---
title: "coding.sh v0.1.6 (page 2) · Changelog"
description: "What changed in coding.sh v0.1.6, page 2 of 4: every change to Refine, Export, Capture, Explore, Viewer, API, Harness A/B and Attribution, one line each."
canonical: https://coding.sh/changelog/v0-1-6/2
human_url: https://coding.sh/changelog/v0-1-6/2
markdown_url: https://coding.sh/changelog/v0-1-6/2.md
agents_url: https://coding.sh/agents.md
llms_url: https://coding.sh/llms.txt
updated: 2026-11-11
---

[Changelog](https://coding.sh/changelog)

Unreleased · 149 changes · page 2 of 4

# coding.sh v0.1.6

## Refine

- Added `coding.sh refine mine` ranks failure patterns across sessions with no model call: session flags, normalized error lines (20 `TS2307` errors in 5 sessions are one pattern), instructions you typed again and again, and failed eval runs, each with its count, sessions and example events, redacted. `refine propose --mined FILE` shows the top patterns to the proposer. [Mining failure patterns](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#mining-failure-patterns).
- Added `coding.sh refine diagnose` asks a model what went wrong in recent sessions and groups the answers into Signals with stable ids; `refine signals` lists them. Every problem needs a citation that code checks against the redacted trace, severity is computed by code, replies are cached so a rerun makes no call, and with no API key it prints a $0 plan of the sessions and tokens it would send. [Diagnosing sessions into Signals](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#diagnosing-sessions-into-signals).
- Added `refine test|run --suite --canary-model <model>` re-tests a kept edit that deletes or rewords lines (`--canary all`: every kept edit) under a cheaper model and rejects it as `canary-regression` when the pass rate falls there; `refine recheck <r_…> --model` runs the same check later. A subtractive edit kept without a canary gets a note. Wrapper agents take a `{model}` slot in their flags. [Canary re-test](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#canary-re-test).
- Added `coding.sh refine distill` writes an experiment's runs (or recent sessions) as a redacted corpus, leaving out held-out tasks, and has Claude Code or Codex analyze it with its own code and write one skill in an isolated directory. The skill is size-capped, checked by the critics and ledgered as a proposed candidate with its provenance for `refine test`. [Distilling a skill](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#distilling-a-skill).
- Added The proposal prompt lists, per earlier edit that was not kept, the tasks it fixed, regressed and left failing, read from the ledger, and asks for lines aimed at the still-failing tasks. With no such rounds the prompt is unchanged. [Refine loop](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#refine-loop).
- Fixed `refine signals show <id>` takes the Signal id or a prefix of it again; it rejected every id with `Unexpected argument`. An unknown id says `No Signal <id> in <file>` and exits 2. [Diagnosing sessions into Signals](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#diagnosing-sessions-into-signals)
- Fixed `refine log`, the `refine test` verdict line and the `refine apply` refusal lead with the canary's reason for a round the canary rejected or left inconclusive, not the reason the candidate was first kept. [Canary re-test](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#canary-re-test)
- Fixed `refine distill --keep-corpus DIR` no longer deletes a directory that holds a file named SCHEMA.md next to other work. Only a directory that holds nothing but an earlier corpus is replaced, entry by entry; any other non-empty directory is refused and left as it is. With `--dry-run` nothing is written to DIR. [Distilling a skill](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#distilling-a-skill)
- Fixed `refine diagnose --session` takes an id prefix or `latest`, as `show` does. An id that matches no session is a not-found error (exit 1) instead of an empty plan. [Diagnosing sessions into Signals](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#diagnosing-sessions-into-signals)
- Fixed `refine mine` reports failed eval runs with the default `--repo`: a run counts for the repo when its task starts from it or belongs to a suite under its `evals/`. The summary line and `--json` (`evalRuns`) say how many eval runs were read. [Mining failure patterns](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#mining-failure-patterns)

## Export

- Added `coding.sh export --evidence <dir>` writes each matching session as a folder of files: `index.md` with stats and a timeline, `session.json`, `events.jsonl`, and one file per tool call with its input and full output. Everything is redacted first, files are size-capped, and the same store gives the same bytes. [Query and export](https://github.com/jackulau/coding.sh/blob/main/docs/reference/query.md#evidence-folders).
- Added `eval export --format atif` writes the task's source session as an ATIF-v1.8 trajectory (redacted, with subagents embedded). `--format harbor` now writes `task.toml` schema 1.4 with an explicit verifier mode, and the trajectory under `solution/`. Both pass Harbor 0.25's loaders. [Session to eval](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#session-to-eval).

## Capture

- Added `coding.sh doctor --conformance` runs each agent's backfill over the transcripts on this machine and checks the events: duplicate ids, timestamps, tool and subagent pairing, parent links, double-counted usage, sessions without a prompt and failed commands marked ok. It only reads, never opens the store, and exits 1 on a violation. [Troubleshooting](https://github.com/jackulau/coding.sh/blob/main/docs/troubleshooting.md#check-what-the-adapters-read).
- Added A tool call that loads a skill names it on its `tool.start` (`payload.skill`, and `payload.skills` when it loaded several): a Skill tool call, a read of a file under an agent's `skills/<name>/` folder, a `cat`, `head` or `sed` of one by a literal path, or an MCP read of a `skill://` resource. Every adapter goes through the same check. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#subagents).
- Added Copilot CLI hook events keep the OpenTelemetry trace from the `traceparent` Copilot 1.0.107 passes its hooks, and ingest records which session the trace belongs to, so an OTLP span of that trace that names no conversation lands in the hook session. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#known-breakage-to-design-around).
- Added `coding.sh run -- aider` records each reply's tokens and cost while Aider runs: the wrapper reads Aider's analytics log (a temp `AIDER_ANALYTICS_LOG`, or the log you named) and the cache split from its chat history, so live Aider sessions have usage and cost, not only eval runs. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#transcripts-headless-runs-isolation)
- Changed Outside Windows the hook agents run is a POSIX sh script, `~/.coding.sh/bin/hook.sh`, which writes the same spool line without starting node: under bash 5, about 3 ms more than `/bin/true` per hook call for payloads up to 256 KB, instead of about 30 ms ([Hook](https://github.com/jackulau/coding.sh/blob/main/docs/perf.md#hook)). It hands `--reply`, eval runs, gateway base URLs and anything else it does not cover to `hook.mjs`. Run `coding.sh init` again to switch existing hooks. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#hook-command).
- Fixed A Claude Code response with parallel tool calls is one `llm.call` again, with its usage counted once. Claude Code writes a tool's result between the lines of the response that called it, and each part used to become its own call; the call is now timed from the request's `api-request` line. A subagent that another subagent spawned hangs off that subagent's session instead of the main one. Stored sessions are parsed again on the next ingest. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#known-breakage-to-design-around).
- Fixed A Codex subagent thread has a prompt and a title: the task its parent sent it (an `agent_message` addressed to the thread) is its `user.message`, with `from`, `taskName` and `encrypted`. Codex encrypts the task text, so the prompt says which agent asked for which task. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#subagents).
- Fixed OpenCode history imports when OpenCode has set its database aside as `opencode.db.schema-mismatch-<ms>` and not yet written a new one, and `doctor` says when a database has no session tables coding.sh knows or cannot be opened, where backfill used to import nothing without a word. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#known-breakage-to-design-around).
- Fixed An Antigravity command that exited nonzero is a failed tool call with its `exitCode`, read from the result's `The command exited with code N.` line, and the result's `Created At`/`Completed At` time it. Every Antigravity tool call used to count as ok. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#known-breakage-to-design-around).
- Fixed The sh hook no longer hangs when an agent starts it with stdin closed. Under macOS `/bin/sh` and bash 3.2 it never exited and left a child process behind. It now treats a closed stdin as an empty payload and exits 0 at once, as `hook.mjs` does. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#hook-command)
- Fixed `hook.sh` no longer fails the agent's hook call when it hands an event to `hook.mjs` and node cannot run (not on the agent's `PATH`, a version manager's shim that fails, a missing `hook.mjs`): it exits 0 and still prints the `--echo-continue` reply. Before, an eval run, a gateway base URL or `--reply` made the hook exit 127 on such a machine. That event is not captured. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#hook-command)
- Fixed Claude Code hooks registered in two settings files with different commands (user settings on `hook.sh`, a project's `.claude/settings.local.json` still on `node …/hook.mjs`) no longer store each prompt, turn end and session end twice. The spool lines of one hook firing (the same payload, at most 2 s apart) get the same event ids; the same prompt sent again later is still a second event. `coding.sh init` also looks for project hooks at the root of the repository it runs in, reports them and skips the user install unless `--force`. Stored Claude Code sessions are parsed again. [Adapters](https://github.com/jackulau/coding.sh/blob/main/docs/ADAPTERS.md#hook-command)
- Fixed A session whose hooks ran with a stale `CLAUDE_CODE_SESSION_ID` or `CODEX_THREAD_ID` is no longer hidden as a subagent of a session that is not in the store or had already ended. The marker links a child only when the named session is in the store and was open when the child started; stored sessions with such a parent become top-level after the refold. [Concepts](https://github.com/jackulau/coding.sh/blob/main/docs/concepts.md)
- Fixed When the ingest the hook starts fails, `coding.sh status`, the status line and `coding.sh doctor` print `ingest stopped 4h ago` with the command that fixes it, and `status --json` and `doctor --json` carry `ingestStopped`. `status` prints the home, the spool and that line even when the store can't be opened. [Troubleshooting](https://github.com/jackulau/coding.sh/blob/main/docs/troubleshooting.md#run-doctor)

## Explore

- Added `coding.sh stats` and the viewer's new Explore page (`#/explore`) show sessions, failure rate, cost, tokens, tool error rate and p95 model-call time per day or week, split by agent, model, repo or flag, from one engine that `GET /api/metrics` also serves. [Explore sessions](https://github.com/jackulau/coding.sh/blob/main/docs/guides/explore.md#trends-with-stats), [API](https://github.com/jackulau/coding.sh/blob/main/docs/reference/api.md#get-apimetrics).

## Viewer

- Added A model call in `coding.sh ui` opens in a playground: the call is rebuilt as system prompt, messages and tools, you edit it, run it against Anthropic, OpenAI or any OpenAI-compatible server, see the answer beside the recorded one, and save it as a dataset case. [Explore sessions](https://github.com/jackulau/coding.sh/blob/main/docs/guides/explore.md#model-calls), [API](https://github.com/jackulau/coding.sh/blob/main/docs/reference/api.md#get-apiplayground-get-apiplaygroundcallsid-post-apiplaygroundrun-post-apiplaygroundsave).
- Added The viewer page arrives with the first sessions page drawn and its first responses embedded, so the list shows before the script runs (on Slow 4G with a 4x slower CPU, the first row shows about 2.7 s sooner, 95% CI 2.71 to 2.75 s), and a session the pointer rests on, the keyboard moves to, or a press lands on loads in the background, so it opens without a request. [Explore sessions](https://github.com/jackulau/coding.sh/blob/main/docs/guides/explore.md#viewer).
- Changed Moving through sessions and steps with the keyboard is instant: rows snap, the query suggestions and pills do not animate or push rows under the cursor, and a held `j` or `k` stays smooth in long sessions. Counts read "1 tool call", large costs and token counts keep their separators, long durations roll up to days, relative times keep refreshing, and long titles, model ids and file names stay readable. In the benchmark table a long cost source no longer pushes the cost out of its column. [Viewer](https://github.com/jackulau/coding.sh/blob/main/docs/guides/explore.md)
- Fixed "Open in playground" works for model calls in subagent and workflow-agent sessions: the request is rebuilt from the subagent's own conversation, without the calls of a subagent it started. Every such call used to answer 404 `no_request`. [API](https://github.com/jackulau/coding.sh/blob/main/docs/reference/api.md#get-apiplayground-get-apiplaygroundcallsid-post-apiplaygroundrun-post-apiplaygroundsave)

## API

- Added `GET /api/sessions/{id}/rows` pages through one turn of a long session, with runs of routine events folded and failures always shown; the outline adds turns, failures, compactions, subagents and a minimap; `GET /api/events/{id}` returns one event; and `GET /api/blobs/{sha256}?range=a-b` reads part of a blob. [API](https://github.com/jackulau/coding.sh/blob/main/docs/reference/api.md#get-apisessionsidrows).

## Harness A/B

- Added `compare` grades each run in a fresh copy of the task's start tree plus the agent's source changes. A `conftest.py`, `sitecustomize.py`, `.pth` or `.npmrc` the agent wrote, an edited test config or Makefile, and a changed `test` script in `package.json` no longer reach the verifier, and each run records what was left out in `isolation`. `--no-isolation` grades the agent's own tree. [Verifier isolation](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#verifier-isolation)
- Added The `compare` report adds cost and tokens per solved task, `pass@k`, `pass^k` and the flaky tasks with `--k 2` or more, and how many paired tasks would detect the observed effect at 80% power. [Efficiency, reliability and tasks needed](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#efficiency-reliability-and-tasks-needed)
- Added `compare --otel` gives each agent an OTLP endpoint, a `TRACEPARENT` and `coding_sh.run_id` in its resource attributes, so the spans it exports are stored with the run and join its session. [OpenTelemetry per run](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#opentelemetry-per-run)
- Added `compare --sequential` runs each arm's tasks in order and carries the agent's home (or `--carry <path>`) from one task to the next, and the report adds the pass rate by position. [Sequential runs](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#sequential-runs)
- Added `compare --pick N` and `--budget <USD>` run the tasks that best tell harnesses apart in stored runs first and tasks every run passed last. `--budget` fits the tasks to an estimated cost, caps the spend and shows the estimate in the consent prompt; `--dry-run` lists the picks and runs no agent. [Picking tasks and a budget](https://github.com/jackulau/coding.sh/blob/main/docs/guides/evals.md#picking-tasks-and-a-budget)

## Attribution

- Added `coding.sh attribution` matches the lines each commit added to the captured session that wrote them, from the session's snapshots or its edit tool calls; a rebased commit still matches, and a session is credited only for files it could have written. `coding.sh blame <path>[:line]` shows it per line, and `coding.sh attribution export` writes Agent Trace (agent-trace.dev, RFC 0.1.0) records. git-ai notes are read as a second source. Read-only on git. [Attribute commits](https://github.com/jackulau/coding.sh/blob/main/docs/how-to/attribute-commits.md).
- Fixed A session is credited a file from the tree diff only when its tools named the file or it ran a shell or subagent call; a named file takes the lines its edit steps added, not the diff. Lines a person typed in the same window match no session of a run that only read files. A session that ran a shell tool can still be credited a file a person wrote by hand, at lower confidence. [Attribute commits](https://github.com/jackulau/coding.sh/blob/main/docs/how-to/attribute-commits.md#how-matching-works)
- Fixed Without snapshots (a store filled by `ingest --backfill`, or a session whose end snapshot is gone), a session is credited only for the lines its own Write, Edit and patch calls added, less the ones it later removed. Lines a person added to the file between two of the agent's edits used to be credited to the session once the agent read the file again. Sources cached by an older build are built again. [Attribute commits](https://github.com/jackulau/coding.sh/blob/main/docs/how-to/attribute-commits.md#how-matching-works)
- Fixed A person's copy of a long line in another file of the same commit no longer takes the session's credit. Every file of a commit gets its same-file matches before a long line may match across files, so `blame` credits the agent's own line and shows `-` for the copy. [Attribute commits](https://github.com/jackulau/coding.sh/blob/main/docs/how-to/attribute-commits.md#how-matching-works)
- Fixed A commit made on a branch that was no longer checked out when the session's end snapshot was taken got 0 lines, because an empty or unrelated snapshot diff hid the session's own edit tool calls. `coding.sh attribution` and `coding.sh blame` now take every file the session's tools named that the snapshot diff does not hold from those calls, at confidence 0.8. [Attribute commits](https://github.com/jackulau/coding.sh/blob/main/docs/how-to/attribute-commits.md#how-matching-works)

[Previous page v0.1.6, page 1](https://coding.sh/changelog/v0-1-6) [Next page v0.1.6, page 3](https://coding.sh/changelog/v0-1-6/3)

From [CHANGELOG.md](https://github.com/jackulau/coding.sh/blob/main/CHANGELOG.md) · [RSS](https://coding.sh/changelog.xml) · [All releases](https://coding.sh/changelog)

To set coding.sh up for a user, follow the agent workflow at [/agents.md](https://coding.sh/agents.md).