2026-06-28 18:17:27 +08:00
|
|
|
"""CLI plugin-stack helper.
|
|
|
|
|
|
|
|
|
|
Exercises :func:`build_plugin_registry` and
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
:func:`maybe_build_memory_backend` against the ``raven_everos`` plugin,
|
|
|
|
|
which the dev environment installs from ``plugins-dist/everos-memory`` and
|
|
|
|
|
which discovery finds through the ``raven.plugins`` entry-point group.
|
2026-06-28 18:17:27 +08:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
import ast
|
fix(core): the memory service stops holding up the first session (#630)
## Summary
Two changes against the same symptom: the first session after an install
waits
on the memory service and then runs without long-term memory anyway.
**The wait is unnecessary.** A resident host awaited `backend.start()`
at boot,
so it held for the readiness budget -- 10s -- before serving anything.
The
backend already has a state machine for exactly that window: `store`
answers
False so the loop retries the record, and `recall` returns no hits for
that turn
and schedules a probe. Waiting for the service before serving the first
turn is
what the state machine replaced everywhere else.
`plugin_stack.start_backend_detached` is the same shape as
`warm_up_in_background` for litellm: a resident process starts the slow
thing
once and goes on serving, and the on-demand path reports a failure to
whoever
needs it. Three callers take it -- the gateway at boot and at a
generation swap,
and `raven a2a serve`. The other three keep awaiting, because for them
there is
no later turn to recover into: an import checks readiness immediately, a
sub-agent writes one record, and a one-shot turn exits. It is retired in
`Runtime.dispose`, the single point both resident hosts go through.
**The wait was also far longer than its budget.** uv does not compile
bytecode
by default, so the first process to import a module compiles it, and for
raven
that process is the EverOS service the first session starts. Measured on
a fresh
isolated install: 22s from spawn to ready, of which 18s elapses before
the
service writes its first log line. `UV_COMPILE_BYTECODE=1` in the
installer
moves that into the install, where the user is already watching a
progress line.
## Type
- [x] Fix
- [ ] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Measured on a throwaway install in an isolated `RAVEN_HOME` /
`UV_TOOL_DIR` /
`UV_TOOL_BIN_DIR`, built from this checkout:
- cold first start, as shipped today: 22s spawn to ready (readiness
budget 10s)
- second start against the same tree: 2.2s
- freshly scaffolded root, bytecode already compiled: 2.1s
- byte-compiling the rest of that tree: 13.9s for 16756 files, single
threaded,
so the cost is compilation and it is paid once per machine
The detached start was read at the layer that owns the ordering, the
gateway's
own log. Before this change `Page:` cannot appear until after
`everos server ready`; after it:
```
17 EverosBackend.start
20 Page: http://127.0.0.1:18894
28 started everos server
31 everos server ready
```
The page is serving at line 20 and the child is only spawned at line 28.
The
interval this removes from the boot measured 5.5s on a machine whose
bytecode is
already compiled.
Commands:
- `uv run --frozen --python 3.12 --all-extras pytest
tests/test_core_plugin_stack.py tests/test_core_runtime_swap.py
tests/test_cli_gateway_commands.py tests/test_cli_a2a_commands.py
tests/test_cli_import_commands.py tests/test_memory_backend_protocol.py
-q` -- 191 passed after the rebase onto main
- the same set plus `tests/test_everos_backend.py` and
`tests/test_core_runtime_eval_hooks.py` -- 364 passed
- `ruff check raven/ tests/` -- all checks passed
- `ruff format --check raven/ tests/` -- 1654 files already formatted
- `sh -n install.sh` -- clean
Each of the six new cases was mutated to confirm it can fail: dropping
the task
reference, dropping the done-callback, making the cancel a no-op, and
removing
the cancel from `dispose`. Every mutation turned the case that names
that
behaviour red, and the source was restored and hash-compared afterwards.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots are updated when needed
## Risk
User-visible change: a resident host now serves its first turn before
the memory
service has answered. A turn that arrives in that window gets no recall,
and its
record is retried rather than lost. Previously the host waited and, when
the wait
overran, that session had no memory at all -- so the window is narrower
than what
it replaces, not wider.
The installer now compiles bytecode, which makes an install slower by
roughly the
compile time and larger by the `.pyc` tree.
Rollback: both commits are independent and revert cleanly. Reverting the
first
restores the awaited start; reverting the second restores the uncompiled
install.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-09-22 15:46:12 +08:00
|
|
|
import logging
|
2026-06-28 18:17:27 +08:00
|
|
|
from pathlib import Path
|
|
|
|
|
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
import raven
|
2026-06-28 18:17:27 +08:00
|
|
|
from raven.config.raven import (
|
|
|
|
|
MemoryConfig,
|
|
|
|
|
PluginsConfig,
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
RavenConfig,
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
from raven.config.schema import Config, MediaGenConfig, ToolsConfig, WebToolsConfig
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
from raven.contracts.memory import MemoryBackend
|
|
|
|
|
from raven.core.plugin_stack import (
|
|
|
|
|
build_plugin_hooks,
|
|
|
|
|
build_plugin_registry,
|
|
|
|
|
build_plugin_tools,
|
|
|
|
|
everos_plugin_installed,
|
|
|
|
|
everos_plugin_missing_note,
|
|
|
|
|
maybe_build_memory_backend,
|
|
|
|
|
named_plugin_roots,
|
|
|
|
|
)
|
|
|
|
|
from raven.plugins import PluginRegistry
|
|
|
|
|
from tests._everos_presence import everos_plugin_absent, everos_plugin_broken
|
2026-06-28 18:17:27 +08:00
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# Helpers
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _config(
|
|
|
|
|
*,
|
|
|
|
|
memory_backend: str | None = "everos",
|
|
|
|
|
disabled: list[str] | None = None,
|
|
|
|
|
plugin_config: dict | None = None,
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
dirs: list[str] | None = None,
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
tools: ToolsConfig | None = None,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> RavenConfig:
|
|
|
|
|
return RavenConfig(
|
|
|
|
|
memory=MemoryConfig(backend=memory_backend),
|
|
|
|
|
plugins=PluginsConfig(
|
|
|
|
|
disabled=list(disabled or []),
|
|
|
|
|
config=dict(plugin_config or {}),
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
dirs=list(dirs or []),
|
2026-06-28 18:17:27 +08:00
|
|
|
),
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
base=Config(tools=tools) if tools is not None else Config(),
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# build_plugin_registry
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestBuildRegistry:
|
|
|
|
|
def test_returns_registry_with_everos_activated(self) -> None:
|
|
|
|
|
reg = build_plugin_registry(_config())
|
|
|
|
|
assert isinstance(reg, PluginRegistry)
|
|
|
|
|
assert "everos-memory" in reg.activated_ids()
|
|
|
|
|
assert "everos" in reg.memory_backend_names()
|
|
|
|
|
|
|
|
|
|
def test_disabled_plugin_id_skipped(self) -> None:
|
|
|
|
|
reg = build_plugin_registry(
|
|
|
|
|
_config(disabled=["everos-memory"]),
|
|
|
|
|
)
|
|
|
|
|
assert "everos-memory" not in reg.activated_ids()
|
|
|
|
|
assert "everos" not in reg.memory_backend_names()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# maybe_build_memory_backend
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestMaybeBuildBackend:
|
|
|
|
|
def test_default_config_builds_everos(self, tmp_path: Path) -> None:
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, _config())
|
|
|
|
|
assert backend is not None
|
|
|
|
|
assert isinstance(backend, MemoryBackend)
|
|
|
|
|
|
|
|
|
|
def test_memory_backend_none_returns_none(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
self,
|
|
|
|
|
tmp_path: Path,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> None:
|
|
|
|
|
backend = maybe_build_memory_backend(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
tmp_path,
|
|
|
|
|
_config(memory_backend=None),
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
assert backend is None
|
|
|
|
|
|
|
|
|
|
def test_unknown_backend_returns_none_no_raise(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
self,
|
|
|
|
|
tmp_path: Path,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> None:
|
|
|
|
|
"""A user-config typo / missing plugin must NOT crash boot —
|
|
|
|
|
the helper logs + degrades, AgentLoop falls back to legacy."""
|
|
|
|
|
backend = maybe_build_memory_backend(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
tmp_path,
|
|
|
|
|
_config(memory_backend="nonexistent"),
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
assert backend is None
|
|
|
|
|
|
|
|
|
|
def test_disabled_backend_returns_none(self, tmp_path: Path) -> None:
|
|
|
|
|
backend = maybe_build_memory_backend(
|
|
|
|
|
tmp_path,
|
|
|
|
|
_config(
|
|
|
|
|
memory_backend="everos",
|
|
|
|
|
disabled=["everos-memory"],
|
|
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
assert backend is None
|
|
|
|
|
|
refactor(*): seal the memory backend seam so a memory plugin needs no host edits (#414)
## Summary
Make `MemoryBackend` the only seam between the host and the memory
subsystem, so a second memory plugin can be installed without editing
host code.
The abstraction is the goal; no second backend is being added.
What the branch does:
- `health()` joins the Protocol. `raven doctor` and `raven import` read
a `BackendHealth(ready, checks)` the backend fills in with its own
vocabulary, instead of reaching into EverOS internals. Doctor prints the
checks verbatim and never interprets a label.
- A new `[[plugin.contributes.onboard]]` kind, with
`raven/contracts/onboard.py` as its paper. The host lends the wizard
shell as one `OnboardUI` and records the result; the screen returns a
`StepOutcome`. The plugin never writes `memory.backend` -- that key
stays the host's. EverOS's step-4 screen and its `everos.toml`
management move into the plugin.
- The skill source and the after-turn feedback prefix are named from
`memory.backend` rather than the literal `everos`.
- `enabled_by_default` is gone from the manifest: an installed plugin
the user has not disabled is active.
- `tests/test_plugin_boundary.py` pins the dependency direction in both
directions, with an equality assertion so the remaining exceptions
cannot grow.
That guard's allowlist started at five host files still speaking
EverOS's wire protocol. The follow-ups below close three of them.
Two things this branch itself introduced were found in manual acceptance
on an install without the plugin and fixed here: a turn printed which
backends were installed -- empty on exactly the install that needs the
sentence -- and `settings.everos` / `settings.everosSet` let
`ModuleNotFoundError` reach the dispatcher as an internal error carrying
a traceback. Both now carry the note doctor and the wizard already use,
naming the distribution to install.
Review on this PR found four blockers, all fixed and covered. A fifth
defect came out of manual acceptance rather than review, and four more
out of the rounds that followed it -- every one of those in the
embedding endpoint's own plumbing, each found by the round after the fix
that introduced it. They are listed under Risk; the blockers are:
1. `onboard` is an optional contribution, but the wizard equated "no
matching screen" with "not configured", so one `raven onboard
--skip-memory` wrote `memory.backend` back to null for a third-party
backend configured by hand. A backend with no screen now answers on the
strength of having been selected; only one whose own screen says it is
unconfigured is cleared, which is the case that rule exists for.
2. The record a sub-agent call leaves behind ran through a backend
nobody had started. The shipped adapter begins in an unknown state, so
the first flushing write only scheduled a readiness probe and answered
false -- the record said "unavailable" while the service was up the
whole time, and each per-record HTTP client was left open. One context
manager now owns start and stop around a record, in both the manager and
the DAG runner.
3. That record's write and the recall after it addressed different
owners: a real config spells its keys in camelCase and the block reaches
the backend as written, while the adapter read only the contract's
snake_case, so a sub-agent's memories were filed under the host
identity. The adapter reads both spellings.
4. Legacy embedding discovery had narrowed to the recorded plugin root,
so an install predating root recording lost its knowledge-base endpoint
with a valid file still on disk.
**The five follow-ups the seam left behind are in this PR too**, rather
than in three stacked ones, because they are one goal and the branch
protection dismisses an approval on every push:
- The embedding endpoint is raven's. A knowledge base indexes inside the
gateway process and never speaks to the memory service, yet it read its
endpoint out of everos.toml, so selecting another backend left it with
no vectors and no message naming the cause. Raven holds the block now
and hands it to the backend at start -- as a shared default, not an
override: a plugin that was given an endpoint of its own keeps it, and
only one that has none takes raven's. Discovery of an existing
everos.toml still checks all three places the plugin itself looks, read
with plain tomllib so it works where the plugin is not installed. No
data migrates: a base is keyed on its model and measured width, not on
the base url.
- `delete()` joins the Protocol. The browser used to delete a row out of
EverOS's index, in the host process, through the plugin's repository
layer -- while the markdown EverOS treats as the source of truth kept
the text, so the memory came back on the next rebuild, after the user
was told it was gone. The adapter now uses only operations EverOS
already performs, for the kinds it performs them for.
- Sub-agent memory goes through the contract. The read half is a new
optional `recall_session`; the write half needed no new surface, only
two metadata conventions written down. `agents.<name>.config.everos`
becomes `config.memory`, opaque to the host except the two keys the host
reads; the old spelling still loads.
- The memory and settings pages say why they are empty -- no plugin, or
a backend this page does not read -- instead of four zeros and a retry
button that cannot help.
- The `everos` package leaves the host's dependencies for the plugin's
own, at the same exact pin; the host reaches the tree through the
plugin. This is the package layer only: the installers already deliver
`everos-memory` as a sibling wheel from the same release, so an ordinary
install still has long-term memory.
The boundary guard's allowlist falls from five entries to two, both GUI
surfaces still shaped around EverOS's own store. Generalising their wire
is a frontend change and is deliberately not in scope.
This branch was reviewed on GitLab as merge request 639 over three
rounds, including a post-rebase range-diff check. It is being moved here
because GitHub is now the source of truth.
## Type
- [x] Refactor
## Verification
- `uv run pytest` on this branch, rebased onto `main`: 22146 passed, 4
failed, 45 skipped. Three of the four (`test_agents_oncall_launcher`,
`test_agent_loop_token_budget`, `test_agents_code_launcher`) were re-run
on a detached checkout of that same `main` commit in this environment
and fail there identically. The fourth (`test_ppt_engine_image_search`)
could not run in that checkout, whose environment lacks the deck
engine's extras; this branch's only change anywhere under
`plugins-dist/ppt-engine` is the removal of the `enabled_by_default`
manifest key, which that test does not reach. So this branch adds no
regression.
- `npx vitest run` in ui-web: 1680 passed across 103 files. `npm run
type-check` and `npm run gen:check` clean, so the generated client
matches the contract.
- Every fix in the follow-up commits was mutated away and its test
confirmed red, then restored and confirmed green. For the record path
that is three separate mutations: dropping `start()`, dropping `stop()`,
and narrowing the owner lookup back to one spelling.
- `uv run ruff check .` and `uv run ruff format --check` on the changed
files: clean.
- `uv lock --check`: consistent.
- `scripts/check_commit_messages.py`, `scripts/check_large_files.py`,
`scripts/check_source_language.py` over the branch range: clean.
- Manual acceptance against a real isolated install (temporary
RAVEN_HOME, isolated EverOS root and port), 34 cases: `raven plugins`,
`raven doctor` across four backend states, `raven onboard` interactive
and non-interactive including all three step-4 lanes, `raven import`
refusing and importing, an end-to-end write and recall, the web UI's
memory and settings pages driven through a real browser, a sub-agent
trace record, and an install with no memory plugin at all. 31 passed; 1
failed and was fixed; 1 partial; 1 carried over from the earlier round.
- The failure is the one worth reading. On a fresh managed install the
wizard reported embedding configured and the service it started the next
moment ran keyword-only: the spawned process carried no
`EVEROS_EMBEDDING__` values, and EverOS logged that the embedding key
was not configured. The rule deciding whether everos.toml already held
an operator's own endpoint asked whether its model name was a `"<...>"`
placeholder; the shipped template seeds every section with a real model
name and an empty key, so every fresh install read as a deliberate
choice and the host's endpoint was never bound. It now asks the
criterion the module already had -- model and key. The unit tests missed
it because each built its "operator's own" section with a key in it; the
regression copies the shipped template itself.
- The partial: the memory page's search returned relevant results
without error, but every memory in the test corpus was on one subject,
so narrowing could not be observed. The carried-over case is the
skill-source prefix, whose path this branch does not touch.
- Findings recorded and not fixed here, none introduced by this branch:
a progress spinner is still drawn after `import` reports it imported
nothing; an unsupported delete surfaces as a generic internal error; the
TUI log and `doctor` word "no memory plugin" differently; a turn that
did reach disk still prints that it was not written.
- The partial case: an induced agent skill is discovered through
`find_skill` with the backend's prefix, but `read_skill` / `use_skill`
on that id fail. Nothing writes the on-disk layer those tools look in,
on this branch or on `main`, and no test covers it. Pre-existing; filed
as a follow-up.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
User-visible changes:
1. User-track recall is now strictly bounded by `top_k`. A profile row
used to ride outside that bound.
2. `raven doctor` builds the plugin factory, so a managed EverOS setup
writes its env var and config templates during a doctor run. It used to
be read-only. The `--json` memory section is reshaped around
`health.checks`.
3. A third-party drop-in plugin without `enabled_by_default = true` used
to be skipped and now loads.
4. The loader no longer back-fills the EverOS config slice's `root` /
`owned`, nor strips a legacy `mode` key; a leftover `mode` now draws an
unknown-key warning.
5. The wizard's recap shows the contribution name `everos` rather than
`EverOS`.
6. `use_skill` with an unknown prefix reports "not found" after a disk
lookup instead of "unknown source".
From the follow-ups:
7. Config gains an optional top-level `embedding` block. Absent, the
knowledge base reads the EverOS file as before and says so once. An
operator who moves the values across changes nothing else; one who names
a *different* model there gets the existing `StaleBaseError` telling
them to rebuild that base. The block is a default for the memory plugin
rather than an override, so an install that had configured the plugin
separately keeps what it had. Note that a config carrying this block
does not load on an older Raven, which rejects unknown top-level keys.
8. `agents.<name>.everos` is written back as `agents.<name>.memory`. The
old spelling still loads; a per-agent `baseUrl` is ignored with a
warning, having never had a user.
9. Deleting a memory now changes what EverOS treats as the source of
truth, so it stays deleted. Profiles and cases report that they cannot
be deleted rather than appearing to succeed.
10. `pip install raven` no longer pulls the memory engine in.
`install.sh` and `install.ps1` are unaffected: both already resolve
`everos_memory-*.whl` from the release they install and pass it as
`--with everos-memory`, and the source path installs it editable, so
those installs keep long-term memory. An install that reaches neither --
a release predating the sibling wheel, or a bare `pip install` -- now
boots without memory and says which distribution to install rather than
failing on an import.
Found after the acceptance run, in review, all fixed here. They share
one cause worth stating once: the endpoint acquired a second home, and
each fix taught one more reader about it while leaving the next one
behind.
11. The endpoint the wizard saved never reached the EverOS process it
then started. The rule for "does everos.toml already hold an operator's
own endpoint" asked whether its model name was a `"<...>"` placeholder;
the shipped template seeds every section with a real model name and an
empty key, so every fresh managed install read as a deliberate choice
and the host's endpoint was never bound. The service came out of the
wizard running keyword-only while the wizard said embedding was
configured. The rule now asks the criterion the module already had:
model and key.
12. The exported `EVEROS_EMBEDDING__*` variables are a third home,
documented by EverOS and ranked above its file. They were being
overwritten. A complete triple is now an operator's choice; an
incomplete one is not an endpoint and is replaced whole rather than
topped up from the host.
13. Raven writes those same variables itself at startup, so a reader
that asked only whether all three were set called raven's own binding an
operator's export -- a blank settings card and a save refused by naming
variables nobody had set. The module now records which of them it set.
14. That record lived in a module-level set, and `raven gateway
--restart` re-launches through `os.execv`: the values survive, module
state does not. The record now travels in a variable beside them, and is
stripped from the environment handed to EverOS.
15. A settings save the environment would outrank is refused with the
variable names, rather than written and silently ignored.
Four of the five arrived one per review round, each in the fix for the
one before it. The tests that missed them all shared a shape: each built
its "an operator configured this" fixture with a key in it, or cleared
the environment before the case, so the states the product actually
produces -- a template with no key, a live process that has just bound
its own endpoint -- were never the input. The regressions now copy the
shipped template, and run the startup sequence and a second interpreter
rather than a prepared state.
Rollback is a revert of the branch: the seam is additive, and
`memory.backend` keeps its shipped default.
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: gloryfromca <23442919+gloryfromca@users.noreply.github.com>
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-09-16 22:19:50 +08:00
|
|
|
def test_a_missing_backend_is_said_out_loud(self, tmp_path: Path, capsys) -> None:
|
|
|
|
|
cfg = _config(memory_backend="ghost")
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, cfg, registry=PluginRegistry())
|
|
|
|
|
assert backend is None
|
|
|
|
|
err = capsys.readouterr().err
|
|
|
|
|
assert "memory.backend" in err and "ghost" in err
|
|
|
|
|
|
|
|
|
|
def test_the_shipped_default_missing_names_what_to_install(self, tmp_path: Path, capsys) -> None:
|
|
|
|
|
"""The commonest way to reach that line is an install without the plugin.
|
|
|
|
|
|
|
|
|
|
Naming only the backends that ARE installed leaves such a reader with
|
|
|
|
|
nothing to do; doctor and the wizard both answer it in one sentence, and
|
|
|
|
|
a turn is the surface that actually reaches this code.
|
|
|
|
|
"""
|
|
|
|
|
from tests._everos_presence import everos_plugin_absent
|
|
|
|
|
|
|
|
|
|
with everos_plugin_absent():
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, _config(memory_backend="everos"), registry=PluginRegistry())
|
|
|
|
|
|
|
|
|
|
assert backend is None
|
|
|
|
|
assert "everos-memory" in capsys.readouterr().err
|
|
|
|
|
|
2026-06-28 18:17:27 +08:00
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# Per-plugin config slice resolution
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestConfigSliceResolution:
|
|
|
|
|
def test_config_by_plugin_id(self, tmp_path: Path) -> None:
|
|
|
|
|
backend = maybe_build_memory_backend(
|
|
|
|
|
tmp_path,
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
_config(
|
|
|
|
|
plugin_config={
|
|
|
|
|
"everos-memory": {"mode": "embedded", "base_url": "http://x"},
|
|
|
|
|
}
|
|
|
|
|
),
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
# Backend received the config slice keyed by plugin id.
|
|
|
|
|
assert backend._config["mode"] == "embedded"
|
|
|
|
|
assert backend._config["base_url"] == "http://x"
|
|
|
|
|
|
|
|
|
|
def test_config_by_backend_name_fallback(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
self,
|
|
|
|
|
tmp_path: Path,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> None:
|
|
|
|
|
"""When the user uses the shorter key (backend name), the
|
|
|
|
|
helper still finds it. Useful for handwritten configs."""
|
|
|
|
|
backend = maybe_build_memory_backend(
|
|
|
|
|
tmp_path,
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
_config(
|
|
|
|
|
plugin_config={
|
|
|
|
|
"everos": {"mode": "http", "base_url": "http://y"},
|
|
|
|
|
}
|
|
|
|
|
),
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
assert backend._config["mode"] == "http"
|
|
|
|
|
assert backend._config["base_url"] == "http://y"
|
|
|
|
|
|
|
|
|
|
def test_plugin_id_takes_precedence_over_backend_name(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
self,
|
|
|
|
|
tmp_path: Path,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> None:
|
|
|
|
|
"""If both keys are present, the canonical (plugin id) wins."""
|
|
|
|
|
backend = maybe_build_memory_backend(
|
|
|
|
|
tmp_path,
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
_config(
|
|
|
|
|
plugin_config={
|
|
|
|
|
"everos-memory": {"marker": "canonical"},
|
|
|
|
|
"everos": {"marker": "fallback"},
|
|
|
|
|
}
|
|
|
|
|
),
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
assert backend._config["marker"] == "canonical"
|
|
|
|
|
|
|
|
|
|
def test_no_config_slice_yields_empty_dict(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
self,
|
|
|
|
|
tmp_path: Path,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> None:
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, _config())
|
|
|
|
|
assert backend._config == {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# Registry injection — caller can pass a pre-built registry
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestRegistryInjection:
|
|
|
|
|
def test_caller_supplied_registry_used(self, tmp_path: Path) -> None:
|
|
|
|
|
reg = build_plugin_registry(_config())
|
|
|
|
|
backend = maybe_build_memory_backend(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
tmp_path,
|
|
|
|
|
_config(),
|
|
|
|
|
registry=reg,
|
2026-06-28 18:17:27 +08:00
|
|
|
)
|
|
|
|
|
# Backend constructed via the explicit registry.
|
|
|
|
|
assert backend is not None
|
|
|
|
|
|
|
|
|
|
def test_default_construction_creates_internal_registry(
|
build: whole-repo lint + pre-commit convention (config only) (#59)
## Change description
> Whole-repo lint + pre-commit convention, CONFIG ONLY (no source
reformat in this PR). Python (ruff) and TypeScript (eslint + prettier)
share a 120-col margin via the committed pre-commit gate. This upgrades
main's existing basic ruff setup and adds the TS lint stack (none
existed on main).
>
> What this PR adds:
> - ruff: line-length 120; security rules
S101/S105/S106/S107/S506/S605/S607; policy per-file-ignores (tests +
accepted CLI deferred-imports + product asserts + N818, each commented);
ruff pinned <0.16.
> - eslint/prettier: shared base (`eslint.base.mjs` +
`prettier.config.mjs`); ui-tui extends it with React rules, bridge with
a Node-only config; hermes-ink vendor and generated RPC types excluded.
> - pre-commit: keeps main's hooks (conventional-commit,
detect-private-key, etc.), adds a top-level exclude and 4 local
eslint/prettier hooks; bumps the pre-commit dev dep.
> - 2 lint-surfaced fixes: PlannerContext import (F821) in the sentinel
runner; lower-cased file-local cron-heartbeat constants (N806).
(raven/config/raven.py's F821 was already fixed on main.)
>
> Sequencing: config only. `ruff check` is intentionally red on ~307
auto-fixables (I001/F401/F541/E701/E702); a SEPARATE reformat branch
runs `ruff --fix` + `ruff format` + eslint/prettier --fix to clear them
(100% auto-resolvable, zero manual). Enforcement (pre-commit install /
CI) turns on only after the reformat lands, so do not expect a green
tree from this PR alone.
>
> CLI-owned files (the reformat and several per-file-ignores touch
`raven/cli/*`) are under review by the CLI team. Judgment items (TS
no-explicit-any, no-unused-expressions, S101 convert-vs-keep, N818
rename, C90, mypy) are deferred to v2.
## Type of change
- [ ] Bug fix
- [x] New feature
- [ ] Document
- [x] Others
## Related issues (if there is)
> none
## Checklists
### Development
- [ ] Lint rules pass locally
- [ ] Application changes have been tested thoroughly
- [ ] Automated tests covering modified code pass
> config-only: `ruff check` is red on auto-fixables by design (the
reformat branch clears them); eslint/prettier configs load in both
ui-tui and bridge.
### Security
- [x] Security impact of change has been considered
- [ ] Code follows company security practices and guidelines
> Only dependency change is the dev-only pre-commit tool plus the ruff
pin; the detect-private-key hook from main is retained.
### Code review
- [x] Pull request has a descriptive title and context useful to a
reviewer
- [ ] Pull request linked to JIRA ticket when applicable
---------
Co-authored-by: Sheng Zhao <sheng.zhao@evermind.ai>
Co-authored-by: Claude (claude-opus-4-8) <noreply@anthropic.com>
2026-07-01 12:09:42 +08:00
|
|
|
self,
|
|
|
|
|
tmp_path: Path,
|
2026-06-28 18:17:27 +08:00
|
|
|
) -> None:
|
|
|
|
|
# Sanity: with no registry passed, the helper still works.
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, _config())
|
|
|
|
|
assert backend is not None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# Workspace plumbing through ServiceLocator
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestServiceLocatorPlumbing:
|
|
|
|
|
def test_workspace_reaches_backend(self, tmp_path: Path) -> None:
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, _config())
|
|
|
|
|
# EverosBackend stores ctx.services on construction.
|
|
|
|
|
assert backend._services.workspace == tmp_path
|
feat(*): add hermes as a cold-start import source (#264)
## Summary
Adds Hermes as a cold-start import source, alongside the existing Claude
Code
scanner, across three kinds of data.
**Memory files.** `MEMORY.md` and `USER.md` are discovered through the
same
profile resolution Hermes itself uses (`HERMES_HOME`, then
`active_profile`
redirecting to `<root>/profiles/<name>`). `USER.md` entries are
additionally
mirrored into the native `user_memory/profile/user.md`: six host
consumers
(Curator, Personalizer, four Sentinel producers) read that file directly
and
never see EverOS-only content. An LLM picks each entry's H2 heading;
every
failure path lands the entry under `## Notes`, which injection always
includes,
so a misclassification costs tokens rather than visibility.
**Conversations.** Sessions are enumerated by shelling out to
`hermes sessions export --dry-run`, whose listing is capped at 100 rows.
The
scanner walks time windows until every session is covered rather than
silently
importing the first 100. Only ended sessions are candidates, and
`reopen_session()` can clear `ended_at`, so the window reconciliation
documents
the resulting race in both directions instead of assuming monotonicity.
**Skills.** Provenance is classified from on-disk evidence -- the
`.bundled_manifest` name-to-md5 map, `.hub/lock.json`, and `.usage.json`
-- with
a `package_hash` byte-identical to Hermes' own `_dir_hash`, so a skill
still
matching its factory content is left alone and only user-authored or
curator-managed skills are copied into the local skill pool. Skills
never travel
as ScanResults, so the menus, the confirm line and the final summary all
state
the skill count explicitly; without it a run that installs 12 of 82
reads as
having dropped 70.
Failure isolation: `scan_all` now reports a failing scanner through an
`on_error` callback and keeps the other platforms' results, and a Hermes
run
whose conversations cannot be enumerated still returns its memory files.
Two pre-existing defects found while working here are fixed in the same
branch:
a multi-line recall hit escaped its bullet in the context segment
renderer, and
a recalled EverOS profile was rendered as a Python repr and left
uncapped.
Also in this branch, from hands-on testing of the finished flow:
- `raven import run` could never reach its interactive path. The
selectors
called questionary's synchronous `ask()` from inside `asyncio.run()`,
and
prompt_toolkit drives `Application.run()` through `asyncio.run()`, which
raises inside a running loop. No test covered it: every case passed
`--platform` and `--tier`, bypassing the selectors.
- Import outcomes now render as one block after the progress display
closes.
Printing them from `_build_and_run` sent them to this module's Console
while
onboard's live progress belongs to its themed Console, and Rich's Live
can
only hold back writes on its own console, so they landed mid-bar and
left the
bar duplicated.
- The `import run` selectors use the shared prompt style and glyphs
instead of
questionary's defaults; onboard's foreground import gains the phase
reporter
it never had, so the multi-second USER.md mirror is no longer silent
behind a
bar reading 100%.
The EverOS backend moves with it. Agent-track recall turned out to be
dead:
agent-track HYBRID fuses `agent_case` and `agent_skill` through a rerank
cross-encoder, and with no rerank provider the server refuses the
request
outright, which `recall` catches and turns into an empty list against a
file-only logger. A live 1.1.3 probe returns `RuntimeError:
owner_type='agent'
with method='hybrid' requires a rerank provider`. The adapter now reads
`capabilities.rerank` from `/health` and asks for the LLM lane only when
the
cross-encoder is genuinely absent -- always sending it would make every
correctly configured user pay an LLM call per recall, never sending it
leaves
the track dead for anyone who skipped the optional rerank role in
onboard.
That capability is only readable from everos 1.2.1, so the pin moves
1.1.3 ->
1.2.1, skipping 1.2.0 (built from a branch missing the 1.1.4 fixes,
including a
knowledge-upload path traversal). Memory endpoints move to `/api/v2`,
canonical
since 1.2.0; `/api/v1` still resolves to the same handlers but is
documented as
a legacy alias. Only everos endpoints move -- the Skill Hub and
OpenRouter
clients have their own v1 surfaces.
That upgrade also broke an assumption Raven was making. "Server running"
and
"server can recall" used to be the same statement; 1.2.1 boots with
`[llm]` alone
instead of aborting, so a misconfigured provider answers 200 and quietly
serves
less. Raven decided a role was configured by reading model + api_key out
of
`everos.toml`, which cannot see that. Capabilities are now read from
`/health` at
all three points where it matters: the memory step (right after the
server it
already starts), `raven doctor` (which had no EverOS check at all), and
`backend.start()` -- the only one of the three on the path every session
takes,
which is where an expired key actually surfaces. It follows the
precedent already
set there for native Windows and prints to stderr rather than a log
nobody reads,
but does not drop to a no-op: writes still land, and `everos cascade
backfill`
gives those rows their vectors once the provider is fixed.
The same reading makes the embedding role genuinely optional. It was not
before:
recall sends no `method`, so it took the server default of HYBRID, which
everos
refuses without an embedding provider -- skipping the role produced a
memory that
stored everything and returned nothing. The adapter now asks for KEYWORD
when no
embedding capability is reported, searching the same rows lexically
instead of
semantically, and that also rules out the rerank fallback because
KEYWORD's agent
path never reaches the cross-encoder. So the wizard stops requiring
embedding and
states what each role buys before asking for it -- llm alone gets
keyword recall,
embedding adds meaning, rerank sharpens ordering -- and skipping
embedding is
reported in colour rather than dim, because skipping rerank costs
ordering while
skipping embedding costs semantic recall entirely.
Fault and degradation are now distinguished rather than lumped together:
only a
missing llm sets doctor's exit code, and `raven doctor` names what each
unconfigured optional role costs, per role, since "optional" alone does
not help
anyone decide. The wizard also stops asking whether to enable memory at
all --
everos is the only backend, so the question framed a choice that does
not exist,
and both of its answers were described wrongly (declining was said to
use "native
Markdown memory", which does not exist: `raven/plugin/memory/` holds
only everos,
and `ContextAssembler.owns_compaction` is a hardcoded True that stops
the
consolidator from ever updating user.md). Backing out is still possible
and now
states the real consequence in colour. The memory LLM field is
pre-filled with
the user's own main model rather than a recommended id, because a
recommendation
is only reachable if their key carries it.
Two rounds of review on this branch found defects worth naming, since
each was
invisible for the same reason -- no test covered the path:
- **Skills were copied before the run's own `Proceed?` gate.** The two
early
returns that install a skills-only import sit above it, so a machine
whose only
importable data is skills had directories copied before being asked
anything.
Both paths now name the count and ask; the wizard's `Start?` gate is
further
down still, so its two call sites ask as well. Every covering test
passed
`--yes`, which is what hid it.
- **A cancelled run still ran both post-phases.** `run_import` returns
normally
once it sees the cancel file, so `raven import stop` halted the
conversation
loop and then started an LLM call per USER.md entry plus a full skill
copy.
- **Org-mirror skills were imported past a gate Hermes applies itself.**
Hermes
token-gates `_org/`: with no `.active_org` marker it prunes the whole
mirror,
and with one it descends only into the named org, so a stale mirror is
content
Hermes no longer loads. Discovery now mirrors that. Excluding `_org`
outright
would have been the opposite error -- it drops the active org's skills.
- **`doctor` and the wizard probed the default address.** Both took
`DEFAULT_EVEROS_BASE_URL` while the backend reads the configured
`base_url`, so
a user who moved everos off port 18791 was told it was not running -- by
the
checks added to make a degraded server visible.
- **An unbuilt multimodal role was reported by nobody.** The
section-to-capability
mapping had an entry both consumers skipped.
- **The USER.md progress line reached 100% before the last call.** Each
report
counted the call about to start; on a measured 9.4s run that left ~3s
sitting at
100%, the exact symptom the phase reporter was added to remove.
- **Registry-name collisions were only checked within one run**, so a
name an
earlier import or the user's own skill already claimed produced the
invisible
skill that `get(name)` never returns.
- **"All platforms" plus "run in background" could not work.** `import
run` has no
all-platforms flag, so the child reached its platform picker with
DEVNULL on
both streams and no terminal, after the wizard reported the import as
started.
It now runs in the foreground and says so.
The e2e tests this branch made dead are fixed too: identity moved to the
host, so
`config={"agent_id": ...}` is ignored, and the agent-track test wrote
under the
services default while querying the tag -- `hits` was empty, its per-hit
assertions vacuous, and an `xfail` absorbed it. The plugin manifest
moves to
1.1.0, which the upgrade SOP in this same diff asks for.
Not in scope: Codex, KimiCode and OpenClaw remain placeholders;
cold-start
import stays an EverOS-only path with no native fallback.
## Type
- [x] Feature
- [ ] Fix
## Verification
```
uv run --all-extras pytest -q 5405 passed, 30 skipped, 13 deselected
uv run ruff check . All checks passed!
uv run ruff format --check . 873 files already formatted
make check-large-files passed
```
Beyond the suite, the importer was run against a real Hermes install at
`--tier full`: memory files, conversations and skills all landed, EverOS
extracted agent cases from the imported conversations
(`quality_score=1.0` in
the server log), and a second run over the same data reported
`Submitted: 0, Skipped: 4`, confirming the checkpointing is idempotent.
The everos upgrade was verified against a live server holding real
imported
data: on 1.1.3 the agent track returns 500 and `/api/v2` returns 404; on
1.2.1
with this change the agent track returns an `agent_case` and the user
track is
unchanged at three episodes. Re-verified after killing the server and
cold
starting it, with the resolved binary printed to confirm which build
answered.
`raven doctor` and the wizard both report llm and embedding available
with
rerank absent against that server.
The suite was also run with HOME pointed at an empty directory, which is
how the
memory-probe and import-step tests were caught reading the developer's
own
configuration instead of their own fixtures. That pass also found the
test suite
waiting out `ensure_everos_server`'s 30s readiness timeout on every
machine
without a running server -- always, on CI -- which cost one file 34 of
its 35
seconds and is now stubbed.
The interactive flow was verified under a pty, comparing the two console
wirings directly, and each new assertion was mutation-tested: every
behavioural
change on this branch had its fix reverted and the covering test
confirmed red,
and only that test. Where a fix had a plausible wrong shape, that shape
was
mutated too -- excluding `_org` wholesale rather than token-gating it,
reporting
progress after the await instead of before, seeding the registry-name
check from
the pool without ordering it after the target resolution. Two of those
mutations
survived and were the more useful result: one showed a guard clause
could not
fire (`_target_for` only ever returns a path that does not exist, so
excluding it
from the pool lookup was dead code, now removed), the other showed the
wizard's
own confirmation sits below the returns it was supposed to cover.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
User-facing docs are unchanged: this adds a platform to an existing
documented
command rather than a new surface. The developer docs move with the code
--
`docs/memory-plugin-architecture.md` (the everos pin, and the upgrade
SOP now
stating that a one-way migration belongs in the release notes) and
`scripts/README.md` (two deleted scripts).
## Risk
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
The import writes to EverOS and to `user_memory/profile/user.md`, and
copies
skill directories into the local skill pool. EverOS has no delete
endpoint, so
an unwanted import is not undone by reverting this branch; the skill
copies and
the profile edits are plain files and can be removed by hand. Import
state
lives in `~/.raven/import_state.json` and can be deleted to start over.
Behaviour changes for existing users: the onboard wizard's import step
and
`raven import run` both look different (shared prompt style, skill
counts,
one summary block). `raven import run`'s interactive path changes from
"crashes immediately" to working. Rolling back restores the crash.
Three more, from the review round: a skills-only import now asks before
copying
(one extra prompt, skippable with `--yes`), an all-platforms import
chosen with
"run in background" runs in the foreground instead and says so, and
skills under
a stale `_org/` mirror are no longer imported -- Hermes does not load
them
either, but anyone who had them imported by an earlier build keeps them,
since
nothing here deletes.
Two consequences of the everos upgrade that operators need to know:
- **The index migration is one-way.** everos 1.2.1 migrates the LanceDB
schema
on first start and prunes older manifest versions, so once a machine has
run
this, its memory index can no longer be read by an older everos.
Reverting
the branch does not undo it.
- **A missing provider no longer aborts startup.** 1.2.1 boots with
`[llm]`
alone. A misconfigured embedding provider used to fail loudly; it now
degrades
to keyword search, and rows written in that state carry no vector until
`everos cascade backfill` is run. everos itself only logs one warning
line,
which is why the wizard, `raven doctor` and `backend.start()` all
surface it --
the last of those runs every session, so an expired key is reported
rather
than discovered.
- **Behaviour change for users who skip embedding.** Recall degrades to
keyword
matching instead of failing, and the wizard no longer stops them from
getting
there. That is the point of the change, but it means a user can now end
up with
a working memory that is measurably worse at recall than the previous
all-or-nothing setup would have allowed.
## Related Issues
N/A
---------
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-08-04 20:44:07 +08:00
|
|
|
|
|
|
|
|
def test_the_two_identities_do_not_arrive_swapped(self, tmp_path: Path) -> None:
|
|
|
|
|
"""The whole point of moving identity into ServiceLocator is that a
|
|
|
|
|
mismatch makes every written memory unrecallable with no warning. Until
|
|
|
|
|
this assertion existed, swapping the two arguments at the only
|
|
|
|
|
production wiring point left the entire suite green."""
|
|
|
|
|
config = _config()
|
|
|
|
|
config.memory.user_id = "u-distinct"
|
|
|
|
|
config.memory.agent_id = "a-distinct"
|
|
|
|
|
backend = maybe_build_memory_backend(tmp_path, config)
|
|
|
|
|
assert backend._services.user_id == "u-distinct"
|
|
|
|
|
assert backend._services.agent_id == "a-distinct"
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# plugins.dirs
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestConfiguredDirs:
|
|
|
|
|
def test_named_roots_resolve_from_config(self, tmp_path: Path) -> None:
|
|
|
|
|
assert named_plugin_roots(_config(dirs=[str(tmp_path)])) == (tmp_path,)
|
|
|
|
|
assert named_plugin_roots(_config()) == ()
|
|
|
|
|
assert named_plugin_roots(None) == ()
|
|
|
|
|
|
|
|
|
|
def test_a_plugin_under_a_named_root_activates(self, tmp_path: Path) -> None:
|
|
|
|
|
root = tmp_path / "plugins"
|
|
|
|
|
(root / "shelf").mkdir(parents=True)
|
|
|
|
|
(root / "shelf" / "raven-plugin.toml").write_text(
|
refactor(*): seal the memory backend seam so a memory plugin needs no host edits (#414)
## Summary
Make `MemoryBackend` the only seam between the host and the memory
subsystem, so a second memory plugin can be installed without editing
host code.
The abstraction is the goal; no second backend is being added.
What the branch does:
- `health()` joins the Protocol. `raven doctor` and `raven import` read
a `BackendHealth(ready, checks)` the backend fills in with its own
vocabulary, instead of reaching into EverOS internals. Doctor prints the
checks verbatim and never interprets a label.
- A new `[[plugin.contributes.onboard]]` kind, with
`raven/contracts/onboard.py` as its paper. The host lends the wizard
shell as one `OnboardUI` and records the result; the screen returns a
`StepOutcome`. The plugin never writes `memory.backend` -- that key
stays the host's. EverOS's step-4 screen and its `everos.toml`
management move into the plugin.
- The skill source and the after-turn feedback prefix are named from
`memory.backend` rather than the literal `everos`.
- `enabled_by_default` is gone from the manifest: an installed plugin
the user has not disabled is active.
- `tests/test_plugin_boundary.py` pins the dependency direction in both
directions, with an equality assertion so the remaining exceptions
cannot grow.
That guard's allowlist started at five host files still speaking
EverOS's wire protocol. The follow-ups below close three of them.
Two things this branch itself introduced were found in manual acceptance
on an install without the plugin and fixed here: a turn printed which
backends were installed -- empty on exactly the install that needs the
sentence -- and `settings.everos` / `settings.everosSet` let
`ModuleNotFoundError` reach the dispatcher as an internal error carrying
a traceback. Both now carry the note doctor and the wizard already use,
naming the distribution to install.
Review on this PR found four blockers, all fixed and covered. A fifth
defect came out of manual acceptance rather than review, and four more
out of the rounds that followed it -- every one of those in the
embedding endpoint's own plumbing, each found by the round after the fix
that introduced it. They are listed under Risk; the blockers are:
1. `onboard` is an optional contribution, but the wizard equated "no
matching screen" with "not configured", so one `raven onboard
--skip-memory` wrote `memory.backend` back to null for a third-party
backend configured by hand. A backend with no screen now answers on the
strength of having been selected; only one whose own screen says it is
unconfigured is cleared, which is the case that rule exists for.
2. The record a sub-agent call leaves behind ran through a backend
nobody had started. The shipped adapter begins in an unknown state, so
the first flushing write only scheduled a readiness probe and answered
false -- the record said "unavailable" while the service was up the
whole time, and each per-record HTTP client was left open. One context
manager now owns start and stop around a record, in both the manager and
the DAG runner.
3. That record's write and the recall after it addressed different
owners: a real config spells its keys in camelCase and the block reaches
the backend as written, while the adapter read only the contract's
snake_case, so a sub-agent's memories were filed under the host
identity. The adapter reads both spellings.
4. Legacy embedding discovery had narrowed to the recorded plugin root,
so an install predating root recording lost its knowledge-base endpoint
with a valid file still on disk.
**The five follow-ups the seam left behind are in this PR too**, rather
than in three stacked ones, because they are one goal and the branch
protection dismisses an approval on every push:
- The embedding endpoint is raven's. A knowledge base indexes inside the
gateway process and never speaks to the memory service, yet it read its
endpoint out of everos.toml, so selecting another backend left it with
no vectors and no message naming the cause. Raven holds the block now
and hands it to the backend at start -- as a shared default, not an
override: a plugin that was given an endpoint of its own keeps it, and
only one that has none takes raven's. Discovery of an existing
everos.toml still checks all three places the plugin itself looks, read
with plain tomllib so it works where the plugin is not installed. No
data migrates: a base is keyed on its model and measured width, not on
the base url.
- `delete()` joins the Protocol. The browser used to delete a row out of
EverOS's index, in the host process, through the plugin's repository
layer -- while the markdown EverOS treats as the source of truth kept
the text, so the memory came back on the next rebuild, after the user
was told it was gone. The adapter now uses only operations EverOS
already performs, for the kinds it performs them for.
- Sub-agent memory goes through the contract. The read half is a new
optional `recall_session`; the write half needed no new surface, only
two metadata conventions written down. `agents.<name>.config.everos`
becomes `config.memory`, opaque to the host except the two keys the host
reads; the old spelling still loads.
- The memory and settings pages say why they are empty -- no plugin, or
a backend this page does not read -- instead of four zeros and a retry
button that cannot help.
- The `everos` package leaves the host's dependencies for the plugin's
own, at the same exact pin; the host reaches the tree through the
plugin. This is the package layer only: the installers already deliver
`everos-memory` as a sibling wheel from the same release, so an ordinary
install still has long-term memory.
The boundary guard's allowlist falls from five entries to two, both GUI
surfaces still shaped around EverOS's own store. Generalising their wire
is a frontend change and is deliberately not in scope.
This branch was reviewed on GitLab as merge request 639 over three
rounds, including a post-rebase range-diff check. It is being moved here
because GitHub is now the source of truth.
## Type
- [x] Refactor
## Verification
- `uv run pytest` on this branch, rebased onto `main`: 22146 passed, 4
failed, 45 skipped. Three of the four (`test_agents_oncall_launcher`,
`test_agent_loop_token_budget`, `test_agents_code_launcher`) were re-run
on a detached checkout of that same `main` commit in this environment
and fail there identically. The fourth (`test_ppt_engine_image_search`)
could not run in that checkout, whose environment lacks the deck
engine's extras; this branch's only change anywhere under
`plugins-dist/ppt-engine` is the removal of the `enabled_by_default`
manifest key, which that test does not reach. So this branch adds no
regression.
- `npx vitest run` in ui-web: 1680 passed across 103 files. `npm run
type-check` and `npm run gen:check` clean, so the generated client
matches the contract.
- Every fix in the follow-up commits was mutated away and its test
confirmed red, then restored and confirmed green. For the record path
that is three separate mutations: dropping `start()`, dropping `stop()`,
and narrowing the owner lookup back to one spelling.
- `uv run ruff check .` and `uv run ruff format --check` on the changed
files: clean.
- `uv lock --check`: consistent.
- `scripts/check_commit_messages.py`, `scripts/check_large_files.py`,
`scripts/check_source_language.py` over the branch range: clean.
- Manual acceptance against a real isolated install (temporary
RAVEN_HOME, isolated EverOS root and port), 34 cases: `raven plugins`,
`raven doctor` across four backend states, `raven onboard` interactive
and non-interactive including all three step-4 lanes, `raven import`
refusing and importing, an end-to-end write and recall, the web UI's
memory and settings pages driven through a real browser, a sub-agent
trace record, and an install with no memory plugin at all. 31 passed; 1
failed and was fixed; 1 partial; 1 carried over from the earlier round.
- The failure is the one worth reading. On a fresh managed install the
wizard reported embedding configured and the service it started the next
moment ran keyword-only: the spawned process carried no
`EVEROS_EMBEDDING__` values, and EverOS logged that the embedding key
was not configured. The rule deciding whether everos.toml already held
an operator's own endpoint asked whether its model name was a `"<...>"`
placeholder; the shipped template seeds every section with a real model
name and an empty key, so every fresh install read as a deliberate
choice and the host's endpoint was never bound. It now asks the
criterion the module already had -- model and key. The unit tests missed
it because each built its "operator's own" section with a key in it; the
regression copies the shipped template itself.
- The partial: the memory page's search returned relevant results
without error, but every memory in the test corpus was on one subject,
so narrowing could not be observed. The carried-over case is the
skill-source prefix, whose path this branch does not touch.
- Findings recorded and not fixed here, none introduced by this branch:
a progress spinner is still drawn after `import` reports it imported
nothing; an unsupported delete surfaces as a generic internal error; the
TUI log and `doctor` word "no memory plugin" differently; a turn that
did reach disk still prints that it was not written.
- The partial case: an induced agent skill is discovered through
`find_skill` with the backend's prefix, but `read_skill` / `use_skill`
on that id fail. Nothing writes the on-disk layer those tools look in,
on this branch or on `main`, and no test covers it. Pre-existing; filed
as a follow-up.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
User-visible changes:
1. User-track recall is now strictly bounded by `top_k`. A profile row
used to ride outside that bound.
2. `raven doctor` builds the plugin factory, so a managed EverOS setup
writes its env var and config templates during a doctor run. It used to
be read-only. The `--json` memory section is reshaped around
`health.checks`.
3. A third-party drop-in plugin without `enabled_by_default = true` used
to be skipped and now loads.
4. The loader no longer back-fills the EverOS config slice's `root` /
`owned`, nor strips a legacy `mode` key; a leftover `mode` now draws an
unknown-key warning.
5. The wizard's recap shows the contribution name `everos` rather than
`EverOS`.
6. `use_skill` with an unknown prefix reports "not found" after a disk
lookup instead of "unknown source".
From the follow-ups:
7. Config gains an optional top-level `embedding` block. Absent, the
knowledge base reads the EverOS file as before and says so once. An
operator who moves the values across changes nothing else; one who names
a *different* model there gets the existing `StaleBaseError` telling
them to rebuild that base. The block is a default for the memory plugin
rather than an override, so an install that had configured the plugin
separately keeps what it had. Note that a config carrying this block
does not load on an older Raven, which rejects unknown top-level keys.
8. `agents.<name>.everos` is written back as `agents.<name>.memory`. The
old spelling still loads; a per-agent `baseUrl` is ignored with a
warning, having never had a user.
9. Deleting a memory now changes what EverOS treats as the source of
truth, so it stays deleted. Profiles and cases report that they cannot
be deleted rather than appearing to succeed.
10. `pip install raven` no longer pulls the memory engine in.
`install.sh` and `install.ps1` are unaffected: both already resolve
`everos_memory-*.whl` from the release they install and pass it as
`--with everos-memory`, and the source path installs it editable, so
those installs keep long-term memory. An install that reaches neither --
a release predating the sibling wheel, or a bare `pip install` -- now
boots without memory and says which distribution to install rather than
failing on an import.
Found after the acceptance run, in review, all fixed here. They share
one cause worth stating once: the endpoint acquired a second home, and
each fix taught one more reader about it while leaving the next one
behind.
11. The endpoint the wizard saved never reached the EverOS process it
then started. The rule for "does everos.toml already hold an operator's
own endpoint" asked whether its model name was a `"<...>"` placeholder;
the shipped template seeds every section with a real model name and an
empty key, so every fresh managed install read as a deliberate choice
and the host's endpoint was never bound. The service came out of the
wizard running keyword-only while the wizard said embedding was
configured. The rule now asks the criterion the module already had:
model and key.
12. The exported `EVEROS_EMBEDDING__*` variables are a third home,
documented by EverOS and ranked above its file. They were being
overwritten. A complete triple is now an operator's choice; an
incomplete one is not an endpoint and is replaced whole rather than
topped up from the host.
13. Raven writes those same variables itself at startup, so a reader
that asked only whether all three were set called raven's own binding an
operator's export -- a blank settings card and a save refused by naming
variables nobody had set. The module now records which of them it set.
14. That record lived in a module-level set, and `raven gateway
--restart` re-launches through `os.execv`: the values survive, module
state does not. The record now travels in a variable beside them, and is
stripped from the environment handed to EverOS.
15. A settings save the environment would outrank is refused with the
variable names, rather than written and silently ignored.
Four of the five arrived one per review round, each in the fix for the
one before it. The tests that missed them all shared a shape: each built
its "an operator configured this" fixture with a key in it, or cleared
the environment before the case, so the states the product actually
produces -- a template with no key, a live process that has just bound
its own endpoint -- were never the input. The regressions now copy the
shipped template, and run the startup sequence and a second interpreter
rather than a prepared state.
Rollback is a revert of the branch: the seam is additive, and
`memory.backend` keeps its shipped default.
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: gloryfromca <23442919+gloryfromca@users.noreply.github.com>
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-09-16 22:19:50 +08:00
|
|
|
'[plugin]\nid = "shelf"\nversion = "0.1.0"\n',
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
encoding="utf-8",
|
|
|
|
|
)
|
|
|
|
|
assert "shelf" in build_plugin_registry(_config(dirs=[str(root)])).activated_ids()
|
|
|
|
|
assert "shelf" not in build_plugin_registry(_config()).activated_ids()
|
|
|
|
|
|
|
|
|
|
|
fix(plugins): a plugin that fails to load no longer takes every other plugin with it (#703)
## Summary
One plugin that failed to activate dropped every plugin.
`PluginRegistry.activate` raised on the first plugin whose factory would
not import (or whose contribution name collided), and
`build_plugin_registry` (`raven/core/plugin_stack.py`) answered by
returning an empty registry. A single broken user plugin therefore
silently removed research-flow, ppt-engine, design-engine, the memory
backend and the bundled playbook tools, with one stderr warning as the
only trace. Reproduced with two mock plugins under a scratch
`RAVEN_HOME`: `aa-broken` (factory raises `ImportError`) beside
`zz-good`; before this change the registry came back with `activated:
[]`, after it with `design-engine, everos-memory, playbook, ppt-engine,
zz-good` activated and `aa-broken` named as failed.
Changes:
- **Per-plugin activation** (`raven/plugins/registry.py`). Each admitted
plugin activates on its own. One that fails is rolled back whole (no
partial contribution in any table, and the `sys.path` entry
`_ensure_importable` appended for it is withdrawn), recorded as a
`PluginActivationFailure` (`activation_failures()`), and the plugins
after it still activate. In a name conflict the plugin activated first
(discovery order, by id) keeps the name and the other is recorded as
failed. A module `__getattr__` that raises something other than
`AttributeError` is now a recorded failure rather than an uncaught
crash.
- **Said to the user** (`plugin_stack.build_plugin_registry`,
`runtime.build_runtime`). Each failure is one notice naming the plugin,
its cause and the `plugins.disabled` escape, through the host's notifier
(`HostWiring.notify`), else stderr - the same channel the
missing-memory-backend notice already uses. When the configured memory
backend belongs to a plugin that failed, the memory notice names that
plugin and its cause instead of "no installed plugin provides it".
- **`raven plugins`** shows a `failed` status and the cause under the
table (the command called `activate` directly and previously crashed on
such a plugin).
- **Agents smoke check** (`raven/cli/agents_commands.py`) matched the
old log line "plugin activation failed", which no longer exists; it now
reads the shared `PLUGIN_FAILURE_MARKER`, and its test prints the notice
the real producer writes, so the two cannot drift.
- **Sub-agents inherit the host's opt-outs**
(`product_render.write_rendered`, `inherit_plugin_opt_outs`). A product
engine inherits `RAVEN_HOME`, so it scans the host's `<home>/plugins`
and the shared interpreter's entry points, but it read
`plugins.disabled` only from its own rendered config; a plugin disabled
on the host came back in every product. Every render now merges the
host's list after the product's own. The product's own engine plugin
never travels (`own_plugins=`, passed by all five launchers and the
scaffold): the PPT agent is `ppt-engine`, and a host turning it off for
its own agent is not a request to run the PPT agent without it. A
contract test reads every launcher's `write_rendered` call and requires
it to name its `*_PLUGIN_ID`.
- `CONTEXT.md` (Plugin Registry) and
`docs-site/docs/building-plugin{,.zh}.md` describe the new behaviour.
Not in this PR: the Web UI plugin list (`ext.list`) is discovery-only
and does not show a failed plugin; adding it is a wire change
(`ExtListResult`, openrpc, generated TS, the page) and is left for a
follow-up. The TUI, gateway and `raven agent` hosts show the notice
through their notifiers; the rpc stack (serve/acp) prints it to stderr,
which is also what the agents smoke check reads.
## Type
- [x] Fix
- [ ] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
**Rebased**: head 7cd000dbc on origin/main 8ee5ae0d8, without conflicts.
`git range-diff` shows every commit replayed unchanged. The branch's own
test files rerun at this head: 395 passed. Numbers elsewhere in this
description are from earlier heads.
Head b4d51aee8, rebased onto origin/main 6551f8259 after #698 and #708
merged. #698 conflicted in `raven/config/product_render.py` and
`tests/test_config_product_render.py`: both PRs added a function at the
same spot (`inherit_host_denials` there, `inherit_plugin_opt_outs` here)
and a call in `write_rendered`. The resolution keeps both functions and
all their tests; `write_rendered` now reads `host_config()` once and
passes it to both. #708 touches none of these files. At this head:
```
COLORTERM=truecolor uv run --frozen --python 3.12 --all-extras pytest -q -p no:cacheprovider
25948 passed, 109 skipped
uv run --frozen --python 3.12 --all-extras pytest -q tests/test_config_product_render.py
44 passed
ruff check / ruff format --check / make lint-imports lint-deps lint-types / git diff --check origin/main...HEAD
check_source_language.py origin/main...HEAD / make check-commits / check-large-files
all clean
cd ui-tui && npm run lint:rpc && npm run type-check && npm test
144 files, 2106 passed
```
The earlier `TUI checks` failure (run 35834019105, head 5fc374035) was
`newInstancePicker.test.tsx > quick-selects by the number it printed`.
This PR changes nothing under `ui-tui/`; the test passed 5 of 5 runs
locally at this head and in the full ui-tui run above.
The numbers below are from the earlier heads and are kept for the
record.
```
uv run --frozen --python 3.12 --extra dev ruff check raven evolver agents plugins-dist tests scripts
All checks passed
uv run --frozen --python 3.12 --extra dev ruff format --check raven evolver agents plugins-dist tests scripts
2083 files already formatted
make lint-imports && make lint-deps && make lint-types
Contracts: 10 kept, 0 broken / No dependency issues found / All checks passed
git diff --check origin/main...HEAD
clean
COLORTERM=truecolor make coverage (full suite, head before rebasing onto 7fdf296f4)
25847 passed, 109 skipped
COVERAGE_BASE_REF=origin/main make coverage-diff
Diff coverage: 100.00% (71/71 executable changed lines)
PYTHONPATH=. uv run --frozen --python 3.12 --extra dev python scripts/check_source_language.py origin/main...HEAD
exit 0
make check-commits
pass
git merge-tree --write-tree HEAD origin/main
clean
```
After rebasing onto 7fdf296f4 (its two new commits touch none of these
files), the touched suites at this head:
```
COLORTERM=truecolor uv run --frozen --python 3.12 --all-extras pytest -q tests/test_plugin_*.py tests/test_core_plugin_stack.py tests/test_cli_plugin_commands.py tests/test_cli_agents_commands.py tests/test_cli_tui_commands.py tests/test_config_product_render.py tests/test_agents_*launcher*.py tests/test_everos_plugin_discovery.py tests/test_release_plugin_list.py tests/test_cli_gateway_commands.py
727 passed
uv run --frozen --python 3.12 --all-extras pytest -q tests/test_subagent_vendored_agents.py tests/test_rpc_subagents.py tests/test_subagent_acp.py
452 passed
```
Revert-to-red, one production file restored to origin/main at a time
with the tests kept:
```
raven/plugins/registry.py -> 2 errors (plugin_stack imports PluginActivationFailure)
raven/core/plugin_stack.py -> 6 failed
raven/core/runtime.py -> 1 failed (build_runtime hands the host's notifier to the registry)
raven/config/product_render.py -> 42 failed
raven/cli/agents_commands.py -> 1 failed (smoke reds a handshake whose plugin did not load)
raven/cli/plugin_commands.py -> 1 failed (failed row and escaped cause)
agents/raven-ppt/run.py -> 2 failed (engine exemption, launcher contract)
```
Ten existing tests pinned "activation raises" (`test_plugin_registry`,
`test_plugin_bootstrap`, and the conflict tests for tools, hooks, tool
gates and session observers). They now assert the new contract instead:
the later plugin is recorded with the same reason text, the earlier one
keeps the name, and nothing of the loser is registered. Two stubs in
`test_cli_tui_commands.py` took `build_plugin_registry(cfg)` and now
accept the `notify` keyword.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
- A plugin conflict used to disable all plugins; it now keeps the plugin
that activates first and skips the other with a notice. Two plugins
contributing the same name therefore run with one of them instead of
none.
- A product sub-agent now starts with the host's `plugins.disabled`
merged into its config (its own engine excepted). A plugin that was
disabled on the host but relied on inside a product stops loading there;
the remedy is to enable it on the host.
- `PluginRegistry.activate` no longer raises `PluginConflictError` /
`PluginFactoryImportError`; the only in-tree callers were
`assemble_plugin_registry` and `raven plugins`. The exception classes
stay exported.
- Security: the change only narrows what loads. A failed plugin's
directory leaves sys.path, and the inherited opt-outs can only remove
plugins from a product, never add one.
- Rollback: revert the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: Claude (claude-opus-5-5) <noreply@anthropic.com>
2026-09-23 22:41:21 +08:00
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# One broken plugin
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _broken_plugin_root(tmp_path: Path, *, backend: str | None = None) -> Path:
|
|
|
|
|
"""A named root holding plugin ``wreck``, whose factory module raises on import."""
|
|
|
|
|
package = f"_wreck_{tmp_path.name.replace('-', '_')}"
|
|
|
|
|
root = tmp_path / "plugins"
|
|
|
|
|
plug = root / "wreck"
|
|
|
|
|
(plug / package).mkdir(parents=True)
|
|
|
|
|
(plug / package / "__init__.py").write_text("raise ImportError('boom')\n", encoding="utf-8")
|
|
|
|
|
kind, name = ("memory_backends", backend) if backend else ("tools", "wreck_tool")
|
|
|
|
|
(plug / "raven-plugin.toml").write_text(
|
|
|
|
|
f'[plugin]\nid = "wreck"\nversion = "0.1.0"\n'
|
|
|
|
|
f'[[plugin.contributes.{kind}]]\nname = "{name}"\nfactory = "{package}:make"\n',
|
|
|
|
|
encoding="utf-8",
|
|
|
|
|
)
|
|
|
|
|
return root
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestOneBrokenPlugin:
|
|
|
|
|
def test_the_rest_of_the_registry_survives_and_the_host_hears_it(self, tmp_path: Path) -> None:
|
|
|
|
|
heard: list[str] = []
|
|
|
|
|
reg = build_plugin_registry(_config(dirs=[str(_broken_plugin_root(tmp_path))]), notify=heard.append)
|
|
|
|
|
|
|
|
|
|
assert "wreck" not in reg.activated_ids()
|
|
|
|
|
assert {"everos-memory", "playbook"} <= set(reg.activated_ids())
|
|
|
|
|
assert [f.plugin_id for f in reg.activation_failures()] == ["wreck"]
|
|
|
|
|
[message] = heard
|
|
|
|
|
assert "'wreck' did not load" in message
|
|
|
|
|
assert "boom" in message
|
|
|
|
|
assert "plugins.disabled" in message
|
|
|
|
|
|
|
|
|
|
def test_two_broken_plugins_each_get_a_notice_that_claims_nothing_about_the_other(self, tmp_path: Path) -> None:
|
|
|
|
|
root = _broken_plugin_root(tmp_path)
|
|
|
|
|
twin = root / "wreck2"
|
|
|
|
|
(root / "wreck").rename(twin)
|
|
|
|
|
(twin / "raven-plugin.toml").write_text(
|
|
|
|
|
(twin / "raven-plugin.toml").read_text(encoding="utf-8").replace('"wreck"', '"wreck2"'), encoding="utf-8"
|
|
|
|
|
)
|
|
|
|
|
_broken_plugin_root(tmp_path / "second")
|
|
|
|
|
heard: list[str] = []
|
|
|
|
|
reg = build_plugin_registry(
|
|
|
|
|
_config(dirs=[str(root), str(tmp_path / "second" / "plugins")]), notify=heard.append
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
assert [f.plugin_id for f in reg.activation_failures()] == ["wreck", "wreck2"]
|
|
|
|
|
assert len(heard) == 2
|
|
|
|
|
for message in heard:
|
|
|
|
|
assert "loaded normally" not in message
|
|
|
|
|
assert "Other plugins continue loading" in message
|
|
|
|
|
|
|
|
|
|
def test_without_a_notifier_it_reaches_stderr(self, tmp_path: Path, capsys) -> None:
|
|
|
|
|
build_plugin_registry(_config(dirs=[str(_broken_plugin_root(tmp_path))]))
|
|
|
|
|
assert "'wreck' did not load" in capsys.readouterr().err
|
|
|
|
|
|
|
|
|
|
def test_a_disabled_broken_plugin_is_not_touched(self, tmp_path: Path) -> None:
|
|
|
|
|
heard: list[str] = []
|
|
|
|
|
reg = build_plugin_registry(
|
|
|
|
|
_config(dirs=[str(_broken_plugin_root(tmp_path))], disabled=["wreck"]), notify=heard.append
|
|
|
|
|
)
|
|
|
|
|
assert reg.activation_failures() == []
|
|
|
|
|
assert heard == []
|
|
|
|
|
|
|
|
|
|
def test_a_backend_whose_plugin_failed_is_not_called_uninstalled(self, tmp_path: Path) -> None:
|
|
|
|
|
cfg = _config(memory_backend="wreckmem", dirs=[str(_broken_plugin_root(tmp_path, backend="wreckmem"))])
|
|
|
|
|
heard: list[str] = []
|
|
|
|
|
reg = build_plugin_registry(cfg, notify=heard.append)
|
|
|
|
|
|
|
|
|
|
assert maybe_build_memory_backend(tmp_path, cfg, registry=reg, notify=heard.append) is None
|
|
|
|
|
memory_notice = heard[-1]
|
|
|
|
|
assert "provided by plugin 'wreck', which did not load: importing" in memory_notice
|
|
|
|
|
assert "boom" in memory_notice
|
|
|
|
|
assert "no installed plugin provides it" not in memory_notice
|
|
|
|
|
|
|
|
|
|
def test_build_runtime_hands_the_hosts_notifier_to_the_registry(self, tmp_path: Path, monkeypatch) -> None:
|
|
|
|
|
from raven.agent.loop.bundles import HostWiring
|
|
|
|
|
from raven.contracts.llm_provider import LLMResponse
|
|
|
|
|
from raven.core import plugin_stack, runtime
|
|
|
|
|
from raven.providers.base import LLMProvider
|
|
|
|
|
|
|
|
|
|
root = _broken_plugin_root(tmp_path)
|
|
|
|
|
monkeypatch.setattr(
|
|
|
|
|
plugin_stack,
|
|
|
|
|
"plugin_discovery_sources",
|
|
|
|
|
lambda: {
|
|
|
|
|
"bundled_dir": tmp_path / "none",
|
|
|
|
|
"user_dir": root,
|
|
|
|
|
"project_dir": tmp_path / "none",
|
|
|
|
|
"entry_points_group": None,
|
|
|
|
|
},
|
|
|
|
|
)
|
|
|
|
|
monkeypatch.setattr(runtime.token_wise_stack, "install_from_config", lambda *a, **k: None)
|
|
|
|
|
monkeypatch.setattr(runtime.token_wise_stack, "caching_probe", lambda *a, **k: False)
|
|
|
|
|
|
|
|
|
|
class _Provider(LLMProvider):
|
|
|
|
|
def __init__(self) -> None:
|
|
|
|
|
super().__init__(api_key="test")
|
|
|
|
|
|
|
|
|
|
async def chat(self, messages, **kwargs):
|
|
|
|
|
return LLMResponse(content="ok", finish_reason="stop")
|
|
|
|
|
|
|
|
|
|
def get_default_model(self) -> str:
|
|
|
|
|
return "fake/default"
|
|
|
|
|
|
|
|
|
|
config = Config()
|
|
|
|
|
config.agents.defaults.workspace = str(tmp_path / "ws")
|
|
|
|
|
heard: list[str] = []
|
|
|
|
|
rt = runtime.build_runtime(
|
|
|
|
|
config, _config(memory_backend=None), provider=_Provider(), host=HostWiring(notify=heard.append)
|
|
|
|
|
)
|
|
|
|
|
try:
|
|
|
|
|
assert any("'wreck' did not load" in m for m in heard)
|
|
|
|
|
finally:
|
|
|
|
|
rt.discard()
|
|
|
|
|
|
|
|
|
|
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# The provider grant
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class _GrantWatch:
|
|
|
|
|
"""A registry stand-in that records what locator each factory was handed."""
|
|
|
|
|
|
|
|
|
|
def __init__(self, seen: list) -> None:
|
|
|
|
|
self._seen = seen
|
|
|
|
|
|
|
|
|
|
def hook_names(self):
|
|
|
|
|
return ["h"]
|
|
|
|
|
|
|
|
|
|
def tool_names(self):
|
|
|
|
|
return ["t"]
|
|
|
|
|
|
|
|
|
|
def hook_plugin_id(self, name):
|
|
|
|
|
return "p"
|
|
|
|
|
|
|
|
|
|
def tool_plugin_id(self, name):
|
|
|
|
|
return "p"
|
|
|
|
|
|
|
|
|
|
def build_hook(self, name, *, config, services):
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
self._seen.append(("hook", services))
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
return object()
|
|
|
|
|
|
|
|
|
|
def build_tool(self, name, *, config, services):
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
self._seen.append(("tool", services))
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
return object()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestProviderGrant:
|
|
|
|
|
def test_the_connections_provider_reaches_hooks_and_tools(self, tmp_path: Path) -> None:
|
|
|
|
|
seen: list = []
|
|
|
|
|
lent = object()
|
|
|
|
|
build_plugin_hooks(tmp_path, _config(), registry=_GrantWatch(seen), provider=lent)
|
|
|
|
|
build_plugin_tools(tmp_path, _config(), registry=_GrantWatch(seen), provider=lent)
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
assert [(kind, services.provider) for kind, services in seen] == [("hook", lent), ("tool", lent)]
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
|
|
|
|
|
def test_no_provider_lends_none(self, tmp_path: Path) -> None:
|
|
|
|
|
seen: list = []
|
|
|
|
|
build_plugin_hooks(tmp_path, _config(), registry=_GrantWatch(seen))
|
feat(ui-tui): tool cards open themselves, the strip marks here, ticker words split
## Summary
Three reader-facing changes to the TUI transcript and the instance strip.
**A settled tool call opens itself.** A tool card had two states, shut and
full, and neither is what a reader wants by default: shut hides the result
that was the point of the call, full spends a thousand rows on a result five
rows would have answered. There are now three levels - shut, a preview capped
at `TOOL_PREVIEW_ROWS` result rows with a `+N` row standing for the
remainder, and full at `TOOL_FULL_ROWS`. The cap is what bounds the cost, so
a call that came back opens unasked and only a call that returned nothing
stays shut, its block being the argument the row above already shows. A
reader's own decision always wins over that default.
The `+N` row becomes its own two-way control: it reveals the rest, then folds
back to the cap, where the block's own click shuts the card outright. It used
to ride inside the output array, which made the one row announcing there was
more to see the row that collapsed the card.
Fold state moves out of the component that draws it into a store keyed by
tool call id. Held in the row's component state, a row that changed - a step
landing in a turn still running - unmounted and took the reader's decision
with it, so a card opened seconds ago closed itself. `useMainApp` now reads
that store when it measures: a resize drops every measured height because the
cache buckets on columns, so without the folds there, rows below the fold came
back at their default height and the transcript scrolled to the wrong place.
**The strip marks the row whose conversation is on screen.** The composer's
top border names the instance being typed to, and the strip listed every
instance without saying which of them that was. The active row now carries a
gutter bar in the strip's own leftmost column, where nothing else draws, so
the bar reads as a position and the bullet beside it goes on saying status
alone. The active row is exempt from every cap, and a line no click can switch
to - a graph line, a loose spawn - never carries it. An interrupted turn also
refreshes the instance registry now: `message.complete` already did, but the
manager moves the row on this path too, writing `cancelled` or `failed`, so
without the re-read an interrupted instance went on showing a filled bullet
while its view went on polling a turn that had ended.
**The censored ticker vocabulary splits from Raven's own.** Wrapped agents
render their status as a kaomoji plus a verb, some of it on the channel the
reasoning arrives on, and `cleanThinkingText` strips exactly that pair - but
it was reading its strip list off Raven's own `FACES` and `VERBS`. That made
the two one list, so a branding change silently changed what gets censored out
of a model's reasoning: rename a verb and the old word stops being stripped,
adopt a word another agent uses and Raven's own ticker starts eating itself.
`tickerNoise.ts` now holds that vocabulary, frozen and deliberately separate;
it describes other agents' output and changes only when one of them does.
`FACES` and `VERBS` are then free to move, and they move here: the kaomoji
become one bird wearing different expressions, and the verbs are ordered as
one round of work rather than by how close the words are in meaning, because
at one word every 2.5s a reader sees most of the list in a single turn. Each
emoji frame is a single code point on purpose - a ZWJ sequence or a variation
selector renders as two glyphs on terminals that do not compose it, which
shifts everything right of the ticker.
## Type
- [ ] Fix
- [x] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Run on a worktree at this branch's tip, against the current main tip:
- `npx vitest run` (ui-tui): 141 files, 2052 tests passed
- `npx tsc --noEmit -p tsconfig.json` (ui-tui): exit 0, no output
- `make check-source-language COMMIT_RANGE=origin/main..HEAD`: exit 0
- `make check-large-files COMMIT_RANGE=origin/main..HEAD`: exit 0
No Python source is touched, so no pytest selection applies. `ui-tui/CONTEXT.md`
is updated for the fold levels and the gutter bar; the tool-card work carries
its design note under `docs/plans/`.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
Three user-visible changes, all inside the terminal UI:
- a tool call that returned something now opens to a capped preview instead of
staying shut. A reader who prefers it shut clicks once, and that decision
holds for the life of the call.
- the instance strip spends one leading column on the gutter bar, so every row
has one column less for its name.
- the status ticker shows a different set of glyphs and words.
No RPC schema, config or on-disk format changes. Fold state lives in memory
and per transcript view, so nothing persists across a restart and there is
nothing to migrate. The split strip list only widens what is removed from
displayed reasoning text; it reads no new input and grants no new capability.
Rollback is a revert of the squash commit.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
2026-09-10 12:42:09 +00:00
|
|
|
assert [(kind, services.provider) for kind, services in seen] == [("hook", None)]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestHostToolsGrants:
|
|
|
|
|
"""The host side of ``media_proxy``, ``web_config`` and ``media_config``.
|
|
|
|
|
|
|
|
|
|
The plugin side is tested with a hand-built locator; this is the link nothing
|
|
|
|
|
else pins, and the one that was broken: every entrance hands the stack its
|
|
|
|
|
``RavenConfig``, whose ``tools`` lives under ``base``, so reading ``tools`` off
|
|
|
|
|
the extension object lent None to every deployment.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
def test_the_hosts_media_proxy_and_web_section_reach_tools(self, tmp_path: Path) -> None:
|
|
|
|
|
seen: list = []
|
|
|
|
|
tools = ToolsConfig(
|
|
|
|
|
media=MediaGenConfig(proxy="http://127.0.0.1:7890"),
|
|
|
|
|
web=WebToolsConfig(proxy="socks5://127.0.0.1:1080"),
|
|
|
|
|
)
|
|
|
|
|
config = _config(tools=tools)
|
|
|
|
|
build_plugin_tools(tmp_path, config, registry=_GrantWatch(seen))
|
|
|
|
|
|
|
|
|
|
[(kind, services)] = seen
|
|
|
|
|
assert kind == "tool"
|
|
|
|
|
assert services.media_proxy == "http://127.0.0.1:7890"
|
|
|
|
|
assert services.web_config is not None
|
|
|
|
|
assert services.web_config() is config.base.tools.web
|
|
|
|
|
assert services.web_config().proxy == "socks5://127.0.0.1:1080"
|
|
|
|
|
assert callable(services.media_config)
|
|
|
|
|
|
|
|
|
|
def test_a_host_without_a_proxy_lends_none_and_its_web_section(self, tmp_path: Path) -> None:
|
|
|
|
|
seen: list = []
|
|
|
|
|
config = _config()
|
|
|
|
|
build_plugin_tools(tmp_path, config, registry=_GrantWatch(seen))
|
|
|
|
|
|
|
|
|
|
[(_, services)] = seen
|
|
|
|
|
assert services.media_proxy is None
|
|
|
|
|
assert services.web_config is not None
|
|
|
|
|
assert services.web_config() is config.base.tools.web
|
|
|
|
|
|
|
|
|
|
def test_a_base_config_is_read_as_itself(self, tmp_path: Path) -> None:
|
|
|
|
|
"""A caller holding the base ``Config`` rather than the extension is read
|
|
|
|
|
directly; the two lanes name the same section."""
|
|
|
|
|
from raven.core.plugin_stack import _host_config
|
|
|
|
|
|
|
|
|
|
base = Config(tools=ToolsConfig(media=MediaGenConfig(proxy="http://10.0.0.1:3128")))
|
|
|
|
|
assert _host_config(base) is base
|
|
|
|
|
assert _host_config(_config(tools=base.tools)).tools.media.proxy == "http://10.0.0.1:3128"
|
fix(tools): an array sent as its own JSON is still an array
## Summary
Reported as "deliver_files is broken". It is not: **the tool never ran.**
Every `deliver_files` call on one install was refused before dispatch -- five in a row in a single session -- and nothing was ever delivered:
```
Error: Invalid parameters for tool 'deliver_files': files should be array
```
What the model sent was the array, spelled as a string:
```json
{"files": "[{\"path\": \"...poster.png\", \"title\": \"...\"}]", "message": "..."}
```
`cast_params` already forgives that spelling for every scalar type -- `"3"` for an integer, `"true"` for a boolean -- and did not for arrays or objects, which are exactly the types a model is most likely to stringify.
## Type
- [x] Fix
- [ ] Feature
## The edge of the forgiving is the design
When the value is a string, try `json.loads`, and take the result **only if it is the type the schema asked for**. A string that is not JSON, or is JSON of the wrong shape, is returned unchanged so the validator still names the real problem -- the point is to widen what is accepted, not to swallow a type error.
**Nothing here can raise.** Turning "your argument has the wrong type" into a traceback would be worse than the refusal it replaces, so the parse is wrapped and failure falls through.
**A `type: "string"` field is never parsed.** JSON is ordinary text in a message body or a file's content, and replacing it would hand the tool something it never asked for. Two independent things prevent it today (the string branch returns before the parse is reached, and the parse only wins on a type match), which is why the case pinning it is a tripwire rather than a load-bearing assertion -- said so in its own docstring rather than left to look like coverage.
## Not just deliver_files
Six built-in tools declare an array or object parameter and were all exposed:
| tool | parameter |
|---|---|
| `deliver_files` | `files` |
| `ask_user` | `questions` |
| `image_generate` | `images` |
| `message` | `media` |
| `create_playbook` | `skills` |
| `video_generate` | `params` |
The same failure was already seen from the other side: `acp_client/acp_agent.py` records `update_task_state` and `operations should be array` from a real dispatch.
## Verification
```
make lint-python ruff check + ruff format --check, 1850 files
make lint-imports 9 contracts kept, 0 broken
pytest tests/ 19,699 passed, 7 failed (all pre-existing, see below)
```
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots -- no user-facing string
**End to end, through the real tool**, with the exact payload that failed five times in production:
```
files sent as: str -> [{"path": ".../poster.png", "title": "..."}]
returned: Delivered 1 file(s): poster.png (72 B).
still "should be array": False
registered in the store: True
```
Twelve cases, five mutations, each killing at least one:
| mutation | red |
|---|---|
| drop the whole branch (the old behaviour) | 3 |
| raise instead of falling through on a parse failure | 5 |
| accept the parse whatever type it yielded | 1 |
| do not re-cast the parsed value, so items are not cast | 1 |
| widen the tuple to include `string` | **survived -- unreachable** |
The last is worth stating rather than hiding: that mutation cannot change behaviour, because the `type == "string"` branch returns earlier and the type check would refuse the result anyway. I also tried moving the new block above that branch, alone and combined with widening the tuple, and neither reddens anything either. The invariant holds by construction; the case that documents it says so.
**Pre-existing failures, checked against the base.** 7 failed in the full run, all in `tests/test_security_network.py` (`test_a_redirect_to_a_dangerous_address_is_refused` and siblings). Running that file alone on this same tree gives 4 -- the count is order-dependent -- and the change touches only `raven/agent/tools/params.py` plus a new test file, neither of which `raven/security/network.py` imports. The failures are the box's resolver: it returns poisoned answers roughly half the time, which I measured separately (`en.wikipedia.org` came back as `2001::1` on 3 of 6 lookups). Not introduced here, and worth someone's attention on its own.
## Risk
- [x] Security impact considered -- widens what reaches a tool's own validation, not what bypasses it. A parsed value is still validated against the same schema, and a parse that yields the wrong type is refused exactly as before
- [x] Backward compatibility considered -- a call that worked before takes the identical path; the new branch is reached only by a `str` where an array or object is declared, which previously always failed
- [x] Rollback path is clear -- single-commit revert
## Related Issues
N/A
## Swept
`mr-review-patterns` pre-submit sweep, over `git diff origin/main...HEAD`.
- **1 (a write location moved)** -- nothing moved; a branch was added to an existing dispatch on `target_type`. Grepped every caller of `cast_params`: the registry is the only one, and it runs `validate_params` right after, which is the reader this affects.
- **2 (a value with several entry points)** -- the cast is the single funnel every tool argument passes through, which is why the fix belongs here and not in `deliver_files`.
- **3 (a guard)** -- checked both directions: what it wrongly lets through (JSON of the wrong type, non-JSON text -- both refused, with cases) and what it wrongly refuses (a real list, unaffected, with a case).
- **4 (tests)** -- five mutations above, one honestly reported as unreachable. Failing-ID sets diffed against the base rather than counts.
- **6 (stale text)** -- the module docstring enumerated what is coerced ("a string that should be an integer"); it now names arrays and objects too. Grepped the tracked tree for other statements of the rule: none.
- **9 (error handling)** -- the new path adds one way to end and it is caught: `json.loads` raises `ValueError` on bad text and `TypeError` on a non-string, and both fall through to the untouched value.
- **11** -- `git ls-files | grep -c node_modules` is 0; the commit-message gate was run, not eyeballed.
Not applicable, with reasons: **3b, 3c, 3d, 3e** (no tool schema produced, no state moved, one lane, no assertion lost its symbol); **4b, 4c, 4d** (no platform branch, no shell, no rendered number); **5, 5b** (no dependency; `json` is stdlib and already imported across this package); **6b, 6c** (no backup, no generated artifact); **7, 7b** (nothing on disk); **8** (no asset, no secret); **10** (no prompt text).
## Deliberately not fixed
The error text still ends with `[Analyze the error above and try a different approach.]`, and the model plainly did not -- it sent the same shape five times. A message naming the expected spelling (`files must be a JSON array, not a string containing one`) would give it something to act on. That is a change to the registry's error surface, affects every tool, and deserves its own argument.
## Moved from !594
Opened on a compliant source branch. AGENTS.md 2.1 asks for a 3-5 word snake_case description and the previous branch had seven; GitLab cannot change an existing merge request's source branch, so the change moves rather than the name.
Same commits, rebased onto `c2a9768f`. Both code findings from the review on !594 are already in them -- `RecursionError` caught with its regression case, and the implementation comment reduced to the two non-obvious reasons. Nothing else changed, so that review carries.
2026-09-09 15:42:36 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
# everos plugin presence
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestEverosPresence:
|
|
|
|
|
def test_the_dev_environment_carries_the_plugin(self) -> None:
|
|
|
|
|
assert everos_plugin_installed() is True
|
|
|
|
|
|
|
|
|
|
def test_an_uninstalled_distribution_reads_as_absent(self) -> None:
|
|
|
|
|
with everos_plugin_absent():
|
|
|
|
|
assert everos_plugin_installed() is False
|
|
|
|
|
|
|
|
|
|
def test_a_plugin_that_is_broken_inside_still_reads_as_installed(self) -> None:
|
|
|
|
|
"""The two failures a host must not confuse: gone, and here but broken.
|
|
|
|
|
|
|
|
|
|
A package whose own imports fail is present -- the guard says so, and the
|
|
|
|
|
import the caller then makes raises the plugin's own error instead of
|
|
|
|
|
being reported as an absence nobody can act on.
|
|
|
|
|
"""
|
|
|
|
|
with everos_plugin_broken():
|
|
|
|
|
assert everos_plugin_installed() is True
|
|
|
|
|
with pytest.raises(ImportError):
|
|
|
|
|
from raven_everos.health import capability_available # noqa: F401
|
|
|
|
|
|
|
|
|
|
def test_no_host_module_imports_the_plugin_at_module_level(self) -> None:
|
|
|
|
|
"""Every one of these imports has to stay inside a function.
|
|
|
|
|
|
|
|
|
|
A module-level one fails at ``import raven.cli``, before any guard can
|
|
|
|
|
run, and no amount of degrading downstream can recover from that.
|
|
|
|
|
"""
|
|
|
|
|
root = Path(raven.__file__).parent
|
|
|
|
|
offenders = [
|
|
|
|
|
f"{path.relative_to(root)}:{node.lineno}"
|
|
|
|
|
for path in sorted(root.rglob("*.py"))
|
|
|
|
|
for node in ast.parse(path.read_text(encoding="utf-8")).body
|
|
|
|
|
if isinstance(node, (ast.Import, ast.ImportFrom))
|
|
|
|
|
for name in ([node.module or ""] if isinstance(node, ast.ImportFrom) else [a.name for a in node.names])
|
|
|
|
|
if name.startswith("raven_everos")
|
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
assert offenders == []
|
|
|
|
|
|
|
|
|
|
def test_the_note_names_the_distribution_and_the_default(self) -> None:
|
|
|
|
|
note = everos_plugin_missing_note()
|
|
|
|
|
assert "everos-memory" in note
|
|
|
|
|
assert "memory.backend" in note
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_build_plugin_tools_stamps_the_contributing_plugin(tmp_path):
|
|
|
|
|
"""[seam-1] The wake grant's namespace comes from this stamp; a plugin
|
|
|
|
|
that could name its own namespace could steal another's partition."""
|
|
|
|
|
from types import SimpleNamespace
|
|
|
|
|
|
|
|
|
|
from raven.core.plugin_stack import build_plugin_tools
|
|
|
|
|
|
|
|
|
|
class _Tool:
|
|
|
|
|
name = "t1"
|
|
|
|
|
|
|
|
|
|
class _Reg:
|
|
|
|
|
def tool_names(self):
|
|
|
|
|
return ["t1"]
|
|
|
|
|
|
|
|
|
|
def tool_plugin_id(self, name):
|
|
|
|
|
return "plug-a"
|
|
|
|
|
|
|
|
|
|
def build_tool(self, name, config, services):
|
|
|
|
|
return _Tool()
|
|
|
|
|
|
|
|
|
|
cfg = SimpleNamespace(
|
|
|
|
|
memory=SimpleNamespace(user_id="u", agent_id="a"),
|
|
|
|
|
plugins=SimpleNamespace(config={}),
|
|
|
|
|
)
|
|
|
|
|
tools = build_plugin_tools(tmp_path, cfg, registry=_Reg(), provider=None)
|
|
|
|
|
assert len(tools) == 1
|
|
|
|
|
assert tools[0].contributed_by == "plug-a"
|
refactor(*): seal the memory backend seam so a memory plugin needs no host edits (#414)
## Summary
Make `MemoryBackend` the only seam between the host and the memory
subsystem, so a second memory plugin can be installed without editing
host code.
The abstraction is the goal; no second backend is being added.
What the branch does:
- `health()` joins the Protocol. `raven doctor` and `raven import` read
a `BackendHealth(ready, checks)` the backend fills in with its own
vocabulary, instead of reaching into EverOS internals. Doctor prints the
checks verbatim and never interprets a label.
- A new `[[plugin.contributes.onboard]]` kind, with
`raven/contracts/onboard.py` as its paper. The host lends the wizard
shell as one `OnboardUI` and records the result; the screen returns a
`StepOutcome`. The plugin never writes `memory.backend` -- that key
stays the host's. EverOS's step-4 screen and its `everos.toml`
management move into the plugin.
- The skill source and the after-turn feedback prefix are named from
`memory.backend` rather than the literal `everos`.
- `enabled_by_default` is gone from the manifest: an installed plugin
the user has not disabled is active.
- `tests/test_plugin_boundary.py` pins the dependency direction in both
directions, with an equality assertion so the remaining exceptions
cannot grow.
That guard's allowlist started at five host files still speaking
EverOS's wire protocol. The follow-ups below close three of them.
Two things this branch itself introduced were found in manual acceptance
on an install without the plugin and fixed here: a turn printed which
backends were installed -- empty on exactly the install that needs the
sentence -- and `settings.everos` / `settings.everosSet` let
`ModuleNotFoundError` reach the dispatcher as an internal error carrying
a traceback. Both now carry the note doctor and the wizard already use,
naming the distribution to install.
Review on this PR found four blockers, all fixed and covered. A fifth
defect came out of manual acceptance rather than review, and four more
out of the rounds that followed it -- every one of those in the
embedding endpoint's own plumbing, each found by the round after the fix
that introduced it. They are listed under Risk; the blockers are:
1. `onboard` is an optional contribution, but the wizard equated "no
matching screen" with "not configured", so one `raven onboard
--skip-memory` wrote `memory.backend` back to null for a third-party
backend configured by hand. A backend with no screen now answers on the
strength of having been selected; only one whose own screen says it is
unconfigured is cleared, which is the case that rule exists for.
2. The record a sub-agent call leaves behind ran through a backend
nobody had started. The shipped adapter begins in an unknown state, so
the first flushing write only scheduled a readiness probe and answered
false -- the record said "unavailable" while the service was up the
whole time, and each per-record HTTP client was left open. One context
manager now owns start and stop around a record, in both the manager and
the DAG runner.
3. That record's write and the recall after it addressed different
owners: a real config spells its keys in camelCase and the block reaches
the backend as written, while the adapter read only the contract's
snake_case, so a sub-agent's memories were filed under the host
identity. The adapter reads both spellings.
4. Legacy embedding discovery had narrowed to the recorded plugin root,
so an install predating root recording lost its knowledge-base endpoint
with a valid file still on disk.
**The five follow-ups the seam left behind are in this PR too**, rather
than in three stacked ones, because they are one goal and the branch
protection dismisses an approval on every push:
- The embedding endpoint is raven's. A knowledge base indexes inside the
gateway process and never speaks to the memory service, yet it read its
endpoint out of everos.toml, so selecting another backend left it with
no vectors and no message naming the cause. Raven holds the block now
and hands it to the backend at start -- as a shared default, not an
override: a plugin that was given an endpoint of its own keeps it, and
only one that has none takes raven's. Discovery of an existing
everos.toml still checks all three places the plugin itself looks, read
with plain tomllib so it works where the plugin is not installed. No
data migrates: a base is keyed on its model and measured width, not on
the base url.
- `delete()` joins the Protocol. The browser used to delete a row out of
EverOS's index, in the host process, through the plugin's repository
layer -- while the markdown EverOS treats as the source of truth kept
the text, so the memory came back on the next rebuild, after the user
was told it was gone. The adapter now uses only operations EverOS
already performs, for the kinds it performs them for.
- Sub-agent memory goes through the contract. The read half is a new
optional `recall_session`; the write half needed no new surface, only
two metadata conventions written down. `agents.<name>.config.everos`
becomes `config.memory`, opaque to the host except the two keys the host
reads; the old spelling still loads.
- The memory and settings pages say why they are empty -- no plugin, or
a backend this page does not read -- instead of four zeros and a retry
button that cannot help.
- The `everos` package leaves the host's dependencies for the plugin's
own, at the same exact pin; the host reaches the tree through the
plugin. This is the package layer only: the installers already deliver
`everos-memory` as a sibling wheel from the same release, so an ordinary
install still has long-term memory.
The boundary guard's allowlist falls from five entries to two, both GUI
surfaces still shaped around EverOS's own store. Generalising their wire
is a frontend change and is deliberately not in scope.
This branch was reviewed on GitLab as merge request 639 over three
rounds, including a post-rebase range-diff check. It is being moved here
because GitHub is now the source of truth.
## Type
- [x] Refactor
## Verification
- `uv run pytest` on this branch, rebased onto `main`: 22146 passed, 4
failed, 45 skipped. Three of the four (`test_agents_oncall_launcher`,
`test_agent_loop_token_budget`, `test_agents_code_launcher`) were re-run
on a detached checkout of that same `main` commit in this environment
and fail there identically. The fourth (`test_ppt_engine_image_search`)
could not run in that checkout, whose environment lacks the deck
engine's extras; this branch's only change anywhere under
`plugins-dist/ppt-engine` is the removal of the `enabled_by_default`
manifest key, which that test does not reach. So this branch adds no
regression.
- `npx vitest run` in ui-web: 1680 passed across 103 files. `npm run
type-check` and `npm run gen:check` clean, so the generated client
matches the contract.
- Every fix in the follow-up commits was mutated away and its test
confirmed red, then restored and confirmed green. For the record path
that is three separate mutations: dropping `start()`, dropping `stop()`,
and narrowing the owner lookup back to one spelling.
- `uv run ruff check .` and `uv run ruff format --check` on the changed
files: clean.
- `uv lock --check`: consistent.
- `scripts/check_commit_messages.py`, `scripts/check_large_files.py`,
`scripts/check_source_language.py` over the branch range: clean.
- Manual acceptance against a real isolated install (temporary
RAVEN_HOME, isolated EverOS root and port), 34 cases: `raven plugins`,
`raven doctor` across four backend states, `raven onboard` interactive
and non-interactive including all three step-4 lanes, `raven import`
refusing and importing, an end-to-end write and recall, the web UI's
memory and settings pages driven through a real browser, a sub-agent
trace record, and an install with no memory plugin at all. 31 passed; 1
failed and was fixed; 1 partial; 1 carried over from the earlier round.
- The failure is the one worth reading. On a fresh managed install the
wizard reported embedding configured and the service it started the next
moment ran keyword-only: the spawned process carried no
`EVEROS_EMBEDDING__` values, and EverOS logged that the embedding key
was not configured. The rule deciding whether everos.toml already held
an operator's own endpoint asked whether its model name was a `"<...>"`
placeholder; the shipped template seeds every section with a real model
name and an empty key, so every fresh install read as a deliberate
choice and the host's endpoint was never bound. It now asks the
criterion the module already had -- model and key. The unit tests missed
it because each built its "operator's own" section with a key in it; the
regression copies the shipped template itself.
- The partial: the memory page's search returned relevant results
without error, but every memory in the test corpus was on one subject,
so narrowing could not be observed. The carried-over case is the
skill-source prefix, whose path this branch does not touch.
- Findings recorded and not fixed here, none introduced by this branch:
a progress spinner is still drawn after `import` reports it imported
nothing; an unsupported delete surfaces as a generic internal error; the
TUI log and `doctor` word "no memory plugin" differently; a turn that
did reach disk still prints that it was not written.
- The partial case: an induced agent skill is discovered through
`find_skill` with the backend's prefix, but `read_skill` / `use_skill`
on that id fail. Nothing writes the on-disk layer those tools look in,
on this branch or on `main`, and no test covers it. Pre-existing; filed
as a follow-up.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [x] User-facing docs or screenshots are updated when needed
## Risk
User-visible changes:
1. User-track recall is now strictly bounded by `top_k`. A profile row
used to ride outside that bound.
2. `raven doctor` builds the plugin factory, so a managed EverOS setup
writes its env var and config templates during a doctor run. It used to
be read-only. The `--json` memory section is reshaped around
`health.checks`.
3. A third-party drop-in plugin without `enabled_by_default = true` used
to be skipped and now loads.
4. The loader no longer back-fills the EverOS config slice's `root` /
`owned`, nor strips a legacy `mode` key; a leftover `mode` now draws an
unknown-key warning.
5. The wizard's recap shows the contribution name `everos` rather than
`EverOS`.
6. `use_skill` with an unknown prefix reports "not found" after a disk
lookup instead of "unknown source".
From the follow-ups:
7. Config gains an optional top-level `embedding` block. Absent, the
knowledge base reads the EverOS file as before and says so once. An
operator who moves the values across changes nothing else; one who names
a *different* model there gets the existing `StaleBaseError` telling
them to rebuild that base. The block is a default for the memory plugin
rather than an override, so an install that had configured the plugin
separately keeps what it had. Note that a config carrying this block
does not load on an older Raven, which rejects unknown top-level keys.
8. `agents.<name>.everos` is written back as `agents.<name>.memory`. The
old spelling still loads; a per-agent `baseUrl` is ignored with a
warning, having never had a user.
9. Deleting a memory now changes what EverOS treats as the source of
truth, so it stays deleted. Profiles and cases report that they cannot
be deleted rather than appearing to succeed.
10. `pip install raven` no longer pulls the memory engine in.
`install.sh` and `install.ps1` are unaffected: both already resolve
`everos_memory-*.whl` from the release they install and pass it as
`--with everos-memory`, and the source path installs it editable, so
those installs keep long-term memory. An install that reaches neither --
a release predating the sibling wheel, or a bare `pip install` -- now
boots without memory and says which distribution to install rather than
failing on an import.
Found after the acceptance run, in review, all fixed here. They share
one cause worth stating once: the endpoint acquired a second home, and
each fix taught one more reader about it while leaving the next one
behind.
11. The endpoint the wizard saved never reached the EverOS process it
then started. The rule for "does everos.toml already hold an operator's
own endpoint" asked whether its model name was a `"<...>"` placeholder;
the shipped template seeds every section with a real model name and an
empty key, so every fresh managed install read as a deliberate choice
and the host's endpoint was never bound. The service came out of the
wizard running keyword-only while the wizard said embedding was
configured. The rule now asks the criterion the module already had:
model and key.
12. The exported `EVEROS_EMBEDDING__*` variables are a third home,
documented by EverOS and ranked above its file. They were being
overwritten. A complete triple is now an operator's choice; an
incomplete one is not an endpoint and is replaced whole rather than
topped up from the host.
13. Raven writes those same variables itself at startup, so a reader
that asked only whether all three were set called raven's own binding an
operator's export -- a blank settings card and a save refused by naming
variables nobody had set. The module now records which of them it set.
14. That record lived in a module-level set, and `raven gateway
--restart` re-launches through `os.execv`: the values survive, module
state does not. The record now travels in a variable beside them, and is
stripped from the environment handed to EverOS.
15. A settings save the environment would outrank is refused with the
variable names, rather than written and silently ignored.
Four of the five arrived one per review round, each in the fix for the
one before it. The tests that missed them all shared a shape: each built
its "an operator configured this" fixture with a key in it, or cleared
the environment before the case, so the states the product actually
produces -- a template with no key, a live process that has just bound
its own endpoint -- were never the input. The regressions now copy the
shipped template, and run the startup sequence and a second interpreter
rather than a prepared state.
Rollback is a revert of the branch: the seam is additive, and
`memory.backend` keeps its shipped default.
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: gloryfromca <23442919+gloryfromca@users.noreply.github.com>
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-09-16 22:19:50 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class _OnboardReg:
|
|
|
|
|
"""A registry stand-in contributing one onboard step."""
|
|
|
|
|
|
|
|
|
|
def __init__(self, step) -> None:
|
|
|
|
|
self._step = step
|
|
|
|
|
|
|
|
|
|
def onboard_names(self):
|
|
|
|
|
return ["everos"]
|
|
|
|
|
|
|
|
|
|
def onboard_plugin_id(self, name):
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
def activated_ids(self):
|
|
|
|
|
return []
|
|
|
|
|
|
|
|
|
|
def manifest_for(self, plugin_id):
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
def build_onboard_step(self, name, *, config, services):
|
|
|
|
|
if isinstance(self._step, Exception):
|
|
|
|
|
raise self._step
|
|
|
|
|
return self._step
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_build_onboard_steps_yields_every_activated_step(tmp_path):
|
|
|
|
|
from raven.core.plugin_stack import build_onboard_steps
|
|
|
|
|
|
|
|
|
|
step = object()
|
|
|
|
|
assert build_onboard_steps(tmp_path, _config(), registry=_OnboardReg(step)) == [("everos", step)]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_build_onboard_steps_skips_a_raising_factory(tmp_path, caplog):
|
|
|
|
|
from raven.core.plugin_stack import build_onboard_steps
|
|
|
|
|
|
|
|
|
|
with caplog.at_level("WARNING"):
|
|
|
|
|
assert build_onboard_steps(tmp_path, _config(), registry=_OnboardReg(RuntimeError("boom"))) == []
|
|
|
|
|
assert "boom" in caplog.text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_build_onboard_steps_hands_each_plugin_its_own_config_slice(tmp_path):
|
|
|
|
|
"""[mrbot] Two plugins, differently named: A owns backend 'a-backend'
|
|
|
|
|
(no onboard screen), B owns both backend and onboard 'b-backend'. B's
|
|
|
|
|
onboard step must receive plugins.config['B'], never A's slice --
|
|
|
|
|
exercises the fix (resolve via the onboard entry's own plugin id)
|
|
|
|
|
directly, independent of the cross-owner case activation now refuses."""
|
|
|
|
|
import sys as _sys
|
|
|
|
|
import types
|
|
|
|
|
|
|
|
|
|
from raven.core.plugin_stack import build_onboard_steps
|
|
|
|
|
from raven.plugins import (
|
|
|
|
|
Contributes,
|
|
|
|
|
DiscoveredPlugin,
|
|
|
|
|
ManifestOrigin,
|
|
|
|
|
MemoryBackendContribution,
|
|
|
|
|
OnboardContribution,
|
|
|
|
|
PluginManifest,
|
|
|
|
|
PluginRegistry,
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
mod = types.ModuleType("_test_onboard_slice_owner")
|
|
|
|
|
mod.make_backend_a = lambda ctx: "a"
|
|
|
|
|
mod.make_backend_b = lambda ctx: "b"
|
|
|
|
|
mod.make_onboard_step_b = lambda ctx: ("step-b", ctx.config)
|
|
|
|
|
_sys.modules["_test_onboard_slice_owner"] = mod
|
|
|
|
|
try:
|
|
|
|
|
mf_a = PluginManifest(
|
|
|
|
|
id="A",
|
|
|
|
|
version="0.1",
|
|
|
|
|
contributes=Contributes(
|
|
|
|
|
memory_backends=[
|
|
|
|
|
MemoryBackendContribution(name="a-backend", factory="_test_onboard_slice_owner:make_backend_a"),
|
|
|
|
|
],
|
|
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
mf_b = PluginManifest(
|
|
|
|
|
id="B",
|
|
|
|
|
version="0.1",
|
|
|
|
|
contributes=Contributes(
|
|
|
|
|
memory_backends=[
|
|
|
|
|
MemoryBackendContribution(name="b-backend", factory="_test_onboard_slice_owner:make_backend_b"),
|
|
|
|
|
],
|
|
|
|
|
onboard=[
|
|
|
|
|
OnboardContribution(name="b-backend", factory="_test_onboard_slice_owner:make_onboard_step_b"),
|
|
|
|
|
],
|
|
|
|
|
),
|
|
|
|
|
)
|
|
|
|
|
reg = PluginRegistry()
|
|
|
|
|
reg.activate(
|
|
|
|
|
[
|
|
|
|
|
DiscoveredPlugin(manifest=mf_a, source=ManifestOrigin.USER, location=None),
|
|
|
|
|
DiscoveredPlugin(manifest=mf_b, source=ManifestOrigin.USER, location=None),
|
|
|
|
|
]
|
|
|
|
|
)
|
|
|
|
|
cfg = _config(
|
|
|
|
|
plugin_config={
|
|
|
|
|
"A": {"marker": "a-slice"},
|
|
|
|
|
"B": {"marker": "b-slice"},
|
|
|
|
|
}
|
|
|
|
|
)
|
|
|
|
|
steps = build_onboard_steps(tmp_path, cfg, registry=reg)
|
|
|
|
|
assert [name for name, _ in steps] == ["b-backend"]
|
|
|
|
|
_step_name, received_config = steps[0][1]
|
|
|
|
|
assert received_config == {"marker": "b-slice"}
|
|
|
|
|
finally:
|
|
|
|
|
_sys.modules.pop("_test_onboard_slice_owner", None)
|
fix(core): the memory service stops holding up the first session (#630)
## Summary
Two changes against the same symptom: the first session after an install
waits
on the memory service and then runs without long-term memory anyway.
**The wait is unnecessary.** A resident host awaited `backend.start()`
at boot,
so it held for the readiness budget -- 10s -- before serving anything.
The
backend already has a state machine for exactly that window: `store`
answers
False so the loop retries the record, and `recall` returns no hits for
that turn
and schedules a probe. Waiting for the service before serving the first
turn is
what the state machine replaced everywhere else.
`plugin_stack.start_backend_detached` is the same shape as
`warm_up_in_background` for litellm: a resident process starts the slow
thing
once and goes on serving, and the on-demand path reports a failure to
whoever
needs it. Three callers take it -- the gateway at boot and at a
generation swap,
and `raven a2a serve`. The other three keep awaiting, because for them
there is
no later turn to recover into: an import checks readiness immediately, a
sub-agent writes one record, and a one-shot turn exits. It is retired in
`Runtime.dispose`, the single point both resident hosts go through.
**The wait was also far longer than its budget.** uv does not compile
bytecode
by default, so the first process to import a module compiles it, and for
raven
that process is the EverOS service the first session starts. Measured on
a fresh
isolated install: 22s from spawn to ready, of which 18s elapses before
the
service writes its first log line. `UV_COMPILE_BYTECODE=1` in the
installer
moves that into the install, where the user is already watching a
progress line.
## Type
- [x] Fix
- [ ] Feature
- [ ] Docs
- [ ] CI / tooling
- [ ] Refactor
- [ ] Other
## Verification
Measured on a throwaway install in an isolated `RAVEN_HOME` /
`UV_TOOL_DIR` /
`UV_TOOL_BIN_DIR`, built from this checkout:
- cold first start, as shipped today: 22s spawn to ready (readiness
budget 10s)
- second start against the same tree: 2.2s
- freshly scaffolded root, bytecode already compiled: 2.1s
- byte-compiling the rest of that tree: 13.9s for 16756 files, single
threaded,
so the cost is compilation and it is paid once per machine
The detached start was read at the layer that owns the ordering, the
gateway's
own log. Before this change `Page:` cannot appear until after
`everos server ready`; after it:
```
17 EverosBackend.start
20 Page: http://127.0.0.1:18894
28 started everos server
31 everos server ready
```
The page is serving at line 20 and the child is only spawned at line 28.
The
interval this removes from the boot measured 5.5s on a machine whose
bytecode is
already compiled.
Commands:
- `uv run --frozen --python 3.12 --all-extras pytest
tests/test_core_plugin_stack.py tests/test_core_runtime_swap.py
tests/test_cli_gateway_commands.py tests/test_cli_a2a_commands.py
tests/test_cli_import_commands.py tests/test_memory_backend_protocol.py
-q` -- 191 passed after the rebase onto main
- the same set plus `tests/test_everos_backend.py` and
`tests/test_core_runtime_eval_hooks.py` -- 364 passed
- `ruff check raven/ tests/` -- all checks passed
- `ruff format --check raven/ tests/` -- 1654 files already formatted
- `sh -n install.sh` -- clean
Each of the six new cases was mutated to confirm it can fail: dropping
the task
reference, dropping the done-callback, making the cancel a no-op, and
removing
the cancel from `dispose`. Every mutation turned the case that names
that
behaviour red, and the source was restored and hash-compared afterwards.
- [x] Relevant tests pass locally
- [x] Relevant lint / type checks pass locally
- [ ] User-facing docs or screenshots are updated when needed
## Risk
User-visible change: a resident host now serves its first turn before
the memory
service has answered. A turn that arrives in that window gets no recall,
and its
record is retried rather than lost. Previously the host waited and, when
the wait
overran, that session had no memory at all -- so the window is narrower
than what
it replaces, not wider.
The installer now compiles bytecode, which makes an install slower by
roughly the
compile time and larger by the `.pyc` tree.
Rollback: both commits are independent and revert cleanly. Reverting the
first
restores the awaited start; reverting the second restores the uncompiled
install.
- [x] Security impact considered
- [x] Backward compatibility considered
- [x] Rollback path is clear for risky changes
## Related Issues
N/A
---------
Co-authored-by: Claude (claude-opus-5) <noreply@anthropic.com>
2026-09-22 15:46:12 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
class TestStartBackendDetached:
|
|
|
|
|
"""The resident hosts start the memory backend without waiting on it.
|
|
|
|
|
|
|
|
|
|
Awaited, the start held every resident boot for the readiness budget --
|
|
|
|
|
10s on a machine whose first everos start has to compile its bytecode --
|
|
|
|
|
and a session that overran it reported no long-term memory while the child
|
|
|
|
|
was still coming up. Detached, the backend's own state machine covers that
|
|
|
|
|
window: ``store`` answers False so the loop retries, ``recall`` returns no
|
|
|
|
|
hits and schedules a probe.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
|
|
|
async def test_the_caller_is_not_held_until_the_start_finishes(self) -> None:
|
|
|
|
|
"""The whole point: control comes back before ``start()`` is done."""
|
|
|
|
|
import asyncio
|
|
|
|
|
|
|
|
|
|
from raven.core.plugin_stack import start_backend_detached
|
|
|
|
|
|
|
|
|
|
released = asyncio.Event()
|
|
|
|
|
finished = asyncio.Event()
|
|
|
|
|
|
|
|
|
|
class _SlowBackend:
|
|
|
|
|
async def start(self) -> None:
|
|
|
|
|
await released.wait()
|
|
|
|
|
finished.set()
|
|
|
|
|
|
|
|
|
|
start_backend_detached(_SlowBackend(), logger=logging.getLogger(__name__))
|
|
|
|
|
|
|
|
|
|
# Still blocked inside start(), and we are already here.
|
|
|
|
|
assert not finished.is_set()
|
|
|
|
|
released.set()
|
|
|
|
|
await asyncio.wait_for(finished.wait(), timeout=2)
|
|
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
|
|
|
async def test_the_task_is_held_so_it_cannot_be_collected_mid_flight(self) -> None:
|
|
|
|
|
"""asyncio keeps only a weak reference; a dropped task is a lost start."""
|
|
|
|
|
import asyncio
|
|
|
|
|
import gc
|
|
|
|
|
|
|
|
|
|
from raven.core import plugin_stack
|
|
|
|
|
|
|
|
|
|
gate = asyncio.Event()
|
|
|
|
|
ran = asyncio.Event()
|
|
|
|
|
|
|
|
|
|
class _Backend:
|
|
|
|
|
async def start(self) -> None:
|
|
|
|
|
await gate.wait()
|
|
|
|
|
ran.set()
|
|
|
|
|
|
|
|
|
|
plugin_stack.start_backend_detached(_Backend(), logger=logging.getLogger(__name__))
|
|
|
|
|
gc.collect()
|
|
|
|
|
assert any(t is not None for _b, t in plugin_stack._PENDING_BACKEND_STARTS), "the in-flight start was not held"
|
|
|
|
|
gate.set()
|
|
|
|
|
await asyncio.wait_for(ran.wait(), timeout=2)
|
|
|
|
|
await asyncio.sleep(0)
|
|
|
|
|
assert not plugin_stack._PENDING_BACKEND_STARTS, "a finished start was not released"
|
|
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
|
|
|
async def test_a_start_that_raises_is_logged_and_not_re_raised(self) -> None:
|
|
|
|
|
"""The three call sites all swallowed it; the helper owes them the same."""
|
|
|
|
|
import asyncio
|
|
|
|
|
|
|
|
|
|
from raven.core import plugin_stack
|
|
|
|
|
|
|
|
|
|
class _Failing:
|
|
|
|
|
async def start(self) -> None:
|
|
|
|
|
raise RuntimeError("no service here")
|
|
|
|
|
|
|
|
|
|
logged: list[str] = []
|
|
|
|
|
|
|
|
|
|
class _Logger:
|
|
|
|
|
def exception(self, msg: str) -> None:
|
|
|
|
|
logged.append(msg)
|
|
|
|
|
|
|
|
|
|
plugin_stack.start_backend_detached(_Failing(), logger=_Logger())
|
|
|
|
|
for _ in range(20):
|
|
|
|
|
await asyncio.sleep(0)
|
|
|
|
|
if logged:
|
|
|
|
|
break
|
|
|
|
|
assert logged and "memory backend start failed" in logged[0]
|
|
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
|
|
|
async def test_no_backend_is_nothing_to_do(self) -> None:
|
|
|
|
|
"""``backend`` is None when no memory plugin is wired."""
|
|
|
|
|
from raven.core import plugin_stack
|
|
|
|
|
|
|
|
|
|
plugin_stack.start_backend_detached(None, logger=logging.getLogger(__name__))
|
|
|
|
|
assert not plugin_stack._PENDING_BACKEND_STARTS
|
|
|
|
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
|
|
|
async def test_cancel_retires_a_start_still_in_flight(self) -> None:
|
|
|
|
|
"""A start left running polls an address for a generation that is gone."""
|
|
|
|
|
import asyncio
|
|
|
|
|
|
|
|
|
|
from raven.core import plugin_stack
|
|
|
|
|
|
|
|
|
|
entered = asyncio.Event()
|
|
|
|
|
cancelled = asyncio.Event()
|
|
|
|
|
|
|
|
|
|
class _Hanging:
|
|
|
|
|
async def start(self) -> None:
|
|
|
|
|
entered.set()
|
|
|
|
|
try:
|
|
|
|
|
await asyncio.sleep(30)
|
|
|
|
|
except asyncio.CancelledError:
|
|
|
|
|
cancelled.set()
|
|
|
|
|
raise
|
|
|
|
|
|
|
|
|
|
backend = _Hanging()
|
|
|
|
|
plugin_stack.start_backend_detached(backend, logger=logging.getLogger(__name__))
|
|
|
|
|
await asyncio.wait_for(entered.wait(), timeout=2)
|
|
|
|
|
await plugin_stack.cancel_pending_backend_starts(backend)
|
|
|
|
|
assert cancelled.is_set(), "cancel returned before the start had left"
|