pydantic-ai-harness

furyhawk/pydantic-ai-harness

Fork 0

mirror of https://github.com/pydantic/pydantic-ai-harness.git synced 2026-07-21 02:45:34 +00:00

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-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/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

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

#386

#387

#388

#389

#390

#390

#391

#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

43633b0b24 docs: point at the new per-capability pages in core's Capabilities section (#391) main Douwe MaanandGitHub 2026-07-20 19:44:34 -06:00
6c60f7cf0d feat(step_persistence): rescue last provider-valid resume point on error (#384) v0.8.0 David SFandGitHub 2026-07-20 19:40:25 -05:00
e094cd71e3 Align docs with the Agent Control UI name; mark ManagedPrompt legacy up front managed-components Douwe Maan 2026-07-21 00:05:30 +00:00
6cc95b8953 Rename ManagedAgent capability to AgentControl; drop @{ref}@ composition Douwe Maan 2026-07-20 23:24:10 +00:00
759c67ecaa docs: point at the new per-capability pages in core's Capabilities section caps-docs-links Douwe Maan 2026-07-20 23:13:18 +00:00
d34a1f9e7e Pin macroscope parse invariants and strengthen test assertions feat/macroscope-capability Bill EastonandClaude Opus 4.8 2026-07-20 16:12:46 -05:00
eb556ece56 Harden macroscope spawn failures and cover agent-spec loading Bill EastonandClaude Opus 4.8 2026-07-20 15:22:35 -05:00
0834f3b0fb Drop the temporary pydantic-ai pin: require released pydantic-ai-slim>=2.13.0 Douwe Maan 2026-07-20 17:30:27 +00:00
31a34ebae0 Run macroscope codereview --raw for machine-readable output Bill EastonandClaude Opus 4.8 2026-07-20 10:21:57 -05:00
68f0d2fb2c Make Code Mode resource acquisition transactional bump_monty Aditya Vardhan 2026-07-20 12:18:23 +05:30
4ad83f8861 Clarify CodeMode final-expression returns (#370) Aditya VardhanandGitHub 2026-07-20 12:08:36 +05:30
ba447822aa docs: macroscope unified-docs page; guidance convention for instructions Bill Easton 2026-07-19 12:52:34 -05:00
ee699cefeb feat: Macroscope CLI code-review capability
Bill Easton Bill Easton Claude Opus 4.8
2026-07-10 21:22:00 -05:00
f2389a893c Add .macroscope/ignore.md to skip mechanical files in review (#387)
Bill Easton GitHub Bill Easton Claude Opus 4.8
2026-07-19 11:45:22 -05:00
57686c6a10 Preserve Macroscope default ignores; keep test code reviewed macroscope-ignore Bill EastonandClaude Opus 4.8 2026-07-19 11:43:14 -05:00
4020c90e92 Add .macroscope/ignore.md to skip mechanical files in code review Bill EastonandClaude Opus 4.8 2026-07-19 11:31:08 -05:00
b7d2406a9b Sync Monty migration with current main Aditya Vardhan 2026-07-18 10:43:56 +05:30
e2d13c1ee4 Require released Temporal Monty passthrough Aditya Vardhan 2026-07-18 10:25:24 +05:30
de2d29af79 Target merged pydantic-ai#6333: pin pydantic-ai-slim to the main merge commit Douwe Maan 2026-07-18 00:25:23 +00:00
b3a7ef657d Source the nameless ManagedAgent model via the get_model selector; drop the pre-get_model fallback Douwe Maan 2026-07-17 18:36:38 +00:00
5cabc2880a test(step_persistence): drop dead validator branch to restore 100% coverage on-run-error-snapshot David SF 2026-07-17 12:54:22 -05:00
39cd255485 fix(cache_stability): latch collapse state so a sustained collapse warns once cache-bust-guard David SF 2026-07-17 12:50:09 -05:00
59f4059877 feat(step_persistence): rescue last provider-valid resume point on error David SF 2026-07-17 12:41:50 -05:00
b0788b12c4 Path-scope the live LocalStack job; drop the stale greenlet pin claude/localstack-aws-emulation-0owHz David SF 2026-07-17 12:35:57 -05:00
5730fb6874 Fix ClearToolResults corrupting typed ToolReturnPart subclasses fix-380-clear-tool-results-typed-parts David SF 2026-07-17 11:49:05 -05:00
caf19e68bb docs(cache_stability): drop stale 'high-water mark' phrasing in README composition note David SF 2026-07-17 10:43:09 -05:00
d97d2e6440 fix(cache_stability): per-key timing + collapse re-baseline; graduate as released David SF 2026-07-17 10:40:24 -05:00
e4839c654b Keep already-empty ModelRequests in LimitWarner._strip_old_warnings (#311) v0.7.1
David SF GitHub Claude Opus 4.8
2026-07-16 23:03:21 -05:00
4e0209841a Merge remote-tracking branch 'origin/main' into fix-limit-warner-empty-request fix-limit-warner-empty-request David SF 2026-07-16 22:06:16 -05:00
c1f97a6189 Collapse the managed family into ManagedAgent: one agent__ variable holding an AgentConfig Douwe Maan 2026-07-17 00:48:54 +00:00
86cc4795b1 feat: excerpt-based web_search, retry seam, domain filters, spec support exa-capability Bill EastonandClaude Fable 5 2026-07-16 16:00:09 -05:00
e72e11353d docs: reframe deep_search guidance around research depth Bill EastonandClaude Fable 5 2026-07-16 15:29:05 -05:00
02540a2409 feat: add opt-in deep_search tool and harden ExaSearch per review Bill EastonandClaude Fable 5 2026-07-16 15:15:48 -05:00
67f8d870a5 Prevent search result format from becoming a return type (#377) Aditya VardhanandGitHub 2026-07-16 14:14:40 +05:30
dc83b13151 Prevent search result format from becoming a return type codex/fix-issue-360-search-files-docstring Aditya Vardhan 2026-07-16 13:55:31 +05:30
1b0d1c3edc feat: add ExaSearch web research capability Bill EastonandClaude Fable 5 2026-07-15 20:26:02 -05:00
04a6760ab7 docs(cache_stability): drop stale 'experimental' wording from Logfire note David SF 2026-07-15 18:47:26 -05:00
921ba84f12 docs: drop duplicate Managed prompt row from README matrix David SF 2026-07-15 18:40:08 -05:00
487c5e9078 fix(cache_stability): validate thresholds; don't overclaim empty cache David SF 2026-07-15 18:35:12 -05:00
94396f937e refactor(cache_stability): graduate out of experimental to top-level David SF 2026-07-15 18:26:55 -05:00
b1c225f0b3 Merge remote-tracking branch 'origin/main' into cache-bust-guard David SF 2026-07-15 18:13:42 -05:00
8b603d1502 fix(cache_stability): key marks per model, hedge cache-expiry cause David SF 2026-07-15 18:08:14 -05:00
efc0e0a312 Merge origin/main; retarget overflow query surface onto graduated module claude/spill-query-surface Douwe MaanandClaude Opus 4.8 2026-07-15 20:01:02 +00:00
42d883cf81 Merge origin/main; retarget compaction receipts/pins onto graduated module claude/compaction-structural Douwe MaanandClaude Opus 4.8 2026-07-15 19:55:33 +00:00
e93a64352f refactor(cross_model_label): graduate to top-level layout, add docs-site page claude/cross-model-history-label Douwe MaanandClaude Opus 4.8 2026-07-15 19:52:44 +00:00
38162829f3 refactor(permission_policy): graduate to top-level layout, add docs-site page claude/permission-policy Douwe MaanandClaude Opus 4.8 2026-07-15 19:51:59 +00:00
447e1f9155 refactor(loop_detection): graduate to top-level layout, add docs-site page claude/loop-detection Douwe MaanandClaude Opus 4.8 2026-07-15 19:50:28 +00:00
166f8d7ca7 refactor(budget_disclosure): graduate to top-level layout, add docs-site page claude/budget-disclosure Douwe MaanandClaude Opus 4.8 2026-07-15 19:50:22 +00:00
6f25fd7b2a refactor(checkpoints): graduate to top-level layout, add docs-site page claude/checkpoints Douwe MaanandClaude Opus 4.8 2026-07-15 19:49:37 +00:00
db8e739921 chore(terminal-bench): merge main, retarget graduated compaction import claude/terminal-bench-agent Douwe MaanandClaude Opus 4.8 2026-07-15 19:48:48 +00:00
e1eca45f15 Merge remote-tracking branch 'origin/main' into claude/terminal-bench-agent Douwe Maan 2026-07-15 19:47:43 +00:00
5715be9d24 Merge remote-tracking branch 'origin/main' into claude/permission-policy Douwe Maan 2026-07-15 19:47:35 +00:00
d718138aa1 Merge remote-tracking branch 'origin/main' into claude/cross-model-history-label Douwe Maan 2026-07-15 19:47:00 +00:00
6b4bee0f7a Merge remote-tracking branch 'origin/main' into claude/loop-detection Douwe Maan 2026-07-15 19:46:39 +00:00
c082742362 Merge remote-tracking branch 'origin/main' into claude/checkpoints Douwe Maan 2026-07-15 19:46:11 +00:00
3fa45e5f9c Merge remote-tracking branch 'origin/main' into claude/budget-disclosure Douwe Maan 2026-07-15 19:45:47 +00:00
8eb4f6eb9c refactor(staleness): graduate to top-level layout, add docs-site page claude/staleness-tracker Douwe MaanandClaude Opus 4.8 2026-07-15 19:43:05 +00:00
6b89817923 Merge remote-tracking branch 'origin/main' into claude/staleness-tracker Douwe Maan 2026-07-15 19:37:49 +00:00
f6a51760e4 Gate check on localstack-integration; make docker timeouts asyncio-safe David SF 2026-07-14 16:24:05 -05:00
c4a04e7588 Apply CodeRabbit review: scope CI token, bound docker subprocesses, validate output cap David SF 2026-07-14 16:06:51 -05:00
de3864d8c1 Restore uv.lock [options] block to match main David SF 2026-07-14 15:42:36 -05:00
528657697c Restore uv.lock exclude-newer-package options dropped by the merge David SF 2026-07-14 15:37:13 -05:00
cb25642407 Graduate LocalStack from experimental; use auth token, not the expired account bypass David SF 2026-07-14 13:02:24 -05:00
fb801af948 Conform LocalStack README to merged docs-parity checks David SF 2026-07-14 12:40:51 -05:00
a414e1f67e Merge remote-tracking branch 'origin/main' into claude/localstack-aws-emulation-0owHz David SF 2026-07-14 12:35:04 -05:00
d808d05ef6 Separate CodeMode print return cases codex/issue-346-clarify-code-mode-return Aditya Vardhan 2026-07-14 23:04:00 +05:30
3e6981293b Explain None results in CodeMode Aditya Vardhan 2026-07-14 23:01:40 +05:30
95ec5f0c35 Match CodeMode guidance to exact return shapes Aditya Vardhan 2026-07-14 22:58:39 +05:30
f674bb9229 Document every CodeMode return shape Aditya Vardhan 2026-07-14 22:55:41 +05:30
d5191951df Make CodeMode return guidance unambiguous Aditya Vardhan 2026-07-14 22:53:58 +05:30
e755dcd187 Prevent empty CodeMode results through clearer guidance Aditya Vardhan 2026-07-14 22:48:58 +05:30
73513a60bc Remove third-party MCP endpoint from pydantic-ai-harness skill (#368) Aditya VardhanandGitHub 2026-07-14 21:49:21 +05:30
cff03682b6 Make live teardown check tolerate control-plane lag claude/modal-sandbox-capability Aditya Vardhan 2026-07-14 20:10:44 +05:30
4c2a8a2125 Polish Modal sandbox capability for release Aditya Vardhan 2026-07-14 19:52:58 +05:30
7bffe65b2d Merge remote-tracking branch 'origin/main' into codex/pr-269-review Aditya Vardhan 2026-07-14 19:12:03 +05:30
abdb118c0e fix(filesystem): align walkers with read-only protection contract codex/fix-322-protected-walkers David SF 2026-07-13 16:41:01 -05:00
818808d6fe feat: add Memory capability (#354) v0.7.0
Kacper Włodarczyk GitHub David SF
2026-07-13 23:15:40 +02:00
39b4c569cb Stop attributing every AICA comment to Claude (#362) David SFandGitHub 2026-07-13 14:20:00 -05:00
a0d068bf95 Stop attributing every AICA comment to Claude codex/aica-attribution David SF 2026-07-13 13:44:41 -05:00
416f4d6d01 Make memory safe for durable shared use codex/pr-354-memory David SF 2026-07-13 13:15:20 -05:00
73033d9c25 Merge remote-tracking branch 'origin/main' into codex/pr-354-memory David SF 2026-07-13 12:01:56 -05:00
4ee2b3291f ci: drop the pydantic-ai v2 beta early-warning job (#359) Aditya VardhanandGitHub 2026-07-13 21:38:47 +05:30
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

1 2 3 4 5 ...