read_file_tool resolves relative paths against TERMINAL_CWD (or the
task's live terminal cwd), but the prior call passed the original
unresolved string to get_read_block_error. That function's own
resolve() is anchored at the Python process cwd, so when a task's
TERMINAL_CWD pointed at HERMES_HOME and the agent issued read_file
on the relative path "auth.json", the credential-store denylist was
never reached and the file was read normally.
Pass the already-resolved absolute path string at the file_tools call
site, document the contract on get_read_block_error, and add a
read_file_tool-level regression test that pins the relative-path
case under TERMINAL_CWD == HERMES_HOME.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`get_read_block_error` previously only denied reads inside
`${HERMES_HOME}/skills/.hub`, which left `auth.json` (provider OAuth
state + plaintext API keys) and `.anthropic_oauth.json` (Anthropic PKCE
tokens) directly readable by the agent. A prompt-injection reaching
`read_file` could exfiltrate active provider credentials in plaintext.
Mode-0600 file permissions only protect against *other Unix users* —
the agent runs as the file's owner, so `read_file` is unaffected.
Extend the existing deny list with the three credential paths
identified in #17656 (`auth.json`, `auth.lock`, `.anthropic_oauth.json`).
The check uses the same `Path.resolve()` pattern as `skills/.hub`, so
symlink/path-traversal indirection is caught too. The agent doesn't
need to read these directly — `auxiliary_client` and `credential_pool`
consume them through process env / OAuth flows that bypass `read_file`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Move the autouse `_disable_lazy_stt_install` fixture out of the three
transcription test files and into `tests/tools/conftest.py` as a regular
(non-autouse) fixture. Each transcription test module opts in once at
the top via `pytestmark = pytest.mark.usefixtures(...)`.
Why: addresses three Copilot inline review comments on this PR that
flagged the verbatim duplication across files. Centralizing also keeps
the patch target in a single place, so a future rename of
`_try_lazy_install_stt` only updates one location.
Why opt-in (not autouse in conftest): other `tests/tools/` files do not
patch `_HAS_FASTER_WHISPER` and have no reason to bypass the runtime
lazy-install probe; making the fixture autouse globally would silently
mask any future test that wants to exercise the real lazy-install path.
`b5c6d9ac0` ("fix: wire STT lazy-install into transcription_tools.py")
added `_try_lazy_install_stt()`, which calls
`importlib.util.find_spec("faster_whisper")` after `ensure()` runs.
In the dev / CI environment `faster_whisper` is already installed, so
the probe returns truthy and `_get_provider()` returns "local" even
when the test has patched `_HAS_FASTER_WHISPER=False` to simulate
"not installed".
Add a per-file autouse fixture that patches `_try_lazy_install_stt`
to return False so the simulation stays accurate. The 16 baseline
failures across `test_transcription_tools.py`,
`test_transcription.py`, and `test_transcription_dotenv_fallback.py`
disappear; the production lazy-install path is unaffected at runtime.
Four findings from Copilot's review on PR #22891, all in the AX
elements-array cap added by 22fa1ed:
1. The truncation note ("response truncated to N of M elements") was
appended unconditionally — including in the som/vision multimodal
path, whose response carries a screenshot rather than an `elements`
array. The note described a payload field that wasn't present.
Moved the note into the AX-text branch where the array actually
appears.
2. `_format_elements(cap.elements)` ran on the full untrimmed list with
its own `max_lines=40` cap, so a caller passing `max_elements=10`
would see summary lines referencing `#11..#40` even though the JSON
`elements` array only held #1..#10. Format on `visible_elements`
instead so the summary indices always exist in the response.
3. `_coerce_max_elements` enforced a lower bound but no upper bound,
so `max_elements=10_000_000` silently disabled the safeguard and
reintroduced the original context-blow-up. Added a hard cap
(`_MAX_ALLOWED_MAX_ELEMENTS = 1000`) that clamps oversized values.
4. The schema string said "Default 100" but the property carried no
`default` field, and claimed `max_elements` had no effect on som/
vision while the image-missing fallback path can still return an
elements array. Added `"default": 100`, `"maximum": 1000`, and
clarified the fallback-path wording.
Each finding gets a regression test:
- test_capture_ax_clamps_oversized_max_elements_to_hard_cap
- test_capture_ax_summary_indices_match_returned_elements
- test_capture_multimodal_summary_omits_truncation_note
- test_schema_max_elements_documents_default_and_upper_bound
Verified with `pytest tests/tools/test_computer_use.py` (53 passed,
including the 5 new cases). Confirmed each new test fails on the
pre-fix code path before applying the production change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`computer_use(action='capture', mode='ax')` returned the full AX element
list verbatim in the JSON response. Dense Electron / Obsidian / JetBrains
UIs publish 500+ AX nodes (one reproduction in #22865 returned 597
elements against Obsidian), so a single capture could consume enough
context to trigger compression failures or render the session unusable.
The human-readable `_format_elements` summary is already capped at 40
lines, so the truncation gap was invisible to anyone reading the summary
output.
Add a `max_elements` argument to the tool schema, default 100, that
trims the AX `elements` array. When the cap fires, the response surfaces
`total_elements` and `truncated_elements` and appends a "raise
max_elements or pass app= to narrow" hint to the summary so the model
knows the JSON view is partial and can re-issue with a tighter scope.
Validation is centralized in `_coerce_max_elements`: missing /
non-integer / sub-1 inputs fall back to the default cap, so the
protection can never be silently disabled by a malformed tool-call
argument. The cap only affects AX-mode JSON; `mode='som'` and
`mode='vision'` keep returning a screenshot + image-aware summary
unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`CuaDriverBackend.capture(app=X)` and `focus_app(app=X)` silently fell back
to the frontmost on-screen window when X matched no app — typically a
menu-bar utility (e.g. "Fuwari" in the bug reporter's case) rather than
the requested app. The agent then received UI elements for the wrong app
and clicked / typed into it.
The root cause is a localized macOS app name mismatch: `list_windows`
returns the localized `app_name` (e.g. "計算機" on a Japanese/Chinese
system) but callers naturally pass the English name ("Calculator"). The
substring filter doesn't match, and the code falls through to picking the
frontmost window with no signal that the filter was effectively dropped.
Fix:
- `capture(app=…)`: when the filter matches nothing, return a
`CaptureResult` with empty `app`/`elements` and a diagnostic
`window_title` pointing the caller at `list_apps` and noting the
localized-name convention. `_active_pid` / `_active_window_id` are left
untouched so a subsequent action doesn't inadvertently hit the wrong
process.
- `focus_app(app=…)`: when the filter matches nothing, set `target = None`
and let the existing `return ActionResult(ok=False, …, "No on-screen
window found for app …")` path fire instead of falsely reporting success
on the frontmost window.
This addresses bug 1 only from #24170. Bugs 2 & 5 are addressed in #30046;
bugs 3 & 4 in #30032.
In Telegram "important" notifications mode (default), TelegramPlatformAdapter
sets ``disable_notification=True`` on every send unless metadata carries
``notify=True``. GatewayRunner._send_voice_reply already passes thread
metadata through to ``adapter.send_voice``, but never marks the final
auto-TTS voice reply as notify-worthy — so users with the default mode get
the final voice note delivered silently with no push notification.
Mirror the final-text path in gateway/platforms/base.py (the existing
text-response final send already adds ``metadata["notify"] = True``).
Issue #27970 Bug 2. Bug 1 (MP3 vs. native OGG voice-note) is being
addressed by existing PRs #20182 / #20878 — this PR is intentionally
scoped to the silent-delivery bug only.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The text /approve and /deny paths in gateway/run.py call
resume_typing_for_chat() after resolve_gateway_approval() succeeds, but
the Telegram inline-button (ea:*) callback in _handle_callback_query did
not. Typing is paused when the approval is sent (gateway/run.py:15658),
so without a matching resume the typing indicator stayed gone for the
remainder of a long-running turn after a button click.
Symmetry-match the text path: after a successful resolve, call
self.resume_typing_for_chat(str(query_chat_id)). Guarded by count > 0
to match /approve's "if not count" early-return — if nothing was
actually resolved, the agent thread was never unblocked, so typing
should remain paused.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Archiving or deleting a board via remove_board() leaves the path's
"schema already initialized" entry in the module-level cache. A
concurrent connect(board=<slug>) call (e.g. the dashboard event-stream
poll loop) then:
1. resolves the same kanban.db path,
2. recreates the directory + an empty sqlite file because
connect() does mkdir(parents=True, exist_ok=True),
3. skips the CREATE TABLE pass because the cache entry says the
schema is already in place,
4. errors on the next read with `no such table: task_events`.
Drop the cache entry before mutating the filesystem so the fresh file
gets a proper schema init on next connect(). Applies to both
archive=True (rename) and archive=False (rmtree) branches.
Fixes#23833.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Qwen3.x and DeepSeek-V3.x default to chatty/hallucinatory tool use without
enforcement steering — agents narrate "calling tool X" without actually
emitting a tool call, or run partial loops. Both model families fit the
same failure pattern TOOL_USE_ENFORCEMENT_GUIDANCE was already injected
for (gpt, codex, gemini, gemma, grok, glm).
Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>
Squashed salvage of:
- 403e567ce fix(agent): add qwen and deepseek to TOOL_USE_ENFORCEMENT_MODELS
- 9433eabe7 test(agent): use realistic qwen-plus identifier in enforcement test
Fixes#28079.
When xAI's auth backend fails to redirect (e.g. the German "We couldn't reach
your app" fallback shown in #27385), users sometimes navigate manually to the
bare loopback callback URL — `http://127.0.0.1:<port>/callback` with no query
string. The handler used to return 200 "xAI authorization received" for any
GET that hit the expected path, because `parse_qs("")` yields no `code` and no
`error`, leaving `result` untouched while the success page was still served.
The CLI's wait loop, of course, still saw no code and timed out with
`AuthError: xAI authorization timed out waiting for the local callback.`
The user is left looking at a browser tab that claims success and a terminal
that says failure — exactly the contradiction in #27385.
This change makes the empty-callback case return 400 with an explicit
"not received" page and a hint to retry `hermes auth add xai-oauth`. The
wait-loop semantics are unchanged: `result["code"]` and `result["error"]`
both stay None, so the CLI still raises a real timeout rather than treating
the bare hit as a successful callback.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`hermes update` ran the repo-root and ui-tui npm installs with both
`--silent` and `subprocess.run(..., capture_output=True)`, which hides
all output from optional postinstall scripts. The largest of those —
`@askjo/camofox-browser`'s `npx camoufox-js fetch` — downloads a
Firefox-fork browser binary that can take many minutes on slow
connections. Because nothing was printed during that wait, the updater
appeared to hang at "Updating Node.js dependencies..." and users
Ctrl-C'd, sometimes leaving `node_modules` partially installed.
Drop `--silent` and pass `capture_output=False` for the repo-root and
ui-tui paths so npm streams its `info run …` postinstall lines straight
to the terminal. Output is still mirrored to `~/.hermes/logs/update.log`
by the existing `_UpdateOutputStream` wrapper, so SSH-disconnect safety
is preserved.
The `web/` install path is untouched — its build step is fast and does
not run binary-fetching postinstalls.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`lsp` is registered as a top-level subparser in `main()` (lines 9539-9545)
via `agent.lsp.cli.register_subparser`, so it shows up in `hermes --help`
output alongside the other built-ins. The `_BUILTIN_SUBCOMMANDS` set used
by `_plugin_cli_discovery_needed` to short-circuit the ~500-650ms plugin
import pass did not list it, so every `hermes lsp ...` invocation paid
the full discovery cost despite being a fully-built-in command.
This is also caught by the parity guard added in #22120:
`tests/hermes_cli/test_startup_plugin_gating.py::test_builtin_set_covers_every_registered_subcommand`
has been failing on clean origin/main with:
AssertionError: _BUILTIN_SUBCOMMANDS is missing these live
subcommands: ['lsp']. Add them to hermes_cli/main.py::_BUILTIN_SUBCOMMANDS
so plugin discovery can be skipped when the user targets them.
Fix: add `"lsp"` to the frozenset (alphabetical position between `logs`
and `mcp`). The accompanying `test_builtin_set_has_no_phantom_entries`
guard still passes because `lsp` is genuinely live — registered via the
guarded `try/except Exception` in main() since #24168.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When a Telegram user replies using the native quote feature to select
only part of a prior message, _build_message_event was injecting the
ENTIRE replied-to message into reply_to_text via
message.reply_to_message.text/caption. python-telegram-bot exposes
the user-selected substring as message.quote (TextQuote.text); we now
prefer that and fall back to the full replied-to text only when no
native quote is present.
The agent-visible "[Replying to: \"...\"]" prefix can otherwise expand
the user's narrow quote into the full prior message, causing the agent
to act on unrelated actionable-looking text the user did not select
(e.g. multi-item briefings where the user quotes one bullet but the
prefix injects every bullet). Falls back cleanly when message.quote
is absent (PTB <21 or replies that don't quote a substring).
Fixes#22619
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Models that enforce required-only constraints (e.g. kimi-k2.x) were
omitting old_string/new_string for replace mode and patch for patch mode
because the schema only declared required: ["mode"].
Add explicit "REQUIRED when mode='X'" markers to each conditionally-required
property description and a top-level "REQUIRED PARAMETERS: ..." summary for
each mode. Avoids anyOf/oneOf which break Anthropic, Fireworks, and
Kimi/Moonshot providers. Add TestPatchSchemaShape to lock the shape.
Fixes#15524
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
In native image mode (vision-capable models like gpt-4o, claude-sonnet-4),
build_native_content_parts() previously emitted only the user's caption
plus image_url parts. The local file path of each attached image never
appeared in the conversation text, so the model could see the pixels but
had no string handle for tools that take image_url: str (custom MCP
tools, vision_analyze on a re-look, attach-to-tracker workflows).
The text-mode path already injects an equivalent hint via
Runner._enrich_message_with_vision ("...vision_analyze using image_url:
<path>..."). This brings native mode to parity by appending one
"[Image attached at: <path>]" line per successfully attached image to
the user-text part of the multimodal turn. Skipped (unreadable) paths
are NOT advertised, so the model is never told a non-existent file is
attached.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Copilot review on PR #17012 noted the docstring/comment lists `0`
among the falsy effort values that fall back to `medium`, but the
existing regression tests only cover `None` and `""`. Add the third
case to lock in the full contract.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
auxiliary.<task>.extra_body.reasoning, but the new translation path in
_CodexCompletionsAdapter.create() reads the effort with
``reasoning_cfg.get("effort", "medium")``. That returns the configured
value verbatim when the key is present, so ``effort: null`` /
``effort: ""`` (both common YAML shapes) flow through as
``{"effort": null, "summary": "auto"}`` and Codex rejects the request
with "Invalid value for parameter ``reasoning.effort``".
agent/transports/codex.py::build_kwargs() — which the new adapter is
documented to mirror — uses a truthy check (``elif
reasoning_config.get("effort"):``) so the same falsy values keep the
"medium" default. Switch the auxiliary adapter to the same
``or "medium"`` truthy form so identical config produces identical
requests on both paths.
- [x] Two new regression tests cover ``effort: None`` and
``effort: ""`` and assert the request goes out as
``{"effort": "medium", "summary": "auto"}``.
- [x] Old behaviour fails the new tests (``{'effort': None} !=
{'effort': 'medium'}``); fixed behaviour passes all 11 tests in the
``TestCodexAdapterReasoningTranslation`` class.
- [x] Adjacent suites green: ``tests/agent/test_auxiliary_client.py``
(108 passed) and ``tests/agent/transports/test_codex_transport.py +
test_chat_completions.py`` (73 passed).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Address Copilot review on PR #17569:
1. _resolve_safe_cwd never tested the filesystem root because the loop
exited when `os.path.dirname(parent) == parent`, which is true once
`parent == '/'`. Restructure so the root is checked before the
self-equal exit. Adds `test_returns_root_when_only_root_exists` —
regression-guarded by reverting the loop and watching it fail.
2. The fake `Popen.stdout` was a `MagicMock`; `BaseEnvironment._wait_for_process`
calls `proc.stdout.fileno()` then `select.select`/`os.read` against it,
which raised `TypeError: fileno() returned a non-integer` (visible as a
thread exception in test output) and could in theory read from an
unrelated real fd. Hand `fake_popen` a real `os.pipe()` with the write
end pre-closed so the drain loop sees EOF immediately. Helper records
each fd so the test cleans up after itself.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When a tool call deletes its own working directory (`cd /tmp/foo &&
rm -rf /tmp/foo`), the next `subprocess.Popen(args, cwd=self.cwd)` raised
`FileNotFoundError: [Errno 2]` before bash even started — every subsequent
terminal/file-tool call hit the same wedge until the gateway restarted.
Fix in `LocalEnvironment._run_bash`: before handing `self.cwd` to Popen,
resolve a safe alternative when the path is gone (walk up to the nearest
existing ancestor, falling back to `tempfile.gettempdir()` only as a last
resort). Log a warning so the recovery is visible — not silent — and
update `self.cwd` so the next call doesn't repeat the message.
Defense in depth in `LocalEnvironment._update_cwd`: only adopt the new
cwd when it still exists as a directory. `pwd -P` from a deleted cwd can
leave a stale value in the marker file; refusing to store a missing path
keeps `self.cwd` valid by construction.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR #9931 ("feat(google-workspace): add --from flag for custom sender display name")
accidentally removed the required_credential_files frontmatter block that tells
hermes to bind-mount google_token.json and google_client_secret.json into Docker
and Modal remote terminals before running setup.py.
Without this header the credential files are never registered in the session-scoped
ContextVar, so get_credential_file_mounts() returns an empty list at container
creation time and the OAuth files are invisible inside the sandbox.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the TUI backend (tui_gateway/entry.py) is spawned by Node.js with the
user's CWD containing a local utils/ directory, that directory shadows the
installed utils module, causing ImportError in run_agent and hermes_cli.
Strip '' and '.' from sys.path and prepend HERMES_PYTHON_SRC_ROOT (already
set by hermes_cli before spawning the subprocess) so installed packages
always win over CWD artifacts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
models.dev appends :cloud and -cloud suffixes to Ollama Cloud model IDs
(e.g. kimi-k2.6:cloud, qwen3-coder:480b-cloud) that the live Ollama Cloud
API does not use. Without normalisation, these suffixed IDs bypass the
dedup check and appear alongside the correct clean IDs, causing 400/404
errors when users select them in /model or hermes model.
Add _strip_ollama_cloud_suffix() and apply it to mdev entries before the
dedup merge in fetch_ollama_cloud_models() so all model IDs stored in the
disk cache use the canonical form the API accepts.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Copilot review: the helper accepted None in one test but was annotated str.
Matches actual usage where no-content-type attachments are a tested scenario.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The cron scheduler's run_job() loaded config.yaml with yaml.safe_load()
but never called _expand_env_vars(), so ${HERMES_MODEL} and similar
references in model:, fallback_providers:, and other config.yaml fields
were forwarded to the LLM API as literal strings, causing HTTP 400 errors.
The normal CLI path has always called _expand_env_vars() via load_config(),
so this was a cron-only gap. The .env load at the top of run_job() already
populates os.environ before config.yaml is read, so the expansion sees the
correct values.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`hermes update` iterated only non-active profiles when seeding bundled
skills. `seed_profile_skills()` uses a subprocess with an explicit
HERMES_HOME so it correctly targets any profile path; the `p.name !=
active` filter was the only thing preventing the active profile from
being included, leaving it silently on stale skill content after every
update.
Drop the filter and update the header line from "other profiles" to
"all profiles". The active profile is now seeded on the same path as
every other profile. The earlier `sync_skills()` call (module-level
HERMES_HOME) remains for backward compatibility; the subprocess-based
loop is reliable regardless of which HERMES_HOME the CLI was invoked
with.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Prevents pre-existing TWILIO_PHONE_NUMBER or SMS_WEBHOOK_URL values in
the outer test environment from leaking into the assertion context.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes#16082.
`hermes status` silently omitted four widely-used LLM providers
(Google/Gemini, DeepSeek, xAI/Grok, NVIDIA NIM) from the API Keys
and API-Key Providers sections. Add them, along with tuple-valued
env var support (first found wins) so Google can accept either
GOOGLE_API_KEY or GEMINI_API_KEY.
Also deduplicates the "NVIDIA" and "NVIDIA NIM" rows that were
both pointing at NVIDIA_API_KEY.
Salvage of #16159 (core behavior preserved + NVIDIA dedup fixup
on top of the tuple-support refactor).
Co-authored-by: briandevans <252620095+briandevans@users.noreply.github.com>
When a delegation child session (e.g. source='telegram') contains the
FTS5 hit but _resolve_to_parent() maps it to a different root session
(source='api_server'), the result entry was still reporting the child's
source because the loop discarded session_meta as `_` and fell back to
match_info.get('source'), which carries the child session's value.
Use the resolved parent's session_meta for source, model, and started_at
with match_info as a fallback, so the output accurately reflects the
session the user actually interacted with.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`updates.backup_keep: 0` (or any negative value) wiped the freshly-
created pre-update zip:
_prune_pre_update_backups(backup_dir, keep=0):
backups = sorted(..., reverse=True) # newest first, includes
# the zip we just wrote
for p in backups[0:]: # = all of them
p.unlink()
The wrapper in `main.py` then printed `Saved: <path>` for a file that
no longer existed (the size lookup is wrapped in `try/except OSError`
which silently degrades to "0 B"), leaving operators believing they had
a recovery point when they had none.
This is a real footgun because some config systems treat 0 as "keep
unlimited"; here it does the opposite — every backup is destroyed
right after creation.
Fix: clamp `keep` to a minimum of 1 inside `_prune_pre_update_backups`
since that helper is only invoked immediately after a fresh backup
is written. Operators who genuinely want no backups should set
`updates.pre_update_backup: false` (which gates creation entirely)
rather than relying on `backup_keep: 0`.
Also extends the `backup_keep` config docstring to spell out the floor
and point at `pre_update_backup: false` as the off-switch.
## Tests
Three regression tests added in `TestPreUpdateBackup`:
- `test_keep_zero_does_not_delete_freshly_created_backup` —
asserts the file persists after `keep=0`
- `test_keep_negative_does_not_delete_freshly_created_backup` —
same for negative values
- `test_keep_zero_still_prunes_older_backups` — proves the floor
only protects the new backup; older ones are still rotated out
Verified the new tests fail on origin/main (without the floor) and
pass with it; full `tests/hermes_cli/test_backup.py` suite green
(84 tests).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`_apply_profile_override()` scans `sys.argv` for `-p / --profile` at
module import time. When `hermes_cli.main` is imported inside pytest
with `-p no:xdist` on the command line, it picks up `'no:xdist'` as a
profile name candidate, then passes it to `resolve_profile_env()` which
raises `ValueError` (invalid format), and the function calls
`sys.exit(1)` — aborting test collection with an INTERNALERROR before
any test runs.
The same conflict affects any tool or wrapper that uses `-p` for its
own flag and then imports `hermes_cli.main`.
Fix: add a format guard immediately after step 1 (explicit flag scan).
If `consume == 2` (the value came from `-p <value>`, not
`--profile=value`) and the candidate doesn't match the canonical
profile-name pattern `[a-z0-9][a-z0-9_-]{0,63}` (mirrored from
`hermes_cli.profiles._PROFILE_ID_RE`), discard it and continue as if
no `-p` flag was found. The `active_profile` file-based fallback
(step 2) only reads a file written by hermes itself, so it always
produces valid names and needs no guard.
Regression guard: with the guard reverted, importing
`hermes_cli.main` with `sys.argv = ['pytest', '-p', 'no:xdist', ...]`
raises `SystemExit(1)`. With the guard in place, the import succeeds
and `sys.argv` is left intact for pytest. Legitimate `-p coder` still
flows through to `resolve_profile_env()` unchanged.
Rebased onto current `origin/main` (`e5dad4ac5`) — the prior branch
base (`4fade39c9`) was 824 commits behind and the PR was DIRTY /
CONFLICTING. The 1.5 HERMES_HOME-set early-return block has since
landed between the original insertion point and step 2; the new guard
is positioned correctly before the early return so a bogus `-p` value
no longer prevents the early return from kicking in.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The kanban PR (#17805, c86842546) added the `kanban` toolset and
`tools/kanban_tools.py`, but didn't update three pre-existing test
assertions that bake the full toolset/tool inventory:
* `tests/tools/test_registry.py::test_matches_previous_manual_builtin_tool_set`
hard-codes the manual list of builtin tool modules. `tools.kanban_tools`
was missing.
* `tests/test_tui_gateway_server.py::test_load_enabled_toolsets_rejects_disabled_mcp_env`
and `test_load_enabled_toolsets_falls_back_when_tui_env_invalid` both
expect `["memory"]` from `_load_enabled_toolsets()`. With kanban now
auto-recovered by `_get_platform_tools` (its tools live in hermes-cli's
universe but are not in CONFIGURABLE_TOOLSETS), the resolver returns
`["kanban", "memory"]`.
* `tests/hermes_cli/test_tools_config.py::test_get_platform_tools_preserves_explicit_empty_selection`
asserts `set()` for an explicit empty list. The recovery loop now also
surfaces `kanban`. Reframed to assert the contract the test name
describes — no CONFIGURABLE toolset gets re-enabled when the user
explicitly saved an empty list — which stays correct as more
non-configurable platform toolsets are added.
Verified the failures reproduce on clean origin/main (180a7036b) with
`.[all,dev]`-equivalent extras (fastapi, starlette, httpx, pytest-asyncio)
and that all four pass with this commit applied. CI on main itself is
currently red on these tests; this restores green for everyone's PRs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The `gemini` provider also serves Gemma (e.g. `gemma-4-31b-it`) and
historically other Google models like PaLM. Those reject
`extra_body.thinking_config` with HTTP 400:
Unknown name "thinking_config": Cannot find field
`_build_gemini_thinking_config()` was unconditionally producing a
config dict for any model on the `gemini` / `google-gemini-cli`
provider, which `ChatCompletionsTransport.build_kwargs` then dropped
into `extra_body["thinking_config"]`. The result: every chat turn for
Gemma users on the gemini provider blew up at the API edge.
The fix is the same shape Hermes already uses for the Gemini-2.5 vs
Gemini-3 family clamping: normalise the model id, strip an
`OpenRouter`-style `google/` prefix, and short-circuit early when the
result doesn't start with `gemini`. We return `None` rather than
`{"includeThoughts": False}`, because the API rejects the field name
itself — even the polite "off" form trips the same 400.
Three regression tests cover Gemma with reasoning enabled, Gemma with
reasoning disabled, and the `google/gemma-…` OpenRouter-style id; the
existing Gemini-2.5 / Gemini-3 / `google/gemini-…` cases keep passing
because the Gemini guard fires after the prefix strip.
Fixes#17426
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
run_job() ignored the result's `failed=True` / `completed=False` flags
that agent.run_conversation populates on API exhaustion, mid-run
interrupts, and model aborts. Because final_response on those paths is
often a non-empty error string ("API call failed after 3 retries:
Request timed out."), the existing empty-response soft-fail in
_process_job did not trip either: the error text was delivered as if it
were the agent's reply and last_status was set to "ok" with no error
notification. Detect those flags right after the dict-shape guard and
raise so the existing except handler builds the proper failure tuple,
preserving the agent's error message via result["error"].
Adds a parametrized regression covering: API-retry-exhausted with error
text in final_response, completed=False with no final_response,
completed=False without an explicit failed flag, and the partial-reply
plus failed=True case. Plus a guard that a normal completed=True success
result is still treated as success.
Fixes#17855
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the in-band pending-message drain spawns a fresh task and
transfers ownership via _session_tasks[session_key] = drain_task,
the original task still unwinds through the finally block. The
drain task picks up the same interrupt_event in its own
_process_message_background entry, so an unconditional
_release_session_guard(session_key, guard=interrupt_event) at the
end of the finally matches and deletes _active_sessions[session_key]
while the drain task is still pending its first await.
A concurrent inbound message arriving in that handoff window passes
the Level-1 guard (no entry exists) and spawns a second
_process_message_background for the same session — two agents on
one session_key, duplicate responses, duplicate tool calls.
Fix: only call _release_session_guard when the current task still
owns _session_tasks[session_key]. When ownership has been
transferred to a drain task, leave _active_sessions populated; the
drain task's own lifecycle releases it. This mirrors the
late-arrival drain path in the same finally block, which already
leaves both entries alone after handing off.
Also reorder stdlib imports in the new regression test file to
match the gateway test convention (stdlib before third-party).
Regression test: capture _active_sessions[sk] identity at every
handler entry across a 2-step in-band drain chain and assert the
guard Event identity stays the same. Pre-fix, the original task's
finally deletes the entry, the drain task falls through to the
`or asyncio.Event()` branch, and a fresh Event is installed —
identity diverges. Post-fix, the entry is preserved and the drain
task reuses the original Event.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`_process_message_background` finished a turn, found a queued
follow-up, and drained it via `await
self._process_message_background(pending_event, session_key)`. Each
chained follow-up added a frame to the call stack instead of starting
fresh. Under sustained pending-queue activity (e.g. a user sending
follow-ups faster than the agent finishes turns) the C stack would
exhaust at ~2000 nested frames and SIGSEGV the process.
Mirror the late-arrival drain pattern that already exists in the same
function: spawn a new `asyncio.create_task(...)` for the pending event
and return so the current frame can unwind. The new task takes
ownership via `_session_tasks[session_key]`.
The late-arrival drain in `finally` could now race with the in-band
drain across the `await typing_task` / `await stop_typing` window, so
add a guard: if `_session_tasks[session_key]` is no longer the current
task, an in-band drain already spawned a follow-up task — re-queue the
late-arrival event so that task picks it up after its current event,
instead of spawning a second concurrent task for the same session_key.
Regression test (`test_pending_drain_no_recursion.py`) chains 12
follow-ups and asserts the recorded
`_process_message_background` stack depth stays bounded at handler
entry. Pre-fix: depths grow linearly `[1,2,3,…,12]`. Post-fix: all
depths are `1`.
`test_duplicate_reply_suppression::test_stale_response_suppressed_when_interrupted`
called `_process_message_background` directly and implicitly relied on
the old recursive `await` semantic — updated to wait for the spawned
drain task before checking the sent list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Address Copilot review on PR #16666:
1. **Duplicate event on every tool start** — both ``tool_progress_callback``
and ``tool_start_callback`` fire side-by-side in ``run_agent.py``, so
wiring both into chat completions emitted *two* ``hermes.tool.progress``
events per real tool call. Drop the legacy ``_on_tool_progress`` emit
entirely; ``_on_tool_start`` now produces a single unified event that
carries the legacy ``tool``/``emoji``/``label`` fields plus the new
``toolCallId``/``status`` correlation fields. Label is computed inline
via ``build_tool_preview`` so callers do not need to pre-format it.
2. **Weak per-event correlation in the regression test** — the previous
assertion checked that a ``toolCallId`` appeared *somewhere* in the
aggregate, which would have passed even if ``running`` lacked the id.
Collect ``(status, toolCallId)`` per event and assert each event
carries the correct pair, plus exactly two events on the wire (no
silent duplication regression).
The two existing chat-completions tool-progress tests are updated to fire
``tool_start_callback`` instead of ``tool_progress_callback``, matching
production reality where ``run_agent`` always pairs them.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two fix-ups for #17123:
1. Reword the inline comment in `_warn_stale_dashboard_processes` to
accurately describe the failure mode (locale-dependent decoder, not a
"default UTF-8 decoder") and identify `errors="ignore"` as the
load-bearing protection. Per Copilot's review.
2. Switch `TestWindowsWmicEncoding` from `patch("hermes_cli.main.sys")`
to `monkeypatch.setattr(sys, "platform", "win32")` — the codebase's
canonical pattern (e.g. `tests/hermes_cli/test_auth_ssl_macos.py`).
The MagicMock-replacement approach passed locally on Python 3.12 but
the platform-equality check failed under CI's xdist+Python 3.11,
leaving both new tests red despite the fix being present.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`hermes update` calls `_warn_stale_dashboard_processes()` to warn about
dashboard processes still running the pre-update Python backend. On
Windows, that scan shells out to `wmic process get ProcessId,CommandLine
/FORMAT:LIST` with `text=True` and no explicit encoding.
`wmic` emits text in the system code page (e.g. cp936 on zh-CN locales),
not UTF-8. Without an explicit `encoding=`, Python's default UTF-8
decoder crashes the subprocess reader thread with
`UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 ...`. In
Python 3.11 that crash is silently absorbed: `subprocess.run()` returns
a `CompletedProcess` with `result.stdout = None`, the next line calls
`result.stdout.split("\n")`, and `hermes update` aborts with the
exact `AttributeError: 'NoneType' object has no attribute 'split'`
trace reported in #17049.
Fix: pass `encoding="utf-8", errors="ignore"` so undecodable bytes
cannot take down the reader thread (the parsing only matches the ASCII
prefixes `CommandLine=` and `ProcessId=`, so dropping non-UTF-8 bytes
is safe), and short-circuit when `result.stdout is None` as a defensive
guard for environments where the reader thread still fails for other
reasons.
This is the same root cause as #17074 (which patches
`hermes_cli/gateway._scan_gateway_pids` for the `hermes setup` path).
That PR does not touch `_warn_stale_dashboard_processes`, so
`hermes update` remains broken on the same locales until this lands.
Regression test in `tests/hermes_cli/test_update_stale_dashboard.py`:
- `test_wmic_invoked_with_utf8_ignore_errors` asserts the explicit
encoding/errors kwargs reach `subprocess.run`.
- `test_wmic_returns_none_stdout_does_not_crash` simulates the
reader-thread-crashed `result.stdout=None` aftermath and asserts the
function returns silently instead of raising AttributeError.
Both new tests fail against clean origin/main (7d4648461) reproducing
the original AttributeError; both pass with this patch. The remaining
3 failures in `tests/hermes_cli/test_cmd_update.py` and
`test_update_autostash.py` are pre-existing baselines on origin/main —
they reproduce identically without this change and are unrelated to
the wmic scan.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wrap the new top-level `from hermes_cli.config import get_env_value`
in try/except ImportError and fall back to a thin os.getenv shim, so
importing tools.tts_tool keeps working in environments where
hermes_cli.config is unavailable. This matches the existing tolerance
in `_load_tts_config()` (tools/tts_tool.py) and the same
import-fallback pattern in tools/tool_backend_helpers.py::fal_key_is_configured.
Also update the TestDotenvFallbackPerProvider docstring to accurately
describe the mocking strategy: per-provider tests patch
`tools.tts_tool.get_env_value` directly, while the regression-guard
tests cover the lower-level `hermes_cli.config.load_env` integration.
Addresses Copilot review on #17163.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
TTS provider tools (elevenlabs, xai, minimax, mistral, gemini) called
os.getenv("X_API_KEY") directly, which bypassed Hermes's dotenv bridge in
hermes_cli.config. Users who keep their TTS keys only in ~/.hermes/.env saw
"X_API_KEY not set" errors even though the rest of the stack
(agent/credential_pool, hermes_cli/auth) already resolves keys through
get_env_value() — same class of bug as #15914 fixed for those modules.
Switch every TTS env-var lookup (API keys, base URLs, and
check_tts_requirements gates) to get_env_value, which checks os.environ
first and then ~/.hermes/.env. Behaviour for users with keys exported in
the shell is unchanged; users with dotenv-only keys now succeed. The two
diagnostics prints in __main__ are migrated for consistency.
Regression test (tests/tools/test_tts_dotenv_fallback.py):
- per-provider: each backend reads the dotenv key when only
~/.hermes/.env carries it (5 providers).
- end-to-end: with hermes_cli.config.load_env returning the key and
os.environ empty, _generate_minimax_tts and check_tts_requirements
both succeed; reverting tools/tts_tool.py back to os.getenv makes all
7 tests fail with "MINIMAX_API_KEY not set" / similar.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Address the three Copilot inline findings on the regression test:
- Switch _extract_run_setup_wizard() from str.index() with hard-coded
markers (which raises ValueError if `maybe_start_gateway()` is renamed
or the marker leaks into a comment) to an anchored regex on the
function-definition + closing-brace boundaries.
- Match `[ -e /dev/tty ]` with surrounding whitespace, optional quoting,
and the `test -e /dev/tty` form so the regression guard catches every
spelling of the existence-only check, not just the exact substring.
- Replace the literal `(: </dev/tty)` substring assertion with a
higher-level invariant — the gate must be an `if`/`if !` whose test
redirects stdin from /dev/tty — so equivalent open-based probes
(`exec 3</dev/tty` + close, brace-grouped variants, etc.) keep the
test green while the bare existence check stays caught.
Verified guard: both tests still pass on the fix and both fail on
`origin/main` with the documented messages.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
In Docker builds the `/dev/tty` device node is present in the mount
namespace, so `[ -e /dev/tty ]` returns true — but opening it fails
with `ENXIO: No such device or address`. Under the old gate the
"no terminal available" skip never triggered, the setup wizard ran,
and the build aborted a few lines later when bash tried `< /dev/tty`:
/tmp/install.sh: line 1347: /dev/tty: No such device or address
Replace the existence check with `(: </dev/tty) 2>/dev/null`, which
actually attempts to open /dev/tty in a subshell. The probe succeeds
when piped from `curl | bash` on a real terminal (the wizard's intended
use case) and fails cleanly in Docker build / CI contexts so the skip
kicks in before the redirect can crash.
Add a regression test that statically asserts run_setup_wizard does not
gate on the bare existence check and that the open-based probe is in
place.
Fixes#16746.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Address Copilot review on #16868:
1. Tighten pool iteration. ``validate_copilot_token`` only rejects empty
strings and classic PATs (``ghp_*``); a malformed/unsupported ``gho_*``
token at ``credential_pool.copilot[0]`` would pass the gate and short-
circuit the loop, hiding a later valid entry. Switch to calling
``exchange_copilot_token`` directly: only entries that actually exchange
into a live Copilot API token are returned. Bad/expired entries fall
through to the next, and an exhausted pool returns ``""`` so the picker
falls back to the curated list (existing behaviour).
2. Reword the docstring + test module docstring to describe the pool seed
path accurately — ``hermes auth add copilot`` adds an api-key-typed
credential whose ``access_token`` field stores the pasted token, and
``_seed_from_env`` mirrors ``COPILOT_GITHUB_TOKEN`` from
``~/.hermes/.env`` into the pool. The previous wording implied
``auth add copilot`` itself ran the device-code flow, which it does
not (the device-code flow lives in ``hermes model``).
Two new tests cover the iteration change:
- ``test_skips_pool_entry_that_fails_to_exchange`` — pool[0] raises,
pool[1] succeeds, picker uses pool[1].
- ``test_all_pool_entries_fail_exchange_returns_empty`` — every entry
raises, return ``""``.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Users whose only Copilot credential is the OAuth `access_token` saved by
`hermes auth add copilot` (device-code flow) saw the `/model` picker drop
back to a stale hardcoded list. Reason: `_resolve_copilot_catalog_api_key`
only consulted env vars (`COPILOT_GITHUB_TOKEN` / `GH_TOKEN` /
`GITHUB_TOKEN`) and the `gh auth token` CLI fallback, never the credential
pool that Hermes's own login flow writes into `auth.json`. With no token,
the live catalog fetch silently 401s and the picker hides current models
(claude-opus-4.7, claude-sonnet-4.6, gpt-5.5, grok-code-fast-1) — even
though `/model <id>` works fine because runtime inference reads the pool
through a different code path.
Mirror the Codex catalog resolver pattern: env-var first (unchanged), then
walk `read_credential_pool("copilot")` for the first entry with a
supported `access_token` (`gho_*` / `github_pat_*` / `ghu_*`). Run it
through `get_copilot_api_token()` so the catalog request uses the same
exchanged token the runtime path uses. Classic PATs (`ghp_*`) are still
rejected up-front via `validate_copilot_token` since the Copilot API
doesn't accept them.
Strictly additive: env still wins, and a missing/locked auth.json (or any
exception during pool read) still returns "" so the caller falls through
to the curated catalog.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CI caught that ``test_session_manager_prefers_runtime_user_id_over_config_peer_name``
in ``tests/agent/test_memory_user_id.py`` failed after this branch: that
test passes a ``MagicMock`` for ``config``, where
``mock.pin_peer_name`` silently returns another ``MagicMock`` — truthy by
default. My ``getattr(..., "pin_peer_name", False)`` fallback was
supposed to guard against callers that haven't added the new attr, but
MagicMock *does* have the attr — it just returns a live mock for it.
Tightened the gate to ``getattr(..., False) is True``. Real configs
built via ``HonchoClientConfig.from_global_config`` always yield a
proper boolean, so strict equality matches the pinned case and rejects
both the unset-attr fallback and MagicMock stand-ins. Added a comment
explaining why ``is True`` is intentional, not paranoid.
Also tightened the ``peer_name`` existence check to
``getattr(..., None)`` so a MagicMock with ``peer_name`` left at its
default (also truthy) doesn't spuriously enable pinning either.
Verified against both the new ``test_pin_peer_name.py`` suite (13/13
pass) and the previously-failing
``TestHonchoUserIdScoping`` (3/3 pass). Zero behaviour change for real
``HonchoClientConfig`` values.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When a gateway drives Hermes (Telegram, Discord, Slack, ...), it passes the
platform-native user ID as ``runtime_user_peer_name`` into the Honcho
session manager. That ID wins over ``peer_name`` in ``honcho.json``, so a
single user who connects over three platforms ends up as three separate
Honcho peers — one per platform — with fragmented memory and no cross-
platform context continuity.
For multi-user bots this is correct (and must not change): each user gets
their own peer scope. For the vast majority of personal Hermes deployments
the configured ``peer_name`` is an unambiguous identity, though, so the
reporter asked for an opt-in knob that pins the user peer to that value.
Fix: new ``pinPeerName`` boolean on the host config, default ``false``.
When ``true`` AND ``peerName`` is set, the configured peer_name beats the
gateway's runtime identity; every other resolution case is unchanged.
honcho.json:
{
"peerName": "Igor",
"hosts": {
"hermes": { "pinPeerName": true }
}
}
session.py (resolution order, pinned case):
runtime_user_peer_name → skipped (opt-in flag active)
config.peer_name → WINS "Igor"
session-key fallback → unreached
Parsing follows the same host-block-overrides-root pattern as every other
flag in HonchoClientConfig.from_global_config (``_resolve_bool`` helper).
Tests (tests/honcho_plugin/test_pin_peer_name.py — 13 cases, 5 groups):
- Config parsing: default, root true, host-block true, host overrides
root, explicit false.
- Peer resolution: runtime wins by default (regression guard for multi-
user bots), config wins when pinned, pin-without-peer_name is a no-op
(prevents silent peer-id collapse to session-key fallback), CLI path
where runtime is absent, deepest fallback intact, assistant peer
untouched by the flag.
- Cross-platform unification: Telegram UID + Discord snowflake collapse
to one peer when pinned; negative control confirms two distinct
runtime IDs still produce two peers when unpinned.
244 honcho_plugin tests pass, 3 pre-existing skips, zero regressions.
Defensive detail: session.py uses ``getattr(self._config, "pin_peer_name",
False)`` so callers building partial config objects (several test fixtures
across the codebase do this) don't break if they haven't updated yet.
Runtime cost: one attr lookup per new session.
Closes#14984
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
``_cleanup_agent_resources`` previously invoked
``agent.shutdown_memory_provider()`` with no arguments, so every memory
provider's ``on_session_end`` hook received an empty list. Providers
with an early-return guard on empty input (Holographic, Hindsight) never
extracted facts from the conversation, and users hit
"抱歉，找不到相關的對話記錄" on the first turn after any gateway
restart, session reset, or idle expiry.
Forward ``agent._session_messages`` — the transcript the agent itself
maintains and refreshes every turn via ``_persist_session`` — so
providers see the actual conversation. Falls back to the legacy no-arg
call whenever the attribute is absent or not a list (test stubs built
via ``object.__new__`` or ``MagicMock``) to preserve backward
compatibility with existing suites. ``AIAgent.shutdown_memory_provider``
already accepts ``messages: list = None`` (run_agent.py:4126), so this
is a pure caller-side fix.
Paths that use ``skip_memory=True`` temporary agents (memory flush,
hygiene auto-compress, ``/compress``) are no-ops inside
``shutdown_memory_provider`` because ``self._memory_manager`` is None —
no behaviour change for them.
Covers Part A of the bug report. Part B (adding ``on_session_end`` to
the Hindsight plugin) is a separate concern that would benefit from
this fix landing first.
Regression test added at
``tests/gateway/test_shutdown_memory_provider_messages.py`` covering:
populated messages forwarded, empty list still forwarded, attribute
missing falls back, non-list (MagicMock) falls back, provider
exceptions don't block ``close()``, None agent no-op, and agent
without ``shutdown_memory_provider`` tolerated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The bare-string isinstance guard added in 80ae2621 covered _find_tail_cut_by_tokens
(line 1084) but missed the identical pattern in _calculate_protect_tail_boundary
(line 487, the protect-tail scan loop). Both loops call .get("text", "") on every
list item in message["content"]; both crash with AttributeError when that list
contains a bare string.
Apply the same dict/str/fallback isinstance guard to the protect-tail path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
raw_content from message["content"] can be a list that contains bare
strings, not only dicts. The previous `p.get("text", "")` call raised
AttributeError on string items, crashing context compression for any
session that had a message with mixed content.
Guard with isinstance checks: dict → .get("text"), str → len(p),
fallback → len(str(p)). Adds a regression test covering the bare-string
case that would have AttributeError'd on the pre-fix code.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
_find_tail_cut_by_tokens called len(content) to estimate message tokens.
When content is a list of blocks (multimodal: text + image_url), len()
returns block count (e.g. 2) rather than character count, so a message
with 500 chars of text was counted as ~10 tokens instead of ~135.
This caused the backward walk to exhaust all messages before hitting the
budget ceiling; the head_end safeguard then forced cut = n - min_tail,
shrinking the protected tail to the bare minimum and preventing effective
compression of long multimodal conversations.
Fix mirrors the existing pattern in _prune_old_tool_results (line 487):
sum(len(p.get("text", "")) for p in raw_content)
if isinstance(raw_content, list) else len(raw_content)
Tests: 3 new cases in TestTokenBudgetTailProtection — regression guard
(confirms the test fails with the bug), plain-string regression guard,
and image-only block edge case.
Fixes#16087.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Address Copilot review findings:
1. Gate _last_activity_desc on interrupt_depth == 0 alongside _last_activity_ts.
Both fields are semantically paired — desc describes the activity *at* ts.
Updating desc without ts made get_activity_summary() report "starting new
turn (cached)" for 20+ minutes while the timestamp showed the true stale
duration, producing misleading diagnostic output.
2. Monkeypatch gateway.run.time.time to a fixed epoch in tests that assert
on _last_activity_ts values. Real time.time() comparisons were latently
flaky under slow CI or NTP adjustments. _FAKE_NOW = 10_000.0 is used
as the reference; assertions are now exact equality rather than >=.
3. Add test_fresh_turn_resets_desc and test_interrupt_turn_preserves_desc to
directly cover the gated desc behaviour introduced by (1).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
_last_activity_ts was unconditionally reset to time.time() on every
_agent_cache hit. For interrupt-recursive _run_agent calls
(_interrupt_depth > 0) this silently reset the inactivity watchdog's
idle clock on each re-entry, preventing the 30-min timeout from ever
firing when a turn got stuck in an interrupt loop. A stuck session
would emit "Still working... iteration 0/60, starting new turn (cached)"
heartbeats indefinitely instead of timing out.
Gate the reset on _interrupt_depth == 0 only. Fresh external turns
still receive the reset so a session idle for 29 min doesn't trip the
watchdog before the new turn makes its first API call (#9051).
The per-turn reset logic is extracted into a static helper
_init_cached_agent_for_turn() to make it directly testable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
``run_conversation`` was calling ``memory_manager.sync_all(
original_user_message, final_response)`` at the end of every turn
where both args were present. That gate didn't consider the
``interrupted`` local flag, so an external memory backend received
partial assistant output, aborted tool chains, or mid-stream resets as
durable conversational truth. Downstream recall then treated the
not-yet-real state as if the user had seen it complete, poisoning the
trust boundary between "what the user took away from the turn" and
"what Hermes was in the middle of producing when the interrupt hit".
Extracted the inline sync block into a new private method
``AIAgent._sync_external_memory_for_turn(original_user_message,
final_response, interrupted)`` so the interrupt guard is a single
visible check at the top of the method instead of hidden in a
boolean-and at the call site. That also gives tests a clean seam to
assert on — the pre-fix layout buried the logic inside the 3,000-line
``run_conversation`` function where no focused test could reach it.
The new method encodes three independent skip conditions:
1. ``interrupted`` → skip entirely (the #15218 fix). Applies even
when ``final_response`` and ``original_user_message`` happen to
be populated — an interrupt may have landed between a streamed
reply and the next tool call, so the strings on disk are not
actually the turn the user took away.
2. No memory manager / no final_response / no user message →
preserve existing skip behaviour (nothing new for providerless
sessions, system-initiated refreshes, tool-only turns that never
resolved, etc.).
3. Sync_all / queue_prefetch_all exceptions → swallow. External
memory providers are strictly best-effort; a misconfigured or
offline backend must never block the user from seeing their
response.
The prefetch side-effect is gated on the same interrupt flag: the
user's next message is almost certainly a retry of the same intent,
and a prefetch keyed on the interrupted turn would fire against stale
context.
### Tests (16 new, all passing on py3.11 venv)
``tests/run_agent/test_memory_sync_interrupted.py`` exercises the
helper directly on a bare ``AIAgent`` (``__new__`` pattern that the
interrupt-propagation tests already use). Coverage:
- Interrupted turn with full-looking response → no sync (the fix)
- Interrupted turn with long assistant output → no sync (the interrupt
could have landed mid-stream; strings-on-disk lie)
- Normal completed turn → sync_all + queue_prefetch_all both called
with the right args (regression guard for the positive path)
- No final_response / no user_message / no memory manager → existing
pre-fix skip paths still apply
- sync_all raises → exception swallowed, prefetch still attempted
- queue_prefetch_all raises → exception swallowed after sync succeeded
- 8-case parametrised matrix across (interrupted × final_response ×
original_user_message) asserts sync fires iff interrupted=False AND
both strings are non-empty
Closes#15218
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Salvage of the Gemini-specific piece from PR #12585 by @briandevans.
Gemini's OpenAI-compat /v1beta/openai/models endpoint returns IDs prefixed
with 'models/' (native Gemini-API convention), so set-membership against
curated bare IDs drops every model. Strip the prefix before comparison.
The Anthropic static-catalog piece of #12585 was subsumed by #12618's
_fetch_anthropic_models() branch landing earlier in the same salvage PR.
Full branch cherry-pick was skipped because it also carried unrelated
catalog-version regressions.
Streamable HTTP MCP servers may garbage-collect their server-side
session state while the OAuth token remains valid — idle TTL, server
restart, pod rotation, etc. Before this fix, the tool-call handler
treated the resulting "Invalid or expired session" error as a plain
tool failure with no recovery path, so **every subsequent call on
the affected server failed until the gateway was manually
restarted**. Reporter: #13383.
The OAuth-based recovery path (``_handle_auth_error_and_retry``)
already exists for 401s, but it only fires on auth errors. Session
expiry slipped through because the access token is still valid —
nothing 401'd, so the existing recovery branch was skipped.
Fix
---
Add a sibling function ``_handle_session_expired_and_retry`` that
detects MCP session-expiry via ``_is_session_expired_error`` (a
narrow allow-list of known-stable substrings: ``"invalid or expired
session"``, ``"session expired"``, ``"session not found"``,
``"unknown session"``, etc.) and then uses the existing transport
reconnect mechanism:
* Sets ``MCPServerTask._reconnect_event`` — the server task's
lifecycle loop already interprets this as "tear down the current
``streamablehttp_client`` + ``ClientSession`` and rebuild them,
reusing the existing OAuth provider instance".
* Waits up to 15 s for the new session to come back ready.
* Retries the original call once. If the retry succeeds, returns
its result and resets the circuit-breaker error count. If the
retry raises, or if the reconnect doesn't ready in time, falls
through to the caller's generic error path.
Unlike the 401 path, this does **not** call ``handle_401`` — the
access token is already valid and running an OAuth refresh would be
a pointless round-trip.
All 5 MCP handlers (``call_tool``, ``list_resources``, ``read_resource``,
``list_prompts``, ``get_prompt``) now consult both recovery paths
before falling through:
recovered = _handle_auth_error_and_retry(...) # 401 path
if recovered is not None: return recovered
recovered = _handle_session_expired_and_retry(...) # new
if recovered is not None: return recovered
# generic error response
Narrow scope — explicitly not changed
-------------------------------------
* **Detection is string-based on a 5-entry allow-list.** The MCP
SDK wraps JSON-RPC errors in ``McpError`` whose exception type +
attributes vary across SDK versions, so matching on message
substrings is the durable path. Kept narrow to avoid false
positives — a regular ``RuntimeError("Tool failed")`` will NOT
trigger spurious reconnects (pinned by
``test_is_session_expired_rejects_unrelated_errors``).
* **No change to the existing 401 recovery flow.** The new path is
consulted only after the auth path declines (returns ``None``).
* **Retry count stays at 1.** If the reconnect-then-retry also
fails, we don't loop — the error surfaces normally so the model
sees a failed tool call rather than a hang.
* **``InterruptedError`` is explicitly excluded** from session-expired
detection so user-cancel signals always short-circuit the same
way they did before (pinned by
``test_is_session_expired_rejects_interrupted_error``).
Regression coverage
-------------------
``tests/tools/test_mcp_tool_session_expired.py`` (new, 16 cases):
Unit tests for ``_is_session_expired_error``:
* ``test_is_session_expired_detects_invalid_or_expired_session`` —
reporter's exact wpcom-mcp text.
* ``test_is_session_expired_detects_expired_session_variant`` —
"Session expired" / "expired session" variants.
* ``test_is_session_expired_detects_session_not_found`` — server GC
variant ("session not found", "unknown session").
* ``test_is_session_expired_is_case_insensitive``.
* ``test_is_session_expired_rejects_unrelated_errors`` — narrow-scope
canary: random RuntimeError / ValueError / 401 don't trigger.
* ``test_is_session_expired_rejects_interrupted_error`` — user cancel
must never route through reconnect.
* ``test_is_session_expired_rejects_empty_message``.
Handler integration tests:
* ``test_call_tool_handler_reconnects_on_session_expired`` — reporter's
full repro: first call raises "Invalid or expired session", handler
signals ``_reconnect_event``, retries once, returns the retry's
success result with no ``error`` key.
* ``test_call_tool_handler_non_session_expired_error_falls_through``
— preserved-behaviour canary: random tool failures do NOT trigger
reconnect.
* ``test_session_expired_handler_returns_none_without_loop`` —
defensive: cold-start / shutdown race.
* ``test_session_expired_handler_returns_none_without_server_record``
— torn-down server falls through cleanly.
* ``test_session_expired_handler_returns_none_when_retry_also_fails``
— no retry loop on repeated failure.
Parametrised across all 4 non-``tools/call`` handlers:
* ``test_non_tool_handlers_also_reconnect_on_session_expired``
[list_resources / read_resource / list_prompts / get_prompt].
**15 of 16 fail on clean ``origin/main`` (``6fb69229``)** with
``ImportError: cannot import name '_is_session_expired_error'``
— the fix's surface symbols don't exist there yet. The 1 passing
test is an ordering artefact of pytest-xdist worker collection.
Validation
----------
``source venv/bin/activate && python -m pytest
tests/tools/test_mcp_tool_session_expired.py -q`` → **16 passed**.
Broader MCP suite (5 files:
``test_mcp_tool.py``, ``test_mcp_tool_401_handling.py``,
``test_mcp_tool_session_expired.py``, ``test_mcp_reconnect_signal.py``,
``test_mcp_oauth.py``) → **230 passed, 0 regressions**.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bedrock rejects ``global-anthropic-claude-opus-4-7`` with ``HTTP 400:
The provided model identifier is invalid`` because its inference
profile IDs embed structural dots
(``global.anthropic.claude-opus-4-7``) that ``normalize_model_name``
was converting to hyphens. ``AIAgent._anthropic_preserve_dots`` did
not include ``bedrock`` in its provider allowlist, so every Claude-on-
Bedrock request through the AnthropicBedrock SDK path shipped with
the mangled model ID and failed.
Root cause
----------
``run_agent.py:_anthropic_preserve_dots`` (previously line 6589)
controls whether ``agent.anthropic_adapter.normalize_model_name``
converts dots to hyphens. The function listed Alibaba, MiniMax,
OpenCode Go/Zen and ZAI but not Bedrock, so when a user set
``provider: bedrock`` with a dotted inference-profile model the flag
returned False and ``normalize_model_name`` mangled every dot in the
ID. All four call sites in run_agent.py
(``build_anthropic_kwargs`` + three fallback / review / summary paths
at lines 6707, 7343, 8408, 8440) read from this same helper.
The bug shape matches #5211 for opencode-go, which was fixed in commit
f77be22c by extending this same allowlist.
Fix
---
* Add ``"bedrock"`` to the provider allowlist.
* Add ``"bedrock-runtime."`` to the base-URL heuristic as
defense-in-depth, so a custom-provider-shaped config with
``base_url: https://bedrock-runtime.<region>.amazonaws.com`` also
takes the preserve-dots path even if ``provider`` isn't explicitly
set to ``"bedrock"``. This mirrors how the code downstream at
run_agent.py:759 already treats either signal as "this is Bedrock".
Bedrock model ID shapes covered
-------------------------------
| Shape | Preserved |
| --- | --- |
| ``global.anthropic.claude-opus-4-7`` (reporter's exact ID) | ✓ |
| ``us.anthropic.claude-sonnet-4-5-20250929-v1:0`` | ✓ |
| ``apac.anthropic.claude-haiku-4-5`` | ✓ |
| ``anthropic.claude-3-5-sonnet-20241022-v2:0`` (foundation) | ✓ |
| ``eu.anthropic.claude-3-5-sonnet`` (regional inference profile) | ✓ |
Non-Claude Bedrock models (Nova, Llama, DeepSeek) take the
``bedrock_converse`` / boto3 path which does not call
``normalize_model_name``, so they were never affected by this bug
and remain unaffected by the fix.
Narrow scope — explicitly not changed
-------------------------------------
* ``bedrock_converse`` path (non-Claude Bedrock models) — already
correct; no ``normalize_model_name`` in that pipeline.
* Provider aliases (``aws``, ``aws-bedrock``, ``amazon``,
``amazon-bedrock``) — if a user bypasses the alias-normalization
pipeline and passes ``provider="aws"`` directly, the base-URL
heuristic still catches it because Bedrock always uses a
``bedrock-runtime.`` endpoint. Adding the aliases themselves to the
provider set is cheap but would be scope creep for this fix.
* No other places in ``agent/anthropic_adapter.py`` mangle dots, so
the fix is confined to ``_anthropic_preserve_dots``.
Regression coverage
-------------------
``tests/agent/test_bedrock_integration.py`` gains three new classes:
* ``TestBedrockPreserveDotsFlag`` (5 tests): flag returns True for
``provider="bedrock"`` and for Bedrock runtime URLs (us-east-1 and
ap-northeast-2 — the reporter's region); returns False for non-
Bedrock AWS URLs like ``s3.us-east-1.amazonaws.com``; canary that
Anthropic-native still returns False.
* ``TestBedrockModelNameNormalization`` (5 tests): every documented
Bedrock model-ID shape survives ``normalize_model_name`` with the
flag on; inverse canary pins that ``preserve_dots=False`` still
mangles (so a future refactor can't decouple the flag from its
effect).
* ``TestBedrockBuildAnthropicKwargsEndToEnd`` (2 tests): integration
through ``build_anthropic_kwargs`` shows the reporter's exact model
ID ends up unmangled in the outgoing kwargs.
Three of the new flag tests fail on unpatched ``origin/main`` with
``assert False is True`` (preserve-dots returning False for Bedrock),
confirming the regression is caught.
Validation
----------
``source venv/bin/activate && python -m pytest
tests/agent/test_bedrock_integration.py tests/agent/test_minimax_provider.py
-q`` -> 84 passed (40 new bedrock tests + 44 pre-existing, including
the minimax canaries that pin the pattern this fix mirrors).
CI-aligned broad suite: 12827 passed, 39 skipped, 19 pre-existing
baseline failures (all reproduce on clean ``origin/main``; none in
the touched code path).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
