Work classification
Classification asks a model to label each finished conversation: what kind of work it was, whether it reached its goal, and what evidence supports that judgment. Stats uses these labels for its work-mode, outcome, and work-frontier charts, and for the period comparison in its Changes tab. Classification and automatic labeling are off by default. Existing explicit choices stay unchanged. Enable them here or in setup’s Label conversations guide.
Labeling digests always remove common secret patterns before text limits apply, even when archive redaction is off. Pattern matching cannot remove every secret or identifier. Review the destination before enabling labeling.
- App
- Settings → Classification
- CLI
hansard classify
Configure classification in the app
Section titled “Configure classification in the app”

- Open Settings → Classification.
- Turn Label conversations on to label conversations. Turn it off to stop all classification.
- Turn Label new conversations automatically on to let the watcher label
conversations every 15 minutes. In Wait before labeling, choose how long
a conversation must go without new messages before it is labeled, from
12 hours to 14 days, or choose Custom… and enter a value such as
36h. The default is 7 days. The row also reports the last automatic pass. - To keep a short summary of each conversation after it ends, turn on
Summarize conversations after they end. It is off by default.
Continue from a summary and recall
read the summaries. To summarize older conversations, run
hansard summaries run. - Under Model, choose a Provider. Automatic tries Claude Code if you are signed in, then Codex, then Ollama, and shows which one it uses.
- Each provider labels with its own light model:
claude-sonnet-5through Claude Code or the Anthropic API,gpt-6-lunathrough Codex or the OpenAI API. To use a different model, choose a provider and enter it in Model. Clearing the field restores the light model, never the model you chat with. Jev API key sends each conversation to TypeSafe’s Jev model withTYPESAFE_API_KEY. Jev returns typed labels with calibrated confidence instead of written reasons, is billed by input tokens only, and does not support Task value. Horizons from Jev are the midpoint of the chosen range. - Under Extra labels, turn optional label sets on or off.
- To label waiting conversations now, select Label now beside Label waiting conversations, which also reports how many are waiting. To add the extra labels to conversations that are already labeled, select Add now beside Add to labeled conversations. If the provider sends data off this computer, Hansard asks you to confirm first. Stop ends the run.
A run labels up to 200 conversations, oldest first, and shows pending, complete, retrying, and failed counts while it works. It resumes where it left off if interrupted.
Classify from the CLI
Section titled “Classify from the CLI”Check what is configured and how much is pending:
hansard classify statusTurn labeling on, then automatic labeling:
hansard classify enablehansard classify auto enableLabel pending conversations now, or tune the automatic pass:
hansard classify runhansard classify run --profile enrichment --limit allhansard classify auto --stale-after 3d --limit 50hansard classify auto disableTo inspect one conversation’s stored labels, run hansard classify show
followed by its session ID. hansard classify clear --session followed by a
session ID removes that conversation’s labels, and
hansard classify clear --yes removes every stored label. Clearing labels
never touches archived conversations.
hansard classify run accepts these options:
| Option | Effect |
|---|---|
--profile <profile> |
Chooses which request to run: core (the conversation request, default), task, enrichment (every enabled request except core), or all. |
--limit N|all |
Sets the maximum number of jobs. The default is 200. |
--source <provider> |
Labels only one harness’s conversations. |
--since 30d|all |
Labels only conversations that started in the window. |
--include-sdk-jobs |
Also labels one-shot SDK jobs, which are skipped by default. |
--force |
Labels conversations again even when their labels are current. |
--batch-size N |
Sets conversations per model request, up to 16. |
--workers N |
Sets how many requests run at once, up to 8. |
--no-wait-for-imports |
Starts without waiting for running imports to finish. |
--json |
Prints a machine-readable summary. |
hansard classify auto takes --stale-after (the idle threshold),
--limit (jobs per 15-minute pass, default 100), and --window, which limits
automatic labeling to conversations active within it, 30 days by default.
--window all removes the limit. Older conversations are labeled only by
hansard classify run. The first automatic pass
starts a few minutes after the watcher launches, and pending imports always go
first.
Choose where classification runs
Section titled “Choose where classification runs”| Backend | Setting | What it uses |
|---|---|---|
| Automatic | auto (default) |
Claude Code if it is signed in, then Codex, otherwise Ollama. |
| Ollama | local-model |
Your Ollama server, http://localhost:11434 by default. Needs a model tag such as qwen2.5:7b-instruct. Hansard asks the model not to think, so a thinking model returns its label before the request times out. |
| Claude Code sign-in | claude-cli |
Your signed-in Claude account. No API key. |
| Codex sign-in | codex-cli |
Your signed-in Codex account. No API key. |
| Anthropic API key | anthropic |
ANTHROPIC_API_KEY from Hansard’s environment. Billed by usage. |
| OpenAI API key | openai |
OPENAI_API_KEY from Hansard’s environment. Billed by usage. |
| Jev API key | jev |
TYPESAFE_API_KEY from Hansard’s environment. Billed by TypeSafe. |
To choose a backend and model from the CLI:
hansard config set classify.backend local-modelhansard config set classify.model qwen2.5:7b-instructHansard remembers a model for each backend. Leaving the model blank restores
that backend’s light default. It never selects the CLI’s interactive model.
The Codex CLI runs classification at low reasoning effort
unless you set classify.reasoningEffort.
For every connection Hansard makes, see What leaves your machine.
Label from similar conversations
Section titled “Label from similar conversations”With search by meaning on, Hansard can answer some label requests from the labels of the most similar conversations instead of the model. First measure how often that agrees with the model on your archive:
hansard classify neighborsThe command predicts each labeled conversation only from conversations that started before it, and records for each label the vote share at which the neighbors agree with the model at least 90% of the time. Then turn it on:
hansard config set classify.neighbors.enabled trueA request is answered from neighbors only when every label in it reaches its recorded share. Every other conversation still goes to the model, so this never adds a request. The conversation request, which holds work mode, outcome, and evidence, always goes to the model. Labels from neighbors count in Stats like the model’s, stay out of Personal Sync, and give way to a model label for the same conversation.
What classification records
Section titled “What classification records”Each conversation is labeled by one model request per view of it, so the conversation is sent once instead of once per label. These request defaults apply only after labeling is enabled:
| Request | Reads | Labels | On by default |
|---|---|---|---|
| Conversation | The conversation digest | Work mode, outcome, success and failure evidence, purpose, task family, primary output, collaboration mode, decision autonomy, your expertise in the task, and who made the planning and execution decisions | Yes, always |
| Task horizon & O*NET work | Your requests only, never the agent’s replies | How long the task would take an experienced person without AI, ten difficulty facets rated 1 to 10 (including how hard mistakes are to undo, how novel the task is, how much the environment changes, and how much information must be found), task boundaries, and the work functions matched to a copy of the O*NET taxonomy bundled with Hansard (one extra lookup request; nothing is requested from O*NET) | Yes |
| Task value | The conversation digest | A rough, comparative value estimate for the task | No |
A field the model returns malformed is retried on its own; the rest of the reply is kept.
The core labels use these values:
- Work mode: Plan, Build, Fix, Understand, Test, Operate, Analyze, Orchestrate, or Communicate.
- Outcome: Succeeded, Partially Succeeded, Failed, or No clear goal. Success rates count only the first three, called goal-bearing sessions.
- Success evidence and Failure evidence: how strong the proof is, from 1 to 5. No evidence observed means the model checked and found none. Unclassified means no current label exists yet.
Horizon and difficulty are judged from your requests alone, never from how fast the agent worked or whether it succeeded.
Requests written by another agent
Section titled “Requests written by another agent”For a subagent run without a human request, task labeling reads the request
its parent agent wrote from the parent’s archived conversation. These labels
record request_author: agent, and Stats keeps them apart from human task
figures. A run whose parent request is unavailable remains not applicable and
sends no task request.
If the parent request becomes available later, preview the affected runs:
hansard classify subagents --dry-runRun hansard classify subagents to label them. The default window is 30 days,
with a limit of 200 runs. The automatic pass never sends this catch-up work.
Each run uses one task request, sent in batches, and at most one O*NET
selection request. Existing conversation labels remain in place.
Which conversations are labeled again
Section titled “Which conversations are labeled again”Hansard skips machine-started sessions such as status probes and Codex action
assessments, and one-shot SDK jobs unless you include them. It labels a
conversation again only when its content or the label definitions change.
Switching the model or provider keeps existing labels; run
hansard classify run --profile all --force to relabel with the new one.
See the results
Section titled “See the results”- Stats → Work shows work modes and the work frontier, and Stats → Outcomes shows outcomes and evidence. Detailed charts appear once more than 25% of eligible conversations are labeled; before that, a coverage card shows progress. See Stats.
- The Stats Changes tab compares work-mode mix and outcomes with the prior period, and its Write a retrospective button uses the same backend. See Compare periods.
- In a classified conversation, the Details panel beside the conversation includes a Classification section with its work mode, outcome, evidence, and status flags such as verified success.
hansard statsincludes a classification section, andhansard classify showprints one conversation’s stored labels.
Labels are a model’s estimates, not ground truth. Use them to compare large groups of conversations rather than to grade a single one.
Turn classification off
Section titled “Turn classification off”To stop only the automatic background pass and keep explicit runs:
hansard classify auto disableTo turn classification off entirely:
hansard classify disableIn the app, turn off Label new conversations automatically or Label
conversations in Settings → Classification. Existing labels stay until
you run hansard classify clear --yes.
Troubleshooting
Section titled “Troubleshooting”A run or automatic pass stopped with a usage, spend, or sign-in message.
The CLI backend reported a limit or is no longer signed in.
hansard classify status shows the reason under the last pass. Sign in again
or wait for the limit to reset; the watcher retries on its next pass.
Settings says the model declined some conversations. The model refused to label them on usage-policy grounds. Hansard labels the rest of their batch one conversation at a time, and each declined conversation waits a week before it is tried again, unless its content or the provider changes. The run and the automatic passes continue.
A run waits before starting. Explicit runs wait for active imports to
finish and for a short quiet period. To start anyway, add
--no-wait-for-imports.
Classification requests appear as conversations in the archive.
Run hansard classify cleanup --dry-run to preview them, then
hansard classify cleanup to remove them.
Stats shows a coverage card instead of charts. Fewer than 25% of eligible
conversations have current labels. Run hansard classify run --limit all, or
wait for automatic passes to catch up.