Commit Graph

Select branches

Hide Pull Requests

acp-support

add-plan-debate

agents-md-no-private-test-imports

approvals-code-mode

billea/readme-pydantic-stack-footer

bump-pydantic-ai-2.14

bump-readme-pai-floor-2

bump_monty

cache-bust-guard

capability/adaptive-reasoning

capability/approval

capability/background-tools

capability/code-mode-dynamic-catalog

capability/compaction

capability/filesystem-shell

capability/filesystem-shell-v2

capability/guardrails

capability/knows-current-time

capability/memory

capability/planning

capability/repo-context-injection

capability/secret-masking

capability/session-persistence

capability/skills

capability/stuck-loop-detection

capability/subagent

capability/system-reminders

capability/tool-budget

capability/tool-error-recovery

capability/tool-orphan-repair

capability/tool-output-management

capability/verification-loop

caps-docs-links

chore/bump-vcrpy

chore/untrack-settings-local

clamp-oversized-messages

claude/absurd-durability-capability

claude/budget-disclosure

claude/checkpoints

claude/codemode-os-function-GK8ew

claude/coding-harness

claude/compaction-structural

claude/cross-model-history-label

claude/docling-markdownify-conversion-2o4e67

claude/exciting-turing-TmpC5

claude/localstack-aws-emulation-0owHz

claude/loop-detection

claude/managed-tool-capability-r2vtg

claude/modal-sandbox-capability

claude/permission-policy

claude/planning-capability

claude/quirky-pasteur-DMxCC

claude/readme-codemode-extra-fix

claude/ripgrep-filesystem-support-nYYt5

claude/spill-query-surface

claude/staleness-tracker

claude/subagents-capability

claude/terminal-bench-agent

claude/writing-style-no-em-dashes

cm-temporal

code-mode-final-output

code-mode-monty

code-mode-tool-search

codemode-alias

codemode-example

codex/aica-attribution

codex/describe-code-mode-metadata-selection

codex/exempt-pydantic-ai-upload-age

codex/fix-322-protected-walkers

codex/fix-issue-360-search-files-docstring

codex/harness-ce-guides

codex/issue-346-clarify-code-mode-return

codex/pr-354-memory

codex/readme-completed-capabilities

codex/skills-capability

compat-test-pyright-scope

docs/primitives-architecture

docs/readme-refresh

docs/review-fixes-and-shell-allowlist

docs/unified-harness-docs

drop-pai-git-pin

drop-safe-for-ci

dynamic-workflow

exa-capability

exec_env_code_mode

execution-environments-v1

experimental/confined-self-authoring

feat/macroscope-capability

feat/sandbox-no-wall-clock

feature/logfire-managed-prompt

fix-380-clear-tool-results-typed-parts

fix-guardrails-readme-parity

fix-limit-warner-empty-request

fix-release-permissions

fix/codemode-prompt-tool-surface

fix/remove-codeowners

fix/update-readme-pr-links

guardrails

handle-deferred-in-code-mode

harness-webfetch

infra/repo-setup

launch/deprecation-shim

launch/public-infrastructure

launch/publishing

launch/publishing-v2

launch/publishing-v3

launch/publishing-v4

launch/publishing-v5

launch/publishing-v6

launch/publishing-v7

launch/remove-deprecation-shim

launch/rename-to-pydantic-ai-harness

launch/skills

macroscope-ignore

main

managed-agent-spec

managed-components

monty-beta-0.0.19

on-run-error-snapshot

oversized-tool-output

package-skeleton

plan/issue-42

pydai-latest

readme-version-bump

remove-defer-loading-fallback

remove-expeerimental

revert-258-capability/filesystem-shell-v2

send-tweet-on-release

shell-env-control

sql-mode

step-persistence

subagents-contain-errors

subagents-run-controls

verify-tool-defs-in-durable-tests

vp/zizmor-yamlfmt

worktree-agent-aa3ee95439db547e1

#129

#130

#131

#132

#133

#134

#135

#136

#137

#138

#139

#140

#153

#154

#155

#156

#157

#158

#159

#160

#161

#162

#163

#164

#165

#166

#167

#168

#168

#169

#169

#170

#170

#171

#171

#172

#172

#173

#173

#174

#174

#175

#175

#176

#177

#177

#178

#178

#179

#180

#180

#181

#181

#182

#183

#183

#184

#184

#185

#185

#186

#186

#187

#188

#189

#190

#191

#192

#194

#197

#198

#199

#200

#201

#202

#203

#204

#205

#206

#207

#208

#209

#210

#211

#212

#216

#217

#217

#219

#220

#222

#222

#223

#224

#225

#226

#228

#229

#231

#231

#234

#236

#237

#238

#240

#241

#242

#243

#244

#244

#245

#247

#249

#251

#256

#257

#258

#259

#260

#261

#262

#263

#264

#266

#267

#268

#268

#269

#269

#270

#271

#271

#272

#273

#274

#275

#280

#283

#284

#286

#287

#287

#288

#290

#291

#292

#293

#294

#295

#296

#297

#298

#299

#300

#303

#304

#305

#309

#311

#312

#316

#317

#319

#323

#323

#324

#325

#326

#327

#327

#328

#328

#329

#331

#331

#332

#332

#333

#333

#334

#334

#335

#335

#336

#336

#337

#337

#338

#338

#339

#339

#340

#340

#341

#342

#343

#343

#344

#344

#345

#345

#347

#348

#350

#350

#351

#352

#352

#353

#353

#354

#355

#355

#356

#356

#358

#359

#361

#362

#364

#364

#366

#366

#368

#370

#372

#372

#374

#374

#376

#377

#379

#379

#381

#381

#383

#383

#384

#386

#387

#388

#389

#390

#390

#391

#396

#396

#397

#398

#398

#399

#399

#87

#88

#96

#97

#98

pydantic-harness-v0.1.1

v0.0.1

v0.1.0

v0.1.1

v0.1.2

v0.2.0

v0.2.1

v0.3.0

v0.4.0

v0.5.0

v0.6.0

v0.7.0

v0.7.1

v0.8.0

Mono Color

• 3ba9e2f9a5 docs: capability pages for the unified docs site + README/doc parity gate (#329) David SFandGitHub 2026-07-13 11:00:12 -05:00
• d407c11198 Update Temporal test docstrings for lifecycle-owned Monty pool Aditya VardhanandClaude Opus 4.8 2026-07-13 21:21:51 +05:30
• bf9d8eff12 Remove Temporal section from Code Mode README Aditya VardhanandClaude Opus 4.8 2026-07-13 21:05:03 +05:30
• 73ca5f49df Restore Temporal CodeMode test and docs, drop pydantic_monty passthrough Aditya VardhanandClaude Opus 4.8 2026-07-13 20:31:45 +05:30
• c7895b7556 entering and keeping a pool for Monty, skeptical about where the toolset is entered Aditya Vardhan 2026-07-13 20:15:08 +05:30
• 1571f4af36 Clarify the Temporal sandbox boundary for Code Mode Aditya Vardhan 2026-07-13 18:45:00 +05:30
• 3232691b4a Preserve Temporal durability with Monty subprocesses Aditya Vardhan 2026-07-13 16:58:37 +05:30
• 697077897c Merge main to restore PR mergeability Aditya Vardhan 2026-07-13 16:56:56 +05:30
• 7c1a38a422 Keep the capability roadmap focused on harness work codex/readme-completed-capabilities Aditya Vardhan 2026-07-13 15:12:07 +05:30
• a030d95d9f Keep ModalSandbox compatible with current main Aditya Vardhan 2026-07-13 14:51:56 +05:30
• 2b46e7a6e2 fix(memory): use qmark placeholders in SQLite prefix listing Kacper Włodarczyk 2026-07-13 10:24:08 +02:00
• ace5b3eb85 fix(memory): SQLite in-memory rejection and case-sensitive listing Kacper Włodarczyk 2026-07-13 10:18:23 +02:00
• ca321105d0 style(memory): ASCII dashes, labeled README fence (review follow-up) Kacper Włodarczyk 2026-07-13 10:14:48 +02:00
• 5adefe0db2 test: don't fail doc-snippet check on a missing optional extra docs/unified-harness-docs David SF 2026-07-12 14:35:16 -05:00
• a79c13de0d test: statically validate doc snippets exist and parse David SF 2026-07-12 14:29:26 -05:00
• f15f69197e docs(agents): drop stale folder tree; fix flat docs path + guard names David SF 2026-07-12 14:15:37 -05:00
• 533caacf7d docs: link every capability README to its source module + enforce it David SF 2026-07-12 12:29:43 -05:00
• 2dcd211bc3 test: cover the docs-parity helper edge cases (100% coverage) David SF 2026-07-12 12:24:02 -05:00
• d18ae6644f fix: restore uv.lock [options.exclude-newer-package] block David SF 2026-07-12 12:17:51 -05:00
• cda35e997b fix: restore uv.lock [options.exclude-newer-package] block David SF 2026-07-12 12:16:40 -05:00
• 69be5d6aa1 docs: address CodeRabbit review on #329 David SF 2026-07-12 12:08:00 -05:00
• c0058b0565 fix: restore uv.lock to match pyproject (bad text-merge dropped 8 lines) David SF 2026-07-12 11:59:51 -05:00
• bec6571220 fix(memory): address CI pyright and CodeRabbit review Kacper Włodarczyk 2026-07-12 02:44:19 +02:00
• 6886dfd410 feat(memory): add SQLite and PostgreSQL stores Kacper Włodarczyk 2026-07-12 02:34:51 +02:00
• f223943bb1 feat: add Memory capability Kacper Włodarczyk 2026-07-12 02:15:42 +02:00
• ca59c4ce42 docs: add the stability note to guardrails (parity with sibling capabilities) David SF 2026-07-10 22:41:18 -05:00
• 73e64f0c78 docs: apply team-sync authoring rules + enforce them in CI David SF 2026-07-10 22:32:45 -05:00
• 31a43654d3 docs: flatten harness nav and align with graduated capabilities David SF 2026-07-10 22:16:00 -05:00
• be25646cb5 Merge origin/main into docs branch (post experimental graduation) David SF 2026-07-10 22:04:58 -05:00
• 310ffadf09 refactor: graduate capabilities out of experimental (ACP excepted) (#347) David SFandGitHub 2026-07-10 21:31:08 -05:00
• ca2ee784ea docs: tell capability authors to ask the user when unsure about a name remove-expeerimental David SF 2026-07-10 21:20:24 -05:00
• 34f1eae697 Merge remote-tracking branch 'origin/main' into remove-expeerimental David SF 2026-07-10 20:43:49 -05:00
• d13cdae9cb Fix docs-parity gate and OutputGuard retry test after guardrails merge (#348) David SFandGitHub 2026-07-10 20:39:58 -05:00
• 563578f578 test: use FunctionModel for OutputGuard retry test (survives pyai #6403 text-recovery removal) fix-guardrails-readme-parity David SF 2026-07-10 17:45:19 -05:00
• 39282d09f0 docs: link shipped guardrails package from README (fix docs-parity CI) David SF 2026-07-10 17:02:10 -05:00
• 5ab8dd3d81 feat: input and output guardrails (block, redact, retry) (#249) 4 people 2026-07-10 14:21:23 -05:00
• 44f05e336f refactor: graduate capabilities out of experimental (ACP excepted) David SF 2026-07-10 12:22:36 -05:00
• 1833fcf870 fix(code_mode): silence pyright on the eager _binary side-effect import monty-beta-0.0.19 David SF 2026-07-10 11:51:34 -05:00
• f4aa3e8755 fix(code_mode): eager-import pydantic_monty._binary for Temporal sandbox David SF 2026-07-10 11:47:27 -05:00
• 3ac6bac6f0 Enforce the monty/monty-runtime version lockstep in CI Aditya VardhanandClaude Opus 4.8 2026-07-10 21:36:16 +05:30
• ee1e60d122 Regenerate uv.lock in highest-resolution mode Aditya VardhanandClaude Opus 4.8 2026-07-10 20:49:56 +05:30
• a815b13d82 Pin pydantic-monty-runtime to match the monty version Aditya VardhanandClaude Opus 4.8 2026-07-10 20:46:15 +05:30
• 6cd9ff8601 Exclude the skipped Temporal test from coverage Aditya VardhanandClaude Opus 4.8 2026-07-10 20:18:47 +05:30
• 4c25fc0ecf Report a timeout that tears down as ClosedResourceError as a timeout Aditya VardhanandClaude Opus 4.8 2026-07-10 19:59:02 +05:30
• 167c35271a Skip Temporal CodeMode test and drop obsolete v2-beta CI job Aditya VardhanandClaude Opus 4.8 2026-07-10 19:40:58 +05:30
• 870d765df4 Fix monty dependency resolution and keep it capability-scoped Aditya VardhanandClaude Opus 4.8 2026-07-10 17:38:38 +05:30
• 6bc726e2c4 bumping monty Aditya Vardhan 2026-07-10 17:27:40 +05:30
• 2d4cdeb196 docs: address CodeRabbit review -- runnable snippets, accuracy, multi-class autodoc David SF 2026-07-09 22:32:14 -05:00
• a86751c733 test: dump thread tracebacks on a hung test (faulthandler_timeout) David SF 2026-07-09 22:31:35 -05:00
• e0e35e1516 fix(deps): floor pydantic-monty-runtime so lowest-direct resolves David SF 2026-07-09 22:24:08 -05:00
• 34b425775f ci: skip runtime monty imports on 3.14 (warnings + skill examples) David SF 2026-07-09 22:00:08 -05:00
• 932bbba08b ci: skip monty tests when absent + typecheck where monty installs David SF 2026-07-09 21:47:36 -05:00
• e4504ad5f1 docs: migrate "What goes where?" explainer into harness overview David SF 2026-07-09 21:33:57 -05:00
• a7d244d99e fix(uv.lock): keep [options.exclude-newer-package] so uv sync --locked passes in CI David SF 2026-07-09 21:22:31 -05:00
• b07da6f497 docs: add nav.json to drive the unified-docs harness sidebar David SF 2026-07-09 21:15:52 -05:00
• 2f4a6652b1 fix(code_mode): gate monty to python<3.14 + graceful import + prose David SF 2026-07-09 21:02:48 -05:00
• 189a5efc6a fix(loop_detection): make the nudge marker an unambiguous harness marker Douwe MaanandClaude Fable 5 2026-07-10 00:39:43 +00:00
• 80c9d2827a fix(overflow): mark the Summarize band's output as a harness stand-in Douwe MaanandClaude Fable 5 2026-07-10 00:37:29 +00:00
• 0b9d62d931 fix(permissions): mark denials as harness-authored, not successful results Douwe MaanandClaude Fable 5 2026-07-10 00:34:58 +00:00
• dad88a95ed feat(code_mode): migrate to pydantic-monty 0.0.19 beta API David SF 2026-07-09 19:01:33 -05:00
• 52d77d935b docs(confined-authoring): note slot descriptions are model-visible metadata experimental/confined-self-authoring David SF 2026-07-09 18:50:04 -05:00
• 7402983194 fix(confined-authoring): bound in-sandbox compute + reconcile docs David SF 2026-07-09 17:54:25 -05:00
• 265c7b7ae0 feat(confined-authoring): let an agent author its own sandboxed tools David SF 2026-07-09 17:20:20 -05:00
• bbc28af48d bumping monty broken rn, will fix Aditya Vardhan 2026-07-09 20:57:45 +05:30
• a214b5d6d3 Make resolution-span test tolerant of logfire's version-specific reason Douwe Maan 2026-07-09 14:54:28 +00:00
• 1229858a57 Announce harness releases on Twitter (#341) v0.6.0 Aditya VardhanandGitHub 2026-07-09 20:15:46 +05:30
• 545a703227 feat: Adds Dynamic Workflows (#273) 3 people 2026-07-09 16:53:02 +05:30
• 958714ffe9 docs(dynamic-workflow): correct max_duration_secs semantics and refresh README dynamic-workflow Aditya VardhanandClaude Opus 4.8 2026-07-09 16:25:23 +05:30
• 14e9b747a9 Merge remote-tracking branch 'origin/main' into dynamic-workflow Aditya Vardhan 2026-07-09 15:53:06 +05:30
• 77c08faeb7 docs: reconcile README with shipped capabilities; enforce parity in CI (#342) 3 people 2026-07-09 15:20:17 +05:30
• 8d8bf9611e Close managed-variable test coverage gaps to reach 100% Douwe Maan 2026-07-09 05:59:41 +00:00
• 2fc69a025a Test ManagedMCP and ManagedSkills Douwe Maan 2026-07-09 05:26:45 +00:00
• 72ec8c2771 Add ManagedMCP and ManagedSkills managed capabilities Douwe Maan 2026-07-09 05:26:34 +00:00
• 70285a2ebb docs: add Dynamic Workflows (#273) roadmap row to matrix docs/readme-refresh Aditya VardhanandClaude Opus 4.8 2026-07-09 09:57:19 +05:30
• 536f3ae1f4 docs(checkpoints): correct git-config isolation wording, warn on nested state_dir Douwe MaanandClaude Opus 2026-07-09 03:31:04 +00:00
• 1cb46f08eb fix(budget_disclosure): guard zero-valued limits against division by zero Douwe MaanandClaude Opus 2026-07-09 03:30:49 +00:00
• 4830888c37 Implement optional managed-variable name (base + capabilities + docs) Douwe Maan 2026-07-09 03:16:53 +00:00
• 36c12153e3 Make managed-variable capability name optional, deriving it from the agent's name Douwe Maan 2026-07-09 03:14:19 +00:00
• 3067ec5f8f Fix managed-variable auto-create under logfire >= 4.37 code_default reason Douwe Maan 2026-07-09 02:48:21 +00:00
• 3dd0db1286 Flatten ManagedSettings payload: model + settings at top level Douwe Maan 2026-07-08 17:49:29 +00:00
• 723c189d2d docs: keep README's capability matrix, add shipped rows Aditya VardhanandClaude Opus 4.8 2026-07-08 22:44:32 +05:30
• 1ad638f8ea Scope send-tweet secrets to the release environment send-tweet-on-release Aditya Vardhan 2026-07-08 22:14:11 +05:30
• 3e7afee3d6 test: mark unreachable non-package guard as no-cover Aditya VardhanandClaude Opus 4.8 2026-07-08 22:10:54 +05:30
• 08548b13f1 docs: reconcile README with shipped capabilities; enforce parity in CI Aditya VardhanandClaude Opus 4.8 2026-07-08 18:26:36 +05:30
• ffb45d2b74 refactor(dynamic-workflow): separate from CodeMode instead of merging Aditya VardhanandClaude Opus 4.8 2026-07-08 18:17:45 +05:30
• 177b599420 Announce harness releases on Twitter Aditya Vardhan 2026-07-08 10:08:12 +05:30
• 19d8b38619 feat(benchmarks): add label-gated live-model Terminal-Bench slice Douwe MaanandClaude Fable 5 2026-07-08 04:34:26 +00:00
• 0cfc45c53f test(permissions): reach 100% coverage on the test modules Douwe MaanandClaude Opus 4.7 2026-07-08 04:09:14 +00:00
• 6f1bedcf7e feat(permissions): allow/ask/deny policy engine over tool calls Douwe MaanandClaude Opus 4.7 2026-07-08 04:04:33 +00:00
• c06c60f1bb fix(benchmarks): unpin harness dep so the local editable build resolves in CI Douwe MaanandClaude Fable 5 2026-07-08 04:03:19 +00:00
• 62793a0590 feat(compaction): receipts, pin contract, keep-user-messages, anchored incremental summarization Douwe MaanandClaude Opus 4.8 2026-07-08 04:00:19 +00:00
• e462d9c05f feat(benchmarks): Terminal-Bench reference agent on Harbor Douwe MaanandClaude Fable 5 2026-07-08 04:00:06 +00:00
• f34b653a0a feat(cross_model_label): tell the model when earlier turns came from a different model Douwe MaanandClaude Fable 5 2026-07-08 03:54:35 +00:00
• 24adb91b3d fix(checkpoints): parse commit time from Unix timestamp for py3.10 Douwe MaanandClaude Opus 2026-07-08 02:28:00 +00:00
• 07ad5d90ba feat(loop_detection): detect and interrupt repeated-action loops Douwe MaanandClaude Opus 2026-07-08 02:22:42 +00:00
• fcab7c3c36 feat(checkpoints): shadow-git file snapshots before mutating tool calls Douwe MaanandClaude Opus 2026-07-08 02:22:39 +00:00
• be382ae91e feat(budget_disclosure): disclose remaining usage budget to the model Douwe MaanandClaude Opus 2026-07-08 02:21:38 +00:00
• 6b0e685857 feat(staleness): tell the model when files changed since it read them Douwe MaanandClaude Opus 2026-07-08 02:19:36 +00:00
• 279336dd59 feat(overflow): grep/slice query surface + uniform explicit elision markers Douwe MaanandClaude Opus 2026-07-08 02:19:35 +00:00
• 32a5d8c04b Update ToolSearch test fixtures for pydantic-ai#5654 shape Douwe Maan 2026-07-08 00:04:06 +00:00