49890d1244
Merge PR #3036 from Hmbown: hide internal IDs from normal UI — stable labels for turns and agents
Hunter Bown
2026-06-10 22:20:06 -07:00
418ad5b744
Merge origin/main into v0.8.58-3030-hide-internal-ids — combine #3030 stable agent labels with #3033 AgentProgress redraw throttle (both kept in App state and the AgentProgress arm)
Claude
2026-06-11 05:19:57 +00:00
eb610c83ee
Merge PR #3035 from Hmbown: throttle AgentProgress redraws to prevent freeze under subagent load
Hunter Bown
2026-06-10 22:11:17 -07:00
f68059b9b3
Merge PR #3043 from Hmbown: agent-task issue template, labels, and runner protocol
Hunter Bown
2026-06-10 22:10:42 -07:00
4cf9e52f19
ci: re-run after known Windows test flake (no code changes)
Claude
2026-06-11 04:47:00 +00:00
ff6dca1d45
ci: re-run after known Windows test flake (no code changes)
Claude
2026-06-11 04:46:58 +00:00
f55c54c487
ci: re-run after known Windows test flake (no code changes)
Claude
2026-06-11 04:46:55 +00:00
1a61a79910
fix(hooks): pass the Windows cmd /C command line via raw_arg — Command::arg's CRT-style quoting inserted literal \" into hook commands, which cmd.exe does not unescape, so JSON decisions never parsed (hook_gate_* Windows failures)
Claude
2026-06-11 04:46:05 +00:00
29f75dc19d
fix(lint): fold the sidebar click row lookup into the bounds let-chain — newer clippy (1.96) flags the nested if as collapsible_if and CI lints with -D warnings
Claude
2026-06-11 04:42:18 +00:00
8284f395e6
test(integration): add signature field to ContentBlock::Thinking initializers and pattern in tests/ — the bins-only local run missed integration-test targets when the field landed
Claude
2026-06-11 04:38:39 +00:00
f65d091c65
fix(lint): collapse nested if-let into a let-chain in codex responses reasoning shaping — newer clippy (1.96) flags collapsible_if on if-let nesting and CI lints with -D warnings
Claude
2026-06-11 04:29:24 +00:00
279ad5af90
feat(client): native Anthropic Messages API adapter — /v1/messages dialect with x-api-key + anthropic-version auth, adaptive thinking + output_config.effort shaping, cache_control breakpoints (prefix zones, capped at 4), signed-thinking replay via new signature field + signature_delta, #2961 usage normalization, SSE pass-through with error envelopes; registry/docs sync (#3014)
Claude
2026-06-11 03:54:46 +00:00
3c38dabefb
feat(providers): add Anthropic to the three provider surfaces — ApiProvider/ProviderKind variants, provider metadata (x-api-key auth env, api.anthropic.com, claude-sonnet-4-6 default), AnthropicMessages wire format, ModelRegistry rows for claude-opus-4-8 / claude-sonnet-4-6 / claude-haiku-4-5 (#3014, WIP)
Claude
2026-06-11 03:08:50 +00:00
81b060928b
Merge PR #2579 from encyc: Phase 4 — replace Session.messages Vec with AppendLog
Hunter Bown
2026-06-10 20:10:20 -07:00
544b44bd98
Merge PR #2892 from gordonlu: localize sandbox elevation dialog across 7 locales
Hunter Bown
2026-06-10 20:10:05 -07:00
fc10d10189
feat(routing): complete #3018 — RouterCandidates + provider_router_candidates; candidate-aware heuristics, router prompts and recommendation parsing; skip the network router when no cheap tier exists; validate spawn-time model against the active provider; tests + SUBAGENTS.md per-role models docs
Claude
2026-06-11 03:03:08 +00:00
2bbe25b7e4fix: #3034 audit residuals — correct the constitution renderer doc-comment (renderer NOT reconciled with committed MD, do not regenerate); pin the collapsed-thinking header assertion; align auth list's openai-codex credential source with auth status
Claude
2026-06-11 02:45:25 +00:00
033132a735
fix(tui): #3032 residuals — running-exec hint now says Ctrl+B backgrounds the command; Ctrl+B documented in KEYBINDINGS.md and runbook updated for menu removal; Cannot-background message names the reason (interactive / non-shell tool / nothing running)
Claude
2026-06-11 02:40:07 +00:00
7a64119635
test(reasoning): #3016 coverage — Moonshot in provider_accepts_reasoning_content, kimi-k2.6 stream classification, multi-chunk Moonshot reasoning_content decoder fixture; exclude non-thinking kimi-for-coding from the kimi- prefix rule
Claude
2026-06-11 02:35:36 +00:00
9de6c9d125
docs(remote-smoke): add gh auth setup-git + git identity to the autonomous-loop setup; qualify the AGENT_RUNNER.md cross-reference (file lands in #3043) with an on-branch fallback (#3022)
Claude
2026-06-11 02:31:34 +00:00
e4ea208d53
docs(runner): fix resume example — exec has no 'latest' session alias; use --continue (#3021)
Claude
2026-06-11 02:31:00 +00:00
5fb41cc209
test(errors): add #3020 test extensions — Plan-mode denial passes through verbatim, bare/model denials get the suffix; Model-Not-Exist + OpenAI-style rejections annotated; conflict error includes elapsed time; tighten mode-word predicate so 'model' no longer matches
Claude
2026-06-11 02:30:30 +00:00
948e42397f
fix(tui): #3029 audit fix — interleave OSC 8 open/close per region in diff order (OSC 8 is last-writer-wins state; batched opens linked the whole frame to the last target); drop cursor-move hack and dead pending_links; add byte-stream bracketing tests
Claude
2026-06-11 02:26:45 +00:00
b6e88d2d34
fix(tui): #3031 audit fix — map the literal '(no output)' ToolResult placeholder to None at the routing layer (exec + generic cells) so compact-mode suppression actually fires; add helper + render-mode tests
Claude
2026-06-11 02:18:46 +00:00
5a71d644f5
fix(tui): #3030 audit fixes — nickname beats generated Agent-N label; status bar uses stable labels (with raw-id fallback) for spawn/progress/complete; drop truncated raw id from compact detail line; add label/turn/step-counter tests
Claude
2026-06-11 02:13:30 +00:00
df1b35ba0f
fix(tui): #3033 audit fix — throttled AgentProgress no longer cancels redraws owed to other events in the same drain batch; restore pre-event accumulator value; extract agent_progress_redraw_permitted + unit tests
Claude
2026-06-11 02:03:17 +00:00
6f5039101a
feat(hooks): wire the #3026 decision contract into the engine — JSON deny/ask/updatedInput now steer tool calls (deny>ask>allow, last-writer updatedInput), additionalContext piped into tool results, project .codewhale/hooks.toml loaded at both HookExecutor sites; parser hardening + fold/glob/project tests; docs
Claude
2026-06-11 01:52:22 +00:00
ac3f8c04b6
fix(tui): rebuild sidebar click-action mapping — lines and actions now built in one pass so indices can't drift; shell_* jobs route via /jobs, task jobs via /task; finished jobs lose the cancel target; agents panel gates role-mix slot correctly; fix test compile; add action-mapping + click-resolution tests (#3028)
Claude
2026-06-11 00:46:38 +00:00
c15e937096
fix(exec): wire --disallowed-tools into the gate chain (deny wins over allow), filter the advertised tool catalog, honor --append-system-prompt in needs_engine, surface max-steps notice in text mode; add clap/gate/catalog tests (#3027)
Claude
2026-06-11 00:31:05 +00:00
6a2c529242
fix(prompts): make #3025 placeholders live — base.md now carries {context_window_note}/{subagent_economics}/{model_thinking_note}/{model_characteristics}; add model_characteristics handler (V4 vs generic); fix one-million-token-token wording; genericize Flash V4 tool_agent note; add compose + pricing tests
Claude
2026-06-11 00:23:37 +00:00
b9bcc9c710
fix(providers): update stale Atlascloud/Ollama capability tests to the generic model-based path; add bare Moonshot/MiniMax/Z.ai model rows (kimi-k2.6, kimi-for-coding, minimax-m3, glm-5.1, glm-5v-turbo) mirroring vendor-prefixed rows; add Moonshot capability + engine capacity tests (#3023, #1310)
Claude
2026-06-11 00:17:53 +00:00
29e60cd4b9
fix(reasoning): Atlascloud joins the DeepSeek dialect group — max tier now sends reasoning_effort=max; add Atlascloud/Moonshot/Ollama dialect-shape tests; document per-provider reasoning-effort wire mapping in PROVIDERS.md (#3024)
Claude
2026-06-11 00:13:18 +00:00
e1a61f445e
fix(tui): remove ShellControlView menu now unreachable after direct Ctrl+B
Hunter Bown
2026-06-10 16:49:30 -07:00
Hunter Bown