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

• 26caf2e000 Source managed model via get_model hook so run(model=...) wins and model-less agents run Douwe Maan 2026-07-08 00:02:58 +00:00
• 4fb70fec46 Document ManagedAgentSpec in the Logfire capabilities README Douwe Maan 2026-07-07 23:43:26 +00:00
• 7a1be6760e Test ManagedAgentSpec and ManagedAgent Douwe Maan 2026-07-07 23:43:21 +00:00
• 6d6f0d28a7 Add ManagedAgentSpec capability and ManagedAgent sugar Douwe Maan 2026-07-07 23:43:09 +00:00
• 9d82a1bed4 docs: fix README<->doc<->source inconsistencies across capabilities David SF 2026-07-07 13:51:24 -05:00
• c11e065f89 refactor(dynamic-workflow): move under experimental Aditya VardhanandClaude Fable 5 2026-07-08 00:11:54 +05:30
• bc259a0cec Merge origin/main into dynamic-workflow Aditya VardhanandClaude Fable 5 2026-07-07 23:40:13 +05:30
• b4365440b5 feat: serve a Pydantic AI agent to editors over ACP (experimental) (#274) 4 people 2026-07-07 23:36:09 +05:30
• 770ce584bd feat(acp): expose model_resolver and usage_limits on the stdio entry points acp-support Aditya VardhanandClaude Fable 5 2026-07-07 23:33:03 +05:30
• 5331402d7c docs: publish capability docs to the unified site + add README/doc parity gate David SF 2026-07-07 12:54:37 -05:00
• cb9090ed27 refactor(acp): move under experimental and shrink the public surface Aditya VardhanandClaude Fable 5 2026-07-07 23:19:16 +05:30
• 4dca3d3d78 docs: explain DynamicWorkflow in the main README Aditya VardhanandClaude Fable 5 2026-07-07 23:04:52 +05:30
• da0ad11453 feat(dynamic-workflow): merge into CodeMode when both are on one agent Aditya VardhanandClaude Fable 5 2026-07-07 23:02:10 +05:30
• 059a6e2702 Export ManagedToolDefinitions + ManagedSettings and document the managed family Douwe Maan 2026-07-07 14:56:26 +00:00
• 45a4d270de Auto-create managed variables on first use Douwe Maan 2026-07-07 14:53:31 +00:00
• 708f017d73 Add ManagedSettings capability Douwe Maan 2026-07-07 14:42:02 +00:00
• a9a489c817 Add ManagedToolDefinitions capability Douwe Maan 2026-07-07 14:40:25 +00:00
• 25b1541424 Port ManagedVariableCapability base from #275 and refactor ManagedPrompt onto it Douwe Maan 2026-07-07 14:26:20 +00:00
• dc469b2509 Raise sql-mode duckdb floor to 1.3.0 on Python 3.13 sql-mode Aditya VardhanandClaude Opus 4.8 2026-07-07 14:54:18 +05:30
• 430dcb9c20 Fix lowest-versions CI by raising sql-mode dependency floors Aditya VardhanandClaude Opus 4.8 2026-07-07 14:38:00 +05:30
• 5b1b4c2ba5 test(dynamic-workflow): exclude never-run parent model fn from coverage Aditya VardhanandClaude Opus 4.8 2026-07-07 14:23:14 +05:30
• 153a790e9e chore(acp): fix coverage, trim redundancy, clarify module names Aditya VardhanandClaude Opus 4.8 2026-07-07 13:46:01 +05:30
• 4900926f38 Ship SQLMode as an experimental capability and harden it Aditya VardhanandClaude Fable 5 2026-07-07 13:38:10 +05:30
• de0105d997 Merge remote-tracking branch 'origin/main' into sql-mode Aditya Vardhan 2026-07-07 13:05:16 +05:30
• 86966f4164 Track ACP 0.11 session config models Aditya Vardhan 2026-07-07 10:41:39 +05:30
• 24569b3589 test(modal_sandbox): keep live-test portability notes backend-neutral Aditya VardhanandClaude Opus 4.8 2026-07-07 10:27:23 +05:30
• efa2cbdc43 feat(acp): expose read-only session history Aditya Vardhan 2026-07-07 10:14:58 +05:30
• b7d40e813c feat(acp): resolve selected session models Aditya Vardhan 2026-07-07 10:13:40 +05:30
• 2e4f51cbbc feat(acp): forward usage limits into agent runs Aditya Vardhan 2026-07-07 10:11:20 +05:30
• 98644a2a13 Merge remote-tracking branch 'origin/main' into acp-support Aditya Vardhan 2026-07-07 10:02:23 +05:30
• ca12e687d9 Support Pydantic AI 2.x in ACP Aditya Vardhan 2026-07-07 09:48:41 +05:30
• dccf15e6c8 feat(dynamic-workflow): let sub-agents inherit the run model Aditya Vardhan 2026-07-07 09:47:33 +05:30
• 23dc7ce1ab test(modal_sandbox): add credential-gated live integration tier Aditya VardhanandClaude Opus 4.8 2026-07-07 08:43:21 +05:30
• abda68d068 feat(cache_stability): observational CacheStabilityMonitor capability David SF 2026-07-06 17:53:59 -05:00
• b5b93704c3 feat(subagents): contain unexpected sub-agent crashes as bounded retries (#326) David SFandGitHub 2026-07-06 17:13:30 -05:00
• 611ecd13c2 feat(dynamic-workflow): promote out of experimental Aditya VardhanandClaude Fable 5 2026-07-07 00:47:44 +05:30
• b83425c120 docs: fix pydantic-ai-slim version pin and tighten DynamicWorkflow docstrings Aditya VardhanandClaude Opus 4.8 2026-07-06 23:26:10 +05:30
• 25f4d22114 docs(dynamic-workflow): drop internal decisions log from the PR Aditya VardhanandClaude Opus 4.8 2026-07-06 14:35:42 +05:30
• 7a2ebe3119 docs(dynamic-workflow): use raw-agent shorthand in the examples README Aditya VardhanandClaude Fable 5 2026-07-06 14:05:25 +05:30
• 8151cc5e23 Align Modal API assumptions with validated behavior; rename to ModalSandboxCapability Aditya VardhanandClaude Opus 4.8 2026-07-06 14:04:20 +05:30
• 69785906e4 docs(dynamic-workflow): rewrite README as a progressive tutorial Aditya VardhanandClaude Fable 5 2026-07-06 13:55:46 +05:30
• 689f12189e refactor(dynamic-workflow): accept raw agents, make reveal() the strict mutation API Aditya VardhanandClaude Opus 4.8 2026-07-06 13:37:46 +05:30
• 4bf294965f Harden ModalSandbox failure handling and bound its memory Aditya VardhanandClaude Opus 4.8 2026-07-06 13:28:05 +05:30
• 16df4a85f7 chore: stop tracking .agents/scheduled_tasks.lock Aditya VardhanandClaude Opus 4.8 2026-07-06 13:03:45 +05:30
• c7178467a9 test(dynamic-workflow): align tests with pydantic-ai v2 deps typing Aditya VardhanandClaude Opus 4.8 2026-07-06 12:41:25 +05:30
• e2d394aaba Merge remote-tracking branch 'origin/main' into claude/modal-sandbox-capability Aditya Vardhan 2026-07-06 12:39:20 +05:30
• 9b82505551 Merge remote-tracking branch 'origin/main' into dynamic-workflow Aditya Vardhan 2026-07-06 12:35:00 +05:30
• 84ce34ecd7 feat(subagents): contain unexpected sub-agent crashes as bounded retries subagents-contain-errors David SF 2026-07-04 22:48:44 -05:00
• 10d0ef0814 fix(dynamic-workflow): harden error surfaces, render output schemas, add reveal() API Aditya VardhanandClaude Fable 5 2026-07-04 23:00:49 +05:30
• 069d1ffacf feat(subagents): configurable delegate-tool retries (#324) David SFandGitHub 2026-07-03 23:50:15 -05:00
• 1a1c58be2b Add opt-in CodeMode(allow_final_output=True) with a sandbox final_output() function code-mode-final-output Douwe Maan 2026-07-04 00:53:02 +00:00
• 5a741a9e63 test(code_mode): drop removed ToolSearchMatch.description field guardrails David SF 2026-07-03 00:30:43 -05:00
• 6bc0475090 chore: bump pydantic-ai-slim to 2.4.0 in lock David SF 2026-07-03 00:25:00 -05:00
• 85b9f949f9 Merge remote-tracking branch 'origin/main' into guardrails David SF 2026-07-03 00:02:58 -05:00
• 3c5ec34f9e Bump vcrpy to 8.2.1 to fix YAML deserialization RCE (#300) Aditya VardhanandGitHub 2026-07-01 17:50:40 +05:30
• 4794256765 Merge branch 'main' of github.com:pydantic/pydantic-ai-harness into chore/bump-vcrpy chore/bump-vcrpy Aditya Vardhan 2026-07-01 09:53:47 +05:30
• 6eb91dfe86 Bump pydantic-ai floor to 2.1 (#303) v0.5.0 Aditya VardhanandGitHub 2026-07-01 00:02:14 +05:30
• 51ba5693bf Revert "fix(code_mode): tighten run_code prompt against phantom imports and…" (#317) Aditya VardhanandGitHub 2026-06-30 22:36:40 +05:30
• 326c3d648d Emit a span when compaction happens (#312) 3 people 2026-06-30 14:33:42 +02:00
• 4e21f7bcbf docs(agents): discourage private-helper imports in tests (#316) 3 people 2026-06-30 17:08:21 +05:30
• 55c9e08dee docs(agents): discourage private-helper imports in tests agents-md-no-private-test-imports Aditya VardhanandClaude Opus 4.8 2026-06-30 16:57:10 +05:30
• ea49cdde23 Tear down an owned sandbox cancelled during creation Aditya VardhanandClaude Opus 4.8 2026-06-29 11:19:15 +05:30
• 4704979da1 Surface the reuse-mode command ceiling and harden test fidelity Aditya VardhanandClaude Opus 4.8 2026-06-29 11:13:32 +05:30
• d06a5cf9c6 Fix trailing-newline line inflation and adversarial-review nits Aditya VardhanandClaude Opus 4.8 2026-06-29 11:02:52 +05:30
• 5c12602bee Move Modal timeout quantization into the session layer Aditya VardhanandClaude Opus 4.8 2026-06-29 10:23:57 +05:30
• 172c7fbc17 Document the no-temp-file-spill limitation as a deliberate choice Aditya VardhanandClaude Opus 4.8 2026-06-29 10:18:02 +05:30
• ac7e2b2a9b Cap the per-command timeout so a cancelled command cannot run unbounded Aditya VardhanandClaude Opus 4.8 2026-06-29 10:14:01 +05:30
• 2771779ae6 Align ModalSandbox output truncation with pi; fix max_output_bytes doc Aditya VardhanandClaude Opus 4.8 2026-06-29 09:58:19 +05:30
• a5ceb9e889 Make ModalSandbox output limits configurable; guard read against file growth Aditya VardhanandClaude Opus 4.8 2026-06-29 09:38:35 +05:30
• 250fee068b Harden ModalSandbox against teardown stalls, cwd poisoning, and error leaks Aditya VardhanandClaude Opus 4.8 2026-06-27 10:25:23 +05:30
• ea31b59470 Keep LocalStack CI from starting account-gated service David SF 2026-06-26 18:32:57 -05:00
• e002cb157f Acknowledge LocalStack community startup requirement David SF 2026-06-26 18:28:19 -05:00
• 4ad67154d4 Keep LocalStack CI on community image David SF 2026-06-26 18:20:21 -05:00
• d42b0098f1 Self-review fixes for #275 claude/managed-tool-capability-r2vtg Bill EastonandClaude Opus 4.7 2026-06-26 17:52:37 -05:00
• eac9ac385e Stabilize LocalStack live integration job David SF 2026-06-26 17:51:34 -05:00
• 3d518ea531 Stabilize LocalStack CI jobs David SF 2026-06-26 17:10:51 -05:00
• f2795953a3 Keep already-empty ModelRequests in LimitWarner._strip_old_warnings David SFandClaude Opus 4.8 2026-06-26 15:35:37 -05:00
• cf6c3ed05f Refresh LocalStack container env examples David SF 2026-06-26 13:24:44 -05:00
• fa149f6339 test(localstack): cover the AWS CLI end-of-options separator path Claude 2026-06-26 18:18:17 +00:00
• aba64db154 Merge remote-tracking branch 'origin/main' into codex/pr-268-localstack-review David SF 2026-06-26 13:02:06 -05:00
• 19222e8e16 Harden LocalStack command boundaries David SF 2026-06-26 12:57:34 -05:00
• 746f946c23 Add read-size guard and owned-sandbox env vars Aditya VardhanandClaude Opus 4.8 2026-06-26 23:15:42 +05:30
• 8cc3373c8f Soften the per-exec-kill wording to "not currently" Aditya VardhanandClaude Opus 4.8 2026-06-26 23:05:44 +05:30
• 405a306b07 Bound internal exec deadline and document the cancellation model Aditya VardhanandClaude Opus 4.8 2026-06-26 22:40:33 +05:30
• c946340fcc Re-bless ManagedPrompt baggage snapshot after rebase Bill EastonandClaude Opus 4.7 2026-06-26 11:53:14 -05:00
• 9fa5349746 Consolidate managed-variable tests onto shared scaffolding ClaudeandBill Easton 2026-06-06 19:55:23 +00:00
• 04c9d41f90 Add ManagedTool / ManagedToolset capabilities for Logfire-managed tool framing ClaudeandBill Easton 2026-06-06 16:44:05 +00:00
• 4e32978705 Rename default_timeout to default_command_timeout Aditya VardhanandClaude Opus 4.8 2026-06-26 20:40:32 +05:30
• 66f61d2ffe Harden ModalSandbox public API and tool output from review Aditya VardhanandClaude Opus 4.8 2026-06-26 19:31:16 +05:30
• 2d2f5a015d feat(logfire): add ManagedAgentSpec for whole-spec resolution managed-agent-spec Bill EastonandClaude Opus 4.7 2026-06-26 08:54:16 -05:00
• 73391d633e Merge branch 'claude/modal-sandbox-capability' of github.com:pydantic/pydantic-ai-harness into claude/modal-sandbox-capability Aditya Vardhan 2026-06-26 16:40:58 +05:30
• f460861435 Add experimental CE-discovery capabilities: context, subagents disk-load, docs, authoring (#304) David SFandGitHub 2026-06-24 21:48:47 -05:00
• 0418280d1e test(logfire): tolerate pydantic-ai 2.0.0 agent-span rename (#305) 3 people 2026-06-24 17:42:34 -05:00
• 0a5c37adff Bump vcrpy to 8.2.1 to fix YAML deserialization RCE Aditya VardhanandClaude Opus 4.8 2026-06-24 23:42:48 +05:30
• 886e174e05 Bump vcrpy floor to 8.2.1 for aiohttp 3.14 compatibility Aditya VardhanandClaude Opus 4.8 2026-06-24 23:41:32 +05:30
• f57278ca0a Add vcrpy dev dependency for cassette-based tests Aditya VardhanandClaude Opus 4.8 2026-06-24 23:41:32 +05:30
• 957c117dba Address CodeRabbit review findings on ModalSandbox Aditya VardhanandClaude Opus 4.8 2026-06-24 19:32:27 +05:30
• 08e69988b1 Document the capability/session layering and narrow the headline API Aditya VardhanandClaude Opus 4.8 2026-06-24 17:55:29 +05:30
• 1df006aae5 Merge branch 'main' of github.com:pydantic/pydantic-ai-harness into claude/modal-sandbox-capability Aditya Vardhan 2026-06-24 17:50:40 +05:30
• b04e72b6d8 Add read_file offset/limit paging and shared output truncation Aditya VardhanandClaude Opus 4.8 2026-06-24 17:32:07 +05:30