3.3/fable_engine.egg-info → fable_engine-1.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: fable-engine
-Version: 1.3.3
+Version: 1.3.5
 Summary: Independent deterministic System 2 cognitive engine and mechanical time-lock MCP server
 Author: REX-codebase
 License: MIT License
@@ -116,7 +116,7 @@ pip install fable-engine
 
 Or install the MCP server in your editor:
 
-[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.3%22%2C%22fable-engine%22%5D%7D)
+[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.5%22%2C%22fable-engine%22%5D%7D)
 [![Add to Cursor](https://img.shields.io/badge/Cursor-Add_MCP_server-black)](cursor://anysphere.cursor-deeplink/mcp/install?name=fable-engine&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJmYWJsZS1lbmdpbmU9PTEuMy4zIiwiZmFibGUtZW5naW5lIl19)
 
 These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They do not install a standalone editor extension. Both use `uvx`, which downloads and runs the pinned PyPI release in an isolated environment.
@@ -124,13 +124,13 @@ These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They
 Point your agent at the MCP server manually:
 
 ```jsonc
-// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.3 fable-engine
+// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.5 fable-engine
 // Cursor: ~/.cursor/mcp.json
 {
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.3", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.5", "fable-engine"]
     }
   }
 }
@@ -152,7 +152,7 @@ The complete skill tree ships inside the wheel. To install it into your
 project's skills directory (the cross-client `.agents/skills/` convention):
 
 ```bash
-uvx --from fable-engine==1.3.3 fable-mode install-skill --yes
+uvx --from fable-engine==1.3.5 fable-mode install-skill --yes
 ```
 
 This copies the skill to `.agents/skills/fable-mode`. Preview first with

{fable_engine-1.3.3 → fable_engine-1.3.5}/README.md

@@ -73,7 +73,7 @@ pip install fable-engine
 
 Or install the MCP server in your editor:
 
-[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.3%22%2C%22fable-engine%22%5D%7D)
+[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.5%22%2C%22fable-engine%22%5D%7D)
 [![Add to Cursor](https://img.shields.io/badge/Cursor-Add_MCP_server-black)](cursor://anysphere.cursor-deeplink/mcp/install?name=fable-engine&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJmYWJsZS1lbmdpbmU9PTEuMy4zIiwiZmFibGUtZW5naW5lIl19)
 
 These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They do not install a standalone editor extension. Both use `uvx`, which downloads and runs the pinned PyPI release in an isolated environment.
@@ -81,13 +81,13 @@ These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They
 Point your agent at the MCP server manually:
 
 ```jsonc
-// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.3 fable-engine
+// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.5 fable-engine
 // Cursor: ~/.cursor/mcp.json
 {
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.3", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.5", "fable-engine"]
     }
   }
 }
@@ -109,7 +109,7 @@ The complete skill tree ships inside the wheel. To install it into your
 project's skills directory (the cross-client `.agents/skills/` convention):
 
 ```bash
-uvx --from fable-engine==1.3.3 fable-mode install-skill --yes
+uvx --from fable-engine==1.3.5 fable-mode install-skill --yes
 ```
 
 This copies the skill to `.agents/skills/fable-mode`. Preview first with

{fable_engine-1.3.3 → fable_engine-1.3.5}/docs/stop-ai-agents-writing-too-early.md

@@ -18,13 +18,13 @@ Fable Mode separates research from authority. A session begins with execution lo
 Install [uv](https://docs.astral.sh/uv/getting-started/installation/) so your MCP client can run the package without changing your global Python environment.
 
 ```bash
-uvx --from fable-engine==1.3.3 fable-engine
+uvx --from fable-engine==1.3.5 fable-engine
 ```
 
 For Claude Code:
 
 ```bash
-claude mcp add fable-engine -- uvx --from fable-engine==1.3.3 fable-engine
+claude mcp add fable-engine -- uvx --from fable-engine==1.3.5 fable-engine
 ```
 
 For an MCP client that uses JSON configuration:
@@ -34,7 +34,7 @@ For an MCP client that uses JSON configuration:
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.3", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.5", "fable-engine"]
     }
   }
 }
@@ -68,7 +68,7 @@ It is not a guarantee of correct code. It makes the path to write access explici
 The package has no runtime dependencies. You can confirm the pinned release and inspect its MCP initialization response in an isolated environment before adding it to an editor or agent:
 
 ```bash
-uvx --from fable-engine==1.3.3 fable-engine
+uvx --from fable-engine==1.3.5 fable-engine
 ```
 
 The server communicates over standard input and output. MCP clients start and manage that process for you after configuration.

{fable_engine-1.3.3 → fable_engine-1.3.5}/fable_engine/fable_session.json

@@ -1,15 +1,21 @@
 {
   "name": "fable_session",
-  "description": "Fable Cognitive Engine Session & Telemetry Manager for MCP-compatible agent hosts.\nEnforces immutable authority time-locks, evidence-gated epistemic tracking, formal invariant modeling, continuous rethink-refine cycles, phased progression, subagent delegation contract compilation, internal pacing telemetry, token compression subsystem (Content-Addressed Storage, 0.003 tokens/character invariant), and System 3 Meta-Cognitive Deliberation & Dialectical Evolutionary Architecture (Pearl do-calculus, TRIZ contradiction synthesis, 10D Pareto genetic search, axiom induction, Poincaré hyperbolic embeddings, Kripke modal model checking, Friston active inference, and Gödelian constructive proof oracle).",
+  "description": "Runs one Fable operation selected by action. Use it for Fable sessions, gates, evidence and proofs, review rubrics, checkpoints, compression, design audits, research scrapers, and experimental System 3 operations; use browser tools for web-page interaction. Start stateful workflows with create_session and session_name, then reuse that name. Only the selected action's fields apply. Read-only status, list, telemetry, get, view, and check actions do not persist state; create, log, record, set, advance, checkpoint, restore, track, evaluate, register, compression, generation, evolution, scraper, and update actions can persist state or artifacts. unlock_execution blocks until its gates pass, and apply_auto_update can replace installed files. Results are action-specific text; failures begin with Error:.",
   "parameters": {
     "properties": {
       "a_matrix": {
         "description": "Observation likelihood matrix A [O x S] for Active Inference.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "actions": {
         "description": "List of control action identifiers for Active Inference POMDP.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "action": {
         "description": "The Fable session action to perform.",
@@ -88,11 +94,17 @@
       },
       "axioms": {
         "description": "List of reference axiom names or strings for proof oracle.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "b_matrices": {
         "description": "State transition matrices B [Action -> S x S] for Active Inference.",
-        "type": ["object", "string"]
+        "type": [
+          "object",
+          "string"
+        ]
       },
       "base_step": {
         "description": "Base geodesic step distance for hyperbolic tree embedding (default 1.0).",
@@ -100,7 +112,10 @@
       },
       "c_preferences": {
         "description": "Prior preference distribution C over observations for Active Inference.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "cas_ref": {
         "description": "CAS reference URI (cas://<sha256_hex>) or 64-char hash to retrieve, slice, or decompress.",
@@ -116,7 +131,10 @@
       },
       "context": {
         "description": "Hypothesis typing context dictionary {name: type} for proof oracle.",
-        "type": ["object", "string"]
+        "type": [
+          "object",
+          "string"
+        ]
       },
       "contradiction_density": {
         "description": "Contradiction density index [0.0, 1.0] for System 3 cognitive gear shifting.",
@@ -124,7 +142,10 @@
       },
       "contradictions": {
         "description": "List of parameter trade-offs / contradictions to resolve with TRIZ principles.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "critique_or_bottleneck": {
         "description": "Critical flaw, vulnerability, edge case, memory/latency bottleneck, or assumption scrutinized.",
@@ -135,15 +156,18 @@
         "type": "number"
       },
       "curvature": {
-        "description": "Sectional curvature c > 0 of Poincaré manifold (default 1.0).",
+        "description": "Sectional curvature c > 0 of Poincar\u00e9 manifold (default 1.0).",
         "type": "number"
       },
       "d_prior": {
         "description": "Prior initial state belief distribution D for Active Inference.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "dimension": {
-        "description": "Dimension of Poincaré ball manifold (default 2).",
+        "description": "Dimension of Poincar\u00e9 ball manifold (default 2).",
         "type": "integer"
       },
       "domain": {
@@ -152,7 +176,10 @@
       },
       "edges": {
         "description": "List of directed edge dictionaries for Causal DAG construction.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "end_line": {
         "description": "Ending line number (1-indexed inclusive) for windowed line slice viewing.",
@@ -172,7 +199,10 @@
       },
       "failure_modes": {
         "description": "List of adversarial failure modes identified in critique.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "focus_area": {
         "description": "Specific subsystem, component, algorithm, or interface being critically re-evaluated.",
@@ -208,7 +238,10 @@
       },
       "interventions": {
         "description": "Dictionary of Pearl's do-operator interventions: {node_id: value}.",
-        "type": ["object", "string"]
+        "type": [
+          "object",
+          "string"
+        ]
       },
       "invariant_name": {
         "description": "Identifier or title of the formal invariant (e.g., 'INV-01: Zero-Deadlock Ring Buffer').",
@@ -248,11 +281,17 @@
       },
       "node_labels": {
         "description": "Optional mapping of node IDs to readable labels.",
-        "type": ["object", "string"]
+        "type": [
+          "object",
+          "string"
+        ]
       },
       "nodes": {
         "description": "List of node dictionaries for Causal DAG construction.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "objective": {
         "description": "High-level goal or problem statement for the reasoning session.",
@@ -260,7 +299,10 @@
       },
       "objective_weights": {
         "description": "Optional dictionary of weights across the 10 Pareto dimensions.",
-        "type": ["object", "string"]
+        "type": [
+          "object",
+          "string"
+        ]
       },
       "observation": {
         "description": "Current sensory observation for Active Inference belief updating.",
@@ -268,7 +310,10 @@
       },
       "observations": {
         "description": "List of observation identifiers for Active Inference POMDP.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "payload": {
         "description": "Micro-payload text for adaptive batch accumulator or CAS storage.",
@@ -280,7 +325,10 @@
       },
       "policies": {
         "description": "List of candidate action sequence policies for Expected Free Energy evaluation.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "population_size": {
         "description": "Population size for evolutionary gene pool (default 12).",
@@ -304,7 +352,10 @@
       },
       "seed_paradigms": {
         "description": "Optional list of initial paradigm definitions to seed the gene pool.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "session_name": {
         "description": "Unique identifier / name for the Fable session.",
@@ -316,7 +367,10 @@
       },
       "states": {
         "description": "List of hidden state identifiers for Active Inference POMDP.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "subagent_prompt": {
         "description": "The delegation prompt or contract text for the subagent to validate.",
@@ -361,23 +415,42 @@
       },
       "transitions": {
         "description": "List of transitions or adjacency dictionary for Kripke structure.",
-        "type": ["array", "object", "string"]
+        "type": [
+          "array",
+          "object",
+          "string"
+        ]
       },
       "tree": {
         "description": "Tree hierarchy adjacency list or nested dict for hyperbolic embedding.",
-        "type": ["object", "array", "string"]
+        "type": [
+          "object",
+          "array",
+          "string"
+        ]
       },
       "worlds": {
         "description": "List of world/state definitions for Kripke structure.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "affected_invariants": {
         "description": "List or string of invariant names affected by this file change.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "change_type": {
         "description": "Classification of file change ('modified', 'created', 'deleted', 'slated').",
-        "enum": ["modified", "created", "deleted", "slated"],
+        "enum": [
+          "modified",
+          "created",
+          "deleted",
+          "slated"
+        ],
         "type": "string"
       },
       "diff_summary": {
@@ -390,11 +463,20 @@
       },
       "mockups": {
         "description": "List of concept dictionaries for visual mockup recording.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "proof_type": {
         "description": "Deterministic proof type ('ast', 'receipt', 'file_sha256', 'formal_logic', 'vector_coordinates').",
-        "enum": ["ast", "receipt", "file_sha256", "formal_logic", "vector_coordinates"],
+        "enum": [
+          "ast",
+          "receipt",
+          "file_sha256",
+          "formal_logic",
+          "vector_coordinates"
+        ],
         "type": "string"
       },
       "selected_concept": {
@@ -407,7 +489,10 @@
       },
       "criteria": {
         "description": "List of criteria dictionaries or pointer strings for goal scoring rubric.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "rubric_id": {
         "description": "Identifier for the goal scoring rubric contract.",
@@ -419,7 +504,10 @@
       },
       "evaluations": {
         "description": "List of criterion evaluation dictionaries or score updates for evaluate_goal_rubric.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "pipeline_name": {
         "description": "Name or identifier of the autonomous closed-loop pipeline.",
@@ -455,11 +543,17 @@
       },
       "custom_hypotheses": {
         "description": "List or JSON string of custom adversarial hypotheses / attack vectors.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "broken_scenarios": {
         "description": "List or JSON string of broken attack scenarios found during red-team review.",
-        "type": ["array", "string"]
+        "type": [
+          "array",
+          "string"
+        ]
       },
       "remediated_code": {
         "description": "Remediated code submitted to verify against broken scenarios.",
@@ -467,7 +561,10 @@
       },
       "prior_report": {
         "description": "Prior red-team breakage report dictionary or JSON string to verify remediation against.",
-        "type": ["object", "string"]
+        "type": [
+          "object",
+          "string"
+        ]
       },
       "task_id": {
         "description": "Task identifier for cortical plasticity consolidation or session lineage.",

{fable_engine-1.3.3 → fable_engine-1.3.5}/fable_engine/schema.py

@@ -13,13 +13,40 @@ from fable_engine.session import PHASES
 
 TOOL_SCHEMA = {
     "name": "fable_session",
+    "title": "Fable session, evidence, and review workflow",
     "description": (
-        "Fable Cognitive Engine Session & Telemetry Manager for MCP-compatible agent hosts.\n"
-        "Enforces DeepThink cognitive rigor, hard mechanical time-lock, anti-rush execution lockout, epistemic truth logging (PROVEN/HYPOTHESIS/UNKNOWN),\n"
-        "formal domain invariant modeling, continuous rethink-refine cycles, phased progression gating, subagent delegation contract compilation,\n"
-        "live user-controlled time-budgeted pacing telemetry, token compression subsystem (Content-Addressed Storage, 0.003 tokens/character invariant),\n"
-        "and System 3 Meta-Cognitive Deliberation & Dialectical Evolutionary Architecture (Pearl do-calculus, TRIZ contradiction synthesis, 10D Pareto genetic search, axiom induction)."
+        "Runs one Fable operation selected by `action`. Use it for Fable sessions, gates, "
+        "evidence/proofs, review rubrics, checkpoints, compression, design audits, research "
+        "scrapers, and explicitly experimental System 3 operations; use browser_* tools for "
+        "web-page navigation and interaction. Start stateful workflows with `create_session` "
+        "and a `session_name`; later session actions reuse that name. Only fields documented "
+        "for the selected action are read, and missing or invalid inputs return an `Error:` "
+        "message without raising an MCP transport error. Status/list/telemetry/get/view/check "
+        "operations are read-only. Create, log, record, set, advance, checkpoint, restore, "
+        "track, evaluate, register, compress/accumulate, evolve, generate, and scraper "
+        "operations can persist Fable state or artifacts. `unlock_execution` remains blocked "
+        "until its time and rationale gates pass; `apply_auto_update` can replace installed "
+        "Fable files. The result is action-specific human-readable text in `result`; inspect "
+        "that text for success or `Error:` before continuing."
     ),
+    "annotations": {
+        "title": "Fable session, evidence, and review workflow",
+        "readOnlyHint": False,
+        "destructiveHint": True,
+        "idempotentHint": False,
+        "openWorldHint": True,
+    },
+    "outputSchema": {
+        "type": "object",
+        "properties": {
+            "result": {
+                "type": "string",
+                "description": "Action-specific result text. Failures begin with `Error:`."
+            }
+        },
+        "required": ["result"],
+        "additionalProperties": False,
+    },
     "inputSchema": {
         "type": "object",
         "properties": {
@@ -571,7 +598,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_navigate",
-        "description": "Navigates the browser session to a new URL.",
+        "title": "Navigate current browser session",
+        "annotations": {"title": "Navigate current browser session", "readOnlyHint": False, "destructiveHint": False, "idempotentHint": False, "openWorldHint": True},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Loads `url` into an existing browser session, replacing its current document and adding a history entry. Use this instead of browser_open when continuing in a known session; if `session_id` is omitted, the active session is reused or a default session is created. It waits up to `timeout` seconds and returns the resulting URL, title, viewport, scroll position, and indexed elements; network, timeout, size, and parse failures return an error object without changing committed page state.",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -602,7 +632,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_type",
-        "description": "Types text into an input field identified by its stable element ID.",
+        "title": "Replace text field value",
+        "annotations": {"title": "Replace text field value", "readOnlyHint": False, "destructiveHint": False, "idempotentHint": False, "openWorldHint": False},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Replaces the full value of a text-like input or textarea identified by `element_id`; it does not submit the form. Use browser_press for single-key edits or activation. An omitted `session_id` targets the active/default session. Returns status `typed`, the element ID, and the supplied text; missing or non-editable elements return an error object and are not changed.",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -627,7 +660,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_snapshot_layers",
-        "description": "Captures N sequential screen-sized viewport PNG snapshots (1 layer = 1 PC viewport height, 1280x800 px).",
+        "title": "Capture layered page snapshots",
+        "annotations": {"title": "Capture layered page snapshots", "readOnlyHint": True, "destructiveHint": False, "idempotentHint": False, "openWorldHint": False},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Captures up to `max_layers` PNGs from the top of the current document, one 1280x800 viewport per layer, without changing the session scroll position. Use this for multi-viewport page coverage; use browser_screenshot for only the current viewport. An omitted `session_id` targets the active/default session. Returns layer count, offsets, dimensions, and base64 PNG data; `max_layers` defaults to 3 and is capped at 10.",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -638,7 +674,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_screenshot",
-        "description": "Captures a single viewport PNG snapshot of the current scroll position.",
+        "title": "Capture current viewport",
+        "annotations": {"title": "Capture current viewport", "readOnlyHint": True, "destructiveHint": False, "idempotentHint": False, "openWorldHint": False},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Captures one 1280x800 PNG of the current viewport without navigation or scroll changes. Use this for the visible region; use browser_snapshot_layers for multi-viewport coverage. An omitted `session_id` targets the active/default session. Returns one layer with its offset, dimensions, and base64 PNG data.",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -648,7 +687,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_close",
-        "description": "Closes an active browser tab session.",
+        "title": "Close browser session",
+        "annotations": {"title": "Close browser session", "readOnlyHint": False, "destructiveHint": True, "idempotentHint": False, "openWorldHint": False},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Closes and permanently discards one in-memory browser session, including its current document and history; persistent profile cookies remain saved. Use it when that tab is no longer needed. `session_id` targets a specific session; if omitted, the active session is closed. Returns `closed`, or `not_found` without changing another session.",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -658,7 +700,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_back",
-        "description": "Navigates back in history for the browser session.",
+        "title": "Go back in browser history",
+        "annotations": {"title": "Go back in browser history", "readOnlyHint": False, "destructiveHint": False, "idempotentHint": False, "openWorldHint": True},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Loads the previous history entry in the active or named browser session without adding a new history entry. Use it for history traversal rather than browser_navigate. If history is already at its first entry, it is a no-op that returns current page status. A navigation failure returns an error and preserves the history index; omitting `session_id` reuses or creates the active/default session.",
         "inputSchema": {
             "type": "object",
             "properties": {
@@ -668,7 +713,10 @@ BROWSER_TOOL_SCHEMAS = [
     },
     {
         "name": "browser_forward",
-        "description": "Navigates forward in history for the browser session.",
+        "title": "Go forward in browser history",
+        "annotations": {"title": "Go forward in browser history", "readOnlyHint": False, "destructiveHint": False, "idempotentHint": False, "openWorldHint": True},
+        "outputSchema": {"type": "object", "additionalProperties": True},
+        "description": "Loads the next history entry in the active or named browser session without adding a new history entry. Use it after browser_back rather than browser_navigate. If no forward entry exists, it is a no-op that returns current page status. A navigation failure returns an error and preserves the history index; omitting `session_id` reuses or creates the active/default session.",
         "inputSchema": {
             "type": "object",
             "properties": {

{fable_engine-1.3.3 → fable_engine-1.3.5}/fable_engine/scrapers/base.py

@@ -25,7 +25,7 @@ from typing import Any, Dict, List, Optional, Tuple
 
 logger = logging.getLogger("fable-engine.scrapers.base")
 
-USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 FableResearch/1.3.3"
+USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 FableResearch/1.3.5"
 
 MAX_RETRY_DELAY_SECONDS = 10.0
 

{fable_engine-1.3.3 → fable_engine-1.3.5}/fable_engine/server.py

@@ -237,7 +237,7 @@ def main():
                     },
                     "serverInfo": {
                         "name": "fable-engine",
-                        "version": "1.3.3"
+                        "version": "1.3.5"
                     }
                 }
             })
@@ -282,6 +282,7 @@ def main():
                                     "text": result_text
                                 }
                             ],
+                            "structuredContent": {"result": result_text},
                             "isError": False
                         }
                     })
@@ -370,6 +371,7 @@ def main():
                                     "text": json.dumps(res, indent=2)
                                 }
                             ],
+                            "structuredContent": res if isinstance(res, dict) else {"result": res},
                             "isError": is_error
                         }
                     })

{fable_engine-1.3.3 → fable_engine-1.3.5}/fable_engine/session.py

@@ -1530,7 +1530,7 @@ class FableSession:
     def to_dict(self) -> Dict[str, Any]:
         """Serializes session to dictionary."""
         return {
-            "version": "1.3.3",
+            "version": "1.3.5",
             "session_name": self.session_name,
             "session_id": self.session_id,
             "objective": self.objective,