Raven-1/tests/test_context_assembler.py

240 lines
7.5 KiB
Python
Raw Permalink Normal View History

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
"""Unit tests for PlannerContextAssembler.
2026-06-28 18:17:27 +08:00
Verifies assembly from each source independently + graceful degradation
when a source is unavailable.
"""
from __future__ import annotations
from datetime import datetime, timedelta
from pathlib import Path
from types import SimpleNamespace
import pytest
from raven.config.raven import NudgePolicyConfig
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
from raven.memory_engine.consolidate.consolidator import MemoryStore
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.proactive_engine.sentinel.predictor.context_assembler import PlannerContextAssembler
2026-06-28 18:17:27 +08:00
from raven.proactive_engine.sentinel.predictor.routine_learner import RoutineLearner
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
from raven.proactive_engine.sentinel.trigger_policy.policy import NudgePolicy
2026-06-28 18:17:27 +08:00
def _now():
return datetime(2026, 4, 21, 14, 0, 0)
@pytest.fixture
def workspace(tmp_path: Path) -> Path:
(tmp_path / "memory").mkdir()
return tmp_path
@pytest.fixture
def memory_store(workspace) -> MemoryStore:
m = MemoryStore(workspace)
m.write_long_term("- prefers gentle tone\n- Duolingo streak 47 days")
m.append_history("[2026-04-07 08:00] morning duolingo")
m.append_history("[2026-04-14 08:00] morning duolingo")
m.append_history("[2026-04-21 08:00] morning duolingo")
return m
# ---------------------------------------------------------------------------
# Empty sources — everything defaults to a safe empty context.
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
2026-06-28 18:17:27 +08:00
def test_assemble_empty_sources():
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
asm = PlannerContextAssembler(now_fn=_now)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert ctx.now == _now()
assert ctx.memory_md == ""
assert ctx.history_md_recent == ""
assert ctx.routines == []
assert ctx.active_sessions == []
assert ctx.calendar == []
assert ctx.nudge_policy_state.remaining_today == 10
assert ctx.last_decision is None
# ---------------------------------------------------------------------------
# Memory + history
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
2026-06-28 18:17:27 +08:00
def test_assemble_reads_memory_and_history(memory_store):
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
asm = PlannerContextAssembler(memory_store=memory_store, now_fn=_now)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert "Duolingo streak 47" in ctx.memory_md
assert "morning duolingo" in ctx.history_md_recent
def test_history_tail_limits_lines(workspace, memory_store):
# Write 200 entries; assembler with tail=10 should keep only 10.
for i in range(200):
memory_store.append_history(f"[2026-04-{(i % 28) + 1:02d} 08:00] entry {i}")
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
asm = PlannerContextAssembler(
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
memory_store=memory_store,
now_fn=_now,
history_tail_lines=10,
2026-06-28 18:17:27 +08:00
)
ctx = asm.assemble()
# Each append writes "entry\n\n", so 10 tail lines → ≤ 20 incl blanks.
non_blank = [l for l in ctx.history_md_recent.splitlines() if l.strip()]
assert len(non_blank) <= 10
# ---------------------------------------------------------------------------
# Routines
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
2026-06-28 18:17:27 +08:00
def test_assemble_learns_routines_from_history(memory_store):
learner = RoutineLearner(
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
min_occurrences=3,
hour_slot_size=3,
learning_window_days=60,
now_fn=_now,
2026-06-28 18:17:27 +08:00
)
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
asm = PlannerContextAssembler(
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
memory_store=memory_store,
routine_learner=learner,
now_fn=_now,
2026-06-28 18:17:27 +08:00
)
ctx = asm.assemble()
assert len(ctx.routines) >= 1
assert ctx.routines[0].status == "candidate"
assert any("duolingo" in k for k in ctx.routines[0].keywords)
def test_assemble_no_routines_if_learner_absent(memory_store):
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
asm = PlannerContextAssembler(memory_store=memory_store, now_fn=_now)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert ctx.routines == []
# ---------------------------------------------------------------------------
# Active sessions
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
2026-06-28 18:17:27 +08:00
def test_assemble_active_sessions_from_manager():
now = _now()
# Fake SessionManager: exposes .sessions dict.
sess = SimpleNamespace(
key="cli:direct",
updated_at=now - timedelta(minutes=5),
messages=[
{"role": "user", "content": "hey how do I add a CSP header"},
{"role": "assistant", "content": "you can set Content-Security-Policy…"},
],
)
session_manager = SimpleNamespace(sessions={"cli:direct": sess})
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
asm = PlannerContextAssembler(session_manager=session_manager, now_fn=_now)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert len(ctx.active_sessions) == 1
assert ctx.active_sessions[0].key == "cli:direct"
assert "CSP header" in (ctx.active_sessions[0].last_user_message or "")
def test_assemble_excludes_stale_sessions():
now = _now()
stale = SimpleNamespace(
key="cli:old",
updated_at=now - timedelta(hours=5),
messages=[],
)
session_manager = SimpleNamespace(sessions={"cli:old": stale})
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
asm = PlannerContextAssembler(
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
session_manager=session_manager,
now_fn=_now,
active_session_window_seconds=3600, # 1h window
2026-06-28 18:17:27 +08:00
)
ctx = asm.assemble()
assert ctx.active_sessions == []
def test_assemble_sessions_sorted_recent_first():
now = _now()
old = SimpleNamespace(key="cli:a", updated_at=now - timedelta(minutes=30), messages=[])
new = SimpleNamespace(key="cli:b", updated_at=now - timedelta(minutes=5), messages=[])
session_manager = SimpleNamespace(sessions={"cli:a": old, "cli:b": new})
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
asm = PlannerContextAssembler(session_manager=session_manager, now_fn=_now)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert [s.key for s in ctx.active_sessions] == ["cli:b", "cli:a"]
# ---------------------------------------------------------------------------
# Nudge policy state snapshot
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
2026-06-28 18:17:27 +08:00
def test_assemble_nudge_state():
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
policy = NudgePolicy(
NudgePolicyConfig(
max_nudges_per_hour=3,
max_nudges_per_day=10,
min_interval_seconds=300,
quiet_hours=(23, 7),
cooldown_on_dismiss_seconds=1800,
high_priority_bypasses_limits=True,
dedup_window_seconds=3600,
inject_ttl_seconds=1800,
inject_max_pending_per_session=3,
defer_idle_threshold_seconds=300,
defer_max_wait_seconds=86400,
),
now_fn=_now,
)
2026-06-28 18:17:27 +08:00
policy.record_fired("nudge", "s1", "test")
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
asm = PlannerContextAssembler(nudge_policy=policy, now_fn=_now)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert ctx.nudge_policy_state.nudges_used_this_hour == 1
assert ctx.nudge_policy_state.remaining_today == 9
assert ctx.nudge_policy_state.in_quiet_hours is False
# ---------------------------------------------------------------------------
# Calendar injection
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
2026-06-28 18:17:27 +08:00
def test_assemble_calendar_from_callback():
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
asm = PlannerContextAssembler(
2026-06-28 18:17:27 +08:00
now_fn=_now,
calendar_fn=lambda: ["15:00 standup", "17:00 1:1 with manager"],
)
ctx = asm.assemble()
assert len(ctx.calendar) == 2
assert "standup" in ctx.calendar[0]
def test_assemble_calendar_callback_error_silent():
def boom():
raise RuntimeError("boom")
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
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
asm = PlannerContextAssembler(now_fn=_now, calendar_fn=boom)
2026-06-28 18:17:27 +08:00
ctx = asm.assemble()
assert ctx.calendar == []
# ---------------------------------------------------------------------------
# Last decision
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
2026-06-28 18:17:27 +08:00
def test_remember_last_decision_populates_ctx():
from raven.proactive_engine.sentinel.types import PlannerDecision
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
2026-06-28 18:17:27 +08:00
last = PlannerDecision(action="skip", reason="nothing", proactivity_score=0.1)
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
asm = PlannerContextAssembler(now_fn=_now)
2026-06-28 18:17:27 +08:00
asm.remember_last_decision(last)
ctx = asm.assemble()
assert ctx.last_decision is last
# ---------------------------------------------------------------------------
# User profile passthrough
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
2026-06-28 18:17:27 +08:00
def test_user_profile_passthrough():
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
asm = PlannerContextAssembler(
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
now_fn=_now,
user_profile="Chinese native speaker, works in fintech",
2026-06-28 18:17:27 +08:00
)
ctx = asm.assemble()
assert "Chinese" in ctx.user_profile