Gateway systemd service Python environment path issues

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #8861 fix(gateway): keep venv python symlink unresolved in systemd unit

  merged to main

  files: hermes_cli/gateway.py

  Show the diff

  • hermes_cli/gateway.py

    @@ -768,14 +768,22 @@ def _remap_path_for_user(path: str, target_home_dir: str) -> str:
     
           /root/.hermes/hermes-agent  -> /home/alice/.hermes/hermes-agent
           /opt/hermes                 -> /opt/hermes  (kept as-is)
    +
    +    Note: this function intentionally does NOT resolve symlinks. A venv's
    +    ``bin/python`` is typically a symlink to the base interpreter (e.g. a
    +    uv-managed CPython at ``~/.local/share/uv/python/.../python3.11``);
    +    resolving that symlink swaps the unit's ``ExecStart`` to a bare Python
    +    that has none of the venv's site-packages, so the service crashes on
    +    the first ``import``. Keep the symlinked path so the venv activates
    +    its own environment. Lexical expansion only via ``expanduser``.
         """
    -    current_home = Path.home().resolve()
    -    resolved = Path(path).resolve()
    +    current_home = Path.home()
    +    p = Path(path).expanduser()
         try:
    -        relative = resolved.relative_to(current_home)
    +        relative = p.relative_to(current_home)
             return str(Path(target_home_dir) / relative)
         except ValueError:
    -        return str(resolved)
    +        return str(p)
     
     
     def _hermes_home_for_target_user(target_home_dir: str) -> str:

• #10093 fix: compression model falls back to main model on permanent 503/404 (#8620)

  merged to main

  files: agent/context_compressor.py

  Show the diff

  • agent/context_compressor.py

    @@ -693,6 +693,7 @@ def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]], focus_topi
                 # Store for iterative updates on next compaction
                 self._previous_summary = summary
                 self._summary_failure_cooldown_until = 0.0
    +            self._summary_model_fallen_back = False
                 return self._with_summary_prefix(summary)
             except RuntimeError:
                 # No provider configured — long cooldown, unlikely to self-resolve
    @@ -703,6 +704,34 @@ def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]], focus_topi
                                 _SUMMARY_FAILURE_COOLDOWN_SECONDS)
                 return None
             except Exception as e:
    +            # If the summary model is different from the main model and the
    +            # error looks permanent (model not found, 503, 404), fall back to
    +            # using the main model instead of entering cooldown that leaves
    +            # context growing unbounded.  (#8620 sub-issue 4)
    +            _status = getattr(e, "status_code", None) or getattr(getattr(e, "response", None), "status_code", None)
    +            _err_str = str(e).lower()
    +            _is_model_not_found = (
    +                _status in (404, 503)
    +                or "model_not_found" in _err_str
    +                or "does not exist" in _err_str
    +                or "no available channel" in _err_str
    +            )
    +            if (
    +                _is_model_not_found
    +                and self.summary_model
    +                and self.summary_model != self.model
    +                and not getattr(self, "_summary_model_fallen_back", False)
    +            ):
    +                self._summary_model_fallen_back = True
    +                logging.warning(
    +                    "Summary model '%s' not available (%s). "
    +                    "Falling back to main model '%s' for compression.",
    +                    self.summary_model, e, self.model,
    +                )
    +                self.summary_model = ""  # empty = use main model
    +                self._summary_failure_cooldown_until = 0.0  # no cooldown
    +                return self._generate_summary(messages, summary_budget)  # retry immediately
    +
                 # Transient errors (timeout, rate limit, network) — shorter cooldown
                 _transient_cooldown = 60
                 self._summary_failure_cooldown_until = time.monotonic() + _transient_cooldown