taskledger 0.6.6__tar.gz → 0.6.7__tar.gz

{taskledger-0.6.6 → taskledger-0.6.7}/.ledger/releaseledger/data/ledgers/main/events/events.jsonl

@@ -44,3 +44,9 @@
 {"data":{"updated_rows":1},"event":"audit.updated","event_id":"event-0044","record_revisions":{"commit_audit_sheet":2},"release_version":"v0.6.6","schema_version":2}
 {"data":{"entry_ids":["entry-0001"],"synced_audit_rows":1},"event":"entry.batch_added","event_id":"event-0045","record_revisions":{"commit_audit_sheet":3,"entry:v0.6.6/entry-0001":1,"release:v0.6.6":3},"release_version":"v0.6.6","schema_version":2}
 {"data":{"released_at":"2026-09-04"},"event":"release.finalized","event_id":"event-0046","record_revisions":{"release:v0.6.6":4},"release_version":"v0.6.6","schema_version":2}
+{"data":{"status":"planned"},"event":"release.created","event_id":"event-0047","record_revisions":{"release:v0.6.7":1},"release_version":"v0.6.7","schema_version":2}
+{"data":{"fields":["git_base_ref","git_base_sha","git_commit_count","git_head_ref","git_head_sha","git_range"]},"event":"release.updated","event_id":"event-0048","record_revisions":{"release:v0.6.7":2},"release_version":"v0.6.7","schema_version":2}
+{"data":{"row_count":1},"event":"audit.created","event_id":"event-0049","record_revisions":{"commit_audit_sheet":1},"release_version":"v0.6.7","schema_version":2}
+{"data":{"updated_rows":1},"event":"audit.updated","event_id":"event-0050","record_revisions":{"commit_audit_sheet":2},"release_version":"v0.6.7","schema_version":2}
+{"data":{"entry_ids":["entry-0001"],"synced_audit_rows":1},"event":"entry.batch_added","event_id":"event-0051","record_revisions":{"commit_audit_sheet":3,"entry:v0.6.7/entry-0001":1,"release:v0.6.7":3},"release_version":"v0.6.7","schema_version":2}
+{"data":{"released_at":"2026-09-09"},"event":"release.finalized","event_id":"event-0052","record_revisions":{"release:v0.6.7":4},"release_version":"v0.6.7","schema_version":2}

taskledger-0.6.7/.ledger/releaseledger/data/ledgers/main/releases/v0.6.7/audit/commit-audit.yaml

@@ -0,0 +1,87 @@
+schema_version: 1
+object_type: commit_audit_sheet
+versioning:
+  schema_version: 1
+  revision: 3
+release_version: v0.6.7
+git_base_ref: v0.6.6
+git_base_sha: f7c915cf9d515ab1c15bdffeb73162340d7534df
+git_head_ref: HEAD
+git_head_sha: 562fc8796f821e312877f0c5b2aa09f5daddb138
+git_range: f7c915cf9d515ab1c15bdffeb73162340d7534df..562fc8796f821e312877f0c5b2aa09f5daddb138
+commit_count: 1
+rows:
+  - sha: 562fc8796f821e312877f0c5b2aa09f5daddb138
+    source_ref: git:562fc8796f821e312877f0c5b2aa09f5daddb138
+    short_sha: 562fc87
+    changed_paths:
+      - README.md
+      - docs/command_contract.md
+      - docs/sync.md
+      - docs/transfer.md
+      - docs/usage.md
+      - taskledger/api/config.py
+      - taskledger/exchange.py
+      - taskledger/services/agent_logging.py
+      - taskledger/services/change_tracking.py
+      - taskledger/services/doctor.py
+      - taskledger/services/doctor_checks/artifact_checks.py
+      - taskledger/services/git_sync.py
+      - taskledger/services/implementation_flow.py
+      - taskledger/services/tasks.py
+      - taskledger/services/validation_flow.py
+      - taskledger/storage/agent_logs.py
+      - taskledger/storage/artifact_policy.py
+      - taskledger/storage/project_config.py
+      - tests/test_agent_command_logging.py
+      - tests/test_artifact_policy.py
+      - tests/test_config_cli.py
+      - tests/test_doctor.py
+      - tests/test_project_root_config.py
+      - tests/test_sync_git.py
+      - tests/test_taskledger_v2_exchange.py
+      - tests/test_validation_command.py
+    stats:
+      files_changed: 0
+      insertions: 700
+      deletions: 33
+    inspected: true
+    inspected_paths:
+      - README.md
+      - docs/command_contract.md
+      - docs/sync.md
+      - docs/transfer.md
+      - docs/usage.md
+      - taskledger/api/config.py
+      - taskledger/exchange.py
+      - taskledger/services/agent_logging.py
+      - taskledger/services/change_tracking.py
+      - taskledger/services/doctor.py
+      - taskledger/services/doctor_checks/artifact_checks.py
+      - taskledger/services/git_sync.py
+      - taskledger/services/implementation_flow.py
+      - taskledger/services/tasks.py
+      - taskledger/services/validation_flow.py
+      - taskledger/storage/agent_logs.py
+      - taskledger/storage/artifact_policy.py
+      - taskledger/storage/project_config.py
+      - tests/test_agent_command_logging.py
+      - tests/test_artifact_policy.py
+      - tests/test_config_cli.py
+      - tests/test_doctor.py
+      - tests/test_project_root_config.py
+      - tests/test_sync_git.py
+      - tests/test_taskledger_v2_exchange.py
+      - tests/test_validation_command.py
+    observed_behavior:
+      Added a shared artifact-size policy that bounds stored command
+      output to a configurable limit capped at 20,000,000 bytes, preserves UTF-8-safe
+      head/tail excerpts with truncation metadata, rejects oversized existing artifacts
+      during doctor, export/import, and managed Git sync, and documents the policy with
+      regression coverage.
+    public_impact: public
+    decision: accepted
+    stale: false
+    evidence_subject: "feat: limit artifact file size"
+    target_entry_id: entry-0001
+    notes: ""

taskledger-0.6.7/.ledger/releaseledger/data/ledgers/main/releases/v0.6.7/entries/entry-0001.md

@@ -0,0 +1,53 @@
+---
+schema_version: 2
+object_type: release_entry
+versioning:
+  schema_version: 1
+  revision: 1
+entry_id: entry-0001
+release_version: v0.6.7
+kind: added
+summary:
+  Added configurable artifact limits with UTF-8-safe truncation across command
+  evidence, archives, doctor, and Git sync
+status: accepted
+audience: null
+scopes: []
+source_refs:
+  - git:562fc8796f821e312877f0c5b2aa09f5daddb138
+paths:
+  - README.md
+  - docs/command_contract.md
+  - docs/sync.md
+  - docs/transfer.md
+  - docs/usage.md
+  - taskledger/api/config.py
+  - taskledger/exchange.py
+  - taskledger/services/agent_logging.py
+  - taskledger/services/change_tracking.py
+  - taskledger/services/doctor.py
+  - taskledger/services/doctor_checks/artifact_checks.py
+  - taskledger/services/git_sync.py
+  - taskledger/services/implementation_flow.py
+  - taskledger/services/tasks.py
+  - taskledger/services/validation_flow.py
+  - taskledger/storage/agent_logs.py
+  - taskledger/storage/artifact_policy.py
+  - taskledger/storage/project_config.py
+  - tests/test_agent_command_logging.py
+  - tests/test_artifact_policy.py
+  - tests/test_config_cli.py
+  - tests/test_doctor.py
+  - tests/test_project_root_config.py
+  - tests/test_sync_git.py
+  - tests/test_taskledger_v2_exchange.py
+  - tests/test_validation_command.py
+issues: []
+prs: []
+sources:
+  - git:562fc8796f821e312877f0c5b2aa09f5daddb138
+contributors: []
+breaking: false
+internal: false
+order: 1
+---

taskledger-0.6.7/.ledger/releaseledger/data/ledgers/main/releases/v0.6.7/release.md

@@ -0,0 +1,27 @@
+---
+schema_version: 2
+object_type: release
+versioning:
+  schema_version: 1
+  revision: 4
+version: v0.6.7
+status: released
+history_state: curated
+title: Release v0.6.7
+released_at: "2026-09-09"
+previous_version: v0.6.6
+cancel_reason: null
+superseded_by: null
+changelog_file: null
+boundary_ref: null
+source_refs: []
+source_count: null
+entry_count: 1
+artifact_count: 0
+git_base_ref: v0.6.6
+git_base_sha: f7c915cf9d515ab1c15bdffeb73162340d7534df
+git_head_ref: HEAD
+git_head_sha: 562fc8796f821e312877f0c5b2aa09f5daddb138
+git_range: f7c915cf9d515ab1c15bdffeb73162340d7534df..562fc8796f821e312877f0c5b2aa09f5daddb138
+git_commit_count: 1
+---

{taskledger-0.6.6/taskledger.egg-info → taskledger-0.6.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: taskledger
-Version: 0.6.6
+Version: 0.6.7
 Summary: Durable project-state storage and CLI for coding workflows
 Author: Taskledger Contributors
 Maintainer: Holger Nahrstaedt
@@ -837,6 +837,12 @@ Import safety still relies on `project_uuid`, not the name/slug.
 - `--no-include-bodies` strips record body text (`body` / `context_body`) from exported payloads.
 - `--include-run-artifacts` embeds task and agent-log artifact files under `artifacts/` in the archive.
 
+## Artifact file-size policy
+
+Taskledger-owned artifact files are bounded to prevent command output from creating very large ledger blobs. The default and hard ceiling is 20,000,000 bytes per artifact; configure a lower `artifact_max_bytes` value when needed. Oversized command evidence keeps a UTF-8-safe head and tail with an explicit truncation marker, while command execution and exit-code semantics remain unchanged.
+
+Archive import/export applies the same policy, and `taskledger doctor` reports legacy oversized artifacts without reading their contents. `taskledger sync git push` performs a preflight before committing or pushing. Taskledger does not use Git LFS or rewrite Git history; repair existing blobs separately.
+
 Cross-machine imports preserve durable task/run data, but imported runtime locks
 are quarantined by default. After importing an in-progress implementation,
 run:

{taskledger-0.6.6 → taskledger-0.6.7}/README.md

@@ -784,6 +784,12 @@ Import safety still relies on `project_uuid`, not the name/slug.
 - `--no-include-bodies` strips record body text (`body` / `context_body`) from exported payloads.
 - `--include-run-artifacts` embeds task and agent-log artifact files under `artifacts/` in the archive.
 
+## Artifact file-size policy
+
+Taskledger-owned artifact files are bounded to prevent command output from creating very large ledger blobs. The default and hard ceiling is 20,000,000 bytes per artifact; configure a lower `artifact_max_bytes` value when needed. Oversized command evidence keeps a UTF-8-safe head and tail with an explicit truncation marker, while command execution and exit-code semantics remain unchanged.
+
+Archive import/export applies the same policy, and `taskledger doctor` reports legacy oversized artifacts without reading their contents. `taskledger sync git push` performs a preflight before committing or pushing. Taskledger does not use Git LFS or rewrite Git history; repair existing blobs separately.
+
 Cross-machine imports preserve durable task/run data, but imported runtime locks
 are quarantined by default. After importing an in-progress implementation,
 run:

{taskledger-0.6.6 → taskledger-0.6.7}/docs/changelog.md

@@ -2,6 +2,14 @@
 
 > **Generated by releaseledger.** Manual edits may be overwritten. Update releaseledger entries and rebuild this file instead.
 
+## [v0.6.7] - 2026-09-09
+
+### Added
+
+- Added configurable artifact limits with UTF-8-safe truncation across command evidence, archives, doctor, and Git sync
+
+<!-- generated by releaseledger -->
+
 ## [v0.6.6] - 2026-09-04
 
 ### Added

{taskledger-0.6.6 → taskledger-0.6.7}/docs/command_contract.md

@@ -451,6 +451,7 @@ shell. They execute the child from the CLI invocation directory, or the explicit
 `--root` directory, even when Taskledger discovers an ancestor workspace root for
 ledger state, artifacts, and logs.
 
+Managed command artifacts are bounded by the project `artifact_max_bytes` setting, defaulting to the 20,000,000-byte hard ceiling. Oversized persisted evidence is marked and retains both its beginning and end; only the durable artifact is truncated, not the child command's exit code or CLI stdout/stderr contract.
 `validate command` uses the same managed execution behavior during an active validation run, but records command evidence only. It never automatically maps a non-zero child exit to a criterion result.
 
 Managed commands preserve the caller environment, but resolve child executable lookup

{taskledger-0.6.6 → taskledger-0.6.7}/docs/sync.md

@@ -81,6 +81,10 @@ report project-local vs outside-project dirty paths. `sync git push` commits
 repository-wide changes by design to match the standard Git workflow. Use
 `sync git cd` for advanced manual inspection or conflict resolution.
 
+## Artifact preflight
+
+`taskledger sync git push` checks Taskledger-owned artifact files before staging or committing. It refuses any existing file over the configured `artifact_max_bytes` limit and reports the paths, sizes, limit, and `taskledger doctor` remediation. Plain `git push` remains outside Taskledger's control, and Taskledger does not rewrite history or use Git LFS.
+
 For manual conflict resolution or debugging:
 
 ```bash

{taskledger-0.6.6 → taskledger-0.6.7}/docs/transfer.md

@@ -13,6 +13,12 @@ machines and harnesses.
   \- `project.ledger_ref` (exported ledger)
 - Optional run artifacts under `artifacts/` when `--include-run-artifacts` is set.
 
+## Artifact file-size policy
+
+Taskledger-owned artifact files default to a 20,000,000-byte hard ceiling. Projects may lower this with `artifact_max_bytes`, but cannot configure an unlimited or larger value. Oversized command output is stored as a UTF-8-safe head/tail excerpt with an explicit byte-count marker; the managed command's output and exit code are unchanged.
+
+Import/export enforce the same limit. Run `taskledger doctor` to find existing oversized files; `taskledger sync git push` refuses them before creating a commit. This does not rewrite existing Git history or use Git LFS.
+
 ## Filename policy
 
 When no output path is passed to `taskledger export`, taskledger writes into

{taskledger-0.6.6 → taskledger-0.6.7}/docs/usage.md

@@ -762,6 +762,9 @@ Export include flags are content-affecting:
 - `--no-include-bodies` removes record body fields from the exported payload.
 - `--include-run-artifacts` embeds artifact files under `artifacts/` in the archive.
 
+## Artifact file-size policy
+
+Taskledger-owned artifact files are limited to 20,000,000 bytes by default and may only be lowered with `artifact_max_bytes`. Oversized command evidence retains its head and tail and includes a deterministic truncation marker; it does not change command execution or exit-code behavior. Import/export, doctor, and Taskledger-managed Git push enforce the same policy. Existing Git history is not rewritten and Git LFS is not used.
 Cross-machine imports preserve durable task/run records but quarantine imported
 runtime locks by default. For an imported in-progress implementation, run:
 

{taskledger-0.6.6 → taskledger-0.6.7}/taskledger/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.6.6'
-__version_tuple__ = version_tuple = (0, 6, 6)
+__version__ = version = '0.6.7'
+__version_tuple__ = version_tuple = (0, 6, 7)
 
-__commit_id__ = commit_id = 'gf7c915cf9'
+__commit_id__ = commit_id = 'gfa5b2b772'

{taskledger-0.6.6 → taskledger-0.6.7}/taskledger/api/config.py

@@ -116,6 +116,13 @@ _CONFIG_KEY_HELP: tuple[ConfigKeyHelp, ...] = (
         "boolean",
         default_value=_DEFAULT_CONFIG.default_save_run_reports,
     ),
+    ConfigKeyHelp(
+        "artifact_max_bytes",
+        "Maximum stored size of a Taskledger-owned artifact file; may only lower "
+        "the hard ceiling.",
+        "integer",
+        default_value=_DEFAULT_CONFIG.artifact_max_bytes,
+    ),
     ConfigKeyHelp(
         "default_source_max_chars",
         "Per-source character budget for context composition.",
@@ -601,6 +608,11 @@ def config_set(workspace_root: Path, *, key: str, value_text: str) -> dict[str,
                 target[segment] = table()
             target = target[segment]
         target[segments[-1]] = value
+        from taskledger.storage.project_config import _validate_project_config_overrides
+
+        _validate_project_config_overrides(
+            tomllib.loads(dumps(document)), context.config_path
+        )
         atomic_write_text(context.config_path, dumps(document))
         after = config_get(workspace_root, key=key)["value"]
     else:

{taskledger-0.6.6 → taskledger-0.6.7}/taskledger/exchange.py

@@ -42,11 +42,13 @@ from taskledger.storage.agent_logs import (
     append_agent_command_log,
     load_agent_command_logs,
 )
+from taskledger.storage.artifact_policy import ABSOLUTE_MAX_ARTIFACT_BYTES
 from taskledger.storage.atomic import atomic_write_text
 from taskledger.storage.events import append_event, load_events
 from taskledger.storage.indexes import rebuild_v2_indexes
 from taskledger.storage.locks import write_lock
 from taskledger.storage.paths import load_project_locator
+from taskledger.storage.project_context import load_project_context
 from taskledger.storage.project_identity import (
     assert_same_project_uuid,
     load_project_uuid,
@@ -765,7 +767,7 @@ ARTIFACTS_PREFIX = "artifacts/"
 MAX_ARCHIVE_MEMBERS = 4096
 MAX_MANIFEST_BYTES = 256_000
 MAX_PAYLOAD_BYTES = 50_000_000
-MAX_ARTIFACT_MEMBER_BYTES = 20_000_000
+MAX_ARTIFACT_MEMBER_BYTES = ABSOLUTE_MAX_ARTIFACT_BYTES
 MAX_TOTAL_ARTIFACT_BYTES = 100_000_000
 
 
@@ -781,6 +783,7 @@ def write_project_archive(
     """Export current-ledger state into a gzip-compressed tar archive."""
     paths = require_v2_layout(workspace_root)
     locator = load_project_locator(workspace_root)
+    artifact_limit = load_project_context(workspace_root).config.artifact_max_bytes
     project_uuid = load_project_uuid(locator.config_path)
     if project_uuid is None:
         raise LaunchError("Project manifest does not define a project UUID.")
@@ -846,6 +849,7 @@ def write_project_archive(
         _collect_artifact_members(
             paths,
             selected_task_ids=selected_task_ids if selection.scope == "tasks" else None,
+            max_bytes=artifact_limit,
         )
         if include_run_artifacts
         else []
@@ -881,7 +885,11 @@ def write_project_archive(
     }
 
 
-def read_project_archive(source_path: Path) -> dict[str, object]:
+def read_project_archive(
+    source_path: Path,
+    *,
+    max_artifact_bytes: int | None = None,
+) -> dict[str, object]:
     """Read and validate a taskledger archive in-memory.
 
     Never extracts tar members to disk. Returns dict with keys
@@ -892,7 +900,9 @@ def read_project_archive(source_path: Path) -> dict[str, object]:
 
     with tarfile.open(source_path, "r:gz") as tar:
         members = {m.name: m for m in tar.getmembers()}
-        artifact_members = _validate_archive_members(members)
+        artifact_members = _validate_archive_members(
+            members, max_artifact_bytes=max_artifact_bytes
+        )
 
         manifest_member = members[MANIFEST_MEMBER]
         payload_member = members[PAYLOAD_MEMBER]
@@ -962,7 +972,10 @@ def import_project_archive(
 ) -> dict[str, object]:
     """Import a taskledger archive into the current project."""
     normalized_lock_policy = normalize_import_lock_policy(lock_policy)
-    archive = read_project_archive(source_path)
+    artifact_limit = load_project_context(
+        workspace_root, require_initialized=False
+    ).config.artifact_max_bytes
+    archive = read_project_archive(source_path, max_artifact_bytes=artifact_limit)
     payload = cast(dict[str, object], archive["payload"])
     manifest = cast(dict[str, object], archive["manifest"])
     artifact_members = cast(list[str], archive.get("artifact_members", []))
@@ -1216,7 +1229,15 @@ def _add_json_member(
 
 
 def _add_file_member(tar: tarfile.TarFile, name: str, source_path: Path) -> None:
-    data = source_path.read_bytes()
+    size_bytes = source_path.stat().st_size
+    if size_bytes > MAX_ARTIFACT_MEMBER_BYTES:
+        raise LaunchError(
+            "Cannot export oversized Taskledger artifact: "
+            f"{source_path} ({size_bytes} bytes > {MAX_ARTIFACT_MEMBER_BYTES}). "
+            "Run `taskledger doctor` and repair the artifact before exporting."
+        )
+    with source_path.open("rb") as source:
+        data = source.read()
     info = tarfile.TarInfo(name)
     info.size = len(data)
     info.mtime = 0
@@ -1243,10 +1264,18 @@ def _default_task_archive_path(
     return Path(filename)
 
 
+def _relative_artifact_path(paths: V2Paths, source_path: Path) -> str:
+    try:
+        return source_path.relative_to(paths.project_dir).as_posix()
+    except ValueError:
+        return "logs/" + source_path.relative_to(paths.events_dir.parent).as_posix()
+
+
 def _collect_artifact_members(
     paths: V2Paths,
     *,
     selected_task_ids: set[str] | None = None,
+    max_bytes: int = MAX_ARTIFACT_MEMBER_BYTES,
 ) -> list[tuple[str, Path]]:
     artifact_roots = [paths.tasks_dir.glob("task-*/artifacts/**/*")]
     if selected_task_ids is None:
@@ -1258,6 +1287,15 @@ def _collect_artifact_members(
         for source_path in iterator:
             if not source_path.is_file():
                 continue
+            size_bytes = source_path.stat().st_size
+            if size_bytes > max_bytes:
+                relative_path = _relative_artifact_path(paths, source_path)
+                raise LaunchError(
+                    "Cannot export oversized Taskledger artifact: "
+                    f"{relative_path}\n{size_bytes} bytes > "
+                    f"artifact_max_bytes={max_bytes}. "
+                    "Run `taskledger doctor` and repair the artifact before exporting."
+                )
             if selected_task_ids is not None:
                 match = re.search(
                     r"/tasks/(task-\d+)/artifacts/", source_path.as_posix()
@@ -1322,7 +1360,11 @@ def _extract_artifact_members(
     return extracted
 
 
-def _validate_archive_members(members: dict[str, tarfile.TarInfo]) -> list[str]:
+def _validate_archive_members(
+    members: dict[str, tarfile.TarInfo],
+    *,
+    max_artifact_bytes: int | None = None,
+) -> list[str]:
     if MANIFEST_MEMBER not in members:
         raise LaunchError(f"Archive missing {MANIFEST_MEMBER}")
     if PAYLOAD_MEMBER not in members:
@@ -1357,10 +1399,19 @@ def _validate_archive_members(members: dict[str, tarfile.TarInfo]) -> list[str]:
             raise LaunchError(f"Unexpected archive member: {name!r}")
         if not info.isfile():
             raise LaunchError(f"Archive member {name!r} is not a regular file")
-        if info.size > MAX_ARTIFACT_MEMBER_BYTES:
+        artifact_limit = MAX_ARTIFACT_MEMBER_BYTES
+        if max_artifact_bytes is not None:
+            artifact_limit = min(artifact_limit, max_artifact_bytes)
+        if info.size > artifact_limit:
+            if artifact_limit < MAX_ARTIFACT_MEMBER_BYTES:
+                raise LaunchError(
+                    "Archive artifact member is too large for this Taskledger project: "
+                    f"{name!r}\n{info.size} bytes > "
+                    f"configured artifact_max_bytes={artifact_limit}."
+                )
             raise LaunchError(
                 "Archive artifact member is too large: "
-                f"{name!r} ({info.size} > {MAX_ARTIFACT_MEMBER_BYTES} bytes)"
+                f"{name!r} ({info.size} > {artifact_limit} bytes)"
             )
         total_artifact_bytes += info.size
         if total_artifact_bytes > MAX_TOTAL_ARTIFACT_BYTES:

{taskledger-0.6.6 → taskledger-0.6.7}/taskledger/services/agent_logging.py

@@ -8,7 +8,7 @@ import sys
 import time
 from collections.abc import Callable
 from contextvars import ContextVar
-from dataclasses import dataclass
+from dataclasses import dataclass, replace
 from pathlib import Path
 from typing import TextIO
 
@@ -23,6 +23,10 @@ from taskledger.storage.agent_logs import (
     load_agent_command_logs,
     write_agent_command_artifact,
 )
+from taskledger.storage.artifact_policy import (
+    ABSOLUTE_MAX_ARTIFACT_BYTES,
+    bound_text_to_bytes,
+)
 from taskledger.storage.project_config import (
     AgentLoggingConfig,
     load_project_config_overrides,
@@ -525,7 +529,13 @@ def _load_agent_logging_config(workspace_root: Path) -> AgentLoggingConfig:
 
     paths = resolve_project_paths(workspace_root)
     overrides = load_project_config_overrides(paths)
-    return merge_project_config(overrides).agent_logging
+    project_config = merge_project_config(overrides)
+    agent_config = project_config.agent_logging
+    feature_limit = agent_config.max_artifact_bytes
+    effective_limit = project_config.artifact_max_bytes
+    if feature_limit is not None:
+        effective_limit = min(effective_limit, feature_limit)
+    return replace(agent_config, max_artifact_bytes=effective_limit)
 
 
 def _next_log_id(workspace_root: Path, timestamp: str) -> str:
@@ -557,13 +567,8 @@ def _json_text(payload: object) -> str:
 
 
 def _truncate_artifact(content: str, max_bytes: int | None) -> str:
-    if max_bytes is None:
-        return content
-    encoded = content.encode("utf-8")
-    if len(encoded) <= max_bytes:
-        return content
-    truncated = encoded[:max_bytes]
-    return truncated.decode("utf-8", errors="ignore")
+    limit = ABSOLUTE_MAX_ARTIFACT_BYTES if max_bytes is None else max_bytes
+    return bound_text_to_bytes(content, max_bytes=limit).text
 
 
 def _combined_output(stdout: str, stderr: str) -> str:

{taskledger-0.6.6 → taskledger-0.6.7}/taskledger/services/change_tracking.py

@@ -185,15 +185,18 @@ def run_planning_command(
         command_cwd=execution_cwd,
     )
     output = _tasks._command_output(argv, completed.stdout, completed.stderr)
-    artifact_ref: str | None = None
+    artifact_result = None
     if len(output) > 4000 or output.count("\n") > 50:
-        artifact_ref = _tasks._write_command_artifact(
+        artifact_result = _tasks._write_command_artifact(
             workspace_root,
             task.id,
             run.run_id,
             output,
         )
-    summary = _tasks._command_summary(argv, completed.returncode, artifact_ref)
+    artifact_ref = artifact_result.ref if artifact_result is not None else None
+    summary = _tasks._command_summary(
+        argv, completed.returncode, artifact_ref, artifact_result
+    )
     updated_run = replace(
         run,
         worklog=(*run.worklog, summary),
@@ -222,6 +225,16 @@ def run_planning_command(
         "exit_code": completed.returncode,
         "cwd": str(execution_cwd),
         "artifact_path": artifact_ref,
+        "artifact_truncated": artifact_result.truncated if artifact_result else False,
+        "artifact_original_bytes": artifact_result.original_bytes
+        if artifact_result
+        else None,
+        "artifact_stored_bytes": artifact_result.stored_bytes
+        if artifact_result
+        else None,
+        "artifact_limit_bytes": artifact_result.limit_bytes
+        if artifact_result
+        else None,
         "stdout": completed.stdout,
         "stderr": completed.stderr,
     }

{taskledger-0.6.6 → taskledger-0.6.7}/taskledger/services/doctor.py

@@ -12,6 +12,7 @@ from taskledger.domain.models import (
     TaskRunRecord,
 )
 from taskledger.domain.states import TASKLEDGER_STORAGE_LAYOUT_VERSION
+from taskledger.errors import LaunchError
 from taskledger.storage.events import load_events
 from taskledger.storage.locks import lock_is_expired
 from taskledger.storage.migrations import inspect_records_for_migration
@@ -50,6 +51,8 @@ class DoctorScanContext:
     run_by_key: Mapping[tuple[str, str], TaskRunRecord]
     active_state: ActiveTaskState | None
 
+    artifact_limit_bytes: int
+
 
 def _build_scan_context(workspace_root: Path) -> DoctorScanContext:
     """Build the immutable scan context once at the start of a doctor invocation."""
@@ -57,6 +60,12 @@ def _build_scan_context(workspace_root: Path) -> DoctorScanContext:
     locator = load_project_locator(workspace_root)
     paths = resolve_v2_paths(workspace_root)
 
+    from taskledger.storage.artifact_policy import ABSOLUTE_MAX_ARTIFACT_BYTES
+    from taskledger.storage.project_config import (
+        load_project_config_document,
+        merge_project_config,
+    )
+
     tasks = tuple(list_tasks(workspace_root))
     task_by_id: dict[str, TaskRecord] = {task.id: task for task in tasks}
 
@@ -74,6 +83,12 @@ def _build_scan_context(workspace_root: Path) -> DoctorScanContext:
         active_state = load_active_task_state(workspace_root)
     except Exception:  # noqa: BLE001
         active_state = None
+    try:
+        artifact_limit_bytes = merge_project_config(
+            load_project_config_document(resolved_paths.config_path)
+        ).artifact_max_bytes
+    except LaunchError:
+        artifact_limit_bytes = ABSOLUTE_MAX_ARTIFACT_BYTES
 
     return DoctorScanContext(
         workspace_root=workspace_root,
@@ -86,6 +101,7 @@ def _build_scan_context(workspace_root: Path) -> DoctorScanContext:
         runs_by_task=runs_by_task,
         run_by_key=run_by_key,
         active_state=active_state,
+        artifact_limit_bytes=artifact_limit_bytes,
     )
 
 
@@ -142,6 +158,16 @@ def _inspect_v2_project_phases(workspace_root: Path) -> dict[str, object]:
         diagnostics=diagnostics,
     )
 
+    from taskledger.services.doctor_checks.artifact_checks import (
+        find_oversized_artifacts,
+    )
+
+    for diagnostic in find_oversized_artifacts(
+        ctx.paths, max_bytes=ctx.artifact_limit_bytes
+    ):
+        diagnostics.append(diagnostic)
+        errors.append(str(diagnostic["message"]))
+
     for lock in ctx.locks:
         lock_task = ctx.task_by_id.get(lock.task_id)
         if lock_task is None: