Dark-Alex-17/coyote
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,391 Commits 10 Branches 12 Tags
dc2f26d0e6e123ef3ba0658202307f66ae1a4b60
Commit Graph
265 Commits
Author SHA1 Message Date
Dark-Alex-17 75cc2a4b9c feat(TASK-010): add max_attempts to read-only agent lanes in bundled graphs 2026-09-14 10:50:33 -06:00
Dark-Alex-17 3254fe9f3c feat: Fixed graph agents with new agent variable passing functionality 2026-09-12 01:37:20 -06:00
Dark-Alex-17 99e592565a feat: Significant code review suite rewrite with improved graph agent features 2026-09-11 15:33:21 -06:00
Dark-Alex-17 e744da8870 feat: update the web_search_coyote tool to attempt to use the current model first then fallback to the configured model for web searches 2026-09-11 13:47:44 -06:00
Dark-Alex-17 3e91813cff feat: removed temperature specification in deep-research and finding-verifier agents to make them more univerally usable 2026-09-11 11:22:06 -06:00
Dark-Alex-17 b4c01e0f28 chore(agents): drop the inert output reducers from librarian and finding-verifier 2026-09-11 10:56:28 -06:00
Dark-Alex-17 a7744e7f89 fix(agents): name the map-branch output key in deep-research and finding-verifier 
An llm node never persists its completion under `output` (the binding
is transient), so a map branch without state_updates collected the
stale inherited value: deep-research produced `None` findings and
finding-verifier errored on its first item because `output` was absent.

Both maps now declare an explicit output_key and their branch nodes
write it via state_updates. graph.example.yaml's research_subject gets
the same named-key pattern and its branch comment describes it.

Design: plans/map-subgraph-branches-design.md §2.6, §3.7 (C9).
 2026-09-11 10:56:26 -06:00
Dark-Alex-17 d71cf75209 fix: Fixed the bad formatting in the finding-verifier agent 2026-09-09 17:39:56 -06:00
Dark-Alex-17 ddce9e330e docs: Added whetstone to the architect and sisyphus READMEs 2026-09-09 17:39:42 -06:00
Dark-Alex-17 2928125b0e feat: created the finding-verifier and whetstone agents for continuous code quality improvements 2026-09-09 17:22:26 -06:00
Dark-Alex-17 13ebe04472 feat: support setting the tool_timeout in the main config file instead of only via an environment variable 2026-09-08 17:22:21 -06:00
Dark-Alex-17 6104a48e56 Merge branch 'main' of github.com:Dark-Alex-17/coyote 2026-09-08 11:25:38 -06:00
Dark-Alex-17 a5984eca80 fix: exclude null bytes from fs_grep output on binaries 2026-09-08 11:24:59 -06:00
github-actions[bot] d6dc6c96d6 chore: bump Cargo.toml and sandbox image to 0.10.2 2026-09-04 04:15:00 +00:00
Dark-Alex-17 f1cb6589bc feat: refresh the model catalog from live API data at runtime 2026-09-03 11:17:58 -06:00
Dark-Alex-17 af7d37890c fix: children subagents couldn't properly send messages to parent inboxes 2026-09-02 14:18:16 -06:00
Dark-Alex-17 141289d973 feat: Improved the architect, explore, and sisyphus agents to have a team mode so they can all work in parallel as a team and updated the parallel-research skill to make explicit mention of this functionality 2026-09-02 13:53:12 -06:00
github-actions[bot] 7b37eb4602 chore: bump Cargo.toml and sandbox image to 0.10.1
CI / All (ubuntu-latest) (push) Failing after 29s
Details
CI / All (macos-latest) (push) Canceled after 0s
Details
CI / All (windows-latest) (push) Canceled after 0s
Details
2026-08-31 20:08:42 +00:00
Dark-Alex-17 016f2654e4 fix: make binary shims for custom tools cross-device compatible so users can't accidentally break sandboxes via sbx cp ~/.config/coyote <sbx-name>:/home/agent/.config 2026-08-31 13:48:56 -06:00
github-actions[bot] c102da5665 chore: bump Cargo.toml and sandbox image to 0.10.0
CI / All (ubuntu-latest) (push) Failing after 29s
Details
CI / All (macos-latest) (push) Canceled after 0s
Details
CI / All (windows-latest) (push) Canceled after 0s
Details
2026-08-29 05:49:07 +00:00
Dark-Alex-17 baa45970da feat: upgraded to v2 mixin schema
CI / All (ubuntu-latest) (push) Failing after 29s
Details
CI / All (macos-latest) (push) Canceled after 0s
Details
CI / All (windows-latest) (push) Canceled after 0s
Details
2026-08-28 18:24:58 -06:00
Dark-Alex-17 176a81412a feat: improved first-time run experience and included a templated configuration file that now has comments like the config.example.yaml so users don't have to go to the repo to see all the knobs
CI / All (ubuntu-latest) (push) Failing after 29s
Details
CI / All (macos-latest) (push) Canceled after 0s
Details
CI / All (windows-latest) (push) Canceled after 0s
Details
2026-08-28 15:15:10 -06:00
Dark-Alex-17 d3914955e2 feat(TASK-005): carry the quality bar through sisyphus and architect 
sisyphus: Quality bar line in the code-reviewer spawn prompt (omitted when
the task prompt carried none); rigor-aware WARNING handling with
(deferred by quality bar) FOLLOW-UPS tagging; evidence-cited rejection
protocol for [convention] findings (repo convention at file:line or a
recorded plan decision; never for CRITICAL/[correctness]; escalate on
re-raise); rigor-to-posture default map for security-reviewer spawns.

architect: Phase B quality-bar round + other:<label> librarian lane;
Phase E Sisyphus CONTEXT and adversary prompts carry rigor/surfaces and
the plan's Quality bar excerpt; task-close logs rejected-finding lines;
Phase F PR body gains the Quality bar line and Review decisions section;
two new anti-patterns (bare rejections, rigor suppressing CRITICAL).
 2026-08-28 14:47:57 -06:00
Dark-Alex-17 a8d730cf01 feat(TASK-004): reviewer routing — code-reviewer quality-bar resolution, domain linter pass, surface-skill routing, rigor folding; file-reviewer surface-skill whitelist + convention/correctness marker 2026-08-28 14:47:57 -06:00
Dark-Alex-17 cf638305e6 feat(TASK-003): add surface skills batch B — worker-review, iac-review, migration-review, cicd-review 2026-08-28 14:47:57 -06:00
Dark-Alex-17 3601faa969 feat(TASK-002): add surface skills batch A — rest-api-review, cli-review, library-review 
Three new read-only review skills under assets/skills/, mirroring the
transactional-integrity canon: frontmatter load triggers, read-only
enabled_tools, production-bar severity checklists with
[convention]/[correctness] markers, marker-semantics and
orchestrator-linter paragraphs, and aspect-boundary lists.
rest-api-review includes gRPC and GraphQL sections.
 2026-08-28 14:47:57 -06:00
Dark-Alex-17 e4c5f42a25 feat(TASK-001): add rigor/surfaces declaration layer to planning skills 
design-session: Quality bar round in Step 2 (rigor/surfaces proposal,
per-surface confirm/drop, other:<label> lane, autonomous fallback),
rigor+surfaces frontmatter and Quality bar section in the Step 3 PLAN
template, poc-dodge anti-pattern.
task-tracking: optional per-task surfaces key (inherits the plan's list);
rigor stays run-level only.
plan-gatekeeping: manifest category 11 (Quality bar) with
FRICTION/BLOCKING severity guidance.
 2026-08-28 14:47:57 -06:00
Dark-Alex-17 290f6b257f docs: refined the description of coyote better 2026-08-27 15:55:13 -06:00
Dark-Alex-17 af697d129b docs: updated the coyote description to be more accurate to its true use and purpose 2026-08-27 15:34:38 -06:00
Dark-Alex-17 93e90106a8 feat: create a new probe agent to probe code verifications using usage-pattern testing 2026-08-27 13:59:28 -06:00
Dark-Alex-17 35e4c82f27 feat: Add in the web_search_coyote tool where helpful 2026-08-27 13:59:09 -06:00
Dark-Alex-17 ebe7816600 feat: claude and openai native web search via web_search_coyote
CI / All (ubuntu-latest) (push) Failing after 30s
Details
CI / All (macos-latest) (push) Canceled after 0s
Details
CI / All (windows-latest) (push) Canceled after 0s
Details
2026-08-26 15:22:24 -06:00
Dark-Alex-17 304b8f635f fix(tools): interactive-shell semantics and stderr capture in execute_command 
Two long-standing agent-facing defects:

1. bash -e aborted the model's script at the first intermediate
   non-zero status (grep with no matches exits 1, inspecting a failing
   test run, a probing subshell), so trailing guards like '; exit 0'
   never executed and output was partially or entirely lost. Dropped
   -e: the last statement now decides the exit code, matching the
   interactive-shell semantics models expect. pipefail is kept so a
   failing pipeline stage still surfaces in the exit code.

2. Only stdout was redirected into $LLM_OUTPUT, and the harness
   returns just $LLM_OUTPUT on success, so commands whose useful
   output goes to stderr (git push, cargo progress, curl -v) returned
   empty on success. Added 2>&1.
 2026-08-26 14:15:34 -06:00
Dark-Alex-17 6256b5fcfa docs: document background jobs across prompts, config example, and README 
- Extend the injected Background Jobs prompt guidance: system_notifications
  push on completion, collect-only-when-idle wait protocol, and the graph
  LLM-node collect-before-final-turn rule
- Mention the system_notifications push in the agent spawning guidance and
  in the sisyphus/architect wait-protocol text (agent completions push
  notifications too)
- config.example.yaml: max_concurrent_jobs (default 5, 0 = disabled)
- README: features-list entry pointing at the Background-Jobs wiki page
 2026-08-25 18:24:44 -06:00
Dark-Alex-17andSisyphus c7384b7a9b feat: run an advisory observability pass after implementation in sisyphus 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-25 13:19:10 -06:00
Dark-Alex-17andSisyphus ed9778c07b feat: add an observability-review skill for post-implementation monitoring analysis 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-25 13:19:09 -06:00
Dark-Alex-17andSisyphus 5a32219178 feat: check under- and over-logging in the code review gate 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-25 13:19:09 -06:00
Dark-Alex-17andSisyphus 9e652f7801 feat: calibrate logging registers in the code-writing agents 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-25 13:19:09 -06:00
Dark-Alex-17andSisyphus fcff426ae5 feat: add a logging-discipline skill for calibrating log output to repo conventions 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-25 13:17:33 -06:00
Dark-Alex-17 cb0802c2d0 fix: fix grep "binary" errors when searching UTF-8 files with unicode characters like some of the Coyote source 2026-08-25 13:06:16 -06:00
Dark-Alex-17andSisyphus f8cab9b439 feat: run design interviews as grilling frontier rounds across the planning agents 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 15:12:37 -06:00
Dark-Alex-17andSisyphus 45333db5c2 feat: add a grilling skill for frontier-round design interviews 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 15:12:37 -06:00
Dark-Alex-17andSisyphus 720591d24a feat: add an on-demand architecture-reviewer agent for deepening scans 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 15:07:50 -06:00
Dark-Alex-17andSisyphus dbb0c51b7e feat: add a codebase-design skill with the deep-module design vocabulary 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 15:07:50 -06:00
Dark-Alex-17andSisyphus b5863dded0 feat: add a feedback-loop-first diagnosing-bugs skill to the coding suite 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 15:02:12 -06:00
Dark-Alex-17andSisyphus 03116d2f42 feat: add a Fowler code-smell baseline to the code-review skill 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 15:02:12 -06:00
Dark-Alex-17andSisyphus 9b23247815 feat: flag duplicate helpers in code reviews with a repo-wide DRY check 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 14:46:38 -06:00
Dark-Alex-17andSisyphus 3493b01e9a feat: add a transactional-integrity review skill to the code review gate 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 14:46:38 -06:00
Dark-Alex-17andSisyphus fd989c44d0 feat: add an operational-history prior-art lane to the code-reviewer agent 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-08-24 14:46:13 -06:00
Dark-Alex-17 da640f3dcd feat: created a new comment-discipline skill for the built in sisyphus suite 2026-08-21 14:02:39 -06:00