fix(openwebui): guarantee answer after tool budget

platform/openwebui/Dockerfile

@@ -0,0 +1,7 @@
+FROM ghcr.io/open-webui/open-webui:v0.9.5
+
+COPY platform/openwebui/patch_tool_finalization.py /tmp/patch_tool_finalization.py
+RUN python /tmp/patch_tool_finalization.py \
+      /app/backend/open_webui/utils/middleware.py \
+    && rm /tmp/patch_tool_finalization.py
+

platform/openwebui/filters/stability_guard.py

@@ -1,7 +1,7 @@
 """
 title: MikeAI Stability Guard
 author: MikeAI
-version: 2.1.0
+version: 2.2.0
 description: Bounds tool output and context use and breaks repeated tool-call loops.
 """
 
@@ -29,9 +29,9 @@ class Filter:
         max_total_tool_chars: int = 36000
         compacted_tool_chars: int = 2000
         duplicate_tool_call_limit: int = 2
-        # OpenWebUI itself stops after twelve rounds without giving the model
-        # another completion. Stay below that ceiling so the model still gets
-        # a final, tool-free turn.
+        # Secondary protection for histories that re-enter the filter. The
+        # live internal tool loop is bounded and finalized by the derived
+        # OpenWebUI image because inlet filters do not run between its rounds.
         max_tool_calls_per_turn: int = 10
         max_private_table_tool_calls: int = 6
 

platform/openwebui/install-filters.sh

@@ -237,7 +237,9 @@ with con:
                 "Für Repository-Suche, echte Datei-Inhalte und gezielte "
                 "Code-Suche auf GitHub. Bei Fragen zu Implementierung, README, API-Routen oder "
                 "Quellcode dieses Werkzeug statt allgemeiner Websuche verwenden. Keine Issues, "
-                "Pull Requests, Actions, rekursiven Komplettbäume oder Schreibzugriffe.",
+                "Pull Requests, Actions, rekursiven Komplettbäume oder Schreibzugriffe. Bei einem "
+                "konkreten Repository zuerst README beziehungsweise Wurzel einmal lesen, danach "
+                "höchstens drei gezielte Code-Suchen und nur relevante Trefferdateien öffnen.",
             ),
             "athena-operator-local": (
                 "Athena Operator",

platform/openwebui/install-models.sh

@@ -213,7 +213,13 @@ params = {
         "For GitHub repository implementation details, README files, source trees, "
         "API routes, or code search, use the dedicated official GitHub repository "
         "tool instead of guessing from ordinary web results. Use general web search "
-        "for wider public discussion and non-repository sources. "
+        "for wider public discussion and non-repository sources. For one named repository, "
+        "do not enumerate files recursively. Read the root README or one root listing once, "
+        "then use one to three targeted code searches for terms such as route, API, CLI, "
+        "endpoint, command or the relevant framework, and open only the few matching files "
+        "needed for evidence. If a live deployment is also mentioned, inspect that service "
+        "once with its domain tool. Normally finish within six GitHub calls and always "
+        "synthesize an answer from the evidence already obtained. "
         "If a specialist tool returns an authentication, authorization, connection, "
         "or configuration error, do not repeat the same call. Report the error. For "
         "public information you may make at most one focused fallback attempt with "

platform/openwebui/patch_tool_finalization.py

@@ -0,0 +1,91 @@
+#!/usr/bin/env python3
+"""Make Open WebUI finish with an answer when its internal tool budget is used.
+
+Open WebUI 0.9.5 otherwise ends the request with only
+``Tool-call limit reached``.  The patch is deliberately assertion-based: an
+upstream source change makes the image build fail instead of silently applying
+the modification at the wrong location.
+"""
+
+from pathlib import Path
+import sys
+
+
+if len(sys.argv) != 2:
+    raise SystemExit("usage: patch_tool_finalization.py MIDDLEWARE_PY")
+
+path = Path(sys.argv[1])
+source = path.read_text()
+
+patch_marker = "The tool budget for this turn is exhausted. Do not call"
+if patch_marker in source:
+    raise SystemExit("Open WebUI tool-finalization patch is already present")
+
+needle = """                        res = await generate_chat_completion(
+                            request,
+                            new_form_data,
+                            user,
+                            bypass_system_prompt=True,
+                        )
+"""
+
+replacement = """                        # The upstream loop otherwise stops with only
+                        # `Tool-call limit reached` after executing this batch. Reserve
+                        # the final completion for synthesis: keep every accumulated
+                        # result, but expose no tools to the model and explicitly require
+                        # a useful, evidence-bounded answer.
+                        force_final_response = (
+                            max_tool_call_iterations is not None
+                            and tool_call_iterations >= max_tool_call_iterations
+                        )
+                        if force_final_response:
+                            new_form_data.pop('tools', None)
+                            new_form_data.pop('tool_ids', None)
+                            final_metadata = dict(metadata)
+                            final_metadata['tools'] = {}
+                            final_metadata['tool_ids'] = []
+                            final_metadata['tool_servers'] = []
+                            new_form_data['metadata'] = final_metadata
+                            new_form_data['messages'] = add_or_update_system_message(
+                                'The tool budget for this turn is exhausted. Do not call '
+                                'or imitate any more tools. Give the user a concise final '
+                                'answer now using only the tool results already present. '
+                                'Explicitly distinguish verified findings from inference, '
+                                'and state what could not be verified. Never end without a '
+                                'visible answer.',
+                                new_form_data['messages'],
+                                append=True,
+                            )
+
+                        res = await generate_chat_completion(
+                            request,
+                            new_form_data,
+                            user,
+                            bypass_system_prompt=True,
+                        )
+"""
+
+if source.count(needle) != 1:
+    raise SystemExit(
+        f"expected exactly one Open WebUI continuation anchor, found {source.count(needle)}"
+    )
+source = source.replace(needle, replacement)
+
+needle = """                            await stream_body_handler(res, new_form_data)
+                            output[:0] = prior_output
+"""
+replacement = """                            await stream_body_handler(res, new_form_data)
+                            if force_final_response:
+                                # A model may still print tool-shaped output after the
+                                # schemas were removed. It must not trigger the upstream
+                                # hard-error path or another execution attempt.
+                                tool_calls.clear()
+                            output[:0] = prior_output
+"""
+if source.count(needle) != 1:
+    raise SystemExit(
+        f"expected exactly one Open WebUI stream anchor, found {source.count(needle)}"
+    )
+source = source.replace(needle, replacement)
+
+path.write_text(source)